From e8eddc7ef8cb82e8fb615be48e68ff72386d0e6f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 22:50:49 +0800 Subject: [PATCH 1/3] Rename RFCs to Agent Notes --- .agents/notes/AGENTS.md | 3 + {docs/rfc => .agents/notes}/INDEX.md | 10 +- .agents/notes/README.md | 109 ++++++++++++++++++ .agents/notes/implemented/AGENTS.md | 11 ++ .../notes}/implemented/CLAUDE.md | 0 .../2026-06-11-content-block-vocabulary.md | 6 +- .../2026-06-11-custom-schema-dsl.md | 2 +- ...06-11-dev-invariants-over-deep-readonly.md | 2 +- .../2026-06-11-event-sourced-sessions.md | 2 +- .../2026-06-11-microkernel-event-taxonomy.md | 4 +- .../2026-06-11-runtime-arg-validation.md | 4 +- .../2026-06-11-structured-error-taxonomy.md | 4 +- ...6-06-11-tool-schemas-in-prompt-assembly.md | 2 +- .../2026-06-13-capability-seams.md | 8 +- .../2026-06-13-twin-llm-adapters.md | 4 +- .../2026-06-14-session-persistence.md | 6 +- .../2026-06-15-turn-enclosure-invariant.md | 2 +- .../2026-06-17-filesystem-capability-seam.md | 16 +-- ...-18-agent-lifecycle-and-ownership-seams.md | 4 +- .../2026-06-18-session-surface.md | 2 +- ...18-shared-persistence-write-coordinator.md | 4 +- .../architecture/2026-06-20-branded-ids.md | 10 +- ...2026-06-20-extract-example-app-packages.md | 4 +- ...06-20-generic-long-running-tool-runtime.md | 6 +- .../2026-06-20-package-hierarchy.md | 2 +- ...06-21-mandatory-app-attribution-headers.md | 20 ++-- .../2026-06-24-web-capability-seam.md | 8 +- .../2026-06-26-file-context-as-event-gate.md | 10 +- ...0-bash-stdin-env-trusted-plugin-surface.md | 8 +- .../2026-06-30-event-domain-semantics.md | 10 +- .../2026-07-02-fs-per-session-cwd.md | 4 +- ...26-07-02-result-time-applied-hunk-diffs.md | 4 +- .../2026-07-02-tool-render-intent-union.md | 6 +- ...07-03-filesystem-directory-listing-seam.md | 2 +- ...t-variables-and-tool-guidance-ownership.md | 8 +- .../2026-07-05-reconstructable-requests.md | 4 +- ...7-05-subagent-provider-lifecycle-events.md | 10 +- .../2026-07-06-timeout-deadline-library.md | 2 +- ...026-07-06-tool-result-retention-library.md | 2 +- .../2026-07-07-tool-call-timeout-policy.md | 10 +- .../2026-07-08-agent-scope-contexts.md | 8 +- .../2026-07-08-tool-output-spill-files.md | 4 +- ...n-pressure-and-overflow-recovery.i18n.yaml | 4 +- ...mpaction-pressure-and-overflow-recovery.md | 4 +- ...ction-pressure-and-overflow-recovery.zh.md | 4 +- ...cutable-sdk-runtime-distribution.i18n.yaml | 4 +- ...ile-executable-sdk-runtime-distribution.md | 2 +- ...-executable-sdk-runtime-distribution.zh.md | 2 +- .../2026-07-12-agent-scope-runtime-design.md | 12 +- ...-14-provider-routed-llm-adapters.i18n.yaml | 4 +- ...2026-07-14-provider-routed-llm-adapters.md | 6 +- ...6-07-14-provider-routed-llm-adapters.zh.md | 6 +- ...2026-07-15-agent-initiator-scope.i18n.yaml | 4 +- .../2026-07-15-agent-initiator-scope.md | 4 +- .../2026-07-15-agent-initiator-scope.zh.md | 4 +- ...-model-catalog-and-acp-selection.i18n.yaml | 4 +- ...-15-llm-model-catalog-and-acp-selection.md | 2 +- ...-llm-model-catalog-and-acp-selection.zh.md | 2 +- ...07-15-replay-token-meter-service.i18n.yaml | 4 +- .../2026-07-15-replay-token-meter-service.md | 2 +- ...026-07-15-replay-token-meter-service.zh.md | 2 +- .../2026-06-14-acp-agent-client-protocol.md | 4 +- .../feature/2026-06-14-acp-multi-session.md | 2 +- .../feature/2026-06-15-code-mode.md | 18 +-- .../2026-06-17-filesystem-tool-schemas.md | 10 +- ...6-06-18-acp-terminal-and-tool-rendering.md | 6 +- .../2026-06-18-compaction-capability-seam.md | 12 +- .../2026-06-21-subagent-capability-seam.md | 12 +- .../2026-06-22-acp-subagent-backend.md | 8 +- .../feature/2026-06-24-workspace-context.md | 2 +- .../feature/2026-06-25-ask-user-question.md | 2 +- .../feature/2026-06-29-todo-write-tool.md | 2 +- .../feature/2026-06-30-hook-bridges.md | 8 +- .../feature/2026-06-30-hook-protocol-lib.md | 6 +- .../feature/2026-06-30-interception-seams.md | 6 +- .../2026-06-30-session-store-fork-api.md | 6 +- .../2026-06-30-subagent-observe-enrich.md | 12 +- .../feature/2026-07-05-dynamic-workflows.md | 8 +- .../feature/2026-07-05-skill-system.md | 4 +- .../feature/2026-07-06-approval-seam.md | 16 +-- .../feature/2026-07-06-explicit-tool-order.md | 4 +- .../implemented/feature/2026-07-06-sandbox.md | 16 +-- .../feature/2026-07-07-mcp-client-plugin.md | 6 +- .../feature/2026-07-07-session-prefix.md | 10 +- .../2026-07-08-background-subagent-tasks.md | 2 +- .../feature/2026-07-08-repeat-tool-guard.md | 6 +- ...6-07-08-self-referential-cordis-toolset.md | 8 +- ...6-07-09-bash-backed-grep-glob-discovery.md | 10 +- ...agent-session-identity-and-log-location.md | 6 +- ...2026-07-10-parallel-tool-call-execution.md | 6 +- .../2026-07-10-session-query-service.md | 2 +- ...-subagent-persona-tool-filter-and-depth.md | 2 +- .../2026-07-13-session-query-tracing.md | 2 +- .../2026-07-14-time-context-plugin.i18n.yaml | 4 +- .../feature/2026-07-14-time-context-plugin.md | 4 +- .../2026-07-14-time-context-plugin.zh.md | 6 +- ...16-durable-per-step-time-context.i18n.yaml | 4 +- ...026-07-16-durable-per-step-time-context.md | 2 +- ...-07-16-durable-per-step-time-context.zh.md | 2 +- ...cated-full-screen-tui-front-door.i18n.yaml | 4 +- ...17-dedicated-full-screen-tui-front-door.md | 4 +- ...dedicated-full-screen-tui-front-door.zh.md | 4 +- .../2026-06-11-doc-sync-enforcement.md | 2 +- .../process/2026-06-11-quality-gates.md | 4 +- .../process/2026-06-11-tsdown-over-dumble.md | 6 +- .../2026-06-11-vendor-cordis-as-source.md | 2 +- .../process/2026-06-16-pnpm-over-yarn.md | 2 +- .../process/2026-06-17-ts-build-config.md | 2 +- .../2026-06-18-markdown-cross-link-lint.md | 8 +- .../2026-06-20-agent-note-classification.md | 46 ++++++++ ...2026-06-20-core-data-structures-catalog.md | 8 +- .../2026-06-20-generated-cordis-catalog.md | 4 +- ...-bilingual-docs-and-pairing-gate.i18n.yaml | 4 +- ...6-07-02-bilingual-docs-and-pairing-gate.md | 10 +- ...7-02-bilingual-docs-and-pairing-gate.zh.md | 10 +- .../process/2026-07-02-tool-schema-catalog.md | 4 +- .../2026-07-03-documentation-graph-atlas.md | 18 +-- ...26-07-04-cordis-jsdoc-completeness-gate.md | 2 +- .../2026-07-04-doc-tiers-and-budgets.md | 10 +- ...-07-04-generate-agent-note-index-tables.md | 32 +++++ .../2026-07-04-persistence-log-catalog.md | 2 +- .../2026-07-05-uniform-agent-note-format.md | 28 +++++ .../2026-07-06-export-surface-jsdoc-gate.md | 2 +- .../2026-07-06-generated-config-catalog.md | 4 +- .../process/2026-07-06-node-engine-floor.md | 4 +- .../2026-07-06-parallel-github-ci-gates.md | 2 +- .../2026-07-06-parallel-pre-push-gates.md | 4 +- ...026-07-10-readme-known-limitations-gate.md | 8 +- ...07-12-package-model-experience-contract.md | 6 +- ...pt-program-backed-semantic-gates.i18n.yaml | 4 +- ...ypescript-program-backed-semantic-gates.md | 2 +- ...script-program-backed-semantic-gates.zh.md | 2 +- ...7-run-ci-examples-from-built-lib.i18n.yaml | 4 +- ...26-07-17-run-ci-examples-from-built-lib.md | 2 +- ...07-17-run-ci-examples-from-built-lib.zh.md | 2 +- ...2026-06-19-drop-mutable-session-summary.md | 6 +- ...6-20-collapse-trace-only-session-events.md | 4 +- ...rop-unconsumed-llm-adapter-change-event.md | 8 +- ...-drop-unconsumed-llm-assembled-surfaces.md | 4 +- .../2026-06-20-prune-dead-seam-methods.md | 12 +- .../2026-06-20-public-agent-stop-surface.md | 4 +- ...-20-remove-agent-boundary-mirror-events.md | 10 +- .../2026-06-20-unify-agent-and-session-id.md | 4 +- .../2026-06-26-fsspec-style-fs-seam.md | 18 +-- .../2026-07-02-remove-stream-chunk-mirror.md | 6 +- .../2026-07-04-drop-image-content-block.md | 4 +- .../2026-07-04-drop-inert-request-knobs.md | 8 +- ...drop-unconsumed-web-observation-surface.md | 10 +- .../2026-07-04-fold-stdio-ui-helper.md | 2 +- ...-prune-producerless-vocabulary-variants.md | 31 +++++ .../2026-07-04-prune-write-only-fs-surface.md | 4 +- ...2026-07-04-remove-agent-steering-mirror.md | 10 +- .../2026-07-04-share-app-bin-boot-glue.md | 6 +- ...26-07-04-tighten-hook-protocol-contract.md | 6 +- ...-04-trim-acp-bridge-unreachable-surface.md | 2 +- ...2-drop-unconsumed-skill-provider-events.md | 4 +- ...2026-07-12-prune-unused-web-seam-fields.md | 2 +- ...-12-simplify-session-log-representation.md | 2 +- ...-19-retire-subagent-mock-package.i18n.yaml | 4 +- ...2026-07-19-retire-subagent-mock-package.md | 2 +- ...6-07-19-retire-subagent-mock-package.zh.md | 2 +- ...-use-one-session-surface-manager.i18n.yaml | 4 +- ...6-07-19-use-one-session-surface-manager.md | 2 +- ...7-19-use-one-session-surface-manager.zh.md | 2 +- .../2026-06-11-property-based-testing.md | 4 +- .../testing/2026-06-19-acp-snapshot-tests.md | 12 +- .../testing/2026-06-19-real-api-e2e-ci.md | 10 +- ...-redundant-snapshot-log-expected-output.md | 4 +- ...6-06-22-fork-child-replay-seed-boundary.md | 4 +- .../2026-06-22-fork-snapshot-scenarios.md | 8 +- .../2026-06-22-subagent-snapshot-replay.md | 4 +- .../2026-07-04-hook-snapshot-matrix.md | 4 +- ...6-07-04-single-source-acp-replay-config.md | 4 +- ...-request-header-content-in-one-scenario.md | 4 +- .../2026-07-08-shared-acp-snapshot-package.md | 8 +- ...-18-tui-terminal-state-snapshots.i18n.yaml | 4 +- ...2026-07-18-tui-terminal-state-snapshots.md | 2 +- ...6-07-18-tui-terminal-state-snapshots.zh.md | 2 +- .../2026-06-16-typed-event-schemas.md | 12 +- ...sdk-project-editing-architecture.i18n.yaml | 4 +- ...-07-15-sdk-project-editing-architecture.md | 4 +- ...-15-sdk-project-editing-architecture.zh.md | 2 +- .../2026-06-30-pre-tool-input-rewrite.md | 4 +- .../2026-07-06-recallable-compaction.md | 6 +- ...claude-code-and-codex-subagent-backends.md | 10 +- .../2026-07-08-interactive-side-sessions.md | 4 +- ...026-07-10-sqlite-session-query-provider.md | 4 +- ...am-workflow-progress-through-tool-calls.md | 2 +- ...026-07-14-sdk-developer-projects.i18n.yaml | 4 +- .../2026-07-14-sdk-developer-projects.md | 2 +- .../2026-07-14-sdk-developer-projects.zh.md | 2 +- ...07-17-sdk-follow-up-capabilities.i18n.yaml | 4 +- .../2026-07-17-sdk-follow-up-capabilities.md | 4 +- ...026-07-17-sdk-follow-up-capabilities.zh.md | 4 +- .../2026-06-11-api-extractor-reports.md | 4 +- .../2026-06-11-architectural-conformance.md | 4 +- ...026-06-11-supply-chain-and-vendor-drift.md | 2 +- .../2026-06-20-discover-package-inventory.md | 4 +- ...26-07-13-human-review-skill-maintenance.md | 8 +- ...026-07-04-prune-dead-core-spine-surface.md | 12 +- ...6-07-19-make-jsonrpc-directional.i18n.yaml | 4 +- .../2026-07-19-make-jsonrpc-directional.md | 2 +- .../2026-07-19-make-jsonrpc-directional.zh.md | 2 +- ...-06-11-deterministic-and-stress-testing.md | 4 +- .../testing/2026-06-11-mutation-testing.md | 4 +- .../2026-06-11-immutable-public-surfaces.md | 4 +- .../2026-06-20-providerless-example-base.md | 6 +- ...06-20-assembled-assistant-messages-only.md | 6 +- .../2026-06-20-drop-acp-session-load.md | 4 +- .../2026-06-20-drop-acp-terminal-meta.md | 8 +- ...2026-06-20-drop-bash-output-spill-files.md | 6 +- ...2026-06-20-drop-durable-step-boundaries.md | 6 +- .../2026-06-20-drop-unused-session-lineage.md | 4 +- ...6-20-fold-session-persistence-interface.md | 4 +- .../2026-06-20-generic-tool-rendering.md | 4 +- .../2026-06-20-retire-mid-turn-steering.md | 4 +- .../2026-06-20-single-session-acp-bridge.md | 8 +- .../2026-06-20-truncate-interrupted-turns.md | 4 +- ...prune-unimplemented-subagent-vocabulary.md | 12 +- ...12-collapse-workflow-to-foreground-core.md | 4 +- ...-12-prune-unused-skill-registry-surface.md | 6 +- ...19-fold-compaction-package-split.i18n.yaml | 4 +- ...026-07-19-fold-compaction-package-split.md | 2 +- ...-07-19-fold-compaction-package-split.zh.md | 2 +- .agents/skills/dsh-code-review/SKILL.md | 8 +- .agents/skills/dsh-doc-standards/SKILL.md | 6 +- .../skills/dsh-find-simplifications/SKILL.md | 32 ++--- .agents/skills/dsh-pre-push-checks/SKILL.md | 2 +- .agents/skills/dsh-prose-standard/SKILL.md | 2 +- .../dsh-prose-standard/references/examples.md | 14 +-- .../workflows/build-exe-for-python-sdk.yml | 2 +- .github/workflows/e2e.yml | 2 +- .github/workflows/sandbox.yml | 2 +- AGENTS.md | 5 +- docs/AGENTS.md | 26 ++--- docs/architecture.md | 12 +- docs/config-catalog.md | 4 +- docs/cookbook/adding-a-package.i18n.yaml | 4 +- docs/cookbook/adding-a-package.md | 4 +- docs/cookbook/adding-a-package.zh.md | 4 +- docs/cookbook/adding-a-tool.i18n.yaml | 4 +- docs/cookbook/adding-a-tool.md | 10 +- docs/cookbook/adding-a-tool.zh.md | 10 +- .../adding-a-vendored-package.i18n.yaml | 4 +- docs/cookbook/adding-a-vendored-package.md | 2 +- docs/cookbook/adding-a-vendored-package.zh.md | 2 +- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 10 +- docs/cookbook/extension-cookbook.zh.md | 10 +- docs/cookbook/maintaining-dsh-code-review.md | 6 +- docs/cordis-catalog/events.md | 2 +- docs/core-data-structures/bash.md | 6 +- docs/core-data-structures/code-runtime.md | 2 +- docs/core-data-structures/compaction.md | 6 +- docs/core-data-structures/core.md | 4 +- docs/core-data-structures/llm-streaming.md | 2 +- docs/core-data-structures/persistence.md | 4 +- docs/core-data-structures/scope.md | 2 +- docs/core-data-structures/session.md | 12 +- docs/core-data-structures/skills.md | 2 +- docs/core-data-structures/spill.md | 2 +- docs/core-data-structures/subagent.md | 4 +- docs/core-data-structures/tasks.md | 2 +- docs/core-data-structures/tools.md | 4 +- docs/core-data-structures/web.md | 2 +- docs/core-data-structures/workflow.md | 2 +- docs/development.i18n.yaml | 4 +- docs/development.md | 6 +- docs/development.zh.md | 6 +- docs/glossary.md | 2 +- docs/graph-atlas.md | 2 +- docs/i18n/README.i18n.yaml | 4 +- docs/i18n/README.md | 12 +- docs/i18n/README.zh.md | 12 +- docs/i18n/style-samples.md | 6 +- docs/i18n/terminology.md | 1 + docs/i18n/translation-prompt.md | 2 +- docs/persistence-catalog.md | 4 +- docs/postmortem/README.md | 2 +- docs/rfc/README.md | 109 ------------------ docs/rfc/implemented/AGENTS.md | 11 -- .../process/2026-06-20-rfc-classification.md | 46 -------- .../2026-07-04-generate-rfc-index-tables.md | 32 ----- .../process/2026-07-05-uniform-rfc-format.md | 28 ----- ...-prune-producerless-vocabulary-variants.md | 31 ----- docs/testing.md | 6 +- docs/tool-catalog.md | 10 +- examples/README.md | 2 +- examples/acp-agent/README.md | 6 +- examples/acp-agent/tests/acp.snapshot.ts | 6 +- examples/cordis-agent/README.md | 2 +- examples/cordis-agent/cordis.yml | 2 +- examples/repl-agent/README.md | 2 +- examples/tui-agent/README.md | 2 +- package.json | 8 +- packages/AGENTS.md | 6 +- packages/README.md | 4 +- packages/bash/README.md | 2 +- packages/bash/bash-local/README.md | 2 +- packages/bash/bash-sandbox/README.md | 2 +- packages/bash/bash/README.md | 4 +- packages/bash/bash/src/types.ts | 2 +- packages/bash/tool-bash/README.md | 8 +- packages/bash/tool-bash/tests/tools.spec.ts | 4 +- packages/code-runtime/README.md | 2 +- .../code-runtime-worker/README.md | 2 +- packages/code-runtime/code-runtime/README.md | 4 +- packages/compact/README.md | 4 +- packages/compact/compact-basic/README.md | 4 +- packages/compact/compact/README.md | 2 +- packages/compact/compact/src/index.ts | 2 +- packages/compact/compact/src/types.ts | 4 +- packages/context/README.md | 2 +- packages/context/time-context/README.md | 2 +- packages/cordis/README.md | 2 +- packages/cordis/tool-cordis/README.md | 4 +- .../cordis/tool-cordis/src/api-catalog.ts | 2 +- packages/cordis/tool-cordis/src/index.ts | 2 +- packages/core/agent-loop/README.md | 4 +- packages/core/agent-loop/src/loop.ts | 2 +- .../agent-loop/tests/coverage-edges.spec.ts | 2 +- .../core/agent-loop/tests/properties.spec.ts | 2 +- .../agent-loop/tests/request-cache.e2e.ts | 2 +- packages/core/agent-loop/tests/resume.spec.ts | 2 +- packages/core/agent/README.md | 10 +- packages/core/scope/README.md | 2 +- packages/core/session/README.md | 6 +- packages/core/session/src/index.ts | 2 +- .../core/session/tests/properties.spec.ts | 2 +- packages/core/system-prompt/README.md | 4 +- packages/core/tools/README.md | 16 +-- packages/core/tools/src/index.ts | 2 +- packages/core/tools/src/ts-types.ts | 2 +- packages/core/tools/tests/code-mode.spec.ts | 2 +- packages/core/tools/tests/properties.spec.ts | 4 +- packages/core/tools/tests/tools.spec.ts | 4 +- packages/examples/acp-demo/README.md | 2 +- packages/examples/agent-spine-demo/README.md | 4 +- packages/examples/jsonrpc-demo/README.md | 4 +- packages/examples/stdio-demo/README.md | 2 +- packages/fs/fs-local/README.md | 4 +- packages/fs/fs-local/src/index.ts | 2 +- packages/fs/fs-policy/README.md | 2 +- packages/fs/fs/README.md | 8 +- packages/fs/tool-fs/README.md | 6 +- packages/guard/repeat-tool-guard/README.md | 2 +- packages/guard/repeat-tool-guard/src/index.ts | 2 +- packages/hooks/README.md | 2 +- packages/hooks/hook-protocol/README.md | 4 +- packages/hooks/hook-protocol/src/types.ts | 4 +- packages/hooks/hooks-claude/README.md | 6 +- packages/hooks/hooks-claude/src/index.ts | 2 +- packages/hooks/hooks-codex/README.md | 2 +- packages/hooks/hooks-codex/src/index.ts | 2 +- packages/llm/README.md | 2 +- packages/llm/llm/README.md | 8 +- packages/llm/llm/src/attribution.ts | 2 +- packages/llm/llm/src/index.ts | 2 +- packages/llm/llm/tests/properties.spec.ts | 2 +- packages/mcp/mcp-client/src/tools.ts | 2 +- packages/sandbox/README.md | 6 +- packages/sandbox/sandbox-local/README.md | 4 +- packages/sandbox/sandbox/README.md | 4 +- packages/sdk/README.md | 2 +- packages/sdk/helper/README.md | 2 +- packages/session-persistence/README.md | 2 +- .../session-persistence-jsonl/README.md | 2 +- .../session-persistence-sqlite/README.md | 6 +- .../session-persistence/README.md | 6 +- .../session-query/session-query/README.md | 2 +- packages/skill/tool-skill/README.md | 2 +- packages/spill/README.md | 2 +- packages/spill/spill-local/README.md | 2 +- packages/spill/spill-policy/README.md | 2 +- packages/spill/spill/README.md | 2 +- packages/subagent/README.md | 4 +- packages/subagent/subagent-acp/README.md | 2 +- .../subagent/subagent-subprocess/README.md | 2 +- packages/subagent/subagent/README.md | 2 +- packages/subagent/tool-subagent/README.md | 6 +- packages/support/acp-snapshot/README.md | 4 +- packages/support/acp-snapshot/src/harness.ts | 2 +- packages/support/invariants/README.md | 4 +- packages/support/invariants/src/index.ts | 6 +- .../invariants/tests/invariants.spec.ts | 4 +- packages/tasks/README.md | 2 +- packages/tasks/tasks/README.md | 2 +- packages/timeout/README.md | 2 +- packages/timeout/timeout-policy/README.md | 2 +- packages/todo/tool-todo/README.md | 2 +- packages/ui/acp/README.md | 12 +- packages/ui/acp/acp-feature-support.md | 10 +- packages/ui/acp/src/index.ts | 4 +- packages/ui/jsonrpc/src/index.ts | 2 +- packages/ui/permission/README.md | 2 +- packages/ui/tui/README.md | 2 +- packages/ui/user-approval/README.md | 2 +- packages/util/README.md | 4 +- packages/util/retention/README.md | 2 +- packages/util/timeout/README.md | 2 +- packages/web/README.md | 2 +- packages/web/tool-web/README.md | 2 +- packages/web/tool-web/tests/spill.spec.ts | 4 +- packages/web/web-fetch-local/README.md | 2 +- packages/web/web-fetch-local/src/policy.ts | 2 +- packages/web/web-search-exa/README.md | 2 +- packages/web/web-search-perplexity/README.md | 2 +- packages/web/web/README.md | 4 +- packages/workflow/README.md | 4 +- packages/workflow/tool-workflow/README.md | 2 +- .../workflow-workerthread/src/realm.ts | 2 +- packages/workflow/workflow/README.md | 2 +- pnpm-workspace.yaml | 2 +- python/README.i18n.yaml | 4 +- python/README.md | 2 +- python/README.zh.md | 2 +- scripts/{rfc-index.ts => agent-note-index.ts} | 64 +++++----- scripts/build-exe-for-python-sdk.ts | 6 +- scripts/doc-typecheck.ts | 2 +- scripts/gen-agent-note-index.ts | 36 ++++++ scripts/gen-config-catalog.ts | 2 +- scripts/gen-doc-graphs.ts | 2 +- scripts/gen-persistence-catalog.ts | 2 +- scripts/gen-rfc-index.ts | 36 ------ scripts/gen-tool-catalog.ts | 8 +- scripts/run-gates.ts | 4 +- scripts/translation-pairing.manifest.json | 6 +- scripts/translation-pairing.spec.ts | 8 +- scripts/verify-agent-note-classification.ts | 46 ++++++++ ...-format.ts => verify-agent-note-format.ts} | 42 +++---- scripts/verify-doc-refs.ts | 15 +-- scripts/verify-md-links.ts | 1 + scripts/verify-md-wrap.ts | 1 + scripts/verify-mermaid.ts | 1 + scripts/verify-package-paths.ts | 1 + scripts/verify-package-readme-limitations.ts | 2 +- .../verify-package-readme-model-experience.ts | 2 +- scripts/verify-rfc-classification.ts | 39 ------- scripts/verify-translation-pairing.ts | 18 ++- scripts/verify-type-equiv.ts | 2 +- vitest.config.ts | 4 +- website/zh-CN/api/harness/events.md | 4 +- website/zh-CN/api/index.md | 54 ++++----- website/zh-CN/design/effects-coeffects.md | 4 +- website/zh-CN/design/index.md | 10 +- website/zh-CN/develop/basic/index.md | 4 +- website/zh-CN/develop/basic/tool.md | 2 +- website/zh-CN/develop/framework/index.md | 4 +- website/zh-CN/develop/framework/service.md | 2 +- website/zh-CN/develop/practice/index.md | 2 +- website/zh-CN/guide/index.md | 2 +- website/zh-CN/guide/quickstart.md | 2 +- 452 files changed, 1443 insertions(+), 1414 deletions(-) create mode 100644 .agents/notes/AGENTS.md rename {docs/rfc => .agents/notes}/INDEX.md (97%) create mode 100644 .agents/notes/README.md create mode 100644 .agents/notes/implemented/AGENTS.md rename {docs/rfc => .agents/notes}/implemented/CLAUDE.md (100%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-content-block-vocabulary.md (90%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-custom-schema-dsl.md (95%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-event-sourced-sessions.md (96%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md (91%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-runtime-arg-validation.md (94%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-structured-error-taxonomy.md (94%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md (95%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-13-capability-seams.md (88%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-13-twin-llm-adapters.md (96%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-14-session-persistence.md (90%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-15-turn-enclosure-invariant.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-17-filesystem-capability-seam.md (90%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md (97%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-18-session-surface.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md (93%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-20-branded-ids.md (96%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-20-extract-example-app-packages.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md (95%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-20-package-hierarchy.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md (81%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-24-web-capability-seam.md (97%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-26-file-context-as-event-gate.md (92%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md (94%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-06-30-event-domain-semantics.md (80%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-02-fs-per-session-cwd.md (92%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md (97%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-02-tool-render-intent-union.md (92%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md (96%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-05-reconstructable-requests.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md (77%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-06-timeout-deadline-library.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-06-tool-result-retention-library.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-07-tool-call-timeout-policy.md (83%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-08-agent-scope-contexts.md (95%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-08-tool-output-spill-files.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml (81%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md (94%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md (95%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml (70%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-12-agent-scope-runtime-design.md (96%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml (62%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md (95%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md (95%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml (64%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-agent-initiator-scope.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md (98%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml (60%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml (63%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-replay-token-meter-service.md (99%) rename {docs/rfc => .agents/notes}/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-14-acp-agent-client-protocol.md (97%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-14-acp-multi-session.md (98%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-15-code-mode.md (89%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-17-filesystem-tool-schemas.md (86%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md (90%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-18-compaction-capability-seam.md (89%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-21-subagent-capability-seam.md (82%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-22-acp-subagent-backend.md (84%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-24-workspace-context.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-25-ask-user-question.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-29-todo-write-tool.md (98%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-30-hook-bridges.md (88%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-30-hook-protocol-lib.md (90%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-30-interception-seams.md (92%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-30-session-store-fork-api.md (83%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-06-30-subagent-observe-enrich.md (57%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-05-dynamic-workflows.md (96%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-05-skill-system.md (96%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-06-approval-seam.md (90%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-06-explicit-tool-order.md (96%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-06-sandbox.md (96%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-07-mcp-client-plugin.md (98%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-07-session-prefix.md (87%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-08-background-subagent-tasks.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-08-repeat-tool-guard.md (91%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-08-self-referential-cordis-toolset.md (92%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md (92%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md (94%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-10-parallel-tool-call-execution.md (97%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-10-session-query-service.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-13-session-query-tracing.md (98%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml (65%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-14-time-context-plugin.md (97%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-14-time-context-plugin.zh.md (95%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml (62%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-16-durable-per-step-time-context.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md (99%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml (60%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md (92%) rename {docs/rfc => .agents/notes}/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md (92%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-11-doc-sync-enforcement.md (99%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-11-quality-gates.md (93%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-11-tsdown-over-dumble.md (78%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-11-vendor-cordis-as-source.md (97%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-16-pnpm-over-yarn.md (99%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-17-ts-build-config.md (99%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-18-markdown-cross-link-lint.md (81%) create mode 100644 .agents/notes/implemented/process/2026-06-20-agent-note-classification.md rename {docs/rfc => .agents/notes}/implemented/process/2026-06-20-core-data-structures-catalog.md (85%) rename {docs/rfc => .agents/notes}/implemented/process/2026-06-20-generated-cordis-catalog.md (95%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml (61%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md (83%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md (84%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-02-tool-schema-catalog.md (96%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-03-documentation-graph-atlas.md (74%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md (98%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-04-doc-tiers-and-budgets.md (74%) create mode 100644 .agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md rename {docs/rfc => .agents/notes}/implemented/process/2026-07-04-persistence-log-catalog.md (98%) create mode 100644 .agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md rename {docs/rfc => .agents/notes}/implemented/process/2026-07-06-export-surface-jsdoc-gate.md (99%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-06-generated-config-catalog.md (93%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-06-node-engine-floor.md (96%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-06-parallel-github-ci-gates.md (99%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-06-parallel-pre-push-gates.md (94%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-10-readme-known-limitations-gate.md (57%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-12-package-model-experience-contract.md (88%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml (59%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md (99%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md (99%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml (62%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md (98%) rename {docs/rfc => .agents/notes}/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md (98%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-19-drop-mutable-session-summary.md (88%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md (96%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md (85%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md (89%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-20-prune-dead-seam-methods.md (77%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-20-public-agent-stop-surface.md (92%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md (82%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-20-unify-agent-and-session-id.md (90%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md (86%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md (88%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-drop-image-content-block.md (87%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-drop-inert-request-knobs.md (71%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md (52%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md (98%) create mode 100644 .agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md (94%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md (62%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md (76%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md (85%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md (96%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md (91%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md (98%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-12-simplify-session-log-representation.md (98%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml (62%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-19-retire-subagent-mock-package.md (98%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md (98%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml (61%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-19-use-one-session-surface-manager.md (98%) rename {docs/rfc => .agents/notes}/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md (97%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-06-11-property-based-testing.md (95%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-06-19-acp-snapshot-tests.md (86%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-06-19-real-api-e2e-ci.md (90%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md (94%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md (90%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-06-22-fork-snapshot-scenarios.md (69%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-06-22-subagent-snapshot-replay.md (94%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-07-04-hook-snapshot-matrix.md (97%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-07-04-single-source-acp-replay-config.md (91%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md (94%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-07-08-shared-acp-snapshot-package.md (81%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml (62%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md (99%) rename {docs/rfc => .agents/notes}/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md (99%) rename {docs/rfc => .agents/notes}/proposed/architecture/2026-06-16-typed-event-schemas.md (91%) rename {docs/rfc => .agents/notes}/proposed/architecture/2026-07-15-sdk-project-editing-architecture.i18n.yaml (61%) rename {docs/rfc => .agents/notes}/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md (99%) rename {docs/rfc => .agents/notes}/proposed/architecture/2026-07-15-sdk-project-editing-architecture.zh.md (99%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-06-30-pre-tool-input-rewrite.md (88%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-06-recallable-compaction.md (96%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md (90%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-08-interactive-side-sessions.md (95%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-10-sqlite-session-query-provider.md (97%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md (99%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-14-sdk-developer-projects.i18n.yaml (64%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-14-sdk-developer-projects.md (99%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-14-sdk-developer-projects.zh.md (99%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-17-sdk-follow-up-capabilities.i18n.yaml (63%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-17-sdk-follow-up-capabilities.md (96%) rename {docs/rfc => .agents/notes}/proposed/feature/2026-07-17-sdk-follow-up-capabilities.zh.md (95%) rename {docs/rfc => .agents/notes}/proposed/process/2026-06-11-api-extractor-reports.md (81%) rename {docs/rfc => .agents/notes}/proposed/process/2026-06-11-architectural-conformance.md (93%) rename {docs/rfc => .agents/notes}/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md (97%) rename {docs/rfc => .agents/notes}/proposed/process/2026-06-20-discover-package-inventory.md (95%) rename {docs/rfc => .agents/notes}/proposed/process/2026-07-13-human-review-skill-maintenance.md (96%) rename {docs/rfc => .agents/notes}/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md (87%) rename {docs/rfc => .agents/notes}/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml (63%) rename {docs/rfc => .agents/notes}/proposed/simplification/2026-07-19-make-jsonrpc-directional.md (98%) rename {docs/rfc => .agents/notes}/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md (98%) rename {docs/rfc => .agents/notes}/proposed/testing/2026-06-11-deterministic-and-stress-testing.md (92%) rename {docs/rfc => .agents/notes}/proposed/testing/2026-06-11-mutation-testing.md (93%) rename {docs/rfc => .agents/notes}/rejected/architecture/2026-06-11-immutable-public-surfaces.md (95%) rename {docs/rfc => .agents/notes}/rejected/architecture/2026-06-20-providerless-example-base.md (90%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md (84%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-drop-acp-session-load.md (93%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md (68%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md (88%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md (90%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-drop-unused-session-lineage.md (94%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-fold-session-persistence-interface.md (94%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-generic-tool-rendering.md (93%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-retire-mid-turn-steering.md (96%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-single-session-acp-bridge.md (88%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-06-20-truncate-interrupted-turns.md (96%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md (65%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md (91%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md (76%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml (62%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-07-19-fold-compaction-package-split.md (97%) rename {docs/rfc => .agents/notes}/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md (98%) delete mode 100644 docs/rfc/README.md delete mode 100644 docs/rfc/implemented/AGENTS.md delete mode 100644 docs/rfc/implemented/process/2026-06-20-rfc-classification.md delete mode 100644 docs/rfc/implemented/process/2026-07-04-generate-rfc-index-tables.md delete mode 100644 docs/rfc/implemented/process/2026-07-05-uniform-rfc-format.md delete mode 100644 docs/rfc/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md rename scripts/{rfc-index.ts => agent-note-index.ts} (61%) create mode 100644 scripts/gen-agent-note-index.ts delete mode 100644 scripts/gen-rfc-index.ts create mode 100644 scripts/verify-agent-note-classification.ts rename scripts/{verify-rfc-format.ts => verify-agent-note-format.ts} (60%) delete mode 100644 scripts/verify-rfc-classification.ts diff --git a/.agents/notes/AGENTS.md b/.agents/notes/AGENTS.md new file mode 100644 index 0000000000..958aff54fc --- /dev/null +++ b/.agents/notes/AGENTS.md @@ -0,0 +1,3 @@ +# AGENTS.md — Agent Notes + +Agent Notes are effectively RFCs written by agents: durable proposals and decision records that preserve rationale, alternatives, consequences, and verification contracts. Follow the [documentation standard](../../docs/AGENTS.md) and the [Agent Note contract](README.md). diff --git a/docs/rfc/INDEX.md b/.agents/notes/INDEX.md similarity index 97% rename from docs/rfc/INDEX.md rename to .agents/notes/INDEX.md index 65afa473fc..fe92f57aef 100644 --- a/docs/rfc/INDEX.md +++ b/.agents/notes/INDEX.md @@ -1,6 +1,6 @@ -# RFC index +# Agent Note index -Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; `verify-rfc-classification` fails when this file is stale. The curated front door — layout, classification, when to write one, and the in-file format — is [README.md](README.md). +Generated by `pnpm run gen-agent-note-index` from the Agent Note tree — never edit by hand; `verify-agent-note-classification` fails when this file is stale. The curated front door — layout, classification, when to write one, and the in-file format — is [README.md](README.md). ## Proposed @@ -180,17 +180,17 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [pnpm as the package manager instead of Yarn 4](implemented/process/2026-06-16-pnpm-over-yarn.md) | 2026-06-16 | | [TSC-first build and one tsconfig](implemented/process/2026-06-17-ts-build-config.md) | 2026-06-17 | | [Markdown cross-link validity linting](implemented/process/2026-06-18-markdown-cross-link-lint.md) | 2026-06-18 | +| [Classify Agent Notes by kind via path-encoded subdirectories](implemented/process/2026-06-20-agent-note-classification.md) | 2026-06-20 | | [Core-data-structures catalog and the `ts type-equiv` drift gate](implemented/process/2026-06-20-core-data-structures-catalog.md) | 2026-06-20 | | [Generated cordis events + services catalog](implemented/process/2026-06-20-generated-cordis-catalog.md) | 2026-06-20 | -| [Classify RFCs by kind via path-encoded subdirectories](implemented/process/2026-06-20-rfc-classification.md) | 2026-06-20 | | [Bilingual documentation via paired sibling files and a pairing gate](implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md) | 2026-07-02 | | [Generated tool-schema catalog (boot-and-harvest)](implemented/process/2026-07-02-tool-schema-catalog.md) | 2026-07-02 | | [Documentation graph index for maintainers and SDK users](implemented/process/2026-07-03-documentation-graph-atlas.md) | 2026-07-03 | | [JSDoc completeness gate for the cordis surface](implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md) | 2026-07-04 | | [Documentation tiers, budgets, and the ceiling gate](implemented/process/2026-07-04-doc-tiers-and-budgets.md) | 2026-07-04 | -| [Generate the RFC index tables](implemented/process/2026-07-04-generate-rfc-index-tables.md) | 2026-07-04 | +| [Generate the Agent Note index tables](implemented/process/2026-07-04-generate-agent-note-index-tables.md) | 2026-07-04 | | [Generated persistence log event catalog](implemented/process/2026-07-04-persistence-log-catalog.md) | 2026-07-04 | -| [One gated in-file format for RFCs](implemented/process/2026-07-05-uniform-rfc-format.md) | 2026-07-05 | +| [One gated in-file format for Agent Notes](implemented/process/2026-07-05-uniform-agent-note-format.md) | 2026-07-05 | | [Export-surface JSDoc gate](implemented/process/2026-07-06-export-surface-jsdoc-gate.md) | 2026-07-06 | | [Generated plugin config catalog](implemented/process/2026-07-06-generated-config-catalog.md) | 2026-07-06 | | [Raise the Node LTS engine floor to 22.19](implemented/process/2026-07-06-node-engine-floor.md) | 2026-07-06 | diff --git a/.agents/notes/README.md b/.agents/notes/README.md new file mode 100644 index 0000000000..16cbf07037 --- /dev/null +++ b/.agents/notes/README.md @@ -0,0 +1,109 @@ +# Agent Notes + +One kind of design doc lives here. An **Agent Note** records a decision or proposal that shapes this codebase — the *why* and *what we gave up*, the parts code and docs can't carry. The full list is the generated [INDEX.md](INDEX.md); this file is the contract — where Agent Notes live, when to write one, and [the in-file format](#the-file-format). + +## Layout and naming + +Every Agent Note has two axes, both encoded in its **path** — `{lifecycle}/{class}/yyyy-mm-dd-topic-title.md`: + +- **Lifecycle** (the top-level folder) is the Agent Note's status, and an Agent Note moves between folders as that status changes: + - **`proposed/`** — proposals reviewed before implementation; not yet built (or only partly). + - **`implemented/`** — the decision shipped. The file records what was decided and what was rejected, and is **kept current with what actually shipped**: when the code later moves a file, renames a package, or changes a key/default, the Agent Note is updated in the same change to match (facts only — paths, names, structure — not the decision itself). See [implemented/AGENTS.md](implemented/AGENTS.md). + - **`rejected/`** — the proposal was considered and declined. Kept for the record so the rejection isn't re-litigated. +- **Class** (the nested folder) is the *kind* of decision — see [Classification](#classification) below. + +The date in the filename is when the topic was **first proposed** (per git history). Cross-references between Agent Notes use relative markdown links (`[topic](../../implemented/architecture/2026-…-….md)`) — never bare prose or numbers — so they are mechanically checkable and survive moves between folders. + +## Classification + +Each Agent Note belongs to one path-encoded class from the closed set in `scripts/agent-note-index.ts`; the classification gate rejects other folders. [INDEX.md](INDEX.md) is generated from paths, titles, and filename dates, and its freshness is gated. Adding a class requires updating the canonical set and this section. See the [classification](implemented/process/2026-06-20-agent-note-classification.md) and [index-generation](implemented/process/2026-07-04-generate-agent-note-index-tables.md) Agent Notes. + +| Class | What it covers | +|---|---| +| `feature` | A new user- or model-facing capability. | +| `bug-fix` | Corrects a defect or closes a gap a postmortem surfaced. | +| `simplification` | Removes code, behavior, or surface area without adding a capability. | +| `architecture` | A structural decision about the **shipped source** — how packages relate, what the runtime vocabulary is. | +| `process` | Tooling, policy, or workflow **around** the code — gates, the package manager, vendoring — not runtime behavior. | +| `testing` | Test infrastructure and strategy. | + +The `architecture` / `process` line: **architecture** is about the source we ship; **process** is the surrounding tooling and workflow. (`refactor` is deliberately absent — it overlaps `simplification`, whose discriminator, "does observable behavior change?", already covers it.) + +## When to write one + +Write an Agent Note when a decision is **durable** (it shapes the codebase beyond a single function or package), **contested** (there was a real alternative a reasonable engineer might have chosen), and **surprising** (a future reader would otherwise ask "why on earth is it done this way?"). A proposal for substantial future work starts in `proposed/`; a decision already made starts in `implemented/`. Pick the class folder that matches the decision (see [Classification](#classification)). + +Do NOT write one for a mechanical or local choice (a variable name, a one-file refactor), for anything already enforced and explained by a gate or a convention in AGENTS.md, or for a still-provisional decision tagged `TODO(...)` in the code — record those as TODOs and promote to an Agent Note only once they settle. An Agent Note is never edited into a *different decision*: supersede it with a new one and cross-link. (Editing an `implemented/` Agent Note to track where its already-made decision now *lives* — a moved file, a renamed package — is not a different decision and is required, not forbidden; see [implemented/AGENTS.md](implemented/AGENTS.md).) + +## The file format + +Every Agent Note follows one in-file format, enforced by `pnpm run verify-agent-note-format` ([scripts/verify-agent-note-format.ts](../../scripts/verify-agent-note-format.ts), part of `doc-sync`); the rationale for the format — and the alternatives it rejected — is [the uniform-format Agent Note](implemented/process/2026-07-05-uniform-agent-note-format.md). + +### The header block + +The first three lines of every Agent Note are exactly: + +```markdown +# Agent Note: + +Status: <status> +``` + +followed by a blank line. The `Status:` value is one of three forms, and must agree with the lifecycle folder the file sits in — the gate cross-checks them: + +- `Status: proposed` +- `Status: implemented` +- `Status: rejected — <why, in one line>` + +The status carries no dates and no parentheticals: the filename holds the first-proposed date, git holds everything else, and an "accepted in amended form" note is body content (state the amendment where the decision is stated). The rejection reason is the one status with content, because a rejected Agent Note's verdict is the fact readers come for. + +### The body skeleton + +Every Agent Note opens its body with `## Problem` — the motivation, written to stand without the solution. What follows depends on the lifecycle; recurring sections use these canonical names and nothing else, while genuinely bespoke technical sections (package topology, wire contracts, schemas) remain free-form between the required ones. + +#### `proposed/` + +```markdown +## Problem +## Proposal +…bespoke sections… +## Alternatives considered +## Acceptance criteria +## Risks +``` + +`## Proposal` is the intended change and may legitimately speak in the future tense — plans, migration steps, and open questions belong here while the work is unbuilt. `## Acceptance criteria` says what observable state means done. `## Risks` covers both what could go wrong and what the change knowingly gives up. + +#### `implemented/` + +```markdown +## Problem +## Decision +…bespoke sections… +## Alternatives considered +## Consequences +``` + +`## Decision` describes shipped reality in the present tense, and the whole file is kept current with it per [implemented/AGENTS.md](implemented/AGENTS.md). `## Consequences` records what the trade-off cost **and** bought. Proposal-era headings are spec-speak here and the gate rejects them: `## Proposal`, `## Plan`, `## Migration plan`, and `## Acceptance criteria` may not appear in an implemented Agent Note (the [slop checklist](../../docs/AGENTS.md) names why). A `## Testing`, `## Deferred`, or `## Related` section is fine where it states present-tense fact. + +#### `rejected/` + +A rejected Agent Note is the proposal, frozen: it keeps whatever proposal-time sections it had (including `## Acceptance criteria` or `## Plan`), and the verdict lives on the `Status:` line. Only the header block, the `## Problem` opener, a `## Proposal` section, and the Alternatives-considered mandate below apply. + +### Alternatives considered — mandatory + +Every Agent Note carries an `## Alternatives considered` section: each genuine alternative and why it lost, one bold-led paragraph per alternative or a `### Why not <X>?` subsection per contested one. A decision recorded without what it beat invites re-litigation — the failure Agent Notes exist to prevent. + +Alternatives are recorded, never invented. An Agent Note dated before 2026-07-05 whose alternatives are not reconstructible from the record carries this exact comment in place of the section, which the gate accepts for pre-format files only: + +```markdown +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> +``` + +### Moving between lifecycles + +Moving a file between lifecycle folders means updating the `Status:` line and re-satisfying that folder's skeleton in the same change — the gate fails the move otherwise. Concretely, `proposed/` → `implemented/` rewrites `## Proposal` into a present-tense `## Decision`, folds `## Acceptance criteria` and `## Risks` into `## Consequences` (or a present-tense `## Testing`/`## Verification` section for what now pins the behavior), and drops plans in favor of what shipped — the rewrite [implemented/AGENTS.md](implemented/AGENTS.md) requires, made mechanical. `proposed/` → `rejected/` only adds the reason to the `Status:` line and freezes the file. + +### Chinese counterparts + +A `.zh.md` counterpart mirrors its English sibling's structure section-for-section under the [i18n contract](../../docs/i18n/README.md); the machine-checked header tokens (`# Agent Note: ` and the `Status:` line) stay in English verbatim. The format gate skips `.zh.md` files — the pairing gate owns their consistency. diff --git a/.agents/notes/implemented/AGENTS.md b/.agents/notes/implemented/AGENTS.md new file mode 100644 index 0000000000..5fb3fde8e2 --- /dev/null +++ b/.agents/notes/implemented/AGENTS.md @@ -0,0 +1,11 @@ +# AGENTS.md — Implemented Agent Notes + +These Agent Notes describe shipped decisions. Follow the [root instructions](../../../AGENTS.md), [documentation standard](../../../docs/AGENTS.md), and [Agent Note format](../README.md#the-file-format); `verify-agent-note-format` gates the lifecycle-specific structure. + +## Keep an implemented Agent Note current with what actually shipped + +Keep paths, symbols, defaults, and mechanisms current in the same change that alters them. Rewrite stale facts in place; do not append change history. + +### This is not a license to rewrite the *decision* + +Update factual realization in place. A reversal of the decision or its rationale requires a new Agent Note and cross-link; see the [Agent Note contract](../README.md). diff --git a/docs/rfc/implemented/CLAUDE.md b/.agents/notes/implemented/CLAUDE.md similarity index 100% rename from docs/rfc/implemented/CLAUDE.md rename to .agents/notes/implemented/CLAUDE.md diff --git a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md similarity index 90% rename from docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md rename to .agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md index 77f521834c..35d40ad0f4 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -1,4 +1,4 @@ -# RFC: Provider-neutral content-block vocabulary owned by dsh-llm +# Agent Note: Provider-neutral content-block vocabulary owned by dsh-llm Status: implemented @@ -20,7 +20,7 @@ In-session context injection (`context/message`, `steering/message`) renders as ## Consequences - Reasoning has a core home without provider-specific shapes. -- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md). -- Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../simplification/2026-07-04-drop-inert-request-knobs.md) RFCs. +- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md). +- Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../simplification/2026-07-04-drop-inert-request-knobs.md) Agent Notes. - Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests. - IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost. diff --git a/docs/rfc/implemented/architecture/2026-06-11-custom-schema-dsl.md b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md similarity index 95% rename from docs/rfc/implemented/architecture/2026-06-11-custom-schema-dsl.md rename to .agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md index 18923fbb60..bf8c02140a 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-custom-schema-dsl.md +++ b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md @@ -1,4 +1,4 @@ -# RFC: Custom typed tool-schema DSL instead of schemastery +# Agent Note: Custom typed tool-schema DSL instead of schemastery Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md rename to .agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md index aac3991f46..90e215019b 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md @@ -1,4 +1,4 @@ -# RFC: Source-owned session immutability and dev-mode invariants +# Agent Note: Source-owned session immutability and dev-mode invariants Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-06-11-event-sourced-sessions.md b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md similarity index 96% rename from docs/rfc/implemented/architecture/2026-06-11-event-sourced-sessions.md rename to .agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md index 4539fb40ba..bab36ee783 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-event-sourced-sessions.md +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md @@ -1,4 +1,4 @@ -# RFC: Event-sourced sessions with derived message history +# Agent Note: Event-sourced sessions with derived message history Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md similarity index 91% rename from docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md rename to .agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md index 1d10bfa479..abdadb447b 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md @@ -1,4 +1,4 @@ -# RFC: Microkernel — extension via Cordis event taxonomy, one concrete loop +# Agent Note: Microkernel — extension via Cordis event taxonomy, one concrete loop Status: implemented @@ -23,7 +23,7 @@ The event vocabulary lives in interface packages (dsh-agent declares the agent/* ## Consequences -- Every MVP feature maps to a listener (the [feature → mechanism map](../../../cookbook/extension-cookbook.md#the-feature--mechanism-map) is the proof obligation, kept current). +- Every MVP feature maps to a listener (the [feature → mechanism map](../../../../docs/cookbook/extension-cookbook.md#the-feature--mechanism-map) is the proof obligation, kept current). - HMR and disposal come free: listeners and registrations are Cordis effects. - Waterfall semantics (call `next()` or short-circuit) are non-obvious and must be taught — documented in AGENTS.md and covered by composition tests. - The loop must be defensive: plugin exceptions are contained at turn level, steering from any seam is never stranded (regression-tested). diff --git a/docs/rfc/implemented/architecture/2026-06-11-runtime-arg-validation.md b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md similarity index 94% rename from docs/rfc/implemented/architecture/2026-06-11-runtime-arg-validation.md rename to .agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md index 33bf241c74..454f12d0af 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-runtime-arg-validation.md +++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md @@ -1,4 +1,4 @@ -# RFC: Runtime arg validation at the model boundary +# Agent Note: Runtime arg validation at the model boundary Status: implemented @@ -19,4 +19,4 @@ The validator mirrors `schemaSpecToJsonSchema` semantics exactly — same struct - `ToolArgsError` is a plain `Error` with a `code` field for now; if a harness-wide error taxonomy lands it becomes a subclass without changing callers that read `.message`. - Validation cost is negligible next to a model call. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/architecture/2026-06-11-structured-error-taxonomy.md b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md similarity index 94% rename from docs/rfc/implemented/architecture/2026-06-11-structured-error-taxonomy.md rename to .agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md index 01e50da2ff..eacd409a57 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-structured-error-taxonomy.md +++ b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md @@ -1,4 +1,4 @@ -# RFC: Structured error taxonomy +# Agent Note: Structured error taxonomy Status: implemented @@ -21,4 +21,4 @@ A single `HarnessError extends Error` base in `dsh-llm` (the leaf package every - `deriveMessages` does not surface `error` into model history — the model still sees the text block; the structured field is for code and replay. - Argument validation and dev invariants retain their existing codes and behavior; the shared base adds cross-seam routing metadata without changing model-facing text. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md similarity index 95% rename from docs/rfc/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md rename to .agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md index 5c78ef4280..59ea9117dc 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md +++ b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md @@ -1,4 +1,4 @@ -# RFC: Tool schemas are part of the system-prompt assembly +# Agent Note: Tool schemas are part of the system-prompt assembly Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-06-13-capability-seams.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md similarity index 88% rename from docs/rfc/implemented/architecture/2026-06-13-capability-seams.md rename to .agents/notes/implemented/architecture/2026-06-13-capability-seams.md index 6887660de0..5ca299abc0 100644 --- a/docs/rfc/implemented/architecture/2026-06-13-capability-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md @@ -1,4 +1,4 @@ -# RFC: Capability seams — interface / implementation / consumer split +# Agent Note: Capability seams — interface / implementation / consumer split Status: implemented @@ -6,7 +6,7 @@ Status: implemented The harness has swappable capabilities — bash execution today, sandboxed/remote executors and alternative model providers tomorrow. A capability has three concerns that change at different rates and for different reasons: the *contract* (what the capability is), the *implementation* (how it runs), and the *consumer surface* (what the model and other plugins program against). Bundling them in one package couples those rates of change — swapping a local executor for a sandboxed one would churn the tool schemas the model sees, even though the model-facing contract never changed. -This is distinct from "who provides vs. needs a capability at runtime", which Cordis already answers with services + `inject` (a provider registers `ctx.bash`; a consumer declares `inject: ['bash']` and its fiber pends until the service exists). That mechanism is necessary but doesn't dictate package boundaries; this RFC does. +This is distinct from "who provides vs. needs a capability at runtime", which Cordis already answers with services + `inject` (a provider registers `ctx.bash`; a consumer declares `inject: ['bash']` and its fiber pends until the service exists). That mechanism is necessary but doesn't dictate package boundaries; this Agent Note does. ## Decision @@ -23,8 +23,8 @@ The split is not mandatory when the parts are genuinely one concern: the LLM sea ## Alternatives considered - **One combined package** — rejected because it recouples the three rates of change the split exists to separate (the whole point). -- **`@cordisjs/plugin-capability`** — a different axis entirely: it is a permission/capability-*security* service (named permissions with inheritance, tested against a session via `ctx.capability.test`), a candidate for the deferred permissions/sandbox work on the `tools/pre-execute` deny/ask seam, NOT a mechanism for swapping implementations. Confusing the two ("capability") is the trap this RFC names. +- **`@cordisjs/plugin-capability`** — a different axis entirely: it is a permission/capability-*security* service (named permissions with inheritance, tested against a session via `ctx.capability.test`), a candidate for the deferred permissions/sandbox work on the `tools/pre-execute` deny/ask seam, NOT a mechanism for swapping implementations. Confusing the two ("capability") is the trap this Agent Note names. ## Consequences -More packages and more boilerplate per capability (a `package.json`/`tsconfig`/README trio, the inject wiring). Bought: implementations and consumers ship and version independently, and a new backend never risks the model-facing contract. The rule is documented in [AGENTS.md](../../../../AGENTS.md) § Conventions ("Capability seams are three packages") and [architecture.md](../../../architecture.md) § "Capability seams"; the bash trio is the reference template. When to fold vs. split is a judgment call the architecture doc spells out — this RFC records *why* the default is to split. +More packages and more boilerplate per capability (a `package.json`/`tsconfig`/README trio, the inject wiring). Bought: implementations and consumers ship and version independently, and a new backend never risks the model-facing contract. The rule is documented in [AGENTS.md](../../../../AGENTS.md) § Conventions ("Capability seams are three packages") and [architecture.md](../../../../docs/architecture.md) § "Capability seams"; the bash trio is the reference template. When to fold vs. split is a judgment call the architecture doc spells out — this Agent Note records *why* the default is to split. diff --git a/docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md similarity index 96% rename from docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md rename to .agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md index 0ded28f598..7f2f5933ad 100644 --- a/docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md +++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md @@ -1,4 +1,4 @@ -# RFC: Two LLM adapters as a design-verification twin +# Agent Note: Two LLM adapters as a design-verification twin Status: implemented @@ -22,4 +22,4 @@ The rule they enforce: **anything the StreamChunk vocabulary cannot express for ## Consequences -The twin doubles adapter and key-gated e2e maintenance—both cover V4 Flash and Pro across representative reasoning modes—in exchange for continuous seam-neutrality validation and a second implementation example. Both use `apiKey`, `baseURL`, and `models`; the hand-rolled adapter exposes `thinking`/`reasoningEffort`, while pi-ai exposes one `reasoning` level. A future conformance suite could justify retiring one adapter through a superseding RFC. +The twin doubles adapter and key-gated e2e maintenance—both cover V4 Flash and Pro across representative reasoning modes—in exchange for continuous seam-neutrality validation and a second implementation example. Both use `apiKey`, `baseURL`, and `models`; the hand-rolled adapter exposes `thinking`/`reasoningEffort`, while pi-ai exposes one `reasoning` level. A future conformance suite could justify retiring one adapter through a superseding Agent Note. diff --git a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md similarity index 90% rename from docs/rfc/implemented/architecture/2026-06-14-session-persistence.md rename to .agents/notes/implemented/architecture/2026-06-14-session-persistence.md index 3bd3c3fdf1..e84d7fefd3 100644 --- a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md @@ -1,10 +1,10 @@ -# RFC: Session persistence as an abstract service over the existing `SessionEvent` +# Agent Note: Session persistence as an abstract service over the existing `SessionEvent` Status: implemented ## Problem -Sessions lived only in memory. The example `session-jsonl.ts` plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered `session/event` and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume ("continue yesterday's task"), durable forking, and the ACP `session/load` method ([ACP support](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)) were all impossible. +Sessions lived only in memory. The example `session-jsonl.ts` plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered `session/event` and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume ("continue yesterday's task"), durable forking, and the ACP `session/load` method ([ACP support](../feature/2026-06-14-acp-agent-client-protocol.md)) were all impossible. The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append-only log the single source of truth and derives LLM history from it. Persistence had to stay faithful to that: persist the existing `SessionEvent` directly, with no parallel "persisted message" type that the log is converted to and from. The backend also had to be swappable — a file store now, a database store later — behind one interface. @@ -31,4 +31,4 @@ Format versioning: the header carries a `version`; `load` rejects any non-curren ## Consequences -Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and the foundation the ACP `session/load` ([ACP support](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)) needs — all over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, and serializability semantics. Persisting the full log also settles event fidelity: `assistant/chunk` remains verbatim. +Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and the foundation the ACP `session/load` ([ACP support](../feature/2026-06-14-acp-agent-client-protocol.md)) needs — all over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, and serializability semantics. Persisting the full log also settles event fidelity: `assistant/chunk` remains verbatim. diff --git a/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md rename to .agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md index a54f735219..74ab8b6bf3 100644 --- a/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md +++ b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md @@ -1,4 +1,4 @@ -# RFC: Every session event is enclosed in a turn +# Agent Note: Every session event is enclosed in a turn Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-06-17-filesystem-capability-seam.md b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md similarity index 90% rename from docs/rfc/implemented/architecture/2026-06-17-filesystem-capability-seam.md rename to .agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md index 0121a11fa0..e76ca22e2d 100644 --- a/docs/rfc/implemented/architecture/2026-06-17-filesystem-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md @@ -1,4 +1,4 @@ -# RFC: Filesystem capability seam — ctx.fs, local backend, and model-facing filesystem tools +# Agent Note: Filesystem capability seam — ctx.fs, local backend, and model-facing filesystem tools Status: implemented @@ -18,7 +18,7 @@ We need the filesystem tools to land in the same capability-seam shape as bash b ## Decision -Filesystem access is a first-class capability seam following [the capability-seam RFC](../../implemented/architecture/2026-06-13-capability-seams.md): +Filesystem access is a first-class capability seam following [the capability-seam Agent Note](2026-06-13-capability-seams.md): 1. `@deepseek-ai/dsh-fs` (`packages/fs/fs`) owns the abstract `ctx.fs` service, the filesystem vocabulary types, and the `fs/*` policy event vocabulary. 2. `@deepseek-ai/dsh-fs-local` (`packages/fs/fs-local`) provides the first implementation, backed by the local filesystem. @@ -26,7 +26,7 @@ Filesystem access is a first-class capability seam following [the capability-sea The consumer package depends only on the interface package, never on `dsh-fs-local`. A deployment that wants a different backend loads a different provider for `ctx.fs` without changing the tool schemas or model-facing prompt guidance. -The read-before-write/edit and observed-state policy is a fourth package, `@deepseek-ai/dsh-fs-policy` (`packages/fs/fs-policy`), contributed through the `fs/*` event gate rather than living on `ctx.fs`; a deployment loading `dsh-tool-fs` also loads `dsh-fs-policy` to get read-before-write/edit. This RFC established the three-package seam; the split of policy off the provider base class is decided by [the split-fs-seam RFC](../simplification/2026-06-26-fsspec-style-fs-seam.md), and its realization as an event-gate plugin (not a method service) by [the event-gate RFC](2026-06-26-file-context-as-event-gate.md). This document is updated to describe that landed four-package shape. +The read-before-write/edit and observed-state policy is a fourth package, `@deepseek-ai/dsh-fs-policy` (`packages/fs/fs-policy`), contributed through the `fs/*` event gate rather than living on `ctx.fs`; a deployment loading `dsh-tool-fs` also loads `dsh-fs-policy` to get read-before-write/edit. This Agent Note established the three-package seam; the split of policy off the provider base class is decided by [the split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md), and its realization as an event-gate plugin (not a method service) by [the event-gate Agent Note](2026-06-26-file-context-as-event-gate.md). This document is updated to describe that landed four-package shape. The first backend is deliberately local-only: `dsh-fs-local` implements `ctx.fs` against the host filesystem. Future sibling backends can provide sandboxed, remote, virtual, or project-scoped filesystems behind the same interface. @@ -34,7 +34,7 @@ The first consumer is deliberately text-file-only: `dsh-tool-fs` exposes model-f Filesystem permissions and sandboxing are not implied by this split. The local backend resolves relative paths from its configured base directory, but containment policy is a separate decision: either a stricter `ctx.fs` implementation enforces it, or a permission/sandbox plugin wraps `tools/execute` and vetoes calls before they reach the consumer. -Read-before-write/edit and observed state belong to `dsh-fs-policy`, not `ctx.fs`. Through the `fs/*` event gate, the policy records versions per opaque actor and supplies optional mutation expectations; the provider enforces freshness atomically. `dsh-tool-fs` emits the events without depending on the policy. See the [split-seam](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [event-gate](2026-06-26-file-context-as-event-gate.md) RFCs. +Read-before-write/edit and observed state belong to `dsh-fs-policy`, not `ctx.fs`. Through the `fs/*` event gate, the policy records versions per opaque actor and supplies optional mutation expectations; the provider enforces freshness atomically. `dsh-tool-fs` emits the events without depending on the policy. See the [split-seam](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [event-gate](2026-06-26-file-context-as-event-gate.md) Agent Notes. ## Package topology @@ -71,7 +71,7 @@ The provider seam also carries the freshness hooks that policy builds on — but - `writeText`/`editText` take an OPTIONAL version expectation: omit it for an unconditional bare-provider mutation, or supply it to guard the mutation inside the backend's atomic critical section. - The `dsh-fs-policy` plugin decides that expectation on `fs/write-intent`/`fs/edit-intent` and records observed versions on `fs/observed`, keyed by an owner it derives from the opaque event actor (normally `exec.agent.session`). -Authorization is version freshness, not a full/partial view distinction: any read records the target's version, and a later write/edit is authorized as long as the file is still at that version — so a windowed read of lines 100-150 authorizes an edit of line 120. The observed-state store is a `WeakMap<owner, Map<targetKey, version>>` inside `dsh-fs-policy`; `dsh-fs` holds none of it and treats the actor as opaque. (This RFC first modeled a `FileState` cache with `full`/`partial` views on `ctx.fs`; the split-fs-seam and event-gate RFCs replaced that with the freshness-based policy plugin described here.) +Authorization is version freshness, not a full/partial view distinction: any read records the target's version, and a later write/edit is authorized as long as the file is still at that version — so a windowed read of lines 100-150 authorizes an edit of line 120. The observed-state store is a `WeakMap<owner, Map<targetKey, version>>` inside `dsh-fs-policy`; `dsh-fs` holds none of it and treats the actor as opaque. (This Agent Note first modeled a `FileState` cache with `full`/`partial` views on `ctx.fs`; the split-fs-seam and event-gate Agent Notes replaced that with the freshness-based policy plugin described here.) Path resolution is explicit and allowed to be async. Local resolution may only normalize a path, but sandboxed/remote/project-scoped backends may need I/O to resolve a user-supplied path into a stable target identity. @@ -135,7 +135,7 @@ The defensive-pattern classes this repo has been bitten by are pinned directly: - **Model-facing tools directly over `node:fs`** — the tool package would own execution policy, path resolution, atomic writes, text decoding, and edit semantics at once, coupling the three independently-changing concerns the Problem names and churning schemas on any backend swap. - **One combined `dsh-fs-tools` package** — the pre-seam shape; rejected for the same interface/implementation/consumer split as bash, and the combined name never became public surface. -- **Observed-state on `ctx.fs`** — the shape this RFC first landed; superseded by [the split-fs-seam RFC](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [the event-gate RFC](2026-06-26-file-context-as-event-gate.md): a sandboxed/remote backend must not inherit model-facing observation policy, so the provider keeps only the version token and the optional version-guarded mutation. +- **Observed-state on `ctx.fs`** — the shape this Agent Note first landed; superseded by [the split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [the event-gate Agent Note](2026-06-26-file-context-as-event-gate.md): a sandboxed/remote backend must not inherit model-facing observation policy, so the provider keeps only the version token and the optional version-guarded mutation. ## Consequences @@ -143,11 +143,11 @@ The defensive-pattern classes this repo has been bitten by are pinned directly: **The interface can become too local.** Returning fields such as `absolutePath` from `ctx.fs` would make remote, sandboxed, or virtual backends awkward. The contract should expose display metadata without requiring consumers to understand host paths. -**The interface can become too thin.** If `ctx.fs` only mirrors `node:fs` primitives, `tool-fs` will reimplement binary detection, pagination, atomic writes, and edit semantics. That recreates the coupling this RFC is trying to avoid. +**The interface can become too thin.** If `ctx.fs` only mirrors `node:fs` primitives, `tool-fs` will reimplement binary detection, pagination, atomic writes, and edit semantics. That recreates the coupling this Agent Note is trying to avoid. **Edit semantics are race-prone by nature.** Literal edit is a read-modify-write operation; the guard is the backend's atomic mutation critical section plus the optional version expectation, so concurrent edits settle deterministically — one wins, the other gets `FS_STALE_VERSION`. -**Observed state does not belong on `ctx.fs`.** Recording what an execution context has seen is workflow policy, not raw filesystem I/O. This RFC first placed it inside the filesystem seam; the split-fs-seam RFC then established that a sandboxed/remote backend should not inherit model-facing observation policy, and moved it into the `dsh-fs-policy` plugin. The provider seam keeps only what write/edit safety genuinely needs at the storage layer — a backend-minted version token and an optional version-guarded mutation — while the policy plugin owns owner derivation, observed-state, and read-before-edit gating over the `fs/*` events. +**Observed state does not belong on `ctx.fs`.** Recording what an execution context has seen is workflow policy, not raw filesystem I/O. This Agent Note first placed it inside the filesystem seam; the split-fs-seam Agent Note then established that a sandboxed/remote backend should not inherit model-facing observation policy, and moved it into the `dsh-fs-policy` plugin. The provider seam keeps only what write/edit safety genuinely needs at the storage layer — a backend-minted version token and an optional version-guarded mutation — while the policy plugin owns owner derivation, observed-state, and read-before-edit gating over the `fs/*` events. **The `resolve`-then-operate shape costs an extra round-trip per call.** Each tool may resolve a path to an `FsTarget` and then issue the read/write/edit as a separate `ctx.fs` call. For the local backend this is negligible (resolution is in-memory path normalization), but a remote/sandboxed backend may turn each step into its own request, so a single `read` can become two network round-trips. Backends where the round-trip matters can cache or fold resolution internally while preserving the observable contract. diff --git a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md similarity index 97% rename from docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md rename to .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index d75ec379fc..125ef0946c 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md @@ -1,4 +1,4 @@ -# RFC: Agent lifecycle and ownership seams +# Agent Note: Agent lifecycle and ownership seams Status: implemented @@ -41,7 +41,7 @@ The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` bein - **A public `BashTask.owner` field** instead of the `BashExecutor.ownerOf(id)` seam — rejected: one read path, no redundant API. - **Sibling cordis effects for the agent's session lifecycle** — rejected: a fiber unload disposes sibling effects concurrently (`Promise.all`), racing removal of the store-owned append publication hooks against the loop's closing `session/flush`; the single composite effect's ordered LIFO chain is what captures the closing `turn/end` on both disposal paths. -- **A separate step-only `abort()` beside `cancel()`** — shipped originally, then removed as unused; `cancel()` is the single public stop primitive ([the public-stop-surface RFC](../simplification/2026-06-20-public-agent-stop-surface.md)). +- **A separate step-only `abort()` beside `cancel()`** — shipped originally, then removed as unused; `cancel()` is the single public stop primitive ([the public-stop-surface Agent Note](../simplification/2026-06-20-public-agent-stop-surface.md)). ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-06-18-session-surface.md rename to .agents/notes/implemented/architecture/2026-06-18-session-surface.md index d639fe2917..dbeee097d2 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md @@ -1,4 +1,4 @@ -# RFC: Session surface — an ordered projection over the event log +# Agent Note: Session surface — an ordered projection over the event log Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md similarity index 93% rename from docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md rename to .agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md index fef6ad034c..7c73cf24a4 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md @@ -1,4 +1,4 @@ -# RFC: Shared persistence write coordinator +# Agent Note: Shared persistence write coordinator Status: implemented @@ -10,7 +10,7 @@ Status: implemented Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistence`. The coordinator owns the orchestration once; each first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements a small `PersistenceBackend` hook interface, and delegates its four public service methods (`create`/`append`/`load`/`list`) to it. -Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The RFC's risk — "a coordinator must not make unusual backends fight an inheritance hierarchy" — is avoided: a backend exposes only the hooks; it cannot reach the coordinator's private orchestration state, and the public `SessionPersistence` service shape is unchanged, so a third-party backend MAY still implement the abstract service directly without the coordinator at all. +Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The Agent Note's risk — "a coordinator must not make unusual backends fight an inheritance hierarchy" — is avoided: a backend exposes only the hooks; it cannot reach the coordinator's private orchestration state, and the public `SessionPersistence` service shape is unchanged, so a third-party backend MAY still implement the abstract service directly without the coordinator at all. The coordinator retires each live session from its `session/disposed` notification: it waits for that exact Session object's initialization, serializes a final drain, and then removes the owned state, buffer, and init entries. Failed drains retain their buffers for backend teardown to retry. Settled per-id chain tails remove themselves only when they are still the current tail, so a completion cannot erase a newer operation for the same id. Backend teardown unregisters the write-path listeners before awaiting all admitted retirements, remaining buffers, and chains, then closes the backend. diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md similarity index 96% rename from docs/rfc/implemented/architecture/2026-06-20-branded-ids.md rename to .agents/notes/implemented/architecture/2026-06-20-branded-ids.md index fd5c5bf953..e7a3110fce 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md @@ -1,4 +1,4 @@ -# RFC: Branded IDs everywhere they belong +# Agent Note: Branded IDs everywhere they belong Status: implemented @@ -50,11 +50,11 @@ The obvious shortcut is to type `owner` as `SessionId` directly — it always *i Kept deliberately narrow per the "not every string needs a brand" policy. Each of these is a plausible future brand, deferred with a reason, not a commitment: -- **`ModelId`** (`GenerateOptions.model`, the `LlmService` adapter-registry key) — a real cross-package lookup key (config → agent → llm → adapter); a reasonable next brand, left out only to keep this RFC's blast radius focused. +- **`ModelId`** (`GenerateOptions.model`, the `LlmService` adapter-registry key) — a real cross-package lookup key (config → agent → llm → adapter); a reasonable next brand, left out only to keep this Agent Note's blast radius focused. - **`ToolName`** (the `ToolRegistry` key) — author-defined, human-readable, and rarely confused with another id; the weakest candidate, likely not worth a brand. - **`ErrorCode`** (`HarnessError.code`) — a closed vocabulary (`ABORTED`, `NO_ADAPTER`, …), not a per-instance id; better served by a string-literal union than a brand, if anything. - **Numeric ordinals** — turn number, step number, and the event `seq` are `number`, not `string`, so `Branded<string>` does not apply; a parallel `number & { readonly [BRAND]: B }` variant could brand them, but they are positional ordinals rarely passed across boundaries, so the payoff is low. -- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string today. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what do we do on failure?) and belongs in its own RFC, not bundled into this type-only pass. +- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string today. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what do we do on failure?) and belongs in its own Agent Note, not bundled into this type-only pass. ## Verification @@ -63,5 +63,5 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences - **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. -- **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. -- **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. +- **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This Agent Note does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. +- **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this Agent Note errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/architecture/2026-06-20-extract-example-app-packages.md b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-06-20-extract-example-app-packages.md rename to .agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md index 0582515c62..3fa7227d04 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-extract-example-app-packages.md +++ b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md @@ -1,4 +1,4 @@ -# RFC: Extract example apps into packages +# Agent Note: Extract example apps into packages Status: implemented @@ -40,7 +40,7 @@ The old `base*.yml`/`acp-tail.yml` includes already deduped the *config*, but a - Example directories contain only their config, README, and tests: `start.ts`, the infrastructure preamble, and the shared YAML includes are gone. - `demo:echo`, `demo:repl`, and `demo:acp` invoke the app-package bins. -- Each new package has a README and per-file 100% coverage; each app package also has a keyless real-Loader-path bin smoke that catches export-shape failures described in [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md). +- Each new package has a README and per-file 100% coverage; each app package also has a keyless real-Loader-path bin smoke that catches export-shape failures described in [postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md). - The ACP replay transcript remains unchanged because the plugin set and load order did not change. ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md similarity index 95% rename from docs/rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md rename to .agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md index c99eb9f0fe..4db0d78910 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md @@ -1,4 +1,4 @@ -# RFC: The background task runtime (`ctx.tasks`) and generic task control tools +# Agent Note: The background task runtime (`ctx.tasks`) and generic task control tools Status: implemented @@ -21,7 +21,7 @@ Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into in ## Runtime contract -The literal types live in the [task data-structure catalog](../../../core-data-structures/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id. +The literal types live in the [task data-structure catalog](../../../../docs/core-data-structures/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id. The producer hooks define three responsibilities: @@ -123,6 +123,6 @@ Unit coverage pins preflight atomicity, per-kind ids, stream and final reads, wa ## Consequences -Bash commands and subagents share one id vocabulary, listing, notice format, prompt habit, and set of control tools. New long-running producers implement execution hooks instead of another registry and tool family. The [tool cookbook](../../../cookbook/adding-a-tool.md) points producers to this contract. +Bash commands and subagents share one id vocabulary, listing, notice format, prompt habit, and set of control tools. New long-running producers implement execution hooks instead of another registry and tool family. The [tool cookbook](../../../../docs/cookbook/adding-a-tool.md) points producers to this contract. Owned background bash now stops with its agent instead of surviving it. Background processes have no executor timeout; callers must kill irrelevant work or rely on owner/service disposal. Stream reads support one consuming reader, completion notices do not wake idle agents, and a producer that returns from `cancel` without settling `done` can still stall teardown. Durable jobs, independent observation cursors, and foreground promotion remain separate designs. diff --git a/docs/rfc/implemented/architecture/2026-06-20-package-hierarchy.md b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-06-20-package-hierarchy.md rename to .agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md index 89b50eb3df..d853696226 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-package-hierarchy.md +++ b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md @@ -1,4 +1,4 @@ -# RFC: Reorganize packages into a modular hierarchy +# Agent Note: Reorganize packages into a modular hierarchy Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md similarity index 81% rename from docs/rfc/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md rename to .agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md index 102a29d613..fdd98b89cb 100644 --- a/docs/rfc/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md @@ -1,10 +1,10 @@ -# RFC: Mandatory `User-Agent` attribution for provider requests +# Agent Note: Mandatory `User-Agent` attribution for provider requests Status: implemented ## Problem -LLM provider requests should identify the product making them. That is useful for provider-side support, abuse investigation, compatibility debugging, and traffic analytics. Before this RFC the harness only partially did this: the hand-rolled DeepSeek adapter sent a hand-copied `User-Agent` constant (`packages/llm/llm-deepseek/src/adapter.ts`), while the pi-ai-backed twin sent no harness-owned headers at all (`packages/llm/llm-pi-ai/src/adapter.ts`). New adapters could therefore omit attribution silently, and a library-backed adapter could drift from the hand-rolled adapter even though [the twin-adapter RFC](2026-06-13-twin-llm-adapters.md) exists to keep the provider seam honest across both implementations. +LLM provider requests should identify the product making them. That is useful for provider-side support, abuse investigation, compatibility debugging, and traffic analytics. Before this Agent Note the harness only partially did this: the hand-rolled DeepSeek adapter sent a hand-copied `User-Agent` constant (`packages/llm/llm-deepseek/src/adapter.ts`), while the pi-ai-backed twin sent no harness-owned headers at all (`packages/llm/llm-pi-ai/src/adapter.ts`). New adapters could therefore omit attribution silently, and a library-backed adapter could drift from the hand-rolled adapter even though [the twin-adapter Agent Note](2026-06-13-twin-llm-adapters.md) exists to keep the provider seam honest across both implementations. The immediate prompt came from OpenRouter's [App Attribution](https://openrouter.ai/docs/app-attribution) docs. OpenRouter creates app pages and rankings from `HTTP-Referer` plus display/category headers. That is valuable, but it is not the HTTP standard for application identity. The risk is adopting OpenRouter's exact header set as if it were universal, then leaking provider-specific headers to direct DeepSeek requests, future OpenAI/Anthropic/Vertex adapters, test servers, or proxies that log unknown fields indefinitely. @@ -24,11 +24,11 @@ The immediate prompt came from OpenRouter's [App Attribution](https://openrouter Provider request attribution is mandatory at the LLM adapter boundary, using the standard `User-Agent` header only. The rule: every product LLM adapter sends a static, non-secret application identity on every provider HTTP request, and every adapter has tests proving that `User-Agent` reaches the wire (a mock server asserting received headers; for a library-backed adapter, the library's header hook feeding the same mock-server assertion). -Do **not** implement OpenRouter app attribution in this RFC. `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, and `X-OpenRouter-Categories` are OpenRouter-specific product-surface headers, not provider-neutral model-request attribution. They can be proposed later by an OpenRouter adapter or explicit OpenRouter mode, with its own privacy/product decision, tests, and docs. Until then, even requests pointed at OpenRouter send only the shared `User-Agent` attribution from this RFC. +Do **not** implement OpenRouter app attribution in this Agent Note. `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, and `X-OpenRouter-Categories` are OpenRouter-specific product-surface headers, not provider-neutral model-request attribution. They can be proposed later by an OpenRouter adapter or explicit OpenRouter mode, with its own privacy/product decision, tests, and docs. Until then, even requests pointed at OpenRouter send only the shared `User-Agent` attribution from this Agent Note. The provider-neutral identity is owned by `dsh-llm` (`packages/llm/llm/src/attribution.ts`), not by individual adapters. `AppIdentity` contains only public product facts needed to build `User-Agent`, and the default `APP_IDENTITY` settles the values the proposal left open: -- product token for `User-Agent`: `deepseek-harness` (continuity with the pre-RFC wire value and the repo/org identity) +- product token for `User-Agent`: `deepseek-harness` (continuity with the pre-Agent Note wire value and the repo/org identity) - version: read from the owning package's manifest via `createRequire`, never a hand-copied constant - app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home; a `FIXME` in `attribution.ts` blocks release until that repository actually exists @@ -40,10 +40,10 @@ Wire mapping (`attributionHeaders`; header names lowercase in code - HTTP field |---|---| | All HTTP-based adapters | `User-Agent: {product}/{version} (+{url})` - the parenthesized `+url` comment stays within RFC 9110's conservative product/comment syntax. | | Direct DeepSeek endpoint | `User-Agent`; do not send OpenRouter-only headers unless DeepSeek documents an equivalent contract. | -| OpenRouter endpoints | `User-Agent` only for now. Do not send `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, or `X-OpenRouter-Categories` under this RFC. | -| Future providers | `User-Agent` only unless a later provider-specific RFC accepts additional headers. Do not reuse `HTTP-Referer` by analogy. | +| OpenRouter endpoints | `User-Agent` only for now. Do not send `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, or `X-OpenRouter-Categories` under this Agent Note. | +| Future providers | `User-Agent` only unless a later provider-specific Agent Note accepts additional headers. Do not reuse `HTTP-Referer` by analogy. | -Endpoint detection is not part of this RFC because no endpoint-specific mapping is accepted here. If OpenRouter support lands later, detection must be explicit: either a dedicated OpenRouter provider package or an explicit `provider: 'openrouter'` / `attributionTarget: 'openrouter'` config, not arbitrary path fragments or model names. +Endpoint detection is not part of this Agent Note because no endpoint-specific mapping is accepted here. If OpenRouter support lands later, detection must be explicit: either a dedicated OpenRouter provider package or an explicit `provider: 'openrouter'` / `attributionTarget: 'openrouter'` config, not arbitrary path fragments or model names. ## Verification @@ -53,19 +53,19 @@ The landed contract: - A shared helper (`attributionHeaders` / `userAgent`) constructs the app identity and the standard `User-Agent` value from package metadata, so adapters do not hand-copy version constants. - `dsh-llm-deepseek` sends the shared `User-Agent` on every request and its mock-server suite asserts the exact value. - `dsh-llm-pi-ai` sends the same `User-Agent` through pi-ai's `StreamOptions.headers` hook and its mock-server suite asserts the exact value. -- No adapter sends OpenRouter-specific attribution headers (`HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, `X-OpenRouter-Categories`) as part of this RFC. +- No adapter sends OpenRouter-specific attribution headers (`HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, `X-OpenRouter-Categories`) as part of this Agent Note. - No app-attribution field carries secrets, local paths, session ids, prompt text, model output, user email, or per-user stable identifiers. - The adapter READMEs state the `User-Agent` attribution policy and explicitly avoid documenting OpenRouter app attribution as implemented behavior. ## Alternatives considered -**OpenRouter app attribution now.** Rejected for this RFC. Sending `HTTP-Referer` plus `X-OpenRouter-Title` would satisfy OpenRouter rankings, but those headers are a provider-specific product feature, not the provider-neutral model-request attribution this RFC is trying to standardize. Supporting them should be an explicit OpenRouter adapter/mode decision later, not hidden inside the first shared attribution helper. +**OpenRouter app attribution now.** Rejected for this Agent Note. Sending `HTTP-Referer` plus `X-OpenRouter-Title` would satisfy OpenRouter rankings, but those headers are a provider-specific product feature, not the provider-neutral model-request attribution this Agent Note is trying to standardize. Supporting them should be an explicit OpenRouter adapter/mode decision later, not hidden inside the first shared attribution helper. **OpenRouter headers everywhere.** Rejected. It would treat a custom OpenRouter contract as a universal standard and send fields with misleading semantics to providers that did not ask for them. It also risks using `HTTP-Referer` as a generic app URL field even though standard HTTP already has `User-Agent` for product identity and `Referer` for a different browsing-context concept. **Only provider account/project identity.** Rejected. Organization/project headers, API keys, cloud accounts, and billing projects identify who pays or owns the request, not which application is sending traffic. They also expose no public app title/category and do not help gateways like OpenRouter build app rankings. -**End-user `user`/`metadata` fields.** Rejected for this RFC. Those are valuable for abuse monitoring and customer support but describe the human or tenant behind a request. App attribution must be static product identity and safe to send on every request. +**End-user `user`/`metadata` fields.** Rejected for this Agent Note. Those are valuable for abuse monitoring and customer support but describe the human or tenant behind a request. App attribution must be static product identity and safe to send on every request. **Config-only opt-in attribution.** Rejected. A default-off setting is exactly how adapters keep drifting. The policy is mandatory default attribution with overrideable public values, not optional attribution. diff --git a/docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md similarity index 97% rename from docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md rename to .agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md index 2909ccd0e6..b3dad98f18 100644 --- a/docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md @@ -1,4 +1,4 @@ -# RFC: Web capability seam - stable tools over multiple providers +# Agent Note: Web capability seam - stable tools over multiple providers Status: implemented @@ -14,7 +14,7 @@ There is also a provider-selection question. Existing `tool-bash` and `tool-fs` ## Decision -Web access is a first-class capability seam following [the capability-seam RFC](../../implemented/architecture/2026-06-13-capability-seams.md): +Web access is a first-class capability seam following [the capability-seam Agent Note](2026-06-13-capability-seams.md): 1. `@deepseek-ai/dsh-web` (`packages/web/web`) owns `ctx.web`, provider registration, provider selection, shared request/result vocabulary, and web-specific errors. 2. Provider packages implement concrete backends and register capabilities with `ctx.web`, for example `@deepseek-ai/dsh-web-search-exa`, `@deepseek-ai/dsh-web-search-perplexity`, `@deepseek-ai/dsh-web-search-deepseek`, and `@deepseek-ai/dsh-web-fetch-local`. @@ -32,7 +32,7 @@ Search and fetch are separate tools but one web-access seam. `ctx.web` owns prov This keeps the model schema stable without making plugin load order, credential state, or HMR timing part of the model-facing contract. If web search is enabled but no usable search provider exists, `web_search` remains visible and execution fails with a structured `WebError` such as `WEB_PROVIDER_UNAVAILABLE` or `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`. If a provider appears after `dsh-tool-web`, the next execution can use it without changing the schema. If a provider disappears mid-call, execution fails with a structured `WebError` instead of silently choosing another provider or falling through to `UNKNOWN_TOOL`. -The seam deliberately exposes no observation surface — no registry-change event and no aggregated capability-status query. Unavailability is a fact a caller observes by executing: `search()`/`fetch()` resolve the provider at call time and throw the structured `WebError` that names what failed. [The observation-surface RFC](../simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) records that judgment: derived-on-call selection and enablement-based registration leave no consumer that needs a change signal or an availability probe distinct from executing and routing the error, and a future provider-status panel reintroduces the smallest signal or query it actually consumes. +The seam deliberately exposes no observation surface — no registry-change event and no aggregated capability-status query. Unavailability is a fact a caller observes by executing: `search()`/`fetch()` resolve the provider at call time and throw the structured `WebError` that names what failed. [The observation-surface Agent Note](../simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) records that judgment: derived-on-call selection and enablement-based registration leave no consumer that needs a change signal or an availability probe distinct from executing and routing the error, and a future provider-status panel reintroduces the smallest signal or query it actually consumes. ## Package topology @@ -276,7 +276,7 @@ Tool execution lets these errors flow through `ToolRegistry.execute()`, which al ## Testing -Each layer is pinned at its own seam: the registry/selection/truncation/abort contract and the `WebError` codes in `dsh-web`; per-provider request/response mapping over recorded fixtures (Perplexity fixtures include URL-only citations so the optional source fields stay honest) plus a self-skipping with-key smoke per real provider; real local-HTTP behavior in `web-fetch-local`; and enablement-driven registration, structured execution errors, and result formatting through the real tool registry in `dsh-tool-web`. A real-Loader smoke guards the two export shapes ([postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md)): `dsh-web` is a default-exported service, while the providers and `tool-web` are namespace plugins where a stray `export default` would drop `inject`. +Each layer is pinned at its own seam: the registry/selection/truncation/abort contract and the `WebError` codes in `dsh-web`; per-provider request/response mapping over recorded fixtures (Perplexity fixtures include URL-only citations so the optional source fields stay honest) plus a self-skipping with-key smoke per real provider; real local-HTTP behavior in `web-fetch-local`; and enablement-driven registration, structured execution errors, and result formatting through the real tool registry in `dsh-tool-web`. A real-Loader smoke guards the two export shapes ([postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)): `dsh-web` is a default-exported service, while the providers and `tool-web` are namespace plugins where a stray `export default` would drop `inject`. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-26-file-context-as-event-gate.md b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md similarity index 92% rename from docs/rfc/implemented/architecture/2026-06-26-file-context-as-event-gate.md rename to .agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md index 486d9aafb4..3f34cf3559 100644 --- a/docs/rfc/implemented/architecture/2026-06-26-file-context-as-event-gate.md +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md @@ -1,10 +1,10 @@ -# RFC: Make `dsh-fs-policy` an event-gate plugin, not a method interface +# Agent Note: Make `dsh-fs-policy` an event-gate plugin, not a method interface Status: implemented ## Problem -[The split-fs-seam RFC](../simplification/2026-06-26-fsspec-style-fs-seam.md) put `ctx.fileContext` between the model-facing tools and the `ctx.fs` provider: `dsh-tool-fs` injects `fileContext` and routes every `read`/`write`/`edit` through its methods. That makes `fileContext` **in-path and mandatory**. The tool cannot reach `ctx.fs` without it, the policy layer owns the fs I/O and the read windowing, and a deployment that does not want observed-state policy cannot simply drop the package — `dsh-tool-fs` would fail to resolve `ctx.fileContext`. +[The split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) put `ctx.fileContext` between the model-facing tools and the `ctx.fs` provider: `dsh-tool-fs` injects `fileContext` and routes every `read`/`write`/`edit` through its methods. That makes `fileContext` **in-path and mandatory**. The tool cannot reach `ctx.fs` without it, the policy layer owns the fs I/O and the read windowing, and a deployment that does not want observed-state policy cannot simply drop the package — `dsh-tool-fs` would fail to resolve `ctx.fileContext`. This couples three things that should be separable: @@ -148,7 +148,7 @@ Both mutations are still atomic (the backend's per-target lock is unconditional) ## Supersedes -This amends — does not reverse — [the split-fs-seam RFC](../simplification/2026-06-26-fsspec-style-fs-seam.md). The four-layer split, the provider contract, and the freshness *policy* are all kept. What changes is the **coupling between the tool and the policy layer**: a mandatory method service became a plugin-owned event gate, and the fs I/O + read windowing moved from `fileContext` up into `dsh-tool-fs`. The split-fs-seam RFC's description of `dsh-tool-fs` injecting `fileContext` and of `fileContext` owning `read`/`write`/`edit` was updated to match in the same change. +This amends — does not reverse — [the split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md). The four-layer split, the provider contract, and the freshness *policy* are all kept. What changes is the **coupling between the tool and the policy layer**: a mandatory method service became a plugin-owned event gate, and the fs I/O + read windowing moved from `fileContext` up into `dsh-tool-fs`. The split-fs-seam Agent Note's description of `dsh-tool-fs` injecting `fileContext` and of `fileContext` owning `read`/`write`/`edit` was updated to match in the same change. ## Verification @@ -156,7 +156,7 @@ Tests pin both paths: without `dsh-fs-policy`, the root tool plugin boots agains ## Alternatives considered -- **Keep `ctx.fileContext` as an in-path method service** — the shape [the split-fs-seam RFC](../simplification/2026-06-26-fsspec-style-fs-seam.md) first landed; rejected because the tool could not run without the policy layer, making policy load-bearing for basic operation instead of an opt-in tightening. +- **Keep `ctx.fileContext` as an in-path method service** — the shape [the split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) first landed; rejected because the tool could not run without the policy layer, making policy load-bearing for basic operation instead of an opt-in tightening. - **Policy-side version checking** (`dsh-fs-policy` stats and compares in its waterfall handler) — rejected for the TOCTOU gap between that check and the tool's actual write; the provider's mutation critical section is the only race-free place, so the policy only chooses the CAS basis and gates on prior observation. - **Per-tool `/read`/`/write`/`/edit` subpath plugins** — dropped on implementation: no consumer needed a single-tool deployment, and subpath publishing forced bespoke `tsdown`/`tsconfig`/`files`/workspace-constraint handling no sibling tool package carries; the per-tool registration helpers remain internal modules the root plugin composes. @@ -164,6 +164,6 @@ Tests pin both paths: without `dsh-fs-policy`, the root tool plugin boots agains - **Event indirection over a method call.** A waterfall + emit is less direct than `await ctx.fileContext.edit(...)`. The payoff is removing the tool-to-policy method dependency while keeping the default policy plugin; the cost is one more event vocabulary to learn. Mitigated by keeping the three events narrow and documenting the default-thunk semantics on each. - **Policy events in the storage seam.** `dsh-fs` gains two version-decision events plus a recording event though it is "just storage". This is the price of decoupling (the emitter cannot depend on the policy plugin). The events carry only `dsh-fs` vocabulary plus an opaque `object` actor and no model-facing concepts, so the seam stays free of line-window/observation policy types and of the agent/session owner structure. -- **Single policy occupant, first-wins by convention.** The `fs/write-intent`/`fs/edit-intent` slots hold exactly one decider; the first-registered (or `prepend`ed) listener wins and the rest are short-circuited. `dsh-fs-policy` owning the slot is a deployment convention, not an event-enforced invariant — a second decider registered first would bypass it. This is acceptable because a second fs-version-policy decider is a misconfiguration, not a feature. If a future need for *layered* fs version policy appears, it is a new RFC (a composable value-passing seam), not a silent second listener on these events. Layered permission/audit/sandbox interception already has its home on `tools/execute`. +- **Single policy occupant, first-wins by convention.** The `fs/write-intent`/`fs/edit-intent` slots hold exactly one decider; the first-registered (or `prepend`ed) listener wins and the rest are short-circuited. `dsh-fs-policy` owning the slot is a deployment convention, not an event-enforced invariant — a second decider registered first would bypass it. This is acceptable because a second fs-version-policy decider is a misconfiguration, not a feature. If a future need for *layered* fs version policy appears, it is a new Agent Note (a composable value-passing seam), not a silent second listener on these events. Layered permission/audit/sandbox interception already has its home on `tools/execute`. - **Dropping the post-read confirming stat** makes a follow-up *guarded* edit occasionally fail-closed (`FS_STALE_VERSION` → re-read) under a read/write race. This is a UX nicety lost, never a correctness hole; the provider lock still prevents wrong-version writes. - **The bare provider does no read-before-write/edit and no version check.** A deployment without `dsh-fs-policy` lets the model overwrite or edit any existing file unconditionally. This is the deliberate meaning of keeping the tool independent of a policy service: the safety disciplines live in the `dsh-fs-policy` plugin. A deployment that omits it is opting into an unconstrained filesystem on purpose; that is not the intended stance for a config that ships the fs tools. diff --git a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md similarity index 94% rename from docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md rename to .agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md index bc91d425b6..cc1de3c53e 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md @@ -1,12 +1,12 @@ -# RFC: stdin + extra env on the bash seam +# Agent Note: stdin + extra env on the bash seam Status: implemented ## Problem -The hooks subsystem runs external hook commands the way Claude Code and Codex do: a hook is a shell command that receives its event payload as **JSON on stdin** and reads context from a handful of **environment variables** (`CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, `PLUGIN_ROOT`, …). The harness already has a perfectly good command runner behind the `ctx.bash` capability seam ([dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)), with process-group kills, output truncation/spill, and a credential scrub. Reusing it for hook execution means a hook bridge does not re-implement subprocess plumbing — but the seam had no way to write stdin or set extra env. This RFC adds those two inputs. +The hooks subsystem runs external hook commands the way Claude Code and Codex do: a hook is a shell command that receives its event payload as **JSON on stdin** and reads context from a handful of **environment variables** (`CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, `PLUGIN_ROOT`, …). The harness already has a perfectly good command runner behind the `ctx.bash` capability seam ([dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)), with process-group kills, output truncation/spill, and a credential scrub. Reusing it for hook execution means a hook bridge does not re-implement subprocess plumbing — but the seam had no way to write stdin or set extra env. This Agent Note adds those two inputs. -`stdin` and `env` do not create a new model capability because ordinary shell syntax already supplies both. Ambient credentials are protected by `dsh-bash-local`'s child-environment scrub, not by hiding these seam fields; model tool arguments are static JSON and do not expand shell variables. The fields therefore serve trusted in-process callers, such as hook bridges, that need to pass structured input and `CLAUDE_*` variables without embedding them in model-visible shell text. See [defensive-patterns.md](../../../defensive-patterns.md) for the ambient-environment rule. +`stdin` and `env` do not create a new model capability because ordinary shell syntax already supplies both. Ambient credentials are protected by `dsh-bash-local`'s child-environment scrub, not by hiding these seam fields; model tool arguments are static JSON and do not expand shell variables. The fields therefore serve trusted in-process callers, such as hook bridges, that need to pass structured input and `CLAUDE_*` variables without embedding them in model-visible shell text. See [defensive-patterns.md](../../../../docs/defensive-patterns.md) for the ambient-environment rule. ## Decision @@ -28,4 +28,4 @@ Three deliberate choices: ## Consequences -Hook bridges pass JSON payloads and hook-specific variables through the existing bash seam, retaining its process-group, truncation, and spill behavior. The model surface remains unchanged, and the bash tool remains the sole owner of model-call request construction. The vocabulary lives in [the bash data-structure reference](../../../core-data-structures/bash.md). +Hook bridges pass JSON payloads and hook-specific variables through the existing bash seam, retaining its process-group, truncation, and spill behavior. The model surface remains unchanged, and the bash tool remains the sole owner of model-call request construction. The vocabulary lives in [the bash data-structure reference](../../../../docs/core-data-structures/bash.md). diff --git a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md similarity index 80% rename from docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md rename to .agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md index b38777be38..56c3fdf231 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -1,10 +1,10 @@ -# RFC: Event-domain semantics — session is the fact log, agent is the live surface +# Agent Note: Event-domain semantics — session is the fact log, agent is the live surface Status: implemented ## Problem -The harness extends the agent loop through a Cordis event taxonomy (see [the microkernel event-taxonomy RFC](2026-06-11-microkernel-event-taxonomy.md)). As that taxonomy grew, the line between the three event domains blurred: +The harness extends the agent loop through a Cordis event taxonomy (see [the microkernel event-taxonomy Agent Note](2026-06-11-microkernel-event-taxonomy.md)). As that taxonomy grew, the line between the three event domains blurred: - `session/*` carries the durable, event-sourced log (`SessionEventMap`). - `agent/*` carries live runtime signals that hand a plugin the `Agent` handle. @@ -24,14 +24,14 @@ This vocabulary is the foundation for interception decisions, the durable `hook/ **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. -**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) renders boundaries from `session/event` while retaining its live target object for the fixed `main` label. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). +**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) renders boundaries from `session/event` while retaining its live target object for the fixed `main` label. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events Agent Note](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). ## Consequences - The loop no longer emits any boundary mirror; `closeStep` appends `step/end` only and `closeTurn` appends `turn/end` only. `Session.append` owns post-commit observer containment, so a throwing boundary observer cannot change the turn outcome or starve later consumers; an acceptance or internal validation failure still escapes before the boundary enters the log. - Tests that observed boundaries via the removed emits now observe the durable `turn/start`/`turn/end`/`step/start`/`step/end` session events — the behavior they pin (boundary ordering, step counting) is unchanged; only the feed they read moved to the canonical one. The tests that exercised a *throwing turn-boundary emit listener* were deleted, because that code path no longer exists (there is no emit to throw from). Per [AGENTS.md "tests document behavior, not golden truth"](../../../../AGENTS.md), the behavior and its test moved (or died) together. - The loop marks the step open (`stepOpen = true`) only after `append('step/start')` returns. Internal dispatch validation runs before the log push and may reject without opening a step; post-commit `session/event` observer failures are contained inside `Session.append`. The marker therefore represents exactly the committed boundary that owes a later `step/end`. -- The full realization of this is [the simplification RFC "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that RFC's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable `steering/message`. +- The full realization of this is [the simplification Agent Note "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that Agent Note's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable `steering/message`. - The cordis events catalog (`docs/cordis-catalog/events.md`) is regenerated to drop the mirror events. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/architecture/2026-07-02-fs-per-session-cwd.md b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md similarity index 92% rename from docs/rfc/implemented/architecture/2026-07-02-fs-per-session-cwd.md rename to .agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md index f60607df4d..ece39654ea 100644 --- a/docs/rfc/implemented/architecture/2026-07-02-fs-per-session-cwd.md +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md @@ -1,10 +1,10 @@ -# RFC: Resolve filesystem paths against the caller's session cwd +# Agent Note: Resolve filesystem paths against the caller's session cwd Status: implemented ## Problem -The ACP bridge gives every session its own workspace: `session/new` records the editor's project directory as `SessionHeader.cwd`, and `dsh-tool-bash` defaults each bash call's `workdir` to the calling agent's `session.header.cwd` (see [the per-session cwd RFC work in `packages/ui/acp`](../../../../packages/ui/acp) and `resolveWorkdir` in `dsh-tool-bash`). So a bash command in session A runs in A's project, and in session B runs in B's — one server process, N workspaces. +The ACP bridge gives every session its own workspace: `session/new` records the editor's project directory as `SessionHeader.cwd`, and `dsh-tool-bash` defaults each bash call's `workdir` to the calling agent's `session.header.cwd` (see [the per-session cwd Agent Note work in `packages/ui/acp`](../../../../packages/ui/acp) and `resolveWorkdir` in `dsh-tool-bash`). So a bash command in session A runs in A's project, and in session B runs in B's — one server process, N workspaces. Filesystem resolution used one plugin-load cwd while bash used the session project directory. Relative paths therefore disagreed whenever the editor project differed from the server launch directory; snapshots hid the bug by making those paths identical. diff --git a/docs/rfc/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md similarity index 97% rename from docs/rfc/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md rename to .agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md index 218cb29297..8ddd1e8941 100644 --- a/docs/rfc/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md +++ b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md @@ -1,4 +1,4 @@ -# RFC: Result-time applied-hunk diffs for file mutations +# Agent Note: Result-time applied-hunk diffs for file mutations Status: implemented @@ -54,6 +54,6 @@ Per the [capability-seam split](2026-06-13-capability-seams.md), the storage bac ## Related -- Completes the one remaining representation difference named as a non-goal in [Tagged render-intent union](2026-07-02-tool-render-intent-union.md) — that RFC's Non-goals section is updated to record that applied-hunk diffs shipped here. +- Completes the one remaining representation difference named as a non-goal in [Tagged render-intent union](2026-07-02-tool-render-intent-union.md) — that Agent Note's Non-goals section is updated to record that applied-hunk diffs shipped here. - Builds on the [filesystem capability seam](2026-06-17-filesystem-capability-seam.md) (the before/after are storage facts the backend returns) and [event-sourced sessions](2026-06-11-event-sourced-sessions.md) (the `meta` payload persists on the `tool/result` event, so replay reproduces the card). - The `meta` channel is deliberately generic: a future tool (a structured search, a data-table result) can attach its own durable result presentation without another core change. diff --git a/docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md similarity index 92% rename from docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md rename to .agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md index 899d30416a..9d7fac0471 100644 --- a/docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md @@ -1,4 +1,4 @@ -# RFC: Tagged render-intent union for tool-call presentation +# Agent Note: Tagged render-intent union for tool-call presentation Status: implemented @@ -10,7 +10,7 @@ A tool declares how its calls render in a UI (an editor's tool-call card) throug - Which combinations are *valid* is unwritten: a `terminal` call that also sets `content` means "description above the card"; a generic call that sets `terminal` is meaningless but representable. The type permits nonsense. - There is no way to express the one file-tool affordance an editor most wants — a **diff card** (`{path, oldText, newText}`, which Zed renders as an inline diff / new-file preview). `ToolCallPresentation.content` is the *LLM* `ContentBlock[]` vocabulary (text/image), so a tool literally cannot ask for a diff. -The existing `FIXME(tool-presentation)` in `packages/core/tools/src/index.ts` named the fix: "redesign the type so a tool declares its render INTENT once (e.g. a tagged union over card kinds) rather than a bag of optional fields the bridge stitches together." The rejected RFC [Collapse tool-owned UI presentation](../../rejected/simplification/2026-06-20-generic-tool-rendering.md) deferred it explicitly: rich rendering "should return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is now met — two producer families (`dsh-tool-bash`, `dsh-tool-fs`) and two consumers (the ACP bridge live path + the snapshot replay path). +The existing `FIXME(tool-presentation)` in `packages/core/tools/src/index.ts` named the fix: "redesign the type so a tool declares its render INTENT once (e.g. a tagged union over card kinds) rather than a bag of optional fields the bridge stitches together." The rejected Agent Note [Collapse tool-owned UI presentation](../../rejected/simplification/2026-06-20-generic-tool-rendering.md) deferred it explicitly: rich rendering "should return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is now met — two producer families (`dsh-tool-bash`, `dsh-tool-fs`) and two consumers (the ACP bridge live path + the snapshot replay path). ## Decision @@ -70,7 +70,7 @@ A new render intent is a compile-breaking change at the bridge switch — delibe ## Non-goals -- **Live incremental `terminal_output_delta` streaming** and **command classification** — the terminal-rendering RFC's own deferred follow-ups, untouched here. +- **Live incremental `terminal_output_delta` streaming** and **command classification** — the terminal-rendering Agent Note's own deferred follow-ups, untouched here. ## Related diff --git a/docs/rfc/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md rename to .agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md index 451cce45d3..d40c50695d 100644 --- a/docs/rfc/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md @@ -1,4 +1,4 @@ -# RFC: Add direct directory listing to the filesystem seam +# Agent Note: Add direct directory listing to the filesystem seam Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md similarity index 96% rename from docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md rename to .agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 375949a1e8..631e5b570c 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -1,4 +1,4 @@ -# RFC: Prompt variables and tool-guidance ownership +# Agent Note: Prompt variables and tool-guidance ownership Status: implemented @@ -38,16 +38,16 @@ Per-tool semantics and selection guidance live in tool descriptions. Prompt sect ### The subagent conversation-history descriptor -`SubagentProvider.inheritsParentContext` describes conversation seeding, not scope, services, tools, or authority. Spawn and ACP set it to `false`; fork sets it to `true`. `dsh-tool-subagent` derives its tool and prompt-parameter descriptions from the flag, including that fork inherits completed turns but not the in-flight turn. Provider lifecycle events keep that wording synchronized with reactive provider registration; their rationale lives in the [provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +`SubagentProvider.inheritsParentContext` describes conversation seeding, not scope, services, tools, or authority. Spawn and ACP set it to `false`; fork sets it to `true`. `dsh-tool-subagent` derives its tool and prompt-parameter descriptions from the flag, including that fork inherits completed turns but not the in-flight turn. Provider lifecycle events keep that wording synchronized with reactive provider registration; their rationale lives in the [provider-lifecycle-events Agent Note](2026-07-05-subagent-provider-lifecycle-events.md). ## Alternatives considered - **The loop composes an identity line itself** — hardcodes model-facing prose in the one package that must stay thin ("plugins, not loop changes"), and outside the section pipeline it would be a second composition path. (The identity DOES ship as a code literal — but as an ordinary section registered by `dsh-system-prompt`, whose `system-prompt/assemble` waterfall remains the escape valve for a deployment that must drop it.) - **Inject the model name via the `agent/request` waterfall** — prompt text would be composed in two places and the earlier rendered persona could disagree with the final routed header. The request plugin that owns late routing must also own any earlier prompt claim about that model. -- **Hand-write the model name in each persona** — duplicates the `model:` key one line above and silently lies after a config edit; the exact disease this RFC cures. +- **Hand-write the model name in each persona** — duplicates the `model:` key one line above and silently lies after a config edit; the exact disease this Agent Note cures. - **Lenient interpolation (leave unknown refs verbatim, or substitute empty)** — a typo ships `{{modle}}` (or a hole) to the model and nobody notices until transcript review. - **Per-instance subagent wording in config** — returns model-facing prose to every deployment × instance, the P2 disease again. **Keying wording off the provider NAME** — `providerName` is itself config, so a renamed provider silently gets the wrong words. -- **Resolving the provider at `apply` time (a load-order requirement)** and **section-only subagent wording (lazily resolved at assemble)** — the alternatives to the provider-lifecycle events; both rejected in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +- **Resolving the provider at `apply` time (a load-order requirement)** and **section-only subagent wording (lazily resolved at assemble)** — the alternatives to the provider-lifecycle events; both rejected in [the provider-lifecycle-events Agent Note](2026-07-05-subagent-provider-lifecycle-events.md). ## Out of scope diff --git a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md rename to .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md index cbbfef6611..162a83ad0c 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -1,4 +1,4 @@ -# RFC: Every LLM request is reconstructable from the session log +# Agent Note: Every LLM request is reconstructable from the session log Status: implemented @@ -6,7 +6,7 @@ Status: implemented The request pipeline did not guarantee prefix stability for provider caching, and the session log could not reconstruct what the model saw. It omitted model, system prompt, and tool schemas while allowing per-call request rewrites. Cache behavior and replay equivalence therefore depended on whichever plugins happened to be loaded. -The reference shape for the happy path is MiniCode's `LLMClient`: a stateful conversation client, appended to — never rebuilt — as the conversation advances, resetting only when the system prompt, tool set, or compaction genuinely changes what the model must see. The design question this RFC answers is how to get that discipline without giving up event-sourcing. +The reference shape for the happy path is MiniCode's `LLMClient`: a stateful conversation client, appended to — never rebuilt — as the conversation advances, resetting only when the system prompt, tool set, or compaction genuinely changes what the model must see. The design question this Agent Note answers is how to get that discipline without giving up event-sourcing. ## Decision diff --git a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md similarity index 77% rename from docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md rename to .agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md index a04040d540..44733bb8c9 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md +++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md @@ -1,12 +1,12 @@ -# RFC: Subagent provider-lifecycle events — `subagent/provider-added` / `subagent/provider-removed` +# Agent Note: Subagent provider-lifecycle events — `subagent/provider-added` / `subagent/provider-removed` Status: implemented ## Problem -[The prompt-variables RFC](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description, so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. +[The prompt-variables Agent Note](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description, so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. -Resolving the provider at the tool plugin's `apply` time creates an implicit load-order requirement ("list the backend before the tool in cordis.yml"). That requirement fails because the Cordis Loader starts sibling entries concurrently and `Entry.init()` does not await activation: a delayed backend can leave the tool fiber failed even when listed first. The Loader offers no sibling-order guarantee — "async state is not synchronous state" ([defensive patterns](../../../defensive-patterns.md)). +Resolving the provider at the tool plugin's `apply` time creates an implicit load-order requirement ("list the backend before the tool in cordis.yml"). That requirement fails because the Cordis Loader starts sibling entries concurrently and `Entry.init()` does not await activation: a delayed backend can leave the tool fiber failed even when listed first. The Loader offers no sibling-order guarantee — "async state is not synchronous state" ([defensive patterns](../../../../docs/defensive-patterns.md)). ## Decision @@ -23,12 +23,12 @@ The events also complete the seam's vocabulary: `ctx.subagents` is a named regis - **Resolve the provider at `apply` time and throw when absent** — rejected because "list backends first" would claim a Loader ordering guarantee that does not exist. - **Retrying the lookup (poll until the provider appears)** — converges eventually but invents a private readiness protocol beside the one the framework already has (effect registration + disposal); it also cannot notice a provider LEAVING, so HMR would strand a tool whose wording describes a disposed backend. -- **Section-only subagent wording, lazily resolved at assemble time** — tolerates any load order too, but moves tool-choice guidance out of the DESCRIPTION, contradicting the ownership rule the prompt-variables RFC establishes (per-tool semantics and when-to-use belong in the description). Reactive registration keeps the description authoritative AND order-free. +- **Section-only subagent wording, lazily resolved at assemble time** — tolerates any load order too, but moves tool-choice guidance out of the DESCRIPTION, contradicting the ownership rule the prompt-variables Agent Note establishes (per-tool semantics and when-to-use belong in the description). Reactive registration keeps the description authoritative AND order-free. - **Keying wording off the provider NAME instead of the provider object** — `providerName` is itself config, so a renamed provider silently gets the wrong words; deriving from the resolved provider's own `inheritsParentContext` cannot drift. ## Consequences - Consumers deriving state from a named provider react to `subagent/provider-added`/`-removed` instead of reading the registry at `apply` time; `dsh-tool-subagent` is the reference implementation. -- **Addition fails loud; removal is contained per listener.** An addition listener may unwind registration. Removal runs during disposal, so one throwing listener is logged without starving later mirrors or disrupting teardown. `start()` still resolves the provider by name for every run, preventing stale tools from calling a removed backend. See the [events catalog](../../../cordis-catalog/events.md) and [producer/consumer map](../../../event-producer-consumer.md). +- **Addition fails loud; removal is contained per listener.** An addition listener may unwind registration. Removal runs during disposal, so one throwing listener is logged without starving later mirrors or disrupting teardown. `start()` still resolves the provider by name for every run, preventing stale tools from calling a removed backend. See the [events catalog](../../../../docs/cordis-catalog/events.md) and [producer/consumer map](../../../../docs/event-producer-consumer.md). - **A window where the tool is absent.** Between backend disposal and re-registration (an HMR reload), the model sees no subagent tool. This is the honest state — the alternative is a tool that dispatches into nothing — and the tool registry's `tools/change` emit keeps prompt assembly current. - **Two waiting fibers sharing a `toolName` is an invalid config caught late.** If two loads of `dsh-tool-subagent` name different providers but the same `toolName`, both wait, and whichever provider arrives first registers; the second registration throws only when ITS provider arrives. `TODO(subagent-dup-toolname)` in the plugin records this blast radius; the tool registry's duplicate-name rejection remains the backstop. diff --git a/docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md rename to .agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md index 7aa987c60f..335581ecff 100644 --- a/docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md @@ -1,4 +1,4 @@ -# RFC: A shared timeout/deadline primitive, with hard-kill left to each capability +# Agent Note: A shared timeout/deadline primitive, with hard-kill left to each capability Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-06-tool-result-retention-library.md b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-06-tool-result-retention-library.md rename to .agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md index f35cf56e84..f90e653a7c 100644 --- a/docs/rfc/implemented/architecture/2026-07-06-tool-result-retention-library.md +++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md @@ -1,4 +1,4 @@ -# RFC: Tool result retention library +# Agent Note: Tool result retention library Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md similarity index 83% rename from docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md rename to .agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md index 1e516a9aa0..040a6c2fdc 100644 --- a/docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md @@ -1,10 +1,10 @@ -# RFC: Tool-call timeout policy as a plugin +# Agent Note: Tool-call timeout policy as a plugin Status: implemented ## Problem -The [timeout/deadline RFC](2026-07-06-timeout-deadline-library.md) extracted the timing-and-classification primitive into `@deepseek-ai/dsh-timeout`, but timeout policy was still attached to individual capabilities and model-facing schemas. `bash` exposed `timeoutMs`; `web_fetch` exposed `timeout_ms`; `web_search` had no model-facing timeout even though providers already honor `exec.signal`; a future grep/glob tool would either import the timeout library directly or invent its own timeout policy. That is the wrong authoring shape for a plugin SDK: a tool author should normally forward `exec.signal` to the implementation it calls, and deployment policy should decide the budget. +The [timeout/deadline Agent Note](2026-07-06-timeout-deadline-library.md) extracted the timing-and-classification primitive into `@deepseek-ai/dsh-timeout`, but timeout policy was still attached to individual capabilities and model-facing schemas. `bash` exposed `timeoutMs`; `web_fetch` exposed `timeout_ms`; `web_search` had no model-facing timeout even though providers already honor `exec.signal`; a future grep/glob tool would either import the timeout library directly or invent its own timeout policy. That is the wrong authoring shape for a plugin SDK: a tool author should normally forward `exec.signal` to the implementation it calls, and deployment policy should decide the budget. At the same time, not every timeout in the repo is a model-facing tool-call budget. Hooks execute command hooks by calling `ctx.bash` directly, not through `ctx.tools.execute()`, and the `bash` model tool multiplexes foreground execution, background start, background polling, and hook reuse through the same backend. Moving every timeout into a tool plugin in one step would conflate those paths and risk breaking hook timeout semantics. @@ -84,7 +84,7 @@ A future model-facing grep/glob tool can be implemented on top of `ctx.bash` wit ## Alternatives considered -**Name the plugin `tool-timeout`.** The literal RFC name matched the `gen-tool-catalog` completeness guard's `packages/*/tool-*` glob, which requires every match to register a model-facing tool. This plugin registers none — it is a `tools/execute` wrapper — so a `tool-*` name would either fail `verify-tool-catalog` or force a misleading boot entry. The package is `@deepseek-ai/dsh-timeout-policy` in a new `packages/timeout/` group; the cordis.yml `id` can still be `timeout-policy`. +**Name the plugin `tool-timeout`.** The literal Agent Note name matched the `gen-tool-catalog` completeness guard's `packages/*/tool-*` glob, which requires every match to register a model-facing tool. This plugin registers none — it is a `tools/execute` wrapper — so a `tool-*` name would either fail `verify-tool-catalog` or force a misleading boot entry. The package is `@deepseek-ai/dsh-timeout-policy` in a new `packages/timeout/` group; the cordis.yml `id` can still be `timeout-policy`. **Keep per-tool timeout handling only.** This was the shape for `bash` and `web_fetch`, and it matches Claude Code and Codex for shell commands. It loses for web-style tools because every new timeout-capable tool must choose validation, cap semantics, docs, snapshots, and classification. The plugin centralizes policy and classification while leaving each tool's schema focused on business input. @@ -98,7 +98,7 @@ A future model-facing grep/glob tool can be implemented on top of `ctx.bash` wit **Use `tools/pre-execute` plus `tools/post-execute` instead of a new around seam.** A pre listener could arm a deadline and mutate `exec.signal`; a post listener could classify and replace. That loses because the deadline lifetime would cross two independent waterfalls: a call-id map, cleanup on every pre-deny/tool-throw/post-throw/dispose path, and ordering rules with every other listener. `tools/pre-execute` is also the allow/deny gate, not an execution wrapper. `tools/execute` gives the timeout one lexical scope: arm, delegate, classify, dispose. -**Use `Promise.race` to enforce timeouts for non-cooperative tools.** Rejected for the same reason as the timeout-library RFC: it returns control to the caller while the underlying process, fetch, or provider operation may still be running. The plugin only sends a signal; termination remains the implementation's responsibility. +**Use `Promise.race` to enforce timeouts for non-cooperative tools.** Rejected for the same reason as the timeout-library Agent Note: it returns control to the caller while the underlying process, fetch, or provider operation may still be running. The plugin only sends a signal; termination remains the implementation's responsibility. ## Consequences @@ -106,4 +106,4 @@ A future model-facing grep/glob tool can be implemented on top of `ctx.bash` wit - Multiple `tools/execute` listeners compose by ordinary Cordis waterfall order: a listener that calls `next()` wraps downstream listeners plus dispatch; one that returns without `next()` short-circuits them. A deployment combining timeout with a future retry/sandbox/metrics wrapper chooses semantics by registration order ("timeout covers the whole retry" vs "timeout covers each attempt"). - Opt-in by declaration is a deliberate misconfiguration risk: a tool can declare a `timeoutMs` without honoring `exec.signal`, and that tool will not stop on timeout. The plugin contract states that declaring a budget means cooperative; the web tools prove the pattern on tools that already forward the signal. - During the transition `bash` and the migrated web tools use different timeout paths on purpose: `TOOL_TIMEOUT` is the model-facing tool-call budget, while `BASH_TIMEOUT` remains the bash backend timeout used by bash and hooks. -- Deviation from the literal proposal, recorded per the implemented-RFC rule: the plugin package is `@deepseek-ai/dsh-timeout-policy` (not `tool-timeout`), signal replacement is in-place `exec.signal` mutation before `next()` (not `next({ ...exec, signal })`, which cordis ignores), and the per-tool budget is declared on the `ToolDefinition` (`timeoutMs`, set by the owning tool plugin from its config) rather than mapped by tool name in this plugin's config — so the enforcer is zero-config and a mistyped tool name is impossible. All three are described in `## Decision` above. +- Deviation from the literal proposal, recorded per the implemented-Agent Note rule: the plugin package is `@deepseek-ai/dsh-timeout-policy` (not `tool-timeout`), signal replacement is in-place `exec.signal` mutation before `next()` (not `next({ ...exec, signal })`, which cordis ignores), and the per-tool budget is declared on the `ToolDefinition` (`timeoutMs`, set by the owning tool plugin from its config) rather than mapped by tool name in this plugin's config — so the enforcer is zero-config and a mistyped tool name is impossible. All three are described in `## Decision` above. diff --git a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md similarity index 95% rename from docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md rename to .agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md index 15477e023a..68c9bd3b3e 100644 --- a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -1,4 +1,4 @@ -# RFC: The agent is a registration scope +# Agent Note: The agent is a registration scope Status: implemented @@ -14,7 +14,7 @@ The mechanism also needs a publication boundary. An agent must not become visibl Every live agent owns one flat registration layer exposed as `agent.ctx`. Code registers through the context that owns a contribution; scope-aware services combine deployment-global registrations with exactly one matching agent layer; operations choose that layer from their real agent; and the layer exists for the agent's complete published lifetime. -Cordis is the plugin framework underneath the SDK. A Cordis **context** is the object plugins use to access services and register effects whose cleanup follows that context. The [Cordis primer](../../../cordis-primer.md) explains the framework in more detail. +Cordis is the plugin framework underneath the SDK. A Cordis **context** is the object plugins use to access services and register effects whose cleanup follows that context. The [Cordis primer](../../../../docs/cordis-primer.md) explains the framework in more detail. For most contributors, the complete contract is four rules: @@ -43,7 +43,7 @@ flowchart LR The missing cross-edges are the isolation rule: Agent A's local registrations do not enter Agent B's view, and a parent's registrations do not enter a child merely because the parent owns the child's lifetime. -The companion [runtime-design RFC](2026-07-12-agent-scope-runtime-design.md) explains the implementation and correctness reasoning. The [subagent composition-controls RFC](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns the separate `persona`, `toolFilter`, and `maxDepth` feature. +The companion [runtime-design Agent Note](2026-07-12-agent-scope-runtime-design.md) explains the implementation and correctness reasoning. The [subagent composition-controls Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns the separate `persona`, `toolFilter`, and `maxDepth` feature. ### Registration origin chooses visibility and cleanup @@ -102,7 +102,7 @@ An event about Agent A normally reaches unscoped listeners and A-scoped listener At the Cordis level, `Scoped<T>` is an opaque routing receiver. It carries the filter used to choose listeners but is not the domain object. Event signatures therefore keep the real `Agent`, tool execution, approval request, or other subject as an explicit argument that listeners can inspect. -A listener registered with `{ global: true }` deliberately bypasses contextual audience filtering while its cleanup still follows the registering context. Registry-membership notifications remain unfiltered because they describe shared registry state rather than one agent's operation. The generated [event catalog](../../../cordis-catalog/events.md) is the exhaustive event reference. +A listener registered with `{ global: true }` deliberately bypasses contextual audience filtering while its cleanup still follows the registering context. Registry-membership notifications remain unfiltered because they describe shared registry state rather than one agent's operation. The generated [event catalog](../../../../docs/cordis-catalog/events.md) is the exhaustive event reference. ### Creation publishes last and disposal revokes last diff --git a/docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md rename to .agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md index bbca065d87..1255dc7328 100644 --- a/docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md @@ -1,4 +1,4 @@ -# RFC: Tool output spill policy +# Agent Note: Tool output spill policy Status: implemented @@ -6,7 +6,7 @@ Status: implemented Tool outputs need bounded model-facing previews, but some oversized results are still useful later. A fetched page body or a verbose tool response should not consume the next model request in full, but the model should be able to inspect the complete formatted result later with existing file-reading tools. -Before this change the behavior was uneven. `dsh-bash-local` already writes complete stdout/stderr streams to private temp spill files when its in-memory tail overflows, but ordinary text tool results were returned inline unless the tool hand-rolled its own cap. The [tool result retention library](./2026-07-06-tool-result-retention-library.md) owns preview mechanics, but it does not own storage or an execution-pipeline policy that applies those mechanics to final tool results. +Before this change the behavior was uneven. `dsh-bash-local` already writes complete stdout/stderr streams to private temp spill files when its in-memory tail overflows, but ordinary text tool results were returned inline unless the tool hand-rolled its own cap. The [tool result retention library](2026-07-06-tool-result-retention-library.md) owns preview mechanics, but it does not own storage or an execution-pipeline policy that applies those mechanics to final tool results. The shape matches the timeout policy design: a tool author normally returns the text result, and a policy plugin enforces the deployment's default context budget. Tool-specific early spill remains possible later for outputs that do not survive to the final `ToolExecutionResult`; the first cut proves the default final-result path. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml similarity index 81% rename from docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml rename to .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index c54a0b344d..a6344d276f 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: d88d7aaea8ccec30b10bfeb17f1312cfe87a0ce7 -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 42e6114304de9c8022ef8f1341035858c0c7d9ec +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: f1a1868cd00007fb24efb21779dcc94c098b54e2 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: a4993de2830301610bb2a9b0d28e8bbdf0ed9c46 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md similarity index 94% rename from docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md rename to .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index d88d7aaea8..f1a1868cd0 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -1,4 +1,4 @@ -# RFC: After-call compaction pressure and context-overflow recovery +# Agent Note: After-call compaction pressure and context-overflow recovery Status: implemented @@ -58,4 +58,4 @@ Post-step pressure describes the completed routed request, including durable too The cost is one additional serial checkpoint on successful steps and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window or split one indivisible oversized message/tool unit. -This RFC supersedes only the pre-step automatic-trigger portion of the [compaction capability-seam RFC](../feature/2026-06-18-compaction-capability-seam.md). The service split, standalone token meter, balanced range contract, log-recorded lock, summary replacement, and sole `summarize()` subclass hook remain unchanged. +This Agent Note supersedes only the pre-step automatic-trigger portion of the [compaction capability-seam Agent Note](../feature/2026-06-18-compaction-capability-seam.md). The service split, standalone token meter, balanced range contract, log-recorded lock, summary replacement, and sole `summarize()` subclass hook remain unchanged. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md similarity index 95% rename from docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md rename to .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index 42e6114304..a4993de283 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -1,4 +1,4 @@ -# RFC：调用后压缩压力与上下文溢出恢复 +# Agent Note：调用后压缩压力与上下文溢出恢复 Status: implemented @@ -58,4 +58,4 @@ Post-step 压力描述已完成的路由请求，包括持久工具结果与仅 代价是成功 step 增加一个串行检查点，并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况，也不能拆分单个不可分割的超大消息或工具单元。 -本 RFC 只取代[压缩能力接缝 RFC](../feature/2026-06-18-compaction-capability-seam.md) 中的 pre-step 自动触发部分。服务拆分、独立 token meter、平衡范围契约、日志记录锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。 +本 Agent Note 只取代[压缩能力接缝 Agent Note](../feature/2026-06-18-compaction-capability-seam.md) 中的 pre-step 自动触发部分。服务拆分、独立 token meter、平衡范围契约、日志记录锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。 diff --git a/docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml similarity index 70% rename from docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml rename to .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml index 98131dce38..6db1ef4ece 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-single-file-executable-sdk-runtime-distribution.md: 80d5ab64682f1b72ca1dfa1f96bc34f2a3db5f2d -2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: aea1fb66136b31e0a75ba51471fec4dadd960e8f +2026-07-10-single-file-executable-sdk-runtime-distribution.md: 0d4686a5a233785ca4832ef068a118b484a872fe +2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: dcc9213c6b3a088b8b8bce2a442c5232ed5b7d0b diff --git a/docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md rename to .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md index 80d5ab6468..0d4686a5a2 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md @@ -1,4 +1,4 @@ -# RFC: Single-file executable SDK runtime distribution (single-exe) +# Agent Note: Single-file executable SDK runtime distribution (single-exe) Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md rename to .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md index aea1fb6613..dcc9213c6b 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md @@ -1,4 +1,4 @@ -# RFC: 单文件可执行的 SDK 运行时分发（single-exe） +# Agent Note: 单文件可执行的 SDK 运行时分发（single-exe） Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md similarity index 96% rename from docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md rename to .agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md index 2c3126793f..2ddbe0a351 100644 --- a/docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md @@ -1,4 +1,4 @@ -# RFC: Agent-scope runtime design and correctness +# Agent Note: Agent-scope runtime design and correctness Status: implemented @@ -26,9 +26,9 @@ The design can be skimmed as seven choices: | Compose the model-visible prompt and tool surface | One shared tool view plus the authoritative assembly-waterfall result | | Coordinate subagent, worker, and process shutdown | One cancellation signal plus the independent terminal/quiescence facts of that boundary | -The rest of this RFC expands those choices in dependency order: Cordis mechanics, scope routing, creation and session commit, tools and prompts, subagents and workflows, then executable checks. +The rest of this Agent Note expands those choices in dependency order: Cordis mechanics, scope routing, creation and session commit, tools and prompts, subagents and workflows, then executable checks. -The [July 8 RFC](2026-07-08-agent-scope-contexts.md) remains the contributor contract. The separate [subagent composition-controls RFC](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns `persona`, `toolFilter`, and `maxDepth`; this document discusses only how their setup fits the lifecycle. +The [July 8 Agent Note](2026-07-08-agent-scope-contexts.md) remains the contributor contract. The separate [subagent composition-controls Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns `persona`, `toolFilter`, and `maxDepth`; this document discusses only how their setup fits the lifecycle. ## Cordis model: context, fiber, effect, receiver, and waterfall @@ -206,7 +206,7 @@ Tool presentation and execution share one private resolver. Prompt assembly rema The private resolver applies the current presentation mode, live global restrictions, exact local overlay, and local shadowing. Schemas, lookup, execution, Code Mode SDK generation, and restriction validation all use that resolver or its pre-restriction global-name view. -The [subagent composition-controls RFC](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md#tool-filtering-is-one-live-global-view-rule) owns the user-visible allow/deny semantics. The implementation requirement is agreement: a filtered-away global cannot remain executable through a different lookup path, and a locally shadowed definition is the same definition presented and executed. +The [subagent composition-controls Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md#tool-filtering-is-one-live-global-view-rule) owns the user-visible allow/deny semantics. The implementation requirement is agreement: a filtered-away global cannot remain executable through a different lookup path, and a locally shadowed definition is the same definition presented and executed. `ToolRestriction` accepts readonly allow/deny names and compiles them into internal sets. Multiple restrictions intersect. Public `visible()` and `knownNames()` methods are unnecessary because only the registry needs the intermediate views. @@ -328,13 +328,13 @@ The plugin does not police trusted setup by scanning registries or reject prompt ### Generated artifacts keep public contracts aligned -The event catalog, service catalog, producer/consumer matrix, configuration catalog, module graph, tool catalog, type-equivalence blocks, and scoped-event resolver map are generated or freshness-gated from source. The [TypeScript semantic-gates RFC](../process/2026-07-14-typescript-program-backed-semantic-gates.md) owns Program construction, semantic event discovery, and resolver-generation rules. +The event catalog, service catalog, producer/consumer matrix, configuration catalog, module graph, tool catalog, type-equivalence blocks, and scoped-event resolver map are generated or freshness-gated from source. The [TypeScript semantic-gates Agent Note](../process/2026-07-14-typescript-program-backed-semantic-gates.md) owns Program construction, semantic event discovery, and resolver-generation rules. Behavioral tests pin scoped routing and disposal, final-entry collision cleanup, publication rollback, ordered quiescence, durable pre/post-commit behavior, live tool filtering across presentation and execution, cooperative prompt assembly, structured-output commit in native and Code Mode, async subagent startup and signal cancellation, worker terminal arbitration, ACP settlement, and process teardown. ## Alternatives considered -The [July 8 RFC](2026-07-08-agent-scope-contexts.md#alternatives-considered) owns alternatives to the public flat-scope contract. The alternatives here concern implementation shape. +The [July 8 Agent Note](2026-07-08-agent-scope-contexts.md#alternatives-considered) owns alternatives to the public flat-scope contract. The alternatives here concern implementation shape. ### Use a transparent proxy as the scope carrier diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml similarity index 62% rename from docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml rename to .agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml index 48055ef6b7..3ed38c1282 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-14-provider-routed-llm-adapters.md: 75ef047a7f95621d9a9c018b6dc57439e6f2bb22 -2026-07-14-provider-routed-llm-adapters.zh.md: 75ac9adbe5f8e96930a72a977c1969ff3a119ee8 +2026-07-14-provider-routed-llm-adapters.md: b7944bd31fdb5f63894e867d7c1224215d694f11 +2026-07-14-provider-routed-llm-adapters.zh.md: 7dcadf2521bab079e328b5f0d0a45185778b3b8d diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md similarity index 95% rename from docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md rename to .agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md index 75ef047a7f..b7944bd31f 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md @@ -1,4 +1,4 @@ -# RFC: Provider-routed LLM adapters and a generic pi-ai backend +# Agent Note: Provider-routed LLM adapters and a generic pi-ai backend Status: implemented @@ -20,7 +20,7 @@ The adapter configuration also assumes one DeepSeek API key and endpoint. A gene `GenerateOptions` and `LlmCallConfig` carry `provider: string` beside `model: string`; `AgentOptions` carries the corresponding optional creation field. A loop request is valid only after both values are non-empty, and both values are part of the logged request header. `agent/request` may return a replacement pair on any step, so a session can switch providers and models without changing the Cordis plugin lifecycle. -`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. Model ids are not registration keys; the selected adapter still validates or forwards them. The later [LLM catalog and ACP selection RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) added advisory `listProviders()` / `listModels()` discovery without turning model membership into request validation. +`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. Model ids are not registration keys; the selected adapter still validates or forwards them. The later [LLM catalog and ACP selection Agent Note](2026-07-15-llm-model-catalog-and-acp-selection.md) added advisory `listProviders()` / `listModels()` discovery without turning model membership into request validation. A provider has exactly one adapter owner in a Cordis context. `dsh-llm-deepseek` registers `deepseek`; `dsh-llm-pi-ai` may also register `deepseek`, but loading both owners is a configuration error rather than an ordering rule or fallback. A deployment that wants the hand-rolled DeepSeek implementation excludes `deepseek` from the pi-ai profiles. A deployment that wants pi-ai's DeepSeek implementation does not mount `dsh-llm-deepseek`. @@ -44,7 +44,7 @@ A terminal successful `finish` chunk may carry replay state, and `BlockAssembler The pi-ai replay state is a versioned, minimal projection of its successful `AssistantMessage`: source API/provider/model, response id/model, stop reason, and index-aligned text, thinking, and tool-call signatures. It does not duplicate text or tool arguments already carried by Harness content blocks, and it omits diagnostics, timestamps, usage, and errors. On a later request, `LlmService` gives replay state to the target adapter only when the historical provider and target provider are currently owned by the same adapter instance. That adapter combines the logged Harness content with replay state when it can restore the historical response, and owns any required cross-model or cross-provider conversion. An adapter receiving replay state with an unknown version or mismatched block shape fails explicitly; a different adapter receives only provider-neutral content and provenance. -This state is model-visible replay input and therefore follows the existing [reconstructable-request rule](../../implemented/architecture/2026-07-05-reconstructable-requests.md): it is present in both the terminal `finish` chunk and the assembled `assistant/message` provenance that drives derivation. Resume and fork preserve it verbatim. Compaction that shadows the assistant message also removes its replay state from the active surface; the summary is ordinary provider-neutral content. +This state is model-visible replay input and therefore follows the existing [reconstructable-request rule](2026-07-05-reconstructable-requests.md): it is present in both the terminal `finish` chunk and the assembled `assistant/message` provenance that drives derivation. Resume and fork preserve it verbatim. Compaction that shadows the assistant message also removes its replay state from the active surface; the summary is ordinary provider-neutral content. ### Propagate the target through every request producer diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md similarity index 95% rename from docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md rename to .agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md index 75ac9adbe5..7dcadf2521 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md @@ -1,4 +1,4 @@ -# RFC: 基于提供方路由的 LLM 适配器与通用 pi-ai 后端 +# Agent Note: 基于提供方路由的 LLM 适配器与通用 pi-ai 后端 Status: implemented @@ -20,7 +20,7 @@ Status: implemented `GenerateOptions` 与 `LlmCallConfig` 在 `model: string` 之外携带 `provider: string`，`AgentOptions` 则携带对应的可选创建字段。只有两个值都非空时，agent loop（智能体循环）请求才有效；两个值也都会写入请求头日志。`agent/request` 可以在任意步骤返回替换后的字段组合，因此会话可以切换提供方与模型，无需改变 Cordis 插件生命周期。 -`LlmService` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表，遇到重复项时返回 `DUPLICATE_ADAPTER`，并将整组注册作为一个 effect 释放。模型 ID 不作为注册键；仍由选中的适配器负责验证或转发。后续的 [LLM 目录与 ACP 模型选择 RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) 增加了建议性的 `listProviders()` / `listModels()` 发现接口，但不会把目录成员关系变成请求校验规则。 +`LlmService` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表，遇到重复项时返回 `DUPLICATE_ADAPTER`，并将整组注册作为一个 effect 释放。模型 ID 不作为注册键；仍由选中的适配器负责验证或转发。后续的 [LLM 目录与 ACP 模型选择 Agent Note](2026-07-15-llm-model-catalog-and-acp-selection.md) 增加了建议性的 `listProviders()` / `listModels()` 发现接口，但不会把目录成员关系变成请求校验规则。 在一个 Cordis 上下文中，一个提供方只能有一个适配器所有者。`dsh-llm-deepseek` 注册 `deepseek`；`dsh-llm-pi-ai` 也可以注册 `deepseek`，但同时加载两个所有者属于配置错误，不采用顺序规则或回退行为。若部署选择手写的 DeepSeek 实现，需从 pi-ai 配置中排除 `deepseek`；若部署选择 pi-ai 的 DeepSeek 实现，则不挂载 `dsh-llm-deepseek`。 @@ -44,7 +44,7 @@ pi-ai 的通用流选项不支持停止序列。若 Harness `stop` 选项已定 pi-ai 回放状态是其成功 `AssistantMessage` 的带版本最小投影，包含源 API/provider/model、响应 ID/model、停止原因，以及按索引对齐的文本、thinking 和工具调用签名。它不会重复 Harness 内容块中已有的文本或工具参数，也不包含诊断信息、时间戳、用量或错误。后续请求中，只有历史提供方和目标提供方当前归同一个适配器实例所有时，`LlmService` 才会把回放状态交给目标适配器。适配器在能够恢复历史响应时，将 Harness 记录的内容与回放状态组合，并负责所需的跨模型或跨提供方转换。适配器收到未知版本或块形状不匹配的回放状态时会显式失败；其他适配器只能收到提供方无关的内容与来源信息。 -该状态属于模型可见的回放输入，因此遵循现有的[请求可重建规则](../../implemented/architecture/2026-07-05-reconstructable-requests.md)：它同时存在于终止 `finish` 分片和驱动派生的已组装 `assistant/message` 来源信息中。恢复和 fork 会原样保留该状态。压缩（compaction）遮蔽助手消息时，也会从活动 surface 中移除其回放状态；摘要属于普通的提供方无关内容。 +该状态属于模型可见的回放输入，因此遵循现有的[请求可重建规则](2026-07-05-reconstructable-requests.md)：它同时存在于终止 `finish` 分片和驱动派生的已组装 `assistant/message` 来源信息中。恢复和 fork 会原样保留该状态。压缩（compaction）遮蔽助手消息时，也会从活动 surface 中移除其回放状态；摘要属于普通的提供方无关内容。 ### 在所有请求生产方中传播目标 diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml similarity index 64% rename from docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml rename to .agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml index 52128ea344..d5e16246fe 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-initiator-scope.md: a9df15beb8744216e020c259934db9fdf8b28b79 -2026-07-15-agent-initiator-scope.zh.md: 4198f066ef27042bda0d12fbcaf86f143482d596 +2026-07-15-agent-initiator-scope.md: 69648100e76cfc212469854188d664357fec22f1 +2026-07-15-agent-initiator-scope.zh.md: 835d7a5b2ab6d2d6fce7971de4fd9d6c69e50d77 diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md rename to .agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md index a9df15beb8..69648100e7 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md +++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md @@ -1,4 +1,4 @@ -# RFC: Initiating Agent scope over AsyncLocalStorage +# Agent Note: Initiating Agent scope over AsyncLocalStorage Status: implemented @@ -12,7 +12,7 @@ Deep process-local infrastructure sometimes needs a trusted initiating Agent bel ## Decision -The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; a separate private run token records nested boundary lineage only for teardown bookkeeping and carries no identity. The [core-data catalog](../../../core-data-structures/core.md#initiating-agent) identifies the carried type. +The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; a separate private run token records nested boundary lineage only for teardown bookkeeping and carries no identity. The [core-data catalog](../../../../docs/core-data-structures/core.md#initiating-agent) identifies the carried type. `currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md similarity index 98% rename from docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md rename to .agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md index 4198f066ef..835d7a5b2a 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md @@ -1,4 +1,4 @@ -# RFC: 基于 AsyncLocalStorage 的发起 Agent 作用域 +# Agent Note: 基于 AsyncLocalStorage 的发起 Agent 作用域 Status: implemented @@ -12,7 +12,7 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 ## 决策 -必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`，不引入只有一个字段的帧；另一个私有运行标记只记录嵌套边界的谱系，供 teardown 记账使用，不携带身份。[核心数据目录](../../../core-data-structures/core.md#initiating-agent)标明了所携带的类型。 +必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`，不引入只有一个字段的帧；另一个私有运行标记只记录嵌套边界的谱系，供 teardown 记账使用，不携带身份。[核心数据目录](../../../../docs/core-data-structures/core.md#initiating-agent)标明了所携带的类型。 `currentInitiator()` 用于可选读取，`requireInitiator()` 抛出 `no initiating agent is active`，`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml similarity index 60% rename from docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml rename to .agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml index d1756c9186..e83cfff95e 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-llm-model-catalog-and-acp-selection.md: d84fe9fdb75bd2d28a00269c84d29c4223798253 -2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 019819c4aa5ab4ad281b5b32daa76a004c9d6466 +2026-07-15-llm-model-catalog-and-acp-selection.md: 6cc8afc6c7431fbf3eb29fc358b432db4f72b529 +2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 1cce7a58d0ec83dc01feaf72ccb61d294a78ddd5 diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md rename to .agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md index d84fe9fdb7..6cc8afc6c7 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md @@ -1,4 +1,4 @@ -# RFC: Advisory LLM catalogs and per-session ACP model selection +# Agent Note: Advisory LLM catalogs and per-session ACP model selection Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md rename to .agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md index 019819c4aa..1cce7a58d0 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md @@ -1,4 +1,4 @@ -# RFC: 建议性 LLM 目录与 ACP 会话级模型选择 +# Agent Note: 建议性 LLM 目录与 ACP 会话级模型选择 Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml similarity index 63% rename from docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml rename to .agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml index 3c1e0a2573..d49aedb545 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-replay-token-meter-service.md: a86696a1077c9fa21d9984280009f9a0df0b4bbb -2026-07-15-replay-token-meter-service.zh.md: a6803fc9921a832b7614a7dc26b545a9145a08df +2026-07-15-replay-token-meter-service.md: 9bbc177f456e006179c466f8c245e4599db3dd5a +2026-07-15-replay-token-meter-service.zh.md: 4437626c8651a80537d45197a93733271a592173 diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md rename to .agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md index a86696a107..9bbc177f45 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -1,4 +1,4 @@ -# RFC: Replay token meter service +# Agent Note: Replay token meter service Status: implemented diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md similarity index 99% rename from docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md rename to .agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md index a6803fc992..4437626c86 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -1,4 +1,4 @@ -# RFC: 回放式 token 计量服务 +# Agent Note: 回放式 token 计量服务 Status: implemented diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md similarity index 97% rename from docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md rename to .agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md index ea4b98c31d..7c47fc78e9 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md +++ b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md @@ -1,4 +1,4 @@ -# RFC: Agent Client Protocol (ACP) support — drive the coding agent from external editors +# Agent Note: Agent Client Protocol (ACP) support — drive the coding agent from external editors Status: implemented @@ -48,7 +48,7 @@ The precise supported and deferred protocol rows live in [`packages/ui/acp/acp-f Editors can create, load, prompt, cancel, render, ask, and reconfigure multiple harness sessions over one ACP connection without a loop-specific dependency. The session event log remains the durable source for replay, prompt settlement, cwd, and per-session configuration. Tool presentation and human-answer channels remain extensible plugin contracts instead of ACP-specific behavior. -The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. Runtime model selection was added later through standard session config options by the [LLM catalog and ACP selection RFC](../architecture/2026-07-15-llm-model-catalog-and-acp-selection.md). +The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. Runtime model selection was added later through standard session config options by the [LLM catalog and ACP selection Agent Note](../architecture/2026-07-15-llm-model-catalog-and-acp-selection.md). An idle config selection is truthful in the live response but not durable until the next `agent/prompt-submit` anchors it inside the open turn. Crashing before that boundary loses the pending selection; this is the cost of keeping session events turn-enclosed and replay-safe. diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md similarity index 98% rename from docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md rename to .agents/notes/implemented/feature/2026-06-14-acp-multi-session.md index 64961bee89..def0604df9 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md +++ b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md @@ -1,4 +1,4 @@ -# RFC: Multiplex concurrent ACP sessions over one connection +# Agent Note: Multiplex concurrent ACP sessions over one connection Status: implemented diff --git a/docs/rfc/implemented/feature/2026-06-15-code-mode.md b/.agents/notes/implemented/feature/2026-06-15-code-mode.md similarity index 89% rename from docs/rfc/implemented/feature/2026-06-15-code-mode.md rename to .agents/notes/implemented/feature/2026-06-15-code-mode.md index 3bc07b839f..329eaf2d0a 100644 --- a/docs/rfc/implemented/feature/2026-06-15-code-mode.md +++ b/.agents/notes/implemented/feature/2026-06-15-code-mode.md @@ -1,23 +1,23 @@ -# RFC: Code Mode — the model writes TypeScript against the tool registry +# Agent Note: Code Mode — the model writes TypeScript against the tool registry Status: implemented ## Problem -In the registry's native presentation, the agent loop advertises every visible capability as a JSON-schema function definition. `ToolRegistry` contributes its schemas to the system-prompt assembly, the assembly's `tools` land on the wire (and in the logged request header), the model invokes one `tool-call` block per step, and the loop dispatches each call through `ctx.tools.execute()` **sequentially** (parallel tool execution is an explicit open TODO in `dsh-tools` and [docs/architecture.md](../../../architecture.md)), with **every** intermediate `tool-result` re-entering the model's context on the next request. +In the registry's native presentation, the agent loop advertises every visible capability as a JSON-schema function definition. `ToolRegistry` contributes its schemas to the system-prompt assembly, the assembly's `tools` land on the wire (and in the logged request header), the model invokes one `tool-call` block per step, and the loop dispatches each call through `ctx.tools.execute()` **sequentially** (parallel tool execution is an explicit open TODO in `dsh-tools` and [docs/architecture.md](../../../../docs/architecture.md)), with **every** intermediate `tool-result` re-entering the model's context on the next request. For multi-step tool work this is token-heavy and serial. The model cannot compose tools — loop over a result set, branch on an intermediate value, fan out, post-process — without a full model round-trip per call, and each round-trip drags the entire intermediate result back into context whether the model needs it or not. Cloudflare's [Code Mode](https://blog.cloudflare.com/code-mode/) proposes an alternative grounded in a simple observation: LLMs are better at writing code than at emitting tool calls, because they have seen millions of lines of real code and comparatively few contrived tool-calling traces. Instead of one tool call per step, the model writes a TypeScript program against a generated API over the tools, the program executes in a sandboxed runtime, and the model curates what comes back — only what it prints or returns — instead of every intermediate result. -Tool presentation belongs to the registry that owns tool visibility: implementing a second presentation as an after-the-fact waterfall transform would make correctness depend on listener order and fight [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md). The execution substrate is also part of the foundation rather than a placeholder: Node `worker_threads` provides a separate isolate, an empty environment, heap caps, and termination of a hot synchronous loop, while fitting the harness's existing trust model (§Trust posture). +Tool presentation belongs to the registry that owns tool visibility: implementing a second presentation as an after-the-fact waterfall transform would make correctness depend on listener order and fight [reconstructable requests](../architecture/2026-07-05-reconstructable-requests.md). The execution substrate is also part of the foundation rather than a placeholder: Node `worker_threads` provides a separate isolate, an empty environment, heap caps, and termination of a hot synchronous loop, while fitting the harness's existing trust model (§Trust posture). ## Decision Three decisions, each elaborated in its own section below: 1. **Code Mode is a first-class presentation mode of `ToolRegistry`** (`dsh-tools`), selected by a validated `mode` config: `'native'` (the default, contributing the visible capability schemas), `'code'` (the registry contributes only its reserved `run_code` transport plus a generated SDK `.d.ts` in the system prompt), or `'both'` (native schemas and the transport + SDK). The registry shapes its canonical contribution at the source; the cooperative prompt-assembly result remains authoritative, and the logged request header records exactly that returned presentation. -2. **Code execution is a capability seam** — `packages/code-runtime/` contains the interface package `@deepseek-ai/dsh-code-runtime`, which owns `ctx.codeRuntime` ([capability seams](../../implemented/architecture/2026-06-13-capability-seams.md); consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is another implementation package, not a redesign. +2. **Code execution is a capability seam** — `packages/code-runtime/` contains the interface package `@deepseek-ai/dsh-code-runtime`, which owns `ctx.codeRuntime` ([capability seams](../architecture/2026-06-13-capability-seams.md); consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is another implementation package, not a redesign. 3. **The shipped implementation is `@deepseek-ai/dsh-code-runtime-worker`**: one fresh Node worker thread per run, executing the model's TypeScript after type-strip, with bindings bridged over the message port, an empty environment, configurable heap/output/time caps, and hard termination. Its trust posture is bash-equivalent by design — no unsafe-acknowledgement flags — because the harness already ships `dsh-bash-local`, which executes arbitrary model-written shell commands with strictly *more* ambient authority. ### The registry owns the mode @@ -46,7 +46,7 @@ Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentat **Concurrency is serialized.** Each run owns a dispatch queue, so even `Promise.all` executes tool calls in submission order. Settlement abandons queued calls that have not started. Parallelism requires per-tool concurrency-safety metadata. -**Presentation.** `run_code`'s render intent is decided here per the [render-intent RFC](../../implemented/architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title = the program text, `rawInput` = the same program text; `presentResult` → a `generic` card whose content is the captured output (from `meta`). The program is the title because ACP execute cards reliably render that field while some clients omit body and raw-input content. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not. +**Presentation.** `run_code`'s render intent is decided here per the [render-intent Agent Note](../architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title = the program text, `rawInput` = the same program text; `presentResult` → a `generic` card whose content is the captured output (from `meta`). The program is the title because ACP execute cards reliably render that field while some clients omit body and raw-input content. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not. ### Observability: `tool/code-dispatch` @@ -60,7 +60,7 @@ Each sub-dispatch appends a log-only `tool/code-dispatch` event containing paren - `CodeBindingNamespace = { global: string; functions: Record<string, (args: unknown) => Promise<unknown>> }` — the runtime exposes each namespace as a global object of async functions inside the program; binding arguments and resolutions must be structured-cloneable (a runtime may cross a serialization boundary; ours does). - `CodeRunResult = { value?: unknown; logs: CodeLogEntry[]; error?: CodeRunFailure }` — program execution outcomes, including exception, timeout, abort, and worker exit, resolve as the `error` field. `run()` may reject only for caller/seam misuse (for example a duplicate binding namespace); consumers still contain a non-conforming backend rejection at their own error boundary. - `CodeLogEntry = { source: 'console' | 'stdout' | 'stderr'; level?: 'log' | 'info' | 'warn' | 'error' | 'debug'; text: string }` -- `CodeRunFailure = { kind: 'exception' | 'timeout' | 'abort' | 'worker-exit'; message: string }` — orthogonal outcomes reported independently per [defensive patterns](../../../defensive-patterns.md); a timed-out run is not an exception, an abort is not a timeout. +- `CodeRunFailure = { kind: 'exception' | 'timeout' | 'abort' | 'worker-exit'; message: string }` — orthogonal outcomes reported independently per [defensive patterns](../../../../docs/defensive-patterns.md); a timed-out run is not an exception, an abort is not a timeout. - Two readonly backend descriptors, informational not gating: `language` (what the program must be written in — `'typescript'` for the shipped backend; a Python backend would say so, and pair with its own SDK generator on the presentation side) and `isolation` (`'worker-thread'` for the shipped backend; `'process'`, `'container'`, … for future ones). `dsh-tools` requires `language === 'typescript'` in the MVP — its codegen emits TS — and fails the assembly loudly otherwise, the same misconfiguration idiom as `toolOrder` violations (as when `mode` is non-native with no `ctx.codeRuntime` loaded at all). Requests contain every runtime input; implementations own validated timeout and cap defaults. The registry looks up the optional runtime only when Code Mode is assembled, so native mode does not depend on one. Missing or language-incompatible runtimes fail loudly. Alternate substrates or languages can replace the implementation behind the same seam, paired with the appropriate SDK generator. @@ -74,7 +74,7 @@ Requests contain every runtime input; implementations own validated timeout and 3. **Execute** in the bootstrap: the stripped program becomes the body of an `AsyncFunction` whose parameters are the binding globals and a capturing `console` shim, so top-level `await` and `return` work and the program's completion value is the run's `value` (structured-cloneable values cross as-is; anything else is replaced by its `util.inspect` rendering, documented). 4. **Bridge bindings over the message port**: each binding function in the worker posts `{ id, global, name, args }` and awaits the reply; the host validates the name against the request's bindings, invokes, and replies `{ id, ok, value }` or `{ id, ok: false, message }` (a host-side binding rejection becomes a program-side rejection). The worker-side namespace objects are built null-prototype via `defineProperty`, so a binding named `__proto__`, `constructor`, or `toString` is an ordinary own property, not a prototype collision. Unknown names, duplicate ids, and post-settlement messages are rejected or ignored — the port protocol assumes a hostile peer, because the peer runs model code. 5. **Enforce independent budgets.** `computeMs` meters worker busy time, allowing slow awaited tools without excusing a hot loop. `maxWallMs` bounds total elapsed time, including unresolved waits. Expiry, cancellation, and completion terminate the worker. Heap exits and truncation are reported explicitly; compute, wall, heap, log, and return-value caps are validated configuration. -6. **Dispose to quiescence**: the service's own disposal terminates in-flight workers and *awaits* their exits before resolving, per [defensive patterns](../../../defensive-patterns.md). +6. **Dispose to quiescence**: the service's own disposal terminates in-flight workers and *awaits* their exits before resolving, per [defensive patterns](../../../../docs/defensive-patterns.md). ### Trust posture @@ -97,7 +97,7 @@ Deployments switching to `'code'` must update any native-only `toolOrder`. Assem ## Alternatives considered -**An add-on consumer plugin with zero core changes.** Rejected because `agent/request` is call-config-only under [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md), while transforming an assembled tool list would have to undo `toolOrder` canonicalization without owning its config and would depend on listener order. Which tools the model is offered, and in which representation, is the registry's single concern: native schemas and the SDK are two projections of one visible store. +**An add-on consumer plugin with zero core changes.** Rejected because `agent/request` is call-config-only under [reconstructable requests](../architecture/2026-07-05-reconstructable-requests.md), while transforming an assembled tool list would have to undo `toolOrder` canonicalization without owning its config and would depend on listener order. Which tools the model is offered, and in which representation, is the registry's single concern: native schemas and the SDK are two projections of one visible store. **`node:vm` as the reference runtime, with hardening deferred.** Rejected: `node:vm` is not isolation (prototype-chain escapes reach the host realm) and cannot interrupt a hot loop. A worker thread provides a separate isolate, empty environment, `resourceLimits`, and reliable `terminate()` at bash-equivalent trust, so the reference and production implementation are one package without an unsafe-acknowledgement ceremony. @@ -119,7 +119,7 @@ Deployments switching to `'code'` must update any native-only `toolOrder`. Assem **`stripTypeScriptTypes` is marked experimental.** It is the same engine (amaro/swc) behind Node's own native `.ts` execution, exposed as an API across this repo's whole engines range. Mitigations: the runtime's unit suite pins the behaviors relied on (position preservation, erasable-only rejection message shape loosely), the call sits behind one private function, and `amaro`/`sucrase` are drop-in replacements if the API shifts. The erasable-only subset is a model-facing contract line, and the error path is a working feedback loop, not a dead end. -**Prompt cost of the SDK, especially under `'both'`.** The `.d.ts` can rival the native schemas it complements; `'both'` carries two representations. Prefix stability + provider caching amortize per-session cost; the mode is per-deployment; the RFC makes no unconditional-savings claim. Measured guidance (when to prefer which mode) is explicitly post-ship learning. +**Prompt cost of the SDK, especially under `'both'`.** The `.d.ts` can rival the native schemas it complements; `'both'` carries two representations. Prefix stability + provider caching amortize per-session cost; the mode is per-deployment; the Agent Note makes no unconditional-savings claim. Measured guidance (when to prefer which mode) is explicitly post-ship learning. **Registry scope growth.** `dsh-tools` absorbs codegen, a tool, a bridge, and an event. Contained by module boundaries inside the package (`ts-types.ts`, `code-mode.ts` beside `schema.ts`/`json-schema.ts`/`presentation.ts`) and by the seam: everything substrate-shaped lives behind `ctx.codeRuntime`. diff --git a/docs/rfc/implemented/feature/2026-06-17-filesystem-tool-schemas.md b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md similarity index 86% rename from docs/rfc/implemented/feature/2026-06-17-filesystem-tool-schemas.md rename to .agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md index adad17472d..a318956ddf 100644 --- a/docs/rfc/implemented/feature/2026-06-17-filesystem-tool-schemas.md +++ b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md @@ -1,12 +1,12 @@ -# RFC: Filesystem tool schemas — model-facing read/write/edit shapes +# Agent Note: Filesystem tool schemas — model-facing read/write/edit shapes Status: implemented ## Problem -[The filesystem capability-seam RFC](../architecture/2026-06-17-filesystem-capability-seam.md) defines the filesystem capability seam (`ctx.fs`), the package split (`dsh-fs`, `dsh-fs-local`, `dsh-tool-fs`, plus the `dsh-fs-policy` policy plugin), and the observed-file/stale-version policy for read-before-write/edit checks — which the [split-fs-seam](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [event-gate](../architecture/2026-06-26-file-context-as-event-gate.md) RFCs moved off `ctx.fs` into the `dsh-fs-policy` plugin on the `fs/*` event gate. The remaining decision for the first filesystem tool delivery is the model-facing schema surface: what arguments the model sees for `read`, `write`, and `edit`. +[The filesystem capability-seam Agent Note](../architecture/2026-06-17-filesystem-capability-seam.md) defines the filesystem capability seam (`ctx.fs`), the package split (`dsh-fs`, `dsh-fs-local`, `dsh-tool-fs`, plus the `dsh-fs-policy` policy plugin), and the observed-file/stale-version policy for read-before-write/edit checks — which the [split-fs-seam](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [event-gate](../architecture/2026-06-26-file-context-as-event-gate.md) Agent Notes moved off `ctx.fs` into the `dsh-fs-policy` plugin on the `fs/*` event gate. The remaining decision for the first filesystem tool delivery is the model-facing schema surface: what arguments the model sees for `read`, `write`, and `edit`. -The schema should be small enough to implement in the first `dsh-tool-fs` pass, but stable enough that future local/remote/sandboxed filesystem backends do not require model-facing churn. It should also avoid importing every option from reference systems. Claude Code and OpenCode expose similar core file tools but differ in naming style and extra flags; this RFC chooses the minimal shared surface for the prototype. +The schema should be small enough to implement in the first `dsh-tool-fs` pass, but stable enough that future local/remote/sandboxed filesystem backends do not require model-facing churn. It should also avoid importing every option from reference systems. Claude Code and OpenCode expose similar core file tools but differ in naming style and extra flags; this Agent Note chooses the minimal shared surface for the prototype. ## Decision @@ -103,8 +103,8 @@ Schema tests pin the required/optional argument set per tool, empty-`old_string` ## Consequences -**The first schema is intentionally smaller than Claude Code's.** Dropping PDF pages, multimodal read, rich grep/list flags, and expected hash fields keeps the implementation focused, but users may ask for those quickly. They arrive as separate RFCs or focused follow-ups rather than overloads of the initial schema. +**The first schema is intentionally smaller than Claude Code's.** Dropping PDF pages, multimodal read, rich grep/list flags, and expected hash fields keeps the implementation focused, but users may ask for those quickly. They arrive as separate Agent Notes or focused follow-ups rather than overloads of the initial schema. **No explicit model-facing stale guard in v1.** The schema does not ask the model to provide an expected hash/version. That is intentional: stale checks come from backend-produced versions and the `dsh-fs-policy` plugin's observed state, not from fragile model-copied tokens. Filesystem safety failures surface through structured `FsError` codes owned by `dsh-fs`, not through model-supplied version fields. -**Naming becomes public surface.** Once shipped, changing `file_path` to `filePath` or `old_string` to `oldString` would churn prompts, examples, and downstream clients. This RFC chooses snake_case up front and treats it as the stable model-facing contract. +**Naming becomes public surface.** Once shipped, changing `file_path` to `filePath` or `old_string` to `oldString` would churn prompts, examples, and downstream clients. This Agent Note chooses snake_case up front and treats it as the stable model-facing contract. diff --git a/docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md similarity index 90% rename from docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md rename to .agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md index 3b8cd810a8..8d9c0197eb 100644 --- a/docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md +++ b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md @@ -1,10 +1,10 @@ -# RFC: Rich ACP bash rendering — the terminal card via the `_meta` convention +# Agent Note: Rich ACP bash rendering — the terminal card via the `_meta` convention Status: implemented ## Problem -The ACP bridge lets each tool own its call rendering via `presentCall`/`presentResult` (see [tool-call UI presentation](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) and `packages/core/tools`). For `bash` we surface the exact command as the `tool_call` title, the model's `description` as a content text block, `kind: 'execute'`, and the completed output wrapped in a fenced ` ```console ` text block. +The ACP bridge lets each tool own its call rendering via `presentCall`/`presentResult` (see [tool-call UI presentation](2026-06-14-acp-agent-client-protocol.md) and `packages/core/tools`). For `bash` we surface the exact command as the `tool_call` title, the model's `description` as a content text block, `kind: 'execute'`, and the completed output wrapped in a fenced ` ```console ` text block. Reference editors render terminal metadata as a dedicated card with cwd, command, live-style output, and exit status; plain text loses that structure. The command is the title because execute cards hide raw input, while the human-readable description remains a separate block above the card. @@ -43,4 +43,4 @@ Keep `dsh-bash` agent-side execution; render the terminal card via the `_meta` c ## Out of scope / non-goals -The text-block baseline stays the no-capability default. Two follow-ups are deliberately NOT built here and would each warrant their own RFC when someone takes them on: **live incremental streaming** (`_meta.terminal_output_delta` as chunks arrive, which needs an incremental-output seam on `dsh-bash`), and **command classification** (parsing a `cat`/`sed` as a `read` card with a file location, a `grep` as a `search`, etc., falling back to the terminal card — display-only, must never change what executes). +The text-block baseline stays the no-capability default. Two follow-ups are deliberately NOT built here and would each warrant their own Agent Note when someone takes them on: **live incremental streaming** (`_meta.terminal_output_delta` as chunks arrive, which needs an incremental-output seam on `dsh-bash`), and **command classification** (parsing a `cat`/`sed` as a `read` card with a file location, a `grep` as a `search`, etc., falling back to the terminal card — display-only, must never change what executes). diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md similarity index 89% rename from docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md rename to .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md index 1d767d49fc..a7b06a8379 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -1,4 +1,4 @@ -# RFC: Compaction as a capability seam (abstract contract + basic backend) +# Agent Note: Compaction as a capability seam (abstract contract + basic backend) Status: implemented @@ -6,15 +6,15 @@ Status: implemented A long-running agent conversation grows without bound. As the event log accumulates turns, the derived message history eventually approaches the model's context window — the model then truncates mid-response (`max-tokens`) or degrades. **Compaction** is the mitigation: replace a run of older history with a concise summary, keeping recent context intact. -The [session surface](../../implemented/architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — an ordered projection over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of entries and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*. +The [session surface](../architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — an ordered projection over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of entries and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*. -Two forces shape the design. First, compaction policy and reusable token measurement vary independently: measurement belongs to the LLM-family [`ctx.tokenMeter` service](../../implemented/architecture/2026-07-15-replay-token-meter-service.md), while summarization can be a model call, a template, or a remote service. Second, `SurfaceEventType` is closed to five event types (`user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler rejects `surfaceOp` on it and the invariants plugin rejects it at runtime. +Two forces shape the design. First, compaction policy and reusable token measurement vary independently: measurement belongs to the LLM-family [`ctx.tokenMeter` service](../architecture/2026-07-15-replay-token-meter-service.md), while summarization can be a model call, a template, or a remote service. Second, `SurfaceEventType` is closed to five event types (`user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler rejects `surfaceOp` on it and the invariants plugin rejects it at runtime. ## Decision ### Compaction is a capability seam, split interface / implementation -Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: +Per the [capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: 1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, and the `compact/*` session events. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. 2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. @@ -22,7 +22,7 @@ Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capabil ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation -The capability-seams RFC states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs act on an agent-owned `Session` (`compactRegion(start, end, agent)`) and its output uses the content vocabulary (`CompactionResult.summary: ContentBlock[]`). There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). +The capability-seams Agent Note states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs act on an agent-owned `Session` (`compactRegion(start, end, agent)`) and its output uses the content vocabulary (`CompactionResult.summary: ContentBlock[]`). There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact. @@ -36,7 +36,7 @@ An earlier draft put the full algorithm (the retention walk, token-summing, text Successful-call pressure cannot run at pre-step because final `agent/request` routing, provider output, tool results, buffered context, and steering do not exist there. Serial `agent/post-step(agent, turn, step, signal)` fires after those facts are durable and before `step/end`. `dsh-compact-basic` measures the canonical logged request through `ctx.tokenMeter`, so the next request sees any replacement without a speculative envelope override. -Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic forces one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases; the loop then opens a new numbered step and reconstructs its request from the durable log. No range, no replacement, recovery failure, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. The complete lifecycle decision is in the [after-call recovery RFC](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). +Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic forces one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases; the loop then opens a new numbered step and reconstructs its request from the durable log. No range, no replacement, recovery failure, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. The complete lifecycle decision is in the [after-call recovery Agent Note](../architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). ``` assistant/message → tool/result/context/steering diff --git a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md similarity index 82% rename from docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md rename to .agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md index 3f44940848..3ed2090b22 100644 --- a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md @@ -1,12 +1,12 @@ -# RFC: Subagent capability seam +# Agent Note: Subagent capability seam Status: implemented -> The full seam is shipped: the `dsh-subagent` interface and `dsh-tool-subagent` consumer; the two in-process backends (`dsh-subagent-spawn`, `dsh-subagent-fork`); the nested-agent snapshot infrastructure ([per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md)); and the out-of-process `dsh-subagent-acp` backend ([its RFC](2026-06-22-acp-subagent-backend.md)). +> The full seam is shipped: the `dsh-subagent` interface and `dsh-tool-subagent` consumer; the two in-process backends (`dsh-subagent-spawn`, `dsh-subagent-fork`); the nested-agent snapshot infrastructure ([per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md)); and the out-of-process `dsh-subagent-acp` backend ([its Agent Note](2026-06-22-acp-subagent-backend.md)). ## Problem -The harness has a long-deferred seam for **subagents** — an agent delegating work to another agent. The intent was sketched in the `Agent`/`AgentLoop` interfaces ([packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts), [packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)): a creation option referencing a parent agent (fork = seed the child session with the parent's event log; spawn = fresh session), with the child returned as an `Agent` handle so steering and event subscription work uniformly. This RFC realizes that seam; the banner above lists what shipped. +The harness has a long-deferred seam for **subagents** — an agent delegating work to another agent. The intent was sketched in the `Agent`/`AgentLoop` interfaces ([packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts), [packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)): a creation option referencing a parent agent (fork = seed the child session with the parent's event log; spawn = fresh session), with the child returned as an `Agent` handle so steering and event subscription work uniformly. This Agent Note realizes that seam; the banner above lists what shipped. The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports we foresee: @@ -18,7 +18,7 @@ The distinctive requirement — the one that shapes the whole design — is that ### Why not the bash seam shape -The bash seam ([capability seams](../../implemented/architecture/2026-06-13-capability-seams.md)) registers exactly one `BashExecutor` per context; loading a second throws. That is correct for bash (one machine, one way to run a command) but wrong here: coexistence is the requirement. So the subagent service is a **named-provider registry** — each implementation registers under a unique name and a caller picks one by name — mirroring the **LLM adapter registry** (`LlmService.registerAdapter`), not the single-service bash executor. The seam is still three-package (interface / implementation / consumer); only the "one vs. many implementations" axis differs. +The bash seam ([capability seams](../architecture/2026-06-13-capability-seams.md)) registers exactly one `BashExecutor` per context; loading a second throws. That is correct for bash (one machine, one way to run a command) but wrong here: coexistence is the requirement. So the subagent service is a **named-provider registry** — each implementation registers under a unique name and a caller picks one by name — mirroring the **LLM adapter registry** (`LlmService.registerAdapter`), not the single-service bash executor. The seam is still three-package (interface / implementation / consumer); only the "one vs. many implementations" axis differs. ## Decision @@ -61,11 +61,11 @@ Each subagent runs in its **own `Session`** (own id, `parentSession` lineage), p ## Testing -Registry and tool tests replace only the nondeterministic child boundary with a package-local scripted provider while exercising the real `SubagentService`, lifecycle, task integration, and model-facing tool. Provider and consumer export shapes retain their Loader regression coverage for the failure described in [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md). Registry tests cover reload safety, duplicate names, and start-time capability rejection; nested-agent scenarios replay keylessly through [per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md); in-process backends also have real-loop unit tests and a with-key e2e. +Registry and tool tests replace only the nondeterministic child boundary with a package-local scripted provider while exercising the real `SubagentService`, lifecycle, task integration, and model-facing tool. Provider and consumer export shapes retain their Loader regression coverage for the failure described in [postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md). Registry tests cover reload safety, duplicate names, and start-time capability rejection; nested-agent scenarios replay keylessly through [per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md); in-process backends also have real-loop unit tests and a with-key e2e. ## Consequences -- **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls RFC](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits. +- **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits. - **Blocking the parent turn.** Foreground collection holds the parent's step open for the child's full duration. Background delegation uses the shared `ctx.tasks` runtime and generic `task_*` tools, the same collection mechanism as background bash; the subagent seam itself remains task-agnostic. - **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign. - **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process. diff --git a/docs/rfc/implemented/feature/2026-06-22-acp-subagent-backend.md b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md similarity index 84% rename from docs/rfc/implemented/feature/2026-06-22-acp-subagent-backend.md rename to .agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md index 0b98adb0de..1c5b5b533d 100644 --- a/docs/rfc/implemented/feature/2026-06-22-acp-subagent-backend.md +++ b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md @@ -1,10 +1,10 @@ -# RFC: ACP subagent backend (out-of-process delegation) +# Agent Note: ACP subagent backend (out-of-process delegation) Status: implemented ## Problem -The subagent seam ([the seam RFC](2026-06-21-subagent-capability-seam.md)) was built so multiple backends coexist by name on `ctx.subagents`. The in-process backends (`-spawn`/`-fork`) run a child as a second `Agent` on the SAME cordis context — cheap, but the child shares the parent's process, model client, and tools. The seam's whole point was to also support an OUT-OF-PROCESS child reached over a protocol, proving the abstraction generalizes across a process boundary. This RFC adds the first such backend: an Agent Client Protocol (ACP) client. +The subagent seam ([the seam Agent Note](2026-06-21-subagent-capability-seam.md)) was built so multiple backends coexist by name on `ctx.subagents`. The in-process backends (`-spawn`/`-fork`) run a child as a second `Agent` on the SAME cordis context — cheap, but the child shares the parent's process, model client, and tools. The seam's whole point was to also support an OUT-OF-PROCESS child reached over a protocol, proving the abstraction generalizes across a process boundary. This Agent Note adds the first such backend: an Agent Client Protocol (ACP) client. ## Decision @@ -16,7 +16,7 @@ Each `start` spawns a new child, runs exactly one ACP session (`initialize` → ### Minimal client stub -The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards) in this cut, which surfaces only the child's final answer. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — the first cut surfaces no prompt to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam RFC noted. +The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards) in this cut, which surfaces only the child's final answer. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — the first cut surfaces no prompt to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted. ### No start-time capabilities @@ -52,4 +52,4 @@ Every run pays a fresh subprocess (spawn + `initialize` + `newSession`). The par ## Future providers -The same out-of-process spawn/prompt/stream/cancel shape generalizes to other transports named in the seam RFC — A2A, the Codex app-server, and the Claude Code Agent SDK — each a sibling provider registered by name. The ACP backend is the proof that the seam supports the boundary; those are mechanically similar. +The same out-of-process spawn/prompt/stream/cancel shape generalizes to other transports named in the seam Agent Note — A2A, the Codex app-server, and the Claude Code Agent SDK — each a sibling provider registered by name. The ACP backend is the proof that the seam supports the boundary; those are mechanically similar. diff --git a/docs/rfc/implemented/feature/2026-06-24-workspace-context.md b/.agents/notes/implemented/feature/2026-06-24-workspace-context.md similarity index 99% rename from docs/rfc/implemented/feature/2026-06-24-workspace-context.md rename to .agents/notes/implemented/feature/2026-06-24-workspace-context.md index cc11fd19ff..dc21fb919d 100644 --- a/docs/rfc/implemented/feature/2026-06-24-workspace-context.md +++ b/.agents/notes/implemented/feature/2026-06-24-workspace-context.md @@ -1,4 +1,4 @@ -# RFC: Workspace context instruction files +# Agent Note: Workspace context instruction files Status: implemented diff --git a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.md similarity index 99% rename from docs/rfc/implemented/feature/2026-06-25-ask-user-question.md rename to .agents/notes/implemented/feature/2026-06-25-ask-user-question.md index 8320dc4aa5..4227341aec 100644 --- a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md +++ b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.md @@ -1,4 +1,4 @@ -# RFC: Ask-user question capability +# Agent Note: Ask-user question capability Status: implemented diff --git a/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md similarity index 98% rename from docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md rename to .agents/notes/implemented/feature/2026-06-29-todo-write-tool.md index 127da5d09f..ab9421c2ed 100644 --- a/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md +++ b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md @@ -1,4 +1,4 @@ -# RFC: The `todo_write` tool — model task list as event-sourced session state +# Agent Note: The `todo_write` tool — model task list as event-sourced session state Status: implemented diff --git a/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.md similarity index 88% rename from docs/rfc/implemented/feature/2026-06-30-hook-bridges.md rename to .agents/notes/implemented/feature/2026-06-30-hook-bridges.md index af5c7e928d..0c3c1e13ef 100644 --- a/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md +++ b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.md @@ -1,16 +1,16 @@ -# RFC: dsh-hooks-claude + dsh-hooks-codex — the Claude Code / Codex hook bridges +# Agent Note: dsh-hooks-claude + dsh-hooks-codex — the Claude Code / Codex hook bridges Status: implemented ## Problem -The harness's extension surface is its typed interception seams ([the interception-seams RFC](2026-06-30-interception-seams.md)): a "native hook" is just an ordinary cordis plugin subscribing to `agent/session-start`, `agent/prompt-submit`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation`, `subagent/start`, `subagent/end`. But users arrive with **existing** Claude Code (CC) and Codex hook configs — a `hooks.json` (or a settings file's `hooks` key) full of shell-command hooks — and want those to run unmodified. This RFC introduces the two **bridge plugins** that translate that external shell-hook protocol onto the typed seams, built on the shared wire-protocol library ([the hook-protocol-lib RFC](2026-06-30-hook-protocol-lib.md)). +The harness's extension surface is its typed interception seams ([the interception-seams Agent Note](2026-06-30-interception-seams.md)): a "native hook" is just an ordinary cordis plugin subscribing to `agent/session-start`, `agent/prompt-submit`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation`, `subagent/start`, `subagent/end`. But users arrive with **existing** Claude Code (CC) and Codex hook configs — a `hooks.json` (or a settings file's `hooks` key) full of shell-command hooks — and want those to run unmodified. This Agent Note introduces the two **bridge plugins** that translate that external shell-hook protocol onto the typed seams, built on the shared wire-protocol library ([the hook-protocol-lib Agent Note](2026-06-30-hook-protocol-lib.md)). The framing that shapes the whole design: **a bridge is a compatibility adapter, not a power tool.** Anything a bridge does (block a tool, inject context, force continuation, observe a subagent) a native cordis plugin does more powerfully — typed returns, full `ctx`, no serialization boundary. The bridge's reason to exist is to run the explicitly supported subset of external CC/Codex command hooks. That keeps each bridge thin: parse the config, pick a matcher mode, build the per-event payload, call `runHook` + `mergeHookOutputs` from the shared lib, and map the neutral outcome onto a seam Decision. The package READMEs own the exact current unsupported-event and partial-field inventory against the official protocols. ## Decision -Two independent plugins in the `packages/hooks/` group, each a function/namespace plugin (`name`/`inject`/`Config`/`apply`, NO default export — see [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md)) injecting only `bash`: +Two independent plugins in the `packages/hooks/` group, each a function/namespace plugin (`name`/`inject`/`Config`/`apply`, NO default export — see [postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)) injecting only `bash`: - **`dsh-hooks-claude`** — the CC dialect. Seven of Claude Code's current hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, and `SubagentStop`. Owns CC-shaped per-event stdin payloads (a base of `session_id`/`transcript_path`/`cwd`/`hook_event_name` plus per-event fields), `CLAUDE_PROJECT_DIR` plus `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. `transcript_path` is the persistence locator result or `''`; stdin carries a **trailing newline**. - **`dsh-hooks-codex`** — five of Codex's current hook points: `PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, and `Stop`. It uses an always-regex matcher, Codex-shaped snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no Codex plugin-env injection or config-time placeholder substitution, and no pre-tool approval or rewrite path. `transcript_path` is the same locator result or `null`; tool payloads carry the real `tool_name` in the reduced `tool_input: { command }` shape. @@ -53,7 +53,7 @@ Hooks run in the agent's session workspace, so relative paths target the user's ## Deferred compatibility gaps -- **Tool-input rewrite.** A CC/Codex `updatedInput` is logged + warned, not honored — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)), because the pre-execution args are read by `tool/call` audit + `assistant/message` history + ACP/tool-bash presentation, so an honest rewrite is a design unit, not a field. +- **Tool-input rewrite.** A CC/Codex `updatedInput` is logged + warned, not honored — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite Agent Note](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)), because the pre-execution args are read by `tool/call` audit + `assistant/message` history + ACP/tool-bash presentation, so an honest rewrite is a design unit, not a field. - **Stop loop-guard** (`TODO(stop-loop-guard)`). Claude Code supplies `stop_hook_active` and overrides a hook after eight consecutive blocks; Codex supplies `stop_hook_active` but documents no equivalent cap. Both bridges always report `false`, so a Stop hook that unconditionally blocks force-continues every step — a hook author must self-limit until state tracking lands. - **Hook `continue:false` (hard halt).** A hook can ask to halt the whole run (CC/Codex `continue:false`); the shared merge folds it into `MergedHookOutcome.stop`/`stopReason`, but no bridge acts on it (`TODO(hook-continue-false)`) — the interception seams have no "hard-halt the agent" primitive yet (a Decision blocks/steers a single point, not the run). Deferred with the loop-guard work; the halt request is recorded in the `hook/result` log, and the hook keeps its per-point effect (decision/context) meanwhile. - **Config discovery.** The path is explicit in `cordis.yml` and process-level (see above); the full multi-layer CC/Codex precedence walk, per-session project-local discovery, and the trust/hash model are not reimplemented (`TODO(per-session-hook-config)`). diff --git a/docs/rfc/implemented/feature/2026-06-30-hook-protocol-lib.md b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md similarity index 90% rename from docs/rfc/implemented/feature/2026-06-30-hook-protocol-lib.md rename to .agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md index ac28345791..bb1822504a 100644 --- a/docs/rfc/implemented/feature/2026-06-30-hook-protocol-lib.md +++ b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md @@ -1,4 +1,4 @@ -# RFC: dsh-hook-protocol — the shared Claude Code / Codex hook wire-protocol core +# Agent Note: dsh-hook-protocol — the shared Claude Code / Codex hook wire-protocol core Status: implemented @@ -6,7 +6,7 @@ Status: implemented The hooks subsystem ships two bridge plugins: one that runs a user's existing Claude Code (CC) hooks, one for Codex hooks. Studying the reference implementations (`~/repos/refs/claude-code`, `~/repos/refs/codex`) surfaced a decisive fact: **Codex deliberately reimplements a SUBSET of the CC hook protocol.** Its engine reads the same `hooks.json`, uses the same matcher-group shape, the same exit-code/structured-stdout output contract, and the same command-hook execution model — Codex's source even names the engine after Claude's and comments where it "intentionally diverges." So the two bridges would otherwise duplicate the bulk of the protocol. -This RFC introduces `@deepseek-ai/dsh-hook-protocol`, a **library** (not a plugin — it registers and injects nothing) holding the genuinely-identical primitives both bridges build on. The split between shared and per-dialect is the design's center of gravity. +This Agent Note introduces `@deepseek-ai/dsh-hook-protocol`, a **library** (not a plugin — it registers and injects nothing) holding the genuinely-identical primitives both bridges build on. The split between shared and per-dialect is the design's center of gravity. ## Decision @@ -15,7 +15,7 @@ A new `packages/hooks/` group with `hook-protocol` as a pure library. It owns fo **Shared (here):** - **Matcher** — `matchesMatcher(pattern, query, mode)`. The ONE axis the dialects differ on is collapsed to the `mode` parameter: `claude` treats a pure `[A-Za-z0-9_|]+` pattern as a literal (pipe = exact-match alternation) and anything else as a regex; `codex` is always an unanchored regex. Match-all on absent/`''`/`'*'`; an invalid regex matches nothing (never throws into the loop). - **Execution** — `runHook(bash, hook, options)`. Runs a command hook through the `ctx.bash` seam rather than a bespoke `spawn`: the executor already provides the scrubbed-but-overridable env, process-group kills, and timeout the protocol needs, and `dsh-bash`'s `stdin`/`env` fields (added for exactly this) are the trusted-plugin surface an in-process bridge is allowed to use. It serializes the bridge-built payload to stdin (trailing newline iff CC), honors the hook's `timeoutSec` (else `DEFAULT_HOOK_TIMEOUT_MS`, the 10-minute reference default both dialects share), and never throws (an executor rejection becomes a non-blocking-error `HookOutput`). -- **Decode** — `parseHookOutput(exit, stdout, stderr)`, the exit-code + structured-stdout codec, producing a dialect-neutral `HookOutput`. Exit `0` → lenient JSON parse of stdout; exit `2` → blocking error with `stderr` as the reason (surfaced as `decision: 'block'` so no caller needs a separate exit-code branch); other → non-blocking error. Parses the CC structured-stdout fields that have a consumer on some path (`continue`/`stopReason`/`decision`/`hookSpecificOutput.{permissionDecision,additionalContext,updatedInput}`/`systemMessage`); the bridge honors only the subset meaningful for its dialect. Fields with no consumer on any path are not parsed at all (CC's `suppressOutput` — hook stdout never enters a transcript here, so there is nothing to suppress; see [the tighten-hook-protocol-contract RFC](../simplification/2026-07-04-tighten-hook-protocol-contract.md)). +- **Decode** — `parseHookOutput(exit, stdout, stderr)`, the exit-code + structured-stdout codec, producing a dialect-neutral `HookOutput`. Exit `0` → lenient JSON parse of stdout; exit `2` → blocking error with `stderr` as the reason (surfaced as `decision: 'block'` so no caller needs a separate exit-code branch); other → non-blocking error. Parses the CC structured-stdout fields that have a consumer on some path (`continue`/`stopReason`/`decision`/`hookSpecificOutput.{permissionDecision,additionalContext,updatedInput}`/`systemMessage`); the bridge honors only the subset meaningful for its dialect. Fields with no consumer on any path are not parsed at all (CC's `suppressOutput` — hook stdout never enters a transcript here, so there is nothing to suppress; see [the tighten-hook-protocol-contract Agent Note](../simplification/2026-07-04-tighten-hook-protocol-contract.md)). - **Merge** — `mergeHookOutputs(outputs)`, folding multiple matched hooks into one most-restrictive `MergedHookOutcome`: permission precedence **deny > ask > allow**, halt sticky on the first `continue:false`, block reasons joined `\n\n`, context/system-messages accumulated in order. - **`hook/*` session events** — `hook/invoked` / `hook/result`, declaration-merged into `SessionEventMap` (log-only, like `compact/*` — NOT `SurfaceEventType`s), with `appendHookInvoked`/`appendHookResult` helpers so the invoked/result pairing and turn-enclosure stay consistent across bridges. `appendHookResult` also owns the durable record's semantics — the decision string (the hook's parsed decision, else `'stop'` on `continue:false`, else `'pass'`) and the 500-character `stderrSummary` truncation derive from the `HookOutput` here, not per-bridge. diff --git a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md b/.agents/notes/implemented/feature/2026-06-30-interception-seams.md similarity index 92% rename from docs/rfc/implemented/feature/2026-06-30-interception-seams.md rename to .agents/notes/implemented/feature/2026-06-30-interception-seams.md index 1356afa06b..c0a25081af 100644 --- a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md +++ b/.agents/notes/implemented/feature/2026-06-30-interception-seams.md @@ -1,4 +1,4 @@ -# RFC: Interception seams — the typed-Decision surface a hook programs against +# Agent Note: Interception seams — the typed-Decision surface a hook programs against Status: implemented @@ -6,7 +6,7 @@ Status: implemented The harness needs a hooks subsystem: users extend or gate the agent at lifecycle points the way Claude Code (CC) and Codex do. The key reframe driving this design is that **"native hooks" are not a package** — a native hook is just an ordinary Cordis plugin subscribing to the canonical lifecycle events. So the real product is a *powerful, well-typed canonical event surface*; the CC/Codex bridges (the `dsh-hooks-claude` / `dsh-hooks-codex` packages) are merely translators that map an external shell-hook protocol onto that same surface. Anything a bridge can do, a plain plugin can do directly — more powerfully (no serialization boundary, full `ctx`, typed returns). -The surface needs distinct contracts for per-prompt policy (CC's `UserPromptSubmit`), session-start observation (CC's `SessionStart`), pre-tool policy, around-dispatch control, post-tool transformation, final-result observation, and continuation with a model-facing reason. Conflating those phases gives plugins mutation channels they do not need and makes finality depend on listener ordering. The [event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md) supplies the three-domain rule and the typed-Decision idiom; this RFC applies them to the lifecycle seams. +The surface needs distinct contracts for per-prompt policy (CC's `UserPromptSubmit`), session-start observation (CC's `SessionStart`), pre-tool policy, around-dispatch control, post-tool transformation, final-result observation, and continuation with a model-facing reason. Conflating those phases gives plugins mutation channels they do not need and makes finality depend on listener ordering. The [event-domain-semantics Agent Note](../architecture/2026-06-30-event-domain-semantics.md) supplies the three-domain rule and the typed-Decision idiom; this Agent Note applies them to the lifecycle seams. ## Decision @@ -55,4 +55,4 @@ The seam package does **not** declare `hook/*` session events (the durable hook- ## Consequences -The canonical interception surface is uniformly typed without giving every extension the same power: hooks return decisions, execution wrappers wrap, terminal guards only deny, and final observers only observe. The loop owns session-start, prompt-submit, post-tool context buffering, and continuation; `dsh-tools` owns identity sealing and the five-phase execution pipeline. Their contracts are documented in [architecture.md](../../../architecture.md), package READMEs, [core interception decisions](../../../core-data-structures/core.md#interception-decisions), and [tool structures](../../../core-data-structures/tools.md). The ACP bridge maps `rejected` turns to its `cancelled` codec value, while hook-driven snapshots verify the observable bridge behavior end to end. +The canonical interception surface is uniformly typed without giving every extension the same power: hooks return decisions, execution wrappers wrap, terminal guards only deny, and final observers only observe. The loop owns session-start, prompt-submit, post-tool context buffering, and continuation; `dsh-tools` owns identity sealing and the five-phase execution pipeline. Their contracts are documented in [architecture.md](../../../../docs/architecture.md), package READMEs, [core interception decisions](../../../../docs/core-data-structures/core.md#interception-decisions), and [tool structures](../../../../docs/core-data-structures/tools.md). The ACP bridge maps `rejected` turns to its `cancelled` codec value, while hook-driven snapshots verify the observable bridge behavior end to end. diff --git a/docs/rfc/implemented/feature/2026-06-30-session-store-fork-api.md b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md similarity index 83% rename from docs/rfc/implemented/feature/2026-06-30-session-store-fork-api.md rename to .agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md index 8d8813563b..ee67af7d96 100644 --- a/docs/rfc/implemented/feature/2026-06-30-session-store-fork-api.md +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md @@ -1,4 +1,4 @@ -# RFC: SessionStore fork API +# Agent Note: SessionStore fork API Status: implemented @@ -6,7 +6,7 @@ Status: implemented The event-sourced session log already has the primitive a fork needs: create a new session with a seed event prefix, then derive model history from that seeded log exactly as replay does. That primitive is intentionally low-level: `ctx.sessions.create(id, { seed, meta })` accepts any valid seed, but ordinary live-session branching needs policy around which prefix can be copied, which metadata is stamped on the child, and how errors are classified. -The semantic hazard is the fork boundary. A valid user-visible fork seed must be contiguous and turn-enclosed. Forking inside an active turn would copy an open `turn/start`, possibly an open `step/start`, and possibly dangling tool calls. That violates turn-enclosure and provider-transcript invariants, and it creates a misleading child history that appears to have participated in an unfinished parent turn. The existing [subagent seam](../../implemented/feature/2026-06-21-subagent-capability-seam.md) deliberately solves a different problem: tool-triggered subagent forks usually happen while the parent turn is open, so `dsh-subagent-fork` clips the seed to the parent's last completed-turn prefix. A general session fork should not silently clip; it should either fork the requested boundary or reject it. +The semantic hazard is the fork boundary. A valid user-visible fork seed must be contiguous and turn-enclosed. Forking inside an active turn would copy an open `turn/start`, possibly an open `step/start`, and possibly dangling tool calls. That violates turn-enclosure and provider-transcript invariants, and it creates a misleading child history that appears to have participated in an unfinished parent turn. The existing [subagent seam](2026-06-21-subagent-capability-seam.md) deliberately solves a different problem: tool-triggered subagent forks usually happen while the parent turn is open, so `dsh-subagent-fork` clips the seed to the parent's last completed-turn prefix. A general session fork should not silently clip; it should either fork the requested boundary or reject it. ## Decision @@ -38,4 +38,4 @@ An empty prefix is forkable; any non-empty boundary must be a safe existing sequ The public surface stays small and discoverable: live session branching is part of `ctx.sessions`, next to `create({ seed })`, rather than a standalone service or a two-step helper pair. Persistence continues to work through existing `session/created` and `session/flush` behavior: a forked child starts life with seeded events, so existing backends persist that seed once and preserve `parentSession` / `seedLength` in the header. -The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has transcript/snapshot coverage; this RFC adds no editor-facing updates, so no ACP snapshot is required now. Fork-child replay remains covered by the existing [seed-boundary testing RFC](../../implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md), while this API gets focused `dsh-session` unit tests plus JSONL persistence coverage. +The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has transcript/snapshot coverage; this Agent Note adds no editor-facing updates, so no ACP snapshot is required now. Fork-child replay remains covered by the existing [seed-boundary testing Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md), while this API gets focused `dsh-session` unit tests plus JSONL persistence coverage. diff --git a/docs/rfc/implemented/feature/2026-06-30-subagent-observe-enrich.md b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md similarity index 57% rename from docs/rfc/implemented/feature/2026-06-30-subagent-observe-enrich.md rename to .agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md index aa853edd24..861779fc50 100644 --- a/docs/rfc/implemented/feature/2026-06-30-subagent-observe-enrich.md +++ b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md @@ -1,12 +1,12 @@ -# RFC: Subagent lifecycle enrichment — lastAssistantMessage (observe-only) +# Agent Note: Subagent lifecycle enrichment — lastAssistantMessage (observe-only) Status: implemented ## Problem -The hooks subsystem ([interception seams RFC](2026-06-30-interception-seams.md)) lets a plugin observe and gate the agent at lifecycle points. Claude Code and Codex both expose **SubagentStart / SubagentStop** hooks, and CC's carry the subagent's final message. The harness already emits `subagent/start` and `subagent/end` lifecycle events ([the subagent capability-seam](2026-06-21-subagent-capability-seam.md)), but their payloads were minimal (`provider`, `id`, and on end `stopReason`) — not enough for a hooks bridge to report WHAT a subagent produced without separately reaching for the live run. +The hooks subsystem ([interception seams Agent Note](2026-06-30-interception-seams.md)) lets a plugin observe and gate the agent at lifecycle points. Claude Code and Codex both expose **SubagentStart / SubagentStop** hooks, and CC's carry the subagent's final message. The harness already emits `subagent/start` and `subagent/end` lifecycle events ([the subagent capability-seam](2026-06-21-subagent-capability-seam.md)), but their payloads were minimal (`provider`, `id`, and on end `stopReason`) — not enough for a hooks bridge to report WHAT a subagent produced without separately reaching for the live run. -This RFC enriches the end payload. It is deliberately **observe-only**: no control-flow change and no waterfall. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope. +This Agent Note enriches the end payload. It is deliberately **observe-only**: no control-flow change and no waterfall. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope. ## Decision @@ -16,14 +16,14 @@ Both events stay plain **`emit`s**. Async `SubagentService.start()` attaches res ## Alternatives considered -**An `agentType` subagent-kind label** (the harness analogue of CC's `subagent_type`) on the request + both lifecycle payloads — an earlier draft shipped it; dropped in review because it is a Claude-Code concept that does not fit our own seam (nothing here interprets it, and the only consumer was a CC-dialect bridge). The CC bridge instead feeds Claude Code's own default matcher value `"general-purpose"` for its SubagentStart/Stop `agent_type` matcher, so this RFC ships ONE enrichment: `lastAssistantMessage`. +**An `agentType` subagent-kind label** (the harness analogue of CC's `subagent_type`) on the request + both lifecycle payloads — an earlier draft shipped it; dropped in review because it is a Claude-Code concept that does not fit our own seam (nothing here interprets it, and the only consumer was a CC-dialect bridge). The CC bridge instead feeds Claude Code's own default matcher value `"general-purpose"` for its SubagentStart/Stop `agent_type` matcher, so this Agent Note ships ONE enrichment: `lastAssistantMessage`. **A control-flow `subagent/end`** — deferred; see below. ## Why observe-only, and what is deferred -A control-flow `subagent/end` (an awaited waterfall returning a stop/continue decision, like the other interception seams) would require: reshaping `subagent/end` from emit to waterfall, restructuring `SubagentService.start` to await listeners before settling, and implementing the `resume` capability in the in-process provider so a "continue" can actually re-run the child. That belongs to the background/steering subagent redesign the [capability-seam RFC](2026-06-21-subagent-capability-seam.md) already defers (the same redesign that unifies long-running-tool handling across subagents and bash). This RFC ships the observe-only enrichment a hooks bridge needs today; `FIXME(subagent-continuation)` / `TODO` anchors mark where the control-flow version would land if and when that redesign happens. +A control-flow `subagent/end` (an awaited waterfall returning a stop/continue decision, like the other interception seams) would require: reshaping `subagent/end` from emit to waterfall, restructuring `SubagentService.start` to await listeners before settling, and implementing the `resume` capability in the in-process provider so a "continue" can actually re-run the child. That belongs to the background/steering subagent redesign the [capability-seam Agent Note](2026-06-21-subagent-capability-seam.md) already defers (the same redesign that unifies long-running-tool handling across subagents and bash). This Agent Note ships the observe-only enrichment a hooks bridge needs today; `FIXME(subagent-continuation)` / `TODO` anchors mark where the control-flow version would land if and when that redesign happens. ## Consequences -A hooks bridge (or a native plugin) can now forward the child's `lastAssistantMessage` to a SubagentStop handler by subscribing to the existing emits — no new control-flow surface. The vocabulary addition is documented in [docs/core-data-structures/subagent.md](../../../core-data-structures/subagent.md) (the events prose) and the two subagent READMEs; the catalog is regenerated. No production behavior changes — the events fire exactly as before, with one more (optional) field on the end payload — so no snapshot or e2e change is needed. +A hooks bridge (or a native plugin) can now forward the child's `lastAssistantMessage` to a SubagentStop handler by subscribing to the existing emits — no new control-flow surface. The vocabulary addition is documented in [docs/core-data-structures/subagent.md](../../../../docs/core-data-structures/subagent.md) (the events prose) and the two subagent READMEs; the catalog is regenerated. No production behavior changes — the events fire exactly as before, with one more (optional) field on the end payload — so no snapshot or e2e change is needed. diff --git a/docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md similarity index 96% rename from docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md rename to .agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md index 6302584103..599c895ae2 100644 --- a/docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md +++ b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md @@ -1,4 +1,4 @@ -# RFC: Dynamic workflows — a script-driven multi-agent orchestration seam +# Agent Note: Dynamic workflows — a script-driven multi-agent orchestration seam Status: implemented @@ -18,7 +18,7 @@ One deliberate strictness DIVERGENCE from CC: hook misuse — unknown or deferre ### The seam (dsh-workflow) -`ctx.workflows` is an abstract `WorkflowService` in the bash shape — one engine per context, no named-provider registry (engines are deployment swaps, not co-residents). `start(request)` throws synchronously for a script that cannot begin; a returned `WorkflowRun`'s `result` NEVER rejects (failures resolve as `stopReason: 'error' | 'cancelled'`). The `workflow/*` events are observe-only emits carrying DATA SNAPSHOTS (id + meta; `workflow/end` omits the result value), per-listener contained, mirroring `subagent/start`/`subagent/end` — control stays with the run's holder. Vocabulary details: [core-data-structures/workflow.md](../../../core-data-structures/workflow.md). +`ctx.workflows` is an abstract `WorkflowService` in the bash shape — one engine per context, no named-provider registry (engines are deployment swaps, not co-residents). `start(request)` throws synchronously for a script that cannot begin; a returned `WorkflowRun`'s `result` NEVER rejects (failures resolve as `stopReason: 'error' | 'cancelled'`). The `workflow/*` events are observe-only emits carrying DATA SNAPSHOTS (id + meta; `workflow/end` omits the result value), per-listener contained, mirroring `subagent/start`/`subagent/end` — control stays with the run's holder. Vocabulary details: [core-data-structures/workflow.md](../../../../docs/core-data-structures/workflow.md). ### The engine (dsh-workflow-workerthread): one worker thread per run @@ -26,7 +26,7 @@ One deliberate strictness DIVERGENCE from CC: hook misuse — unknown or deferre **Why `node:worker_threads`**: each run gets one unpooled worker. A vm context limits the documented script surface, while message-port RPC bridges `agent()` to host-side child loops. The worker prevents synchronous script work from blocking the host, provides a serialization boundary, and permits forced termination after cancellation. `isolated-vm` was rejected because of its maintenance state and deployment requirements. -The host validates metadata and parses the body before publication. Private enum-keyed payload maps define the wire protocol; pending starts, published child records, one cancellation signal, worker-death reaping, result precedence, and disposal quiescence preserve the subagent run contract across it. The [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) owns those race algorithms. +The host validates metadata and parses the body before publication. Private enum-keyed payload maps define the wire protocol; pending starts, published child records, one cancellation signal, worker-death reaping, result precedence, and disposal quiescence preserve the subagent run contract across it. The [agent-scope runtime-design Agent Note](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) owns those race algorithms. The engine exposes an in-process `MessageChannel` test path because main-process V8 coverage cannot see worker execution. @@ -44,7 +44,7 @@ A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, awai An output schema makes a schema-valid committed capture mandatory for successful child completion. The scoped runtime presents the capture tool and instruction, commits only a successful final outcome—including the enclosing `run_code` outcome for an SDK call—denies later side effects after capture becomes pending, and stops the child without another model step after commit. A validation failure remains a retryable tool error; clean completion without a committed capture settles as an error. -`StructuredOutputSchema` is the raw enforceable JSON-Schema subset in `dsh-tools` (single-string `type`, `properties`/`required`/`additionalProperties`, `items`, scalar `enum`/`const`), and unsupported keywords fail loudly because that wire data becomes the capture tool's parameters verbatim. The [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#structured-output-commits-only-authoritative-outcomes) owns the assembly, commit, guard, and terminal-stop correctness algorithms. +`StructuredOutputSchema` is the raw enforceable JSON-Schema subset in `dsh-tools` (single-string `type`, `properties`/`required`/`additionalProperties`, `items`, scalar `enum`/`const`), and unsupported keywords fail loudly because that wire data becomes the capture tool's parameters verbatim. The [agent-scope runtime-design Agent Note](../architecture/2026-07-12-agent-scope-runtime-design.md#structured-output-commits-only-authoritative-outcomes) owns the assembly, commit, guard, and terminal-stop correctness algorithms. ## Testing diff --git a/docs/rfc/implemented/feature/2026-07-05-skill-system.md b/.agents/notes/implemented/feature/2026-07-05-skill-system.md similarity index 96% rename from docs/rfc/implemented/feature/2026-07-05-skill-system.md rename to .agents/notes/implemented/feature/2026-07-05-skill-system.md index 0b74aa00ae..e59013c0a8 100644 --- a/docs/rfc/implemented/feature/2026-07-05-skill-system.md +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.md @@ -1,4 +1,4 @@ -# RFC: Skill system — progressive disclosure instructions for agents +# Agent Note: Skill system — progressive disclosure instructions for agents Status: implemented @@ -24,7 +24,7 @@ Local skill filesystem I/O goes through `ctx.fs` when a filesystem service is lo The `skill({ name })` tool loads one full skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills marked `disableModelInvocation` retain distinct tool errors. The tool result is the model-visible disclosure path. -The data structures and catalog/tool contract are documented in [skills.md](../../../core-data-structures/skills.md), with service signatures in the generated [services catalog](../../../cordis-catalog/services.md). +The data structures and catalog/tool contract are documented in [skills.md](../../../../docs/core-data-structures/skills.md), with service signatures in the generated [services catalog](../../../../docs/cordis-catalog/services.md). ## Alternatives considered diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/.agents/notes/implemented/feature/2026-07-06-approval-seam.md similarity index 90% rename from docs/rfc/implemented/feature/2026-07-06-approval-seam.md rename to .agents/notes/implemented/feature/2026-07-06-approval-seam.md index 81e60a726f..af063895e2 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.md @@ -1,10 +1,10 @@ -# RFC: The approval seam — one-shot permission decisions over a waterfall of answerers +# Agent Note: The approval seam — one-shot permission decisions over a waterfall of answerers Status: implemented ## Problem -Two callers need to put one question — "may this specific action proceed?" — to a human: `tools/pre-execute`'s `ask` decision (including the Claude-Code hook bridge's `permissionDecision: ask`) and the [sandbox RFC](2026-07-06-sandbox.md)'s post-denial one-shot escalation retry. A shared seam keeps them from inventing separate outcome vocabularies, UI routing, cancellation, and audit trails, while guaranteeing that a deployment with no UI can never grant an unanswerable request. +Two callers need to put one question — "may this specific action proceed?" — to a human: `tools/pre-execute`'s `ask` decision (including the Claude-Code hook bridge's `permissionDecision: ask`) and the [sandbox Agent Note](2026-07-06-sandbox.md)'s post-denial one-shot escalation retry. A shared seam keeps them from inventing separate outcome vocabularies, UI routing, cancellation, and audit trails, while guaranteeing that a deployment with no UI can never grant an unanswerable request. The routing problem is ownership: an approval prompt must reach the editor session that owns the asking agent (the ACP bridge multiplexes N sessions over one connection), fail closed for agents nobody owns (in-process subagents, tests), and stay out of deployments that compose no UI (headless, CI). @@ -61,13 +61,13 @@ Answerers are `approval/request` waterfall listeners. Zero listeners fall throug #### The per-session policy tier -The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox RFC](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. The prompt states only deterministic `'never'`, switch narration is coalesced, and every request still records the audit pair. +The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox Agent Note](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. The prompt states only deterministic `'never'`, switch narration is coalesced, and every request still records the audit pair. #### The ACP answerer The ACP bridge answers only for an exact agent object owned by its forward session map. It attaches `session/request_permission` to the existing `callId`, advertises one-shot allow/reject options, maps cancellation separately, and never grants an unknown option. Foreign or call-less requests delegate; a failed client RPC becomes `unavailable`. Hooks and `tools/pre-execute` decide whether a call asks at all. -The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). +The answerer routes through the bridge's exact-agent ownership check described by [the ACP support Agent Note](2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session Agent Note](2026-06-14-acp-multi-session.md). #### Audit, and what the model sees @@ -85,7 +85,7 @@ Snapshots record allowed and rejected sandbox escalation through `session/reques ## Deferred -- **`allow_always` grant storage** — honoring a persistent grant means designing storage, scope identity (call? path? prefix? session? time window?), and revocation; until designed, only the one-shot options are advertised ([the sandbox RFC](2026-07-06-sandbox.md) § Escalation records the open scope question). +- **`allow_always` grant storage** — honoring a persistent grant means designing storage, scope identity (call? path? prefix? session? time window?), and revocation; until designed, only the one-shot options are advertised ([the sandbox Agent Note](2026-07-06-sandbox.md) § Escalation records the open scope question). - **A recorded hook-driven `ask` through a composed answerer** — the human-prompt wire is recorded through the sandbox example's escalation branches. The hook matrix's `hook-cc-pretool-ask` pins the no-ApprovalService fallback denial, while the hook-producer-plus-answerer composition remains on the unit tier. - **Routing a child agent's approvals to the parent session** — `subagent-acp`'s child auto-answers its own `permission` requests; surfacing them to the parent's editor is its own design. @@ -131,7 +131,7 @@ Costs and accepted limits: In-repo precedents this design copies or contrasts with: - The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses. -- `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges RFC](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer. -- [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services. -- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the exact-agent ownership check against the forward session map that the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. +- `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges Agent Note](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer. +- [The interception-seams Agent Note](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services. +- [The ACP support Agent Note](2026-06-14-acp-agent-client-protocol.md) — the exact-agent ownership check against the forward session map that the answerer routes through; [the multi-session Agent Note](2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. - The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it. diff --git a/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md similarity index 96% rename from docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md rename to .agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md index e841de8973..d46579dee1 100644 --- a/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md +++ b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md @@ -1,4 +1,4 @@ -# RFC: Explicit model-facing tool order +# Agent Note: Explicit model-facing tool order Status: implemented @@ -32,7 +32,7 @@ Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it: - **A `LlmService` config + `orderTools()` method the loop calls before logging the header** — works, but adds a public service method and a loop edit solely to apply a policy at a distance; every future request composer must remember the call. Canonicalizing where the list is born makes an unordered list unrepresentable, with zero new surface. - **Normalizing inside `llm.stream()`** — runs after the header event is logged (the flake survives) and rebuilds the deep-frozen envelope, silently disarming the reconstruction invariant. - **An exhaustive list (no rest entry)** — every newly loaded tool plugin would break boot; the mandatory rest entry keeps unlisted tools deterministic and their position explicit. -- **A boot-time validation pass (a `SystemPrompt.assertToolOrderSatisfied()` called by `dsh-app-boot` after `loader.await()`)** — would turn the misconfiguration into a startup death instead of a first-turn failure, but costs a public service method plus a structural coupling from the generic boot glue to one service, and cannot replace the assembly-time check anyway (embedded callers never run app boot; registrations change after boot). No existing event can host the check either: cordis v4 has no ready-like event, `loader/entry-init`/`internal/status` fire mid-load (racy against tool registration, the very entropy this RFC kills), and the agent lifecycle events are no earlier than the assembly. One enforcement point at `assemble()` was judged worth the later failure moment. +- **A boot-time validation pass (a `SystemPrompt.assertToolOrderSatisfied()` called by `dsh-app-boot` after `loader.await()`)** — would turn the misconfiguration into a startup death instead of a first-turn failure, but costs a public service method plus a structural coupling from the generic boot glue to one service, and cannot replace the assembly-time check anyway (embedded callers never run app boot; registrations change after boot). No existing event can host the check either: cordis v4 has no ready-like event, `loader/entry-init`/`internal/status` fire mid-load (racy against tool registration, the very entropy this Agent Note kills), and the agent lifecycle events are no earlier than the assembly. One enforcement point at `assemble()` was judged worth the later failure moment. ## Consequences diff --git a/docs/rfc/implemented/feature/2026-07-06-sandbox.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.md similarity index 96% rename from docs/rfc/implemented/feature/2026-07-06-sandbox.md rename to .agents/notes/implemented/feature/2026-07-06-sandbox.md index e236154cdc..32b53d77ea 100644 --- a/docs/rfc/implemented/feature/2026-07-06-sandbox.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.md @@ -1,4 +1,4 @@ -# RFC: The subprocess sandbox — confinement seam, native runners, escalation, and per-session modes +# Agent Note: The subprocess sandbox — confinement seam, native runners, escalation, and per-session modes Status: implemented @@ -12,7 +12,7 @@ Confinement alone leaves two gaps. A denial with no escalation path is terminal ## Decision -One seam, one per-platform chain of local backends, one consumer, and two levers on top: a per-call escalation path and per-session runtime modes. Everything below composes from the leaf `cordis.yml`; nothing touches `agent-loop`. The scope is deliberately bounded: the phases this RFC names but does not design — per-session workspace root, cross-family fs enforcement, the `subagent-acp` consumer, more environments, a Windows chain — are listed under § Deferred phases, each a follow-up design, not a config knob. +One seam, one per-platform chain of local backends, one consumer, and two levers on top: a per-call escalation path and per-session runtime modes. Everything below composes from the leaf `cordis.yml`; nothing touches `agent-loop`. The scope is deliberately bounded: the phases this Agent Note names but does not design — per-session workspace root, cross-family fs enforcement, the `subagent-acp` consumer, more environments, a Windows chain — are listed under § Deferred phases, each a follow-up design, not a config knob. ### How a deployment uses it @@ -27,7 +27,7 @@ Four `cordis.yml` entries turn an unconfined coding agent into the sandboxed pro mode: workspace-write # the deployment default every session starts from workspaceRoot: !!js process.cwd() # the boundary workspace-write may write under - id: approval - name: '@deepseek-ai/dsh-user-approval' # the escalation gate's channel (the approval RFC) + name: '@deepseek-ai/dsh-user-approval' # the escalation gate's channel (the approval Agent Note) config: policy: ask - id: permission @@ -103,7 +103,7 @@ interface SessionEventMap { } ``` -Each owner exports the same three-piece kit: the event declaration, a pure fold (`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)` — a `findLast`, typed to the domain's closed union), and THE write path (`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)` — a switch IS its event; nothing mutates state out of band). No shared owner service, no generic facts map, no registry: a third knob copies the ~40-line pattern into its own package. Execution follows the fold on both sides — the bash tool's per-call stamp reads it as the middle rung of the § Escalation precedence chain, and the approval seam's `'never'` gate is [the approval RFC](2026-07-06-approval-seam.md)'s side of the same pattern. +Each owner exports the same three-piece kit: the event declaration, a pure fold (`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)` — a `findLast`, typed to the domain's closed union), and THE write path (`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)` — a switch IS its event; nothing mutates state out of band). No shared owner service, no generic facts map, no registry: a third knob copies the ~40-line pattern into its own package. Execution follows the fold on both sides — the bash tool's per-call stamp reads it as the middle rung of the § Escalation precedence chain, and the approval seam's `'never'` gate is [the approval Agent Note](2026-07-06-approval-seam.md)'s side of the same pattern. Sandbox mode is not narrated in the prompt; denial results report the mode when it matters, avoiding preemptive refusal based on a standing label. Approval policy is different: only `'never'` is stated because automatic rejection otherwise looks like a user decision. Policy-change notices are coalesced and delivered by the next pre-step, with log-derived fallback after restart. The notice source is inferred from event position: a knob event after the last request header is user-driven; unlogged drift is operator or config driven. @@ -203,8 +203,8 @@ Costs and accepted limits: In-repo precedents this design copies or contrasts with: -- [The capability-seams RFC](../architecture/2026-06-13-capability-seams.md) — the interface/implementation/consumer split and the "don't split preemptively" timing rule the second consumer satisfied. -- The `dsh-bash` request/spec split ([the bash vocabulary catalog](../../../core-data-structures/bash.md)) — the per-call carrier template `sandboxMode` rides, and the explicit-`resolve()` defaulting convention. -- [The approval seam RFC](2026-07-06-approval-seam.md) — the channel escalation asks through; its answerer waterfall, audit pair, and one-package rationale are recorded there. +- [The capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md) — the interface/implementation/consumer split and the "don't split preemptively" timing rule the second consumer satisfied. +- The `dsh-bash` request/spec split ([the bash vocabulary catalog](../../../../docs/core-data-structures/bash.md)) — the per-call carrier template `sandboxMode` rides, and the explicit-`resolve()` defaulting convention. +- [The approval seam Agent Note](2026-07-06-approval-seam.md) — the channel escalation asks through; its answerer waterfall, audit pair, and one-package rationale are recorded there. - [Event-sourced sessions](../architecture/2026-06-11-event-sourced-sessions.md) and [the turn-enclosure invariant](../architecture/2026-06-15-turn-enclosure-invariant.md) — the log-as-store foundation the per-session modes fold over, and the commit boundary the anchoring design obeys. -- [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` vocabulary the escalation gate deliberately does not reuse (an escalating call has no pre-execute moment of its own). +- [The interception-seams Agent Note](2026-06-30-interception-seams.md) — the `tools/pre-execute` vocabulary the escalation gate deliberately does not reuse (an escalating call has no pre-execute moment of its own). diff --git a/docs/rfc/implemented/feature/2026-07-07-mcp-client-plugin.md b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md similarity index 98% rename from docs/rfc/implemented/feature/2026-07-07-mcp-client-plugin.md rename to .agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md index 27c108f0ce..95cad58b46 100644 --- a/docs/rfc/implemented/feature/2026-07-07-mcp-client-plugin.md +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md @@ -1,4 +1,4 @@ -# RFC: MCP client plugin — connect to external MCP servers and bridge their tools +# Agent Note: MCP client plugin — connect to external MCP servers and bridge their tools Status: implemented @@ -12,7 +12,7 @@ The `ToolRegistry` already accepts raw JSON Schema tool definitions (documented ### Package -A single package `@deepseek-ai/dsh-mcp-client` at `packages/mcp/mcp-client/`. No capability-seam three-package split — there is no foreseeable second MCP client implementation, and the convention is "don't split preemptively" ([capability seams RFC](../../implemented/architecture/2026-06-13-capability-seams.md)). +A single package `@deepseek-ai/dsh-mcp-client` at `packages/mcp/mcp-client/`. No capability-seam three-package split — there is no foreseeable second MCP client implementation, and the convention is "don't split preemptively" ([capability seams Agent Note](../architecture/2026-06-13-capability-seams.md)). ### SDK @@ -141,7 +141,7 @@ A unified `execute` handler for all tools from one MCP server: 1. Resolve `rawName` (the executor closes over it) and call `client.callTool({ name: rawName, arguments }, { signal: exec.signal })` with the configured timeout — the public name is never sent to the server. 2. Map the result: - Multiple `text` content blocks → join with `'\n'` into a single `TextBlock` (required: `flattenText` uses `join('')` without separator, so multiple blocks would lose inter-block boundaries). - - `image` content blocks → discard with a `ctx.logger.warn` (the harness has no image content block type; [drop-image RFC](../../implemented/simplification/2026-07-04-drop-image-content-block.md)). + - `image` content blocks → discard with a `ctx.logger.warn` (the harness has no image content block type; [drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md)). - `isError: true` → map to the harness `isError` result path (`{ content: [...], isError: true }`). 3. Cancellation: `exec.signal` (from the agent loop's cancel) is passed through to the MCP SDK's `callTool`, which sends `$/cancelRequest` to the server. diff --git a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md b/.agents/notes/implemented/feature/2026-07-07-session-prefix.md similarity index 87% rename from docs/rfc/implemented/feature/2026-07-07-session-prefix.md rename to .agents/notes/implemented/feature/2026-07-07-session-prefix.md index 0c642e7c68..c2f58dac0c 100644 --- a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md +++ b/.agents/notes/implemented/feature/2026-07-07-session-prefix.md @@ -1,4 +1,4 @@ -# RFC: The session prefix — request-only messages in front of the derived history +# Agent Note: The session prefix — request-only messages in front of the derived history Status: implemented @@ -6,16 +6,16 @@ Status: implemented A plugin often owns a session-stable opener the model must always see — a skills catalog, an AGENTS.md digest, a workspace baseline. Before this seam the harness offered two homes, and both are wrong for that content. The system prompt is one rendered string: message-shaped content (a user-role `<system-reminder>` envelope, a multi-message primer) does not fit it, and providers weight conversation messages differently from system text. Durable history (`agent.inject()`, a `context/message` at session start) makes the opener permanent: every `deriveMessages()` consumer replays it, the compaction retention walk owns it, forks bake it in stale, and a resume cannot refresh it — a catalog captured at session birth outlives the world it described. -The obvious third option — let a plugin edit the request's `messages` on the way out — is banned by [the reconstructable-requests RFC](../architecture/2026-07-05-reconstructable-requests.md): every loop-built request is a pure function of the session log, so whatever channel carries the opener must log exactly what it sends. What was missing was a request-only message channel with a durable record. +The obvious third option — let a plugin edit the request's `messages` on the way out — is banned by [the reconstructable-requests Agent Note](../architecture/2026-07-05-reconstructable-requests.md): every loop-built request is a pure function of the session log, so whatever channel carries the opener must log exactly what it sends. What was missing was a request-only message channel with a durable record. ## Decision -`agent/session-prefix` is a waterfall on the agent event map ([`packages/core/agent/src/types.ts`](../../../../packages/core/agent/src/types.ts)): listeners receive a frozen empty seed and return an extension (the canonical contribution is a prepend, `[mine, ...await next()]`, which yields registration order on the wire). The loop ([`packages/core/agent-loop/src/loop.ts`](../../../../packages/core/agent-loop/src/loop.ts)) fires it once per loop instance, lazily before the instance's first `agent/pre-step`; the composed list is deep-cloned, deep-frozen, cached on the instance, and placed in front of the ENTIRE derived history — directly after the provider's system slot — on every request the instance sends ([wire order](../../../core-data-structures/core.md#the-request-envelope-llmcallconfig-and-the-logged-header)). +`agent/session-prefix` is a waterfall on the agent event map ([`packages/core/agent/src/types.ts`](../../../../packages/core/agent/src/types.ts)): listeners receive a frozen empty seed and return an extension (the canonical contribution is a prepend, `[mine, ...await next()]`, which yields registration order on the wire). The loop ([`packages/core/agent-loop/src/loop.ts`](../../../../packages/core/agent-loop/src/loop.ts)) fires it once per loop instance, lazily before the instance's first `agent/pre-step`; the composed list is deep-cloned, deep-frozen, cached on the instance, and placed in front of the ENTIRE derived history — directly after the provider's system slot — on every request the instance sends ([wire order](../../../../docs/core-data-structures/core.md#the-request-envelope-llmcallconfig-and-the-logged-header)). Three properties carry the design: -- **Request-only, header-logged.** `deriveMessages()` never returns the prefix; its one durable record is `EpochHeader.messagePrefix` on the instance's anchoring `request/header` snapshot — the channel the reconstructable-requests RFC already owns for the request's non-history half, so no new session event exists. The dev invariant ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)) recomputes `messagePrefix + boundary derivation` against every loop-built request; an unlogged prefix cannot reach the wire. -- **Frozen per instance.** Reuse is structural, not disciplined: the cached product cannot change mid-session, so the provider's prompt cache holds by construction and the prefix extends the cacheable region at zero marginal cost per step. A process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` header snapshot. This is the routing rule the seam creates: session-frozen openers ride the prefix; content that changes mid-session rides the append-only history channels (`agent.inject()` or tool/prompt-submit `additionalContexts` — [the interception-seams RFC](2026-06-30-interception-seams.md)), each a durable `context/message` paid once and prefix-cached thereafter. +- **Request-only, header-logged.** `deriveMessages()` never returns the prefix; its one durable record is `EpochHeader.messagePrefix` on the instance's anchoring `request/header` snapshot — the channel the reconstructable-requests Agent Note already owns for the request's non-history half, so no new session event exists. The dev invariant ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)) recomputes `messagePrefix + boundary derivation` against every loop-built request; an unlogged prefix cannot reach the wire. +- **Frozen per instance.** Reuse is structural, not disciplined: the cached product cannot change mid-session, so the provider's prompt cache holds by construction and the prefix extends the cacheable region at zero marginal cost per step. A process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` header snapshot. This is the routing rule the seam creates: session-frozen openers ride the prefix; content that changes mid-session rides the append-only history channels (`agent.inject()` or tool/prompt-submit `additionalContexts` — [the interception-seams Agent Note](2026-06-30-interception-seams.md)), each a durable `context/message` paid once and prefix-cached thereafter. - **Exact in the durable request envelope.** Composition precedes the instance's first `agent/pre-step` and request boundary. The first routed request logs the current prefix on its header, so post-step token pressure reads the exact prefix together with the actual prompt, tools, and routed model; no compaction-only parameter is carried through the generic pre-step seam. A composition interrupted by cancel/dispose is discarded, never cached: an abort-aware listener's degraded fallback cannot leak into later requests, and the next turn recomposes under a live signal. Because composition runs before the boundary snapshot, a composing listener's session append joins the CURRENT request's derived history. Compaction structurally cannot touch the prefix (or the system prompt): it rewrites surface nodes, and header state never enters the surface. diff --git a/docs/rfc/implemented/feature/2026-07-08-background-subagent-tasks.md b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md similarity index 99% rename from docs/rfc/implemented/feature/2026-07-08-background-subagent-tasks.md rename to .agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md index 830d93577b..83ea99dc75 100644 --- a/docs/rfc/implemented/feature/2026-07-08-background-subagent-tasks.md +++ b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md @@ -1,4 +1,4 @@ -# RFC: Background subagent tasks +# Agent Note: Background subagent tasks Status: implemented diff --git a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md similarity index 91% rename from docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md rename to .agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md index 74f4216565..08f5bb01cf 100644 --- a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md +++ b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md @@ -1,4 +1,4 @@ -# RFC: Repeat-tool-call guard plugin +# Agent Note: Repeat-tool-call guard plugin Status: implemented @@ -6,13 +6,13 @@ Status: implemented A model stuck in a loop re-issues the same tool call with byte-identical arguments — re-running a failing grep, re-reading an unchanged file, polling a command that already gave its answer — and each round trip burns tokens, wall-clock, and (for paid APIs) money without adding information. The harness has nothing that notices: the loop has no step budget, no plugin tracks call repetition, and the model only escapes when it happens to vary its own behavior. The failure mode is real and cheap to detect — [pi-repeat-tool-guard](https://github.com/Kingwl/pi-repeat-tool-guard) ships exactly this as a pi coding-agent extension: count consecutive identical calls and, past a threshold, append a `<system-reminder>` telling the model to stop repeating itself and change course. -The harness already has every seam the pi extension uses, and better ones: [the interception-seams RFC](2026-06-30-interception-seams.md) gives `tools/post-execute` a sanctioned way to attach model-facing context to a finished call, the loop buffers and injects that context with call/result adjacency preserved, and injected context is a logged `context/message` — so a native guard satisfies the model-visible ⟺ logged rule with no new session event. What was missing was only the plugin itself. +The harness already has every seam the pi extension uses, and better ones: [the interception-seams Agent Note](2026-06-30-interception-seams.md) gives `tools/post-execute` a sanctioned way to attach model-facing context to a finished call, the loop buffers and injects that context with call/result adjacency preserved, and injected context is a logged `context/message` — so a native guard satisfies the model-visible ⟺ logged rule with no new session event. What was missing was only the plugin itself. ## Decision The guard is a loop-hygiene plugin, not a model-facing tool. It counts consecutive calls to the same tool with identical canonical arguments and injects advisory reminders at configured thresholds. It never delays, blocks, or rewrites a call; the model decides whether to retry differently or finish. -The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers two listeners and holds state in a `WeakMap` keyed by the live `Agent` object — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish; weak object keys also make a disposal-only cleanup listener unnecessary. +The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write Agent Note](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers two listeners and holds state in a `WeakMap` keyed by the live `Agent` object — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish; weak object keys also make a disposal-only cleanup listener unnecessary. - **`tools/post-execute` (waterfall)** — the one detection point. The listener receives `(exec, result)` together, so counting and reminder delivery need no cross-event pending map (the pi extension needs one only because its `tool_call`/`tool_result` hooks are separate events). It always delegates via `next()` and, when a threshold is hit, prepends a reminder to the downstream decision's `additionalContexts` — the observe-and-enrich posture [the hooks bridges](2026-06-30-hook-bridges.md) already use, honoring the waterfall contract. Counting happens here rather than in `tools/pre-execute` because post-execute also runs for denied calls (`ToolRegistry.execute` routes a deny through the same pipeline), and a model hammering a denied call is exactly the loop worth breaking. - **`agent/prompt-submit` (waterfall)** — pure reset hook: delegate via `next()`, clear the submitting agent's chain. A user interjection changes the context; repetition across it is not a loop. diff --git a/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md similarity index 92% rename from docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md rename to .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md index 94d11ee931..144bdd018f 100644 --- a/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md +++ b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md @@ -1,4 +1,4 @@ -# RFC: The self-referential cordis toolset +# Agent Note: The self-referential cordis toolset Status: implemented @@ -22,7 +22,7 @@ The vm isolates accidental global pollution, and the context façade hides frame | `cordis_mount` | Evaluates `code` (the body of an async JavaScript function) in a `node:vm` sandbox; the code must `return` a cordis plugin, which is mounted as a child of the `cordis-dynamic` group fiber and tracked under a fresh id (`dyn-1`, `dyn-2`, …). | | `cordis_unmount` | Disposes one dynamic mount by id and returns only after disposal reaches quiescence — every registration the plugin made is unwound, not merely requested to stop. | -`cordis_inspect` sections: `services` (every provided ctx service and the owning fiber, non-active owners flagged), `plugins` (a flat list of every loaded plugin with its lifecycle state, from `ctx.registry` — what capabilities are loaded, deliberately not the tree shape), `tools` (what the model can call), `dynamic` (the mount table: id, name, state, provided services, awaited services), `api` (live service signatures + the type shapes they reference, from the generated catalog), and `events` (harness events with dispatch mode and signature). Broad `api` and `events` reports omit full JSDoc to stay compact; an exact `name` returns one service or event with its original method/declaration JSDoc. A name is invalid with other sections, unknown targets fail, and an API target must be live. The model-facing tool descriptions carry the operational rules the model needs at call time; [the generated tool catalog](../../../tool-catalog.md) is their exhaustive rendering. +`cordis_inspect` sections: `services` (every provided ctx service and the owning fiber, non-active owners flagged), `plugins` (a flat list of every loaded plugin with its lifecycle state, from `ctx.registry` — what capabilities are loaded, deliberately not the tree shape), `tools` (what the model can call), `dynamic` (the mount table: id, name, state, provided services, awaited services), `api` (live service signatures + the type shapes they reference, from the generated catalog), and `events` (harness events with dispatch mode and signature). Broad `api` and `events` reports omit full JSDoc to stay compact; an exact `name` returns one service or event with its original method/declaration JSDoc. A name is invalid with other sections, unknown targets fail, and an API target must be live. The model-facing tool descriptions carry the operational rules the model needs at call time; [the generated tool catalog](../../../../docs/tool-catalog.md) is their exhaustive rendering. ### Sandbox semantics @@ -50,7 +50,7 @@ Freshness is gated like every generated artifact: `pnpm run verify-cordis-api` ( ### Configuration, rendering, and observability -The plugin exposes one config field, validated by schemastery and documented in [the config catalog](../../../config-catalog.md): `vmTimeoutMs` (default 5000), the millisecond bound on the synchronous portion of mount-code evaluation. Tool names, the `cordis-dynamic` group name, and the `dyn-` id prefix are structural vocabulary and stay fixed. All three tools render as `generic` cards per [the tool cookbook](../../../cookbook/adding-a-tool.md) (`cordis_inspect` a `read`, `cordis_mount` an `execute` carrying the code as `rawInput`, `cordis_unmount` a `delete`), with no `presentResult` overrides. +The plugin exposes one config field, validated by schemastery and documented in [the config catalog](../../../../docs/config-catalog.md): `vmTimeoutMs` (default 5000), the millisecond bound on the synchronous portion of mount-code evaluation. Tool names, the `cordis-dynamic` group name, and the `dyn-` id prefix are structural vocabulary and stay fixed. All three tools render as `generic` cards per [the tool cookbook](../../../../docs/cookbook/adding-a-tool.md) (`cordis_inspect` a `read`, `cordis_mount` an `execute` carrying the code as `rawInput`, `cordis_unmount` a `delete`), with no `presentResult` overrides. Model-visible ⟺ logged holds with no new session event type: a mount or unmount is visible only through its own `tool/call` / `tool/result` pair, which the loop logs, and the changed tool set a mount induces is logged by the full changed request header the loop emits when schemas change between steps. There is deliberately no `cordis/mount` provenance event — it would duplicate what the tool-call pair records. Dynamic mounts are process-lifetime, not session state: resuming a persisted session rehydrates the conversation but does not re-mount plugins. @@ -77,4 +77,4 @@ The correctness investment therefore goes where it pays for every capability at ## Consequences -The toolset is a deliberate opt-in with a fully-privileged `ctx`, so a deployment adopts it as consciously as a bash tool. Several facts follow that the tool descriptions warn the model about directly: a waterfall listener (e.g. `tools/pre-execute`) that returns without calling `next()` vetoes the chain, so a mounted listener can lobotomize the agent's own tool dispatch ([waterfall semantics](../../../cordis-primer.md#cordis-waterfall-semantics)); mount code runs inside a tool call of the current turn, so awaiting anything that resolves only after the turn deadlocks; `vmTimeoutMs` bounds synchronous evaluation only; and mounts do not survive session resume. +The toolset is a deliberate opt-in with a fully-privileged `ctx`, so a deployment adopts it as consciously as a bash tool. Several facts follow that the tool descriptions warn the model about directly: a waterfall listener (e.g. `tools/pre-execute`) that returns without calling `next()` vetoes the chain, so a mounted listener can lobotomize the agent's own tool dispatch ([waterfall semantics](../../../../docs/cordis-primer.md#cordis-waterfall-semantics)); mount code runs inside a tool call of the current turn, so awaiting anything that resolves only after the turn deadlocks; `vmTimeoutMs` bounds synchronous evaluation only; and mounts do not survive session resume. diff --git a/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md b/.agents/notes/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md similarity index 92% rename from docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md rename to .agents/notes/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md index cd4f3b078b..79a26f3a22 100644 --- a/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md +++ b/.agents/notes/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md @@ -1,4 +1,4 @@ -# RFC: Bash-backed grep and glob discovery tools +# Agent Note: Bash-backed grep and glob discovery tools Status: implemented @@ -63,9 +63,9 @@ Routine budgets stay out of the model-facing schema. `@deepseek-ai/dsh-tool-fs-s | `rawOutputMaxBytes` | `20000000` | Max complete raw `rg` stdout the tool will parse; matches Claude Code's ripgrep raw buffer. | | `timeoutMs` | `30000` | Tool-call timeout attached to both tool definitions and enforced by `@deepseek-ai/dsh-timeout-policy`. | -`globMaxResults` and `grepMaxMatches` use `ItemRetainer({ kind: 'head' })`. `grepMaxLineBytes` uses `TextRetainer({ kind: 'head', maxBytes: grepMaxLineBytes })` for each matched line so preview cuts preserve UTF-8 boundaries. This follows the [tool result retention library](../../implemented/architecture/2026-07-06-tool-result-retention-library.md) mapping for discovery items: collect the complete result, retain head items inline, and keep path mapping, grouping, and per-line preview outside the retainer. `grep` does not expose `case_insensitive`, `head_limit`, `offset`, `count`, multiline, context lines, output modes, or file type filters in v1. A model that needs surrounding context reads the matched file with `read`; a model that needs later results follows the returned spill locator's retrieval hint. +`globMaxResults` and `grepMaxMatches` use `ItemRetainer({ kind: 'head' })`. `grepMaxLineBytes` uses `TextRetainer({ kind: 'head', maxBytes: grepMaxLineBytes })` for each matched line so preview cuts preserve UTF-8 boundaries. This follows the [tool result retention library](../architecture/2026-07-06-tool-result-retention-library.md) mapping for discovery items: collect the complete result, retain head items inline, and keep path mapping, grouping, and per-line preview outside the retainer. `grep` does not expose `case_insensitive`, `head_limit`, `offset`, `count`, multiline, context lines, output modes, or file type filters in v1. A model that needs surrounding context reads the matched file with `read`; a model that needs later results follows the returned spill locator's retrieval hint. -The Claude Code values are reference points for the two-layer budget, not model-facing schema precedent. Its dedicated search tools buffer raw ripgrep output up to 20 MB for internal processing, use a 20-second ripgrep timeout on non-WSL platforms (60 seconds on WSL), then apply search-specific caps before the model sees a result: `GrepTool` defaults to `head_limit = 250` and persists formatted results above 20,000 characters, while `GlobTool` defaults to 100 paths and persists formatted results above 100,000 characters. This RFC mirrors the raw-buffer and inline-count defaults, chooses a 30-second default search timeout, and uses this harness's `ctx.spillStore.saveText()` path for formatted-result recovery. +The Claude Code values are reference points for the two-layer budget, not model-facing schema precedent. Its dedicated search tools buffer raw ripgrep output up to 20 MB for internal processing, use a 20-second ripgrep timeout on non-WSL platforms (60 seconds on WSL), then apply search-specific caps before the model sees a result: `GrepTool` defaults to `head_limit = 250` and persists formatted results above 20,000 characters, while `GlobTool` defaults to 100 paths and persists formatted results above 100,000 characters. This Agent Note mirrors the raw-buffer and inline-count defaults, chooses a 30-second default search timeout, and uses this harness's `ctx.spillStore.saveText()` path for formatted-result recovery. The `path` field follows the same split as Claude Code: `grep.path` is a file-or-directory ripgrep target, while `glob.path` is a directory search root. v1 does not expose a separate cwd/workdir argument on these tools. @@ -122,13 +122,13 @@ If the complete logical result fits under the inline cap, no formatted spill art **Put `glob` / `grep` on `ctx.fs`.** Rejected for v1: it forces every filesystem backend to grow a search API and makes local ripgrep behavior part of the provider seam. Search is useful product behavior, but it is not a universal text-storage primitive like `readText` or `writeText`. -**Directly spawn ripgrep from `dsh-fs-local`.** Rejected for this RFC's v1: direct spawn gives the cleanest argv boundary, stdout/stderr control, and early-stop control, but it duplicates process execution concerns that the bash seam already owns: environment scrubbing, process-group kill, timeout propagation, sandbox/remote executor substitution, and bounded output capture. It remains a reasonable optimization if bash-backed search proves too shell-string-sensitive or if foreground streaming becomes necessary. +**Directly spawn ripgrep from `dsh-fs-local`.** Rejected for this Agent Note's v1: direct spawn gives the cleanest argv boundary, stdout/stderr control, and early-stop control, but it duplicates process execution concerns that the bash seam already owns: environment scrubbing, process-group kill, timeout propagation, sandbox/remote executor substitution, and bounded output capture. It remains a reasonable optimization if bash-backed search proves too shell-string-sensitive or if foreground streaming becomes necessary. **Use `ctx.bash.start()` for streaming early stop.** Rejected: `start()` creates model-visible background task semantics: task ids, owner tokens, `bash_output`, `bash_kill`, completion notifications, and no built-in timeout. `grep` needs a foreground tool result, not a background bash workflow. If streaming search becomes necessary, the right abstraction is a foreground streaming process handle on the bash/process seam, not borrowing the public background-task API. **Expose bash raw spill paths to the model.** Rejected: a bash raw spill path contains raw `rg` stdout (`rg --json` records for grep), not the stable formatted search result. Search parses raw stdout only as an internal transport; model recovery uses a formatted result saved through `ctx.spillStore.saveText()`. -**Add `spillStore.saveFile()` for bash output normalization first.** Rejected for this RFC's v1: `saveFile()` would help a future bash normalization pass move existing executor spill files into session-scoped spill storage, but search only needs bounded in-memory raw `rg` stdout before producing the model-facing artifact. `saveText()` is sufficient for the formatted search result. +**Add `spillStore.saveFile()` for bash output normalization first.** Rejected for this Agent Note's v1: `saveFile()` would help a future bash normalization pass move existing executor spill files into session-scoped spill storage, but search only needs bounded in-memory raw `rg` stdout before producing the model-facing artifact. `saveText()` is sufficient for the formatted search result. **Rely on the generic `dsh-spill-policy`.** Rejected: generic post-execute spill sees only the final tool result. If `grep` / `glob` return the first page inline, the generic policy cannot recover omitted results. The search tools must save the complete formatted result themselves before returning the bounded model-facing text. diff --git a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md b/.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md similarity index 94% rename from docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md rename to .agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md index 118009dedb..988052fb2a 100644 --- a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md +++ b/.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md @@ -1,4 +1,4 @@ -# RFC: Expose agent session identity and JSONL location to tools and hooks +# Agent Note: Expose agent session identity and JSONL location to tools and hooks Status: implemented @@ -10,7 +10,7 @@ The boundary must preserve two properties: the owner of a fact decides how to re ## Decision -Extend the [`SessionPersistence`](../../implemented/architecture/2026-06-14-session-persistence.md) seam with a synchronous, side-effect-free location query: +Extend the [`SessionPersistence`](../architecture/2026-06-14-session-persistence.md) seam with a synchronous, side-effect-free location query: ```ts import type { SessionHeader } from '@deepseek-ai/dsh-session' @@ -42,7 +42,7 @@ The bash seam exports `DSH_ENV_PREFIX` as the single namespace source and derive The bash tool description teaches only the durable convention: current harness environment facts are available through managed `$DSH_*` variables and may be inspected when needed. It does not enumerate persistence-specific keys or add a permanent system-prompt section. Tool schemas are already logged in request headers and tool output is logged as `tool/result`, so no new session event is required. -The [Claude Code and Codex hook bridges](../../implemented/feature/2026-06-30-hook-bridges.md) resolve transcript location from the same persistence seam when constructing payloads. Codex uses `transcript_path: string | null`; Claude Code preserves its string field and falls back to `''`. Hook lookup neither materializes nor flushes a session. +The [Claude Code and Codex hook bridges](2026-06-30-hook-bridges.md) resolve transcript location from the same persistence seam when constructing payloads. Codex uses `transcript_path: string | null`; Claude Code preserves its string field and falls back to `''`. Hook lookup neither materializes nor flushes a session. ## Peer product findings diff --git a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md b/.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md similarity index 97% rename from docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md rename to .agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md index 90fbc1cfb4..4904da5bd5 100644 --- a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md +++ b/.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md @@ -1,4 +1,4 @@ -# RFC: Parallel tool-call execution by per-call safety +# Agent Note: Parallel tool-call execution by per-call safety Status: implemented @@ -12,7 +12,7 @@ The session log remains authoritative: every started call has an audit event, ev ## Decision -Each tool may provide an optional `isConcurrencySafe(args)` classifier. It is synchronous and pure: it examines only the current call's parsed arguments and performs no I/O or mutation. Only an explicit `true` opts in; a missing classifier, invalid arguments, a thrown classifier, or any other return value makes the call exclusive. The canonical type contract lives in the [tool data structures](../../../core-data-structures/tools.md). +Each tool may provide an optional `isConcurrencySafe(args)` classifier. It is synchronous and pure: it examines only the current call's parsed arguments and performs no I/O or mutation. Only an explicit `true` opts in; a missing classifier, invalid arguments, a thrown classifier, or any other return value makes the call exclusive. The canonical type contract lives in the [tool data structures](../../../../docs/core-data-structures/tools.md). The classifier is deliberately unary. Returning `true` is the tool's promise that this call may overlap with any sibling call that also returns `true`; the scheduler does not compare calls or prove that their resource accesses are compatible. @@ -56,7 +56,7 @@ Any shared state touched during execution must be concurrency-safe. This include ## Configuration and declarations -`maxParallelToolCalls` is a positive AgentLoop deployment cap shared by every agent the factory creates. It defaults to `10`; `1` preserves serial execution. Exact fields and defaults live in the generated [configuration catalog](../../../config-catalog.md). +`maxParallelToolCalls` is a positive AgentLoop deployment cap shared by every agent the factory creates. It defaults to `10`; `1` preserves serial execution. Exact fields and defaults live in the generated [configuration catalog](../../../../docs/config-catalog.md). The shipped declarations are conservative. Web search, web fetch, and filesystem read opt in. Filesystem writes and edits, bash tools, subagent delegation, workflow, user interaction, todo mutation, Code Mode, and Cordis mutation tools remain exclusive. A subagent may share its parent's workspace or external resources, and the unary classifier cannot prove that sibling delegations have disjoint effects. Bash has no proven input-sensitive classifier and remains exclusive. diff --git a/docs/rfc/implemented/feature/2026-07-10-session-query-service.md b/.agents/notes/implemented/feature/2026-07-10-session-query-service.md similarity index 99% rename from docs/rfc/implemented/feature/2026-07-10-session-query-service.md rename to .agents/notes/implemented/feature/2026-07-10-session-query-service.md index ee2acc62e1..a34d699601 100644 --- a/docs/rfc/implemented/feature/2026-07-10-session-query-service.md +++ b/.agents/notes/implemented/feature/2026-07-10-session-query-service.md @@ -1,4 +1,4 @@ -# RFC: Exact session query service +# Agent Note: Exact session query service Status: implemented diff --git a/docs/rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md similarity index 99% rename from docs/rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md rename to .agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md index 3c2e17aebd..29f77364fa 100644 --- a/docs/rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md +++ b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md @@ -1,4 +1,4 @@ -# RFC: Configure subagent persona, tool visibility, and depth +# Agent Note: Configure subagent persona, tool visibility, and depth Status: implemented diff --git a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md b/.agents/notes/implemented/feature/2026-07-13-session-query-tracing.md similarity index 98% rename from docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md rename to .agents/notes/implemented/feature/2026-07-13-session-query-tracing.md index f16f543ac5..08f856863e 100644 --- a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md +++ b/.agents/notes/implemented/feature/2026-07-13-session-query-tracing.md @@ -1,4 +1,4 @@ -# RFC: Session query relationship tracing +# Agent Note: Session query relationship tracing Status: implemented diff --git a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml b/.agents/notes/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml similarity index 65% rename from docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml rename to .agents/notes/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml index f1d38d7d95..28ecd2a765 100644 --- a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-14-time-context-plugin.md: b8b54156e08aa1212866d46500ad1ca65b4f4f14 -2026-07-14-time-context-plugin.zh.md: 0af261c66a9b52cdf250294b4bfdc240176c8434 +2026-07-14-time-context-plugin.md: 189f75fc12fe12e9dec56fc71ea901ec2eaa8b19 +2026-07-14-time-context-plugin.zh.md: 12671cb891531627fffabb7bd91a1532bc3de6b9 diff --git a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md b/.agents/notes/implemented/feature/2026-07-14-time-context-plugin.md similarity index 97% rename from docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md rename to .agents/notes/implemented/feature/2026-07-14-time-context-plugin.md index b8b54156e0..189f75fc12 100644 --- a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md +++ b/.agents/notes/implemented/feature/2026-07-14-time-context-plugin.md @@ -1,4 +1,4 @@ -# RFC: Optional time-context plugin +# Agent Note: Optional time-context plugin Status: implemented @@ -32,7 +32,7 @@ When `timeZone` is omitted, `Intl.DateTimeFormat` resolves the Node process's sy ### Logging and token shape -The loop records the temporal block in full `request/header` snapshots before transmission, satisfying the [reconstructable-requests contract](../architecture/2026-07-05-reconstructable-requests.md). Each request carries one current block; earlier readings do not remain in conversation history. The plugin owns the fact and contributes it through the prompt registry, following the [prompt-variables RFC](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md) without a loop special case. +The loop records the temporal block in full `request/header` snapshots before transmission, satisfying the [reconstructable-requests contract](../architecture/2026-07-05-reconstructable-requests.md). Each request carries one current block; earlier readings do not remain in conversation history. The plugin owns the fact and contributes it through the prompt registry, following the [prompt-variables Agent Note](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md) without a loop special case. ## Testing diff --git a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md b/.agents/notes/implemented/feature/2026-07-14-time-context-plugin.zh.md similarity index 95% rename from docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md rename to .agents/notes/implemented/feature/2026-07-14-time-context-plugin.zh.md index 0af261c66a..12671cb891 100644 --- a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md +++ b/.agents/notes/implemented/feature/2026-07-14-time-context-plugin.zh.md @@ -1,4 +1,4 @@ -# RFC：可选时间上下文插件 +# Agent Note：可选时间上下文插件 Status: implemented @@ -6,7 +6,7 @@ Status: implemented ## 问题 -本记录中的动态系统提示词存储和刷新决策已由[持久的逐步骤时间上下文](2026-07-16-durable-per-step-time-context.md)取代。需要显式启用的包（package）、分区时间格式和校验仍然保留；后续 RFC 负责当前的模型可见与持久性契约。 +本记录中的动态系统提示词存储和刷新决策已由[持久的逐步骤时间上下文](2026-07-16-durable-per-step-time-context.md)取代。需要显式启用的包（package）、分区时间格式和校验仍然保留；后续 Agent Note 负责当前的模型可见与持久性契约。 如果部署方既未在提示词中提供时钟，也未给模型提供查询工具，agent（智能体）请求就无法获得实时准确的时间。静态文本会变得陈旧，而对于日期、截止时间或闲置时长等常规推理，调用工具会增加开销。缺少已经过去的时长时，模型无法区分紧接着发送的消息与上一条消息几小时后才发送的消息。 @@ -32,7 +32,7 @@ Status: implemented ### 日志与 token 形态 -agent loop（智能体循环）会在发送前通过完整的 `request/header` 快照记录时间区块，从而满足[可重建请求契约](../architecture/2026-07-05-reconstructable-requests.md)。每个请求只携带一个当前区块；先前的读数不会保留在会话历史中。该插件拥有时间信息，并按照[提示词变量 RFC](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)通过提示词注册表贡献该信息，无需为循环添加特殊分支。 +agent loop（智能体循环）会在发送前通过完整的 `request/header` 快照记录时间区块，从而满足[可重建请求契约](../architecture/2026-07-05-reconstructable-requests.md)。每个请求只携带一个当前区块；先前的读数不会保留在会话历史中。该插件拥有时间信息，并按照[提示词变量 Agent Note](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)通过提示词注册表贡献该信息，无需为循环添加特殊分支。 ## 测试 diff --git a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml b/.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml similarity index 62% rename from docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml rename to .agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml index ce964f71da..f037660761 100644 --- a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-16-durable-per-step-time-context.md: 4a0828111faf9f787c2d338024c42680a4a697e2 -2026-07-16-durable-per-step-time-context.zh.md: f745cf7da7c38f9682abf9d8f210bcba328c8a51 +2026-07-16-durable-per-step-time-context.md: 2d7076d51dbe1a64e5042230bddc6844141ff265 +2026-07-16-durable-per-step-time-context.zh.md: 432e0305cf44dcce1053c6580c9f0039309a7af4 diff --git a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md b/.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.md similarity index 99% rename from docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md rename to .agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.md index 4a0828111f..2d7076d51d 100644 --- a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md +++ b/.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.md @@ -1,4 +1,4 @@ -# RFC: Durable per-step time context +# Agent Note: Durable per-step time context Status: implemented diff --git a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md b/.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md similarity index 99% rename from docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md rename to .agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md index f745cf7da7..432e0305cf 100644 --- a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md +++ b/.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md @@ -1,4 +1,4 @@ -# RFC: 持久的逐步骤时间上下文 +# Agent Note: 持久的逐步骤时间上下文 Status: implemented diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml b/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml similarity index 60% rename from docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml rename to .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml index 8618fd884f..34c342ffd3 100644 --- a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-17-dedicated-full-screen-tui-front-door.md: c834594b3af1e1f348aec2cf67324d5123a1ed2d -2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 8cb8eb6d2812e6ecf9d98d20c64da24c2943363c +2026-07-17-dedicated-full-screen-tui-front-door.md: 178b5ea44be67f820a8ea7fed8acb987dffb3f80 +2026-07-17-dedicated-full-screen-tui-front-door.zh.md: ac055bad1b7a692c7a980430fdbd1e34737a9994 diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md b/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md similarity index 92% rename from docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md rename to .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md index c834594b3a..178b5ea44b 100644 --- a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md +++ b/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md @@ -1,4 +1,4 @@ -# RFC: Dedicated full-screen TUI front door +# Agent Note: Dedicated full-screen TUI front door Status: implemented @@ -32,7 +32,7 @@ The built-in palette uses standard 16-color ANSI foregrounds and SGR attributes, ## Verification -The implemented [TUI terminal-state snapshot RFC](../testing/2026-07-18-tui-terminal-state-snapshots.md) owns the four-layer verification contract: direct behavior tests, transient semantic terminal snapshots, recorded JSONL journeys through production tools, and Loader/PTY smoke tests. The package README owns configuration, commands, model-visible effects, and current limitations. +The implemented [TUI terminal-state snapshot Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) owns the four-layer verification contract: direct behavior tests, transient semantic terminal snapshots, recorded JSONL journeys through production tools, and Loader/PTY smoke tests. The package README owns configuration, commands, model-visible effects, and current limitations. ## Alternatives considered diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md b/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md similarity index 92% rename from docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md rename to .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md index 8cb8eb6d28..ac055bad1b 100644 --- a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md +++ b/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md @@ -1,4 +1,4 @@ -# RFC: 独立的全屏 TUI 入口 +# Agent Note: 独立的全屏 TUI 入口 Status: implemented @@ -32,7 +32,7 @@ agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调 ## 验证 -已实现的 [TUI 终端状态快照 RFC](../testing/2026-07-18-tui-terminal-state-snapshots.md) 规定四层验证契约：直接行为测试、瞬态语义终端快照、通过生产工具执行的已录制 JSONL 流程，以及 Loader/PTY 冒烟测试。包（package）README 负责记录配置、命令、模型可见效果和当前限制。 +已实现的 [TUI 终端状态快照 Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) 规定四层验证契约：直接行为测试、瞬态语义终端快照、通过生产工具执行的已录制 JSONL 流程，以及 Loader/PTY 冒烟测试。包（package）README 负责记录配置、命令、模型可见效果和当前限制。 ## 曾考虑的替代方案 diff --git a/docs/rfc/implemented/process/2026-06-11-doc-sync-enforcement.md b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md similarity index 99% rename from docs/rfc/implemented/process/2026-06-11-doc-sync-enforcement.md rename to .agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md index 8fd37a1656..8f32202c8f 100644 --- a/docs/rfc/implemented/process/2026-06-11-doc-sync-enforcement.md +++ b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md @@ -1,4 +1,4 @@ -# RFC: Doc-sync enforcement +# Agent Note: Doc-sync enforcement Status: implemented diff --git a/docs/rfc/implemented/process/2026-06-11-quality-gates.md b/.agents/notes/implemented/process/2026-06-11-quality-gates.md similarity index 93% rename from docs/rfc/implemented/process/2026-06-11-quality-gates.md rename to .agents/notes/implemented/process/2026-06-11-quality-gates.md index 9f92791f4a..1a1cfe5b54 100644 --- a/docs/rfc/implemented/process/2026-06-11-quality-gates.md +++ b/.agents/notes/implemented/process/2026-06-11-quality-gates.md @@ -1,4 +1,4 @@ -# RFC: Mechanical quality gates over prose guidelines +# Agent Note: Mechanical quality gates over prose guidelines Status: implemented @@ -23,4 +23,4 @@ Every AGENTS.md promise gets a command that exits non-zero, wired into git hooks - The gates themselves are code to maintain; config changes are reviewed like any change. - 100%-coverage pressure can produce assertion-free tests — mutation testing is the planned counterweight (see [the mutation-testing proposal](../../proposed/testing/2026-06-11-mutation-testing.md)). -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/process/2026-06-11-tsdown-over-dumble.md b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md similarity index 78% rename from docs/rfc/implemented/process/2026-06-11-tsdown-over-dumble.md rename to .agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md index 1e63cef940..4075d4738a 100644 --- a/docs/rfc/implemented/process/2026-06-11-tsdown-over-dumble.md +++ b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md @@ -1,4 +1,4 @@ -# RFC: tsdown for JS bundling instead of dumble +# Agent Note: tsdown for JS bundling instead of dumble Status: implemented @@ -13,7 +13,7 @@ Build output currently matters only for `pnpm run build` + publint (nothing publ Replace dumble with **tsdown** (rolldown-based, ~2.5M downloads/week, VoidZero-backed, actively released): - Root `tsdown.config.ts` with `workspace: ['vendor/*', 'packages/*/*']` (explicit globs keep bundling to vendored Cordis and the TypeScript package tree; `workspace: true` would also discover example manifests and non-bundled workspace members). -- Shared shape: entry `lib/types/index.js`, `outDir: 'lib'`, ESM, `platform: node`, `target: es2024`, `fixedExtension: false` (keeps `.js` for `"type": "module"` packages), `dts: false` (tsc -b owns declarations), `clean: false` (lib/ also holds TSC's `lib/types` intermediate tree). The entry was originally `src/index.ts`; the [TSC-first build RFC](2026-06-17-ts-build-config.md) later moved tsdown to bundling TSC-emitted JS so TypeScript transform behavior comes from one compiler. +- Shared shape: entry `lib/types/index.js`, `outDir: 'lib'`, ESM, `platform: node`, `target: es2024`, `fixedExtension: false` (keeps `.js` for `"type": "module"` packages), `dts: false` (tsc -b owns declarations), `clean: false` (lib/ also holds TSC's `lib/types` intermediate tree). The entry was originally `src/index.ts`; the [TSC-first build Agent Note](2026-06-17-ts-build-config.md) later moved tsdown to bundling TSC-emitted JS so TypeScript transform behavior comes from one compiler. - Two per-package overrides in vendor/ (ours, like the regenerated tsconfigs; logged in vendor/README.md): schemastery (dual `.mjs`/`.cjs` via `outExtensions`), logger-console (two single-entry passes so the shared base class is inlined into each entry instead of a hash-named chunk, matching upstream's published shape). - `scripts/build.ts` deleted; `pnpm run build` = `tsc -b tsconfig.build.json && tsdown`. @@ -25,4 +25,4 @@ Replace dumble with **tsdown** (rolldown-based, ~2.5M downloads/week, VoidZero-b ## Consequences -Runtime bundle outputs still follow the dumble-era public entry shape (`lib/index.js`, plus package-specific variants such as `schemastery`'s `lib/index.mjs`/`lib/index.cjs` and `logger-console`'s `lib/browser.js`); declarations now live under `lib/types` per the [TSC-first build RFC](2026-06-17-ts-build-config.md). Externals still come from each package's dependencies/peerDependencies. We give up dumble's exports-field inference — new packages with non-default shapes need a per-package `tsdown.config.ts` instead of just package.json fields. Future option: tsdown could also absorb declaration bundling (isolatedDeclarations) if `tsc -b` ever becomes the bottleneck; that would be a new RFC. +Runtime bundle outputs still follow the dumble-era public entry shape (`lib/index.js`, plus package-specific variants such as `schemastery`'s `lib/index.mjs`/`lib/index.cjs` and `logger-console`'s `lib/browser.js`); declarations now live under `lib/types` per the [TSC-first build Agent Note](2026-06-17-ts-build-config.md). Externals still come from each package's dependencies/peerDependencies. We give up dumble's exports-field inference — new packages with non-default shapes need a per-package `tsdown.config.ts` instead of just package.json fields. Future option: tsdown could also absorb declaration bundling (isolatedDeclarations) if `tsc -b` ever becomes the bottleneck; that would be a new Agent Note. diff --git a/docs/rfc/implemented/process/2026-06-11-vendor-cordis-as-source.md b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md similarity index 97% rename from docs/rfc/implemented/process/2026-06-11-vendor-cordis-as-source.md rename to .agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md index 2aa24907d5..a8895ba5e8 100644 --- a/docs/rfc/implemented/process/2026-06-11-vendor-cordis-as-source.md +++ b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md @@ -1,4 +1,4 @@ -# RFC: Vendor Cordis as source, not npm dependencies +# Agent Note: Vendor Cordis as source, not npm dependencies Status: implemented diff --git a/docs/rfc/implemented/process/2026-06-16-pnpm-over-yarn.md b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md similarity index 99% rename from docs/rfc/implemented/process/2026-06-16-pnpm-over-yarn.md rename to .agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md index 7a574a3388..f4a5d43f96 100644 --- a/docs/rfc/implemented/process/2026-06-16-pnpm-over-yarn.md +++ b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md @@ -1,4 +1,4 @@ -# RFC: pnpm as the package manager instead of Yarn 4 +# Agent Note: pnpm as the package manager instead of Yarn 4 Status: implemented diff --git a/docs/rfc/implemented/process/2026-06-17-ts-build-config.md b/.agents/notes/implemented/process/2026-06-17-ts-build-config.md similarity index 99% rename from docs/rfc/implemented/process/2026-06-17-ts-build-config.md rename to .agents/notes/implemented/process/2026-06-17-ts-build-config.md index 0687df250c..8f67b6fc2f 100644 --- a/docs/rfc/implemented/process/2026-06-17-ts-build-config.md +++ b/.agents/notes/implemented/process/2026-06-17-ts-build-config.md @@ -1,4 +1,4 @@ -# RFC: TSC-first build and one tsconfig +# Agent Note: TSC-first build and one tsconfig Status: implemented diff --git a/docs/rfc/implemented/process/2026-06-18-markdown-cross-link-lint.md b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md similarity index 81% rename from docs/rfc/implemented/process/2026-06-18-markdown-cross-link-lint.md rename to .agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md index db98c2fb7d..05dfed2453 100644 --- a/docs/rfc/implemented/process/2026-06-18-markdown-cross-link-lint.md +++ b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md @@ -1,4 +1,4 @@ -# RFC: Markdown cross-link validity linting +# Agent Note: Markdown cross-link validity linting Status: implemented @@ -6,7 +6,7 @@ Status: implemented Docs in this repo link to each other by relative path — `[topic](../implemented/2026-…-….md)`, `[the cookbook](adding-a-tool.md)`, `[architecture.md](../../architecture.md)`. Nothing verified those targets exist. A rename or a move silently breaks every inbound link, and the break is invisible until a reader clicks it. [Doc-sync enforcement](2026-06-11-doc-sync-enforcement.md) already mechanized two classes of doc drift (uncompilable code blocks, a stale event-taxonomy table) and [verify-md-wrap](2026-06-11-doc-sync-enforcement.md) a third (hard-wrapped prose) — but a dead cross-link is a fourth, equally mechanical class that was still verified by eyeball. -The motivating case is the RFC tree reorganization that introduced this gate: unifying `docs/adr/` + `docs/rfc/` into one `docs/rfc/` with `proposed/`/`implemented/`/`rejected/` subfolders renamed roughly forty inter-doc links by hand. A single fat-fingered path would have shipped a broken link with nothing to catch it. +The motivating case is the Agent Note tree reorganization that introduced this gate: unifying `docs/adr/` + `.agents/notes/` into one `.agents/notes/` with `proposed/`/`implemented/`/`rejected/` subfolders renamed roughly forty inter-doc links by hand. A single fat-fingered path would have shipped a broken link with nothing to catch it. ## Decision @@ -26,6 +26,6 @@ This gate checks *existence*, not anchor validity: a link to a real file with a ## Consequences -- Renames and moves that orphan a cross-link now fail the pre-push hook and CI instead of waiting for a reader to click a dead link. This made the RFC reorganization that introduced the gate self-verifying: the same PR that rewrote forty links also added the check that proves none dangle. +- Renames and moves that orphan a cross-link now fail the pre-push hook and CI instead of waiting for a reader to click a dead link. This made the Agent Note reorganization that introduced the gate self-verifying: the same PR that rewrote forty links also added the check that proves none dangle. - One more fast tsx script in the `doc-sync` chain; no new dependency (the mdast/GFM stack is already in devDependencies for `verify-md-wrap`). -- The convention this enforces — cross-reference docs by machine-checkable relative link, never by bare prose or a number — is documented in [docs/AGENTS.md](../../../AGENTS.md) so authors know the gate exists and why. +- The convention this enforces — cross-reference docs by machine-checkable relative link, never by bare prose or a number — is documented in [docs/AGENTS.md](../../../../docs/AGENTS.md) so authors know the gate exists and why. diff --git a/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md new file mode 100644 index 0000000000..4984ac36c2 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md @@ -0,0 +1,46 @@ +# Agent Note: Classify Agent Notes by kind via path-encoded subdirectories + +Status: implemented + +## Problem + +`.agents/notes/` grouped Agent Notes by **lifecycle** only — `proposed/` / `implemented/` / `rejected/`. Nothing recorded what *kind* of decision each Agent Note was. The index was one flat list per lifecycle, with no way to scan "show me every simplification" or "every testing-strategy decision." A wave of simplification Agent Notes landing on the same day made the gap concrete: a reader skimming `proposed/` could not tell a new capability from a removal from a tooling-policy change without opening each file. + +The repo's standing bias is [mechanical quality gates over prose guidelines](2026-06-11-quality-gates.md): a convention that isn't machine-checked rots. So a classification scheme here had to be enforceable, not an honor-system header. + +## Decision + +Add a second axis — the Agent Note's **class** — and encode it in the path: `{lifecycle}/{class}/yyyy-mm-dd-topic.md`. The folder *is* the label. A file's location declares its class, the closed set is "these folders and no others," and the existing [verify-md-links](2026-06-18-markdown-cross-link-lint.md) gate already protects the path rewrites the move required. + +### The closed set of six classes + +| Class | Covers | +|---|---| +| `feature` | A new user- or model-facing capability. | +| `bug-fix` | Corrects a defect or closes a gap a postmortem surfaced. | +| `simplification` | Removes code, behavior, or surface area without adding a capability. | +| `architecture` | A structural decision about the **shipped source** — how packages relate, what the runtime vocabulary is. | +| `process` | Tooling, policy, or workflow **around** the code, not runtime behavior. | +| `testing` | Test infrastructure and strategy. | + +The `architecture` / `process` line: **architecture** is about the source we ship; **process** is the surrounding tooling and workflow. This Agent Note is itself a `process` decision — it changes how the repo is organized and gated, not what the harness does at runtime — so it lives under `implemented/process/`. + +### Two gates + +Both are `doc-sync` members, in the `verify-md-wrap` style (tsx ESM, verify-don't-generate, exit non-zero on the first violation): + +- **`scripts/verify-agent-note-classification.ts`** — the closed set and index freshness. It asserts every file under a lifecycle folder lives in a class folder from the canonical set (a loose `.md` at a lifecycle root, or an unknown class folder, fails), and that the generated [INDEX.md](../../INDEX.md) byte-matches a fresh render from the tree (see [generate the Agent Note index tables](2026-07-04-generate-agent-note-index-tables.md)). The canonical class set lives as a `const` in `scripts/agent-note-index.ts` — the machine source of truth shared with the generator — and [the README](../../README.md) documents it in prose; the class *descriptions* stay hand-written, the index is generated. +- **`scripts/verify-doc-refs.ts`** — source comments that cite docs. Agent Note paths are referenced not only from Markdown but from TypeScript doc comments (root-relative prose like `.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md`). `verify-md-links` never saw those, so the reorg could have silently orphaned them. This gate scans repo-authored `.ts` under `packages/**` and `examples/**` (excluding built `lib/` and `vendor/`) for `docs/….md` tokens, resolves each root-relative, and asserts it exists. It requires the `.md` extension so extensionless prose (`docs/postmortem/0001`, `docs/architecture.md § Extending The Harness`) is left alone. + +## Alternatives considered + +- **A `Classification:` prose line** in each file (next to `Status:`), parsed by the gate. Workable, but it duplicates into the file a fact the path can already carry, and a line can disagree with its folder. Path-encoding makes the label and its storage the same thing — there is nothing to keep in sync. +- **A `refactor` class.** It overlaps `simplification` almost entirely; the only discriminator anyone reached for was "does observable behavior change?", which `simplification` already encodes (it does not). One class, not two. +- **Auto-generating the index** from the filesystem. Rejected here to keep the index hand-written; superseded by [generate the Agent Note index tables](2026-07-04-generate-agent-note-index-tables.md) once stacked proposal waves made the hand-written tables the repo's most conflict-prone docs region — the list is now the fully generated [INDEX.md](../../INDEX.md) while the README prose stays curated. + +## Consequences + +- Every Agent Note now sits under a class folder, and the index groups by class within each lifecycle. A reader scans one heading to see all simplifications, or all testing decisions. +- Two more fast tsx scripts in the `doc-sync` chain; no new dependency (the mdast/GFM stack was already present for `verify-md-wrap`/`verify-md-links`). +- Adding a class is a deliberate act: amend the `const` in `scripts/agent-note-index.ts` and the [Classification section](../../README.md#classification), not just `mkdir` a folder. The gate rejects an unknown folder, so an ad-hoc class can't slip in. +- Source-comment doc references are now gated too — a moved or renamed doc that a `.ts` comment cites fails the pre-push hook, closing a drift class `verify-md-links` structurally could not see. diff --git a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md similarity index 85% rename from docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md rename to .agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md index 47dc370d22..21b86b1812 100644 --- a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md +++ b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md @@ -1,12 +1,12 @@ -# RFC: Core-data-structures catalog and the `ts type-equiv` drift gate +# Agent Note: Core-data-structures catalog and the `ts type-equiv` drift gate Status: implemented ## Problem -A reader trying to understand the harness could find its *behavior* in [architecture.md](../../../architecture.md) (the service map, the session/turn/step lifecycle, the event taxonomy) but had no single place describing its *vocabulary* — the data structures that behavior moves around. The type shapes lived only in source, scattered across `packages/*/src/types.ts`, so understanding "what is a `Message`, a `SessionEvent`, a `StreamChunk`" meant reading the declarations directly. A prose catalog would help, but a catalog that paraphrases or paste-copies type definitions rots the instant a field changes — and an out-of-sync type doc is worse than none, because a reader trusts it. +A reader trying to understand the harness could find its *behavior* in [architecture.md](../../../../docs/architecture.md) (the service map, the session/turn/step lifecycle, the event taxonomy) but had no single place describing its *vocabulary* — the data structures that behavior moves around. The type shapes lived only in source, scattered across `packages/*/src/types.ts`, so understanding "what is a `Message`, a `SessionEvent`, a `StreamChunk`" meant reading the declarations directly. A prose catalog would help, but a catalog that paraphrases or paste-copies type definitions rots the instant a field changes — and an out-of-sync type doc is worse than none, because a reader trusts it. -So the work had two intertwined questions: **what belongs in such a catalog** (the scoping problem — a harness has dozens of cross-package types and dumping all of them helps no one), and **how to keep pasted type definitions from drifting** (the durability problem). This RFC records both decisions. Its sibling, [the generated cordis events + services catalog](2026-06-20-generated-cordis-catalog.md), is the *wiring*-axis complement: this one catalogs the data structures, that one the events and services that move them. +So the work had two intertwined questions: **what belongs in such a catalog** (the scoping problem — a harness has dozens of cross-package types and dumping all of them helps no one), and **how to keep pasted type definitions from drifting** (the durability problem). This Agent Note records both decisions. Its sibling, [the generated cordis events + services catalog](2026-06-20-generated-cordis-catalog.md), is the *wiring*-axis complement: this one catalogs the data structures, that one the events and services that move them. ## Decision @@ -48,7 +48,7 @@ The durability requirement was specific: the doc shows the **literal** current t The spine-vs-seam rule was tested against `BashExecRequest`, tool schemas and definitions, the schema DSL, presentation types, and the session/persistence split before adoption. -`verify-type-equiv` must scan the complete Markdown scope, not only manifest-named documents. Otherwise an unmanifested `type-equiv` block escapes the claimed one-to-one check. The gate therefore reports such blocks as orphans. This RFC records that fail-closed scan rule together with the spine-vs-seam and verbatim-match decisions; the generated Cordis catalog has the symmetric design record in [its RFC](2026-06-20-generated-cordis-catalog.md). +`verify-type-equiv` must scan the complete Markdown scope, not only manifest-named documents. Otherwise an unmanifested `type-equiv` block escapes the claimed one-to-one check. The gate therefore reports such blocks as orphans. This Agent Note records that fail-closed scan rule together with the spine-vs-seam and verbatim-match decisions; the generated Cordis catalog has the symmetric design record in [its Agent Note](2026-06-20-generated-cordis-catalog.md). ## Consequences diff --git a/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md similarity index 95% rename from docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md rename to .agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md index 879f8de701..7de7056b33 100644 --- a/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md +++ b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md @@ -1,4 +1,4 @@ -# RFC: Generated cordis events + services catalog +# Agent Note: Generated cordis events + services catalog Status: implemented @@ -6,7 +6,7 @@ Status: implemented A plugin author needs two reference surfaces that no single document gave them: every cordis **event** they can listen to (with its exact signature and dispatch mode) and every `ctx.<key>` **service** they can call (with its exact interface). The pieces existed but were scattered — a hand-maintained event-taxonomy *table* in `docs/architecture.md` (names + prose Mode/Purpose, name-set-checked by `verify-event-taxonomy`), a Service-map table (8 rows of role prose), and the `interface Events` / `interface Context` declarations themselves. The taxonomy table also could not catch a brand-new *undocumented* event: a name-set verifier only checks the names that are already in the table on both sides. -This is the wiring-axis complement to the [core-data-structures catalog](../../../core-data-structures/core.md) ([its RFC](2026-06-20-core-data-structures-catalog.md)): that one catalogs the *data structures* the loop moves around (verified hand-pastes); this one catalogs the *events and services* that move them. +This is the wiring-axis complement to the [core-data-structures catalog](../../../../docs/core-data-structures/core.md) ([its Agent Note](2026-06-20-core-data-structures-catalog.md)): that one catalogs the *data structures* the loop moves around (verified hand-pastes); this one catalogs the *events and services* that move them. ## Decision diff --git a/docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml similarity index 61% rename from docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml rename to .agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml index 5f83acc3aa..2e152a0072 100644 --- a/docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-02-bilingual-docs-and-pairing-gate.md: 68c0f3bbc0472b0c96f9d64fc6b1b24ac7008795 -2026-07-02-bilingual-docs-and-pairing-gate.zh.md: 2cf8f9b9c17d8a521d8674833e909b34f315cfe0 +2026-07-02-bilingual-docs-and-pairing-gate.md: 45c6edff41a7bc21c76aeeaf14d16af824c601de +2026-07-02-bilingual-docs-and-pairing-gate.zh.md: 91ba7523705d1500150efe0eac9085ea980e80d6 diff --git a/docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md similarity index 83% rename from docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md rename to .agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md index 68c0f3bbc0..45c6edff41 100644 --- a/docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md @@ -1,4 +1,4 @@ -# RFC: Bilingual documentation via paired sibling files and a pairing gate +# Agent Note: Bilingual documentation via paired sibling files and a pairing gate Status: implemented @@ -10,14 +10,14 @@ This repo's README and docs tree are read by people and agents inside and outsid ## Decision -- **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../i18n/terminology.md). +- **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../../docs/i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md). - **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR. - **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: required pairs exist, every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical), excluded (generated or bilingual-by-construction) files stay unpaired, and date-named documents on or after the manifest's `requiredSince` cutoff have complete pairs. The `required` list in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) is a ratchet: each merged translation batch adds its files, so coverage only grows. -- **Translation is agent work with human review.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../../.agents/skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../../.agents/skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. +- **Translation is agent work with human review.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. ## Alternatives considered -- **English as the canonical source with a fingerprint inside the translation** — the design first proposed for this RFC: `.zh.md` files carried an HTML comment recording the English source's blob hash, and translation flowed EN → ZH only. Revised in review: the team wants Chinese-first authoring (write and review a Chinese RFC, then translate to English) with the two languages holding equal authority, which a one-directional canonical model cannot express. The sidecar record covering BOTH sides replaced the in-file one-directional fingerprint; the blob-hash mechanics survived unchanged. +- **English as the canonical source with a fingerprint inside the translation** — the design first proposed for this Agent Note: `.zh.md` files carried an HTML comment recording the English source's blob hash, and translation flowed EN → ZH only. Revised in review: the team wants Chinese-first authoring (write and review a Chinese Agent Note, then translate to English) with the two languages holding equal authority, which a one-directional canonical model cannot express. The sidecar record covering BOTH sides replaced the in-file one-directional fingerprint; the blob-hash mechanics survived unchanged. - **Locale directories (`docs/en/` + `docs/zh/`, the Kubernetes/ECharts model)** — rejected: this repo has no docs-site framework to map locales to routes, moving every English file would churn every existing cross-reference, and `verify-md-links`/`verify-doc-refs` would need path-mapping logic instead of working unchanged. - **A separate translation repo (the PingCAP `docs`/`docs-cn` model)** — rejected: right for a docs product with independent release trains, overkill for a monorepo's own documentation; it also puts the translation outside the reach of this repo's gates. - **Interleaved bilingual files (single file, both languages)** — rejected: doubles every diff, breaks the one-line-per-paragraph convention's diff ergonomics, and makes partial inconsistency invisible. @@ -34,5 +34,5 @@ Paired sibling files with locale suffixes are the dominant Chinese big-tech conv - Every pair adds a third file to the tree. The record is machine-written (`--write`), so the cost is directory noise, not maintenance effort; in exchange, "who confirmed these consistent, and when" is answerable from git blame on the yaml. - When the two sides disagree, no mechanical rule picks a winner — the PR review does. That is the price of equal authority, accepted deliberately: the alternative (a canonical language) forbids Chinese-first authoring. - Generated docs (`cordis-catalog/`, `tool-catalog/`, `module-graph.md`) are excluded for now; the planned follow-up is to teach their generators to emit Chinese alongside English, at which point they leave the exclusion list. -- Rollout is incremental by design: documents outside `required` are visible backlog (`--list`), not red CI, so pairs land in reviewable batches without a big-bang PR. A date-named document dated on or after the manifest's `requiredSince` cutoff merges bilingual or not at all, so new date-named RFCs do not enlarge that backlog. +- Rollout is incremental by design: documents outside `required` are visible backlog (`--list`), not red CI, so pairs land in reviewable batches without a big-bang PR. A date-named document dated on or after the manifest's `requiredSince` cutoff merges bilingual or not at all, so new date-named Agent Notes do not enlarge that backlog. - The recorded hashes double as the update tool (`git cat-file -p <hash>` recovers either side's last-confirmed text for a minimal diff-based update), so re-translation of whole files is never forced by the mechanism. diff --git a/docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md similarity index 84% rename from docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md rename to .agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md index 2cf8f9b9c1..91ba752370 100644 --- a/docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md @@ -1,4 +1,4 @@ -# RFC：通过配对兄弟文件与配对门禁实现双语文档 +# Agent Note：通过配对兄弟文件与配对门禁实现双语文档 Status: implemented @@ -10,14 +10,14 @@ Status: implemented ## 决策 -- **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../i18n/terminology.md)。 +- **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。 - **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR（Pull Request）内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。 - **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：required 的配对必须存在；任何已存在的配对必须完整（三个文件齐全）且一致（两个 hash 匹配、切换行双向互链、结构签名一致）；被排除的文件（生成物或本身即双语的）不得配对；凡文件名以日期开头且日期不早于 manifest（元数据清单）中 `requiredSince` 分界日期的文档，也必须有完整配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 中的 `required` 清单只进不退：每个合并的翻译批次将自己的文件加入其中，覆盖面只增不减。 -- **翻译是 agent 的工作，由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../../.agents/skills/dsh-translate-docs/SKILL.md)，与 [dsh-code-review](../../../../.agents/skills/dsh-code-review/SKILL.md) 模式相同：skill（技能）承载工作流，并将文档作为真源。 +- **翻译是 agent 的工作，由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md)，与 [dsh-code-review](../../../skills/dsh-code-review/SKILL.md) 模式相同：skill（技能）承载工作流，并将文档作为真源。 ## 曾考虑的替代方案 -- **英文为正典源、指纹放在译文内**：本 RFC 最初提出的设计：`.zh.md` 文件携带一条 HTML 注释记录英文源的 blob hash，翻译只沿 EN → ZH 单向流动。评审中修订：团队需要中文先行的撰写方式（先写、先审中文 RFC，再译英文），两种语言同权，而单向正典模型无法表达这一点。覆盖**两侧**的伴随记录取代了文件内的单向指纹；blob hash 的机制本身保持不变。 +- **英文为正典源、指纹放在译文内**：本 Agent Note 最初提出的设计：`.zh.md` 文件携带一条 HTML 注释记录英文源的 blob hash，翻译只沿 EN → ZH 单向流动。评审中修订：团队需要中文先行的撰写方式（先写、先审中文 Agent Note，再译英文），两种语言同权，而单向正典模型无法表达这一点。覆盖**两侧**的伴随记录取代了文件内的单向指纹；blob hash 的机制本身保持不变。 - **语言目录（`docs/en/` + `docs/zh/`，Kubernetes/ECharts 模式）**：否决。本仓库没有将 locale 映射到路由的文档站框架；如果移动所有英文文件，所有既有交叉引用都要随之修改；且 `verify-md-links`/`verify-doc-refs` 将需要路径映射逻辑，而非原样工作。 - **独立翻译仓库（PingCAP `docs`/`docs-cn` 模式）**：否决。适合有独立发布节奏的文档产品，对 monorepo 自身的文档而言过重；还会把译文置于本仓库门禁触及不到的地方。 - **中英混排单文件（一个文件、两种语言）**：否决。每个 diff 都翻倍，破坏一段一行约定的 diff 易读性，且局部不一致不可见。 @@ -34,5 +34,5 @@ Status: implemented - 每个配对给目录树多添一个文件。记录由机器写入（`--write`），代价是目录噪音而非维护负担；换来的是「谁在何时确认过这对文档一致」可以从 yaml 的 git blame 直接回答。 - 两侧说法冲突时，没有机械规则裁决谁赢，由 PR 评审裁决。这是同权的代价，且是有意接受的：另一个选项（正典语言）会禁止中文先行撰写。 - 生成文档（`cordis-catalog/`、`tool-catalog/`、`module-graph.md`）暂被排除；计划中的后续工作是让生成器在输出英文的同时输出中文，届时将这些文件移出排除清单。 -- 推进天然是渐进的：`required` 之外的文档是可见的 backlog（待翻清单，`--list`），而非红色的 CI；因此配对按可评审的批次落地，无需一个巨型 PR。凡文件名以日期开头且日期不早于 manifest 中 `requiredSince` 分界日期的文档，都必须配齐双语文件，因此新建的日期命名 RFC 不会增加这份 backlog。 +- 推进天然是渐进的：`required` 之外的文档是可见的 backlog（待翻清单，`--list`），而非红色的 CI；因此配对按可评审的批次落地，无需一个巨型 PR。凡文件名以日期开头且日期不早于 manifest 中 `requiredSince` 分界日期的文档，都必须配齐双语文件，因此新建的日期命名 Agent Note 不会增加这份 backlog。 - 记录的 hash 兼作更新工具（`git cat-file -p <hash>` 能还原任一侧上次确认的文本，用于基于 diff 的最小更新），因此这套机制从不强迫整篇重译。 diff --git a/docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md similarity index 96% rename from docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md rename to .agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md index 7da1a05a3a..06ab61732c 100644 --- a/docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md +++ b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md @@ -1,4 +1,4 @@ -# RFC: Generated tool-schema catalog (boot-and-harvest) +# Agent Note: Generated tool-schema catalog (boot-and-harvest) Status: implemented @@ -19,7 +19,7 @@ The cordis catalog is a pure TypeScript-AST pass because every event/service nam - `tool-subagent`'s tool name is `config.toolName ?? 'subagent'` — chosen at load, not a literal. - An MCP plugin can register **raw JSON Schema** directly via `ctx.tools.register()` without `defineTool` at all, so enumerating `defineTool(` call sites structurally under-counts. -The only faithful source of truth is the schema the registry actually holds after the plugin loads. Booting is the [testing-policy discipline](../../../testing.md) "verify the world, not the self-report" applied to a doc generator: read the shipped artifact, not a re-derivation of it. +The only faithful source of truth is the schema the registry actually holds after the plugin loads. Booting is the [testing-policy discipline](../../../../docs/testing.md) "verify the world, not the self-report" applied to a doc generator: read the shipped artifact, not a re-derivation of it. ### Restoring "nothing silently omitted" diff --git a/docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md similarity index 74% rename from docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md rename to .agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md index 4e3148ead6..4f3fafe59d 100644 --- a/docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md +++ b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md @@ -1,10 +1,10 @@ -# RFC: Documentation graph index for maintainers and SDK users +# Agent Note: Documentation graph index for maintainers and SDK users Status: implemented ## Problem -The repo already had several high-trust documentation surfaces, each on a different axis: [module-graph.md](../../../module-graph.md) is generated from package `peerDependencies`, the generated [Cordis events](../../../cordis-catalog/events.md) and [services](../../../cordis-catalog/services.md) catalogs are generated from Cordis `Events` and `Context` declarations, [tool-catalog.md](../../../tool-catalog.md) is generated by booting shipped tool plugins, and [core-data-structures/](../../../core-data-structures/core.md) uses `ts type-equiv` blocks to keep pasted type definitions synchronized with source. +The repo already had several high-trust documentation surfaces, each on a different axis: [module-graph.md](../../../../docs/module-graph.md) is generated from package `peerDependencies`, the generated [Cordis events](../../../../docs/cordis-catalog/events.md) and [services](../../../../docs/cordis-catalog/services.md) catalogs are generated from Cordis `Events` and `Context` declarations, [tool-catalog.md](../../../../docs/tool-catalog.md) is generated by booting shipped tool plugins, and [core-data-structures/](../../../../docs/core-data-structures/core.md) uses `ts type-equiv` blocks to keep pasted type definitions synchronized with source. Those references are accurate, but they are mostly catalogs. A maintainer still has to synthesize the relationships: which packages form a capability seam, which app bundles a concrete spine, which event is durable vs live, where a hook or policy plugin can intercept work, and which model-facing tool depends on which service. An SDK user has the same problem from another angle: "Which package do I install or load for the behavior I want, and which event/service/tool do I extend?" @@ -12,7 +12,7 @@ The hooks subsystem makes event producer/consumer topology and interception poin ## Decision -Add generated relationship graph docs, indexed at [docs/graph-atlas.md](../../../graph-atlas.md), produced by focused generators and verified by `pnpm run verify-doc-graphs` / existing catalog freshness checks as part of `doc-sync`. +Add generated relationship graph docs, indexed at [docs/graph-atlas.md](../../../../docs/graph-atlas.md), produced by focused generators and verified by `pnpm run verify-doc-graphs` / existing catalog freshness checks as part of `doc-sync`. The index is a relationship layer above the existing catalogs. It does not replace exact references; instead, it links to them and explains how their pieces fit together. @@ -30,15 +30,15 @@ The first index links ten relationship surfaces. Package topology and tool-packa | Graph | Maintenance mode | Source of truth | |---|---|---| -| [module dependency graph](../../../module-graph.md) | generated | `packages/*/*/package.json` peer dependencies plus package group paths | -| [tool schema catalog and package map](../../../tool-catalog.md) | generated | boot-harvested tool schemas plus tool-package service/effect metadata | -| [capability seams and core services](../../../capability-seams.md) | hybrid generated | Cordis service declarations plus a role manifest in `gen-doc-graphs.ts` | +| [module dependency graph](../../../../docs/module-graph.md) | generated | `packages/*/*/package.json` peer dependencies plus package group paths | +| [tool schema catalog and package map](../../../../docs/tool-catalog.md) | generated | boot-harvested tool schemas plus tool-package service/effect metadata | +| [capability seams and core services](../../../../docs/capability-seams.md) | hybrid generated | Cordis service declarations plus a role manifest in `gen-doc-graphs.ts` | | [echo-agent app composition](../../../../examples/echo-agent/composition.md) | hybrid generated | `examples/echo-agent/cordis.yml` plugin list plus curated app/bundle expansion | | [repl-agent app composition](../../../../examples/repl-agent/composition.md) | hybrid generated | `examples/repl-agent/cordis.yml` plugin list plus curated app/bundle expansion | | [acp-agent app composition](../../../../examples/acp-agent/composition.md) | hybrid generated | `examples/acp-agent/cordis.yml` plugin list plus curated app/bundle expansion | -| [event producer/consumer matrix](../../../event-producer-consumer.md) | hybrid generated | Cordis event declarations, AST-scanned `ctx.on/emit/parallel/serial/waterfall` sites, and explicit dynamic dispatch overrides | -| [agent turn and step lifecycle](../../../agent-lifecycle.md) | curated | architecture.md loop lifecycle, Cordis catalog links, and session event semantics | -| [tool execution pipeline](../../../tool-execution-pipeline.md) | curated | tool pipeline semantics and the `tools/execute` waterfall | +| [event producer/consumer matrix](../../../../docs/event-producer-consumer.md) | hybrid generated | Cordis event declarations, AST-scanned `ctx.on/emit/parallel/serial/waterfall` sites, and explicit dynamic dispatch overrides | +| [agent turn and step lifecycle](../../../../docs/agent-lifecycle.md) | curated | architecture.md loop lifecycle, Cordis catalog links, and session event semantics | +| [tool execution pipeline](../../../../docs/tool-execution-pipeline.md) | curated | tool pipeline semantics and the `tools/execute` waterfall | | [ACP snapshot replay](../../../../packages/ui/acp/snapshot-replay.md) | curated | snapshot harness behavior | ### Why generators own the docs diff --git a/docs/rfc/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md similarity index 98% rename from docs/rfc/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md rename to .agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md index 1c7e515c4f..882ab8cf82 100644 --- a/docs/rfc/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md +++ b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md @@ -1,4 +1,4 @@ -# RFC: JSDoc completeness gate for the cordis surface +# Agent Note: JSDoc completeness gate for the cordis surface Status: implemented diff --git a/docs/rfc/implemented/process/2026-07-04-doc-tiers-and-budgets.md b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md similarity index 74% rename from docs/rfc/implemented/process/2026-07-04-doc-tiers-and-budgets.md rename to .agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md index 3f88e43c1d..68e055f0a2 100644 --- a/docs/rfc/implemented/process/2026-07-04-doc-tiers-and-budgets.md +++ b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md @@ -1,17 +1,17 @@ -# RFC: Documentation tiers, budgets, and the ceiling gate +# Agent Note: Documentation tiers, budgets, and the ceiling gate Status: implemented ## Problem -Standing docs accumulated repeated rules, retold incidents, duplicated package maps, and stale RFC summaries despite existing writing guidance. Because review alone did not prevent that growth, the repository needed a mechanical budget alongside its documentation taxonomy. +Standing docs accumulated repeated rules, retold incidents, duplicated package maps, and stale Agent Note summaries despite existing writing guidance. Because review alone did not prevent that growth, the repository needed a mechanical budget alongside its documentation taxonomy. ## Decision -- **A tier taxonomy with one home per fact.** [docs/AGENTS.md](../../../AGENTS.md) is the documentation standard: it assigns every Markdown tier a single job (standing orders, system map, type catalog, decision records, incident stories, how-tos, per-package contracts, generated catalogs, workflows), forbids restating a fact outside its home tier (link instead), and carries the slop checklist used when writing or reviewing any doc. -- **A narrow, hard budget gate.** [scripts/verify-doc-budgets.ts](../../../../scripts/verify-doc-budgets.ts) joins `doc-sync`: every doc listed in [scripts/doc-budgets.manifest.json](../../../../scripts/doc-budgets.manifest.json) must stay under its word ceiling (`wc -w` semantics, whole file), and a budgeted file that is missing fails the gate so a rename cannot silently orphan its budget. Scope is deliberately only the accretion-prone standing docs — the root and subtree `AGENTS.md` files, `architecture.md`, `packages/README.md`, and the standing policy docs they evict content into (`docs/testing.md`, `docs/defensive-patterns.md`). Reference docs, RFCs, and package READMEs are unbudgeted: length is legitimate there when every row is a fact, and review plus the slop checklist govern them. +- **A tier taxonomy with one home per fact.** [docs/AGENTS.md](../../../../docs/AGENTS.md) is the documentation standard: it assigns every Markdown tier a single job (standing orders, system map, type catalog, decision records, incident stories, how-tos, per-package contracts, generated catalogs, workflows), forbids restating a fact outside its home tier (link instead), and carries the slop checklist used when writing or reviewing any doc. +- **A narrow, hard budget gate.** [scripts/verify-doc-budgets.ts](../../../../scripts/verify-doc-budgets.ts) joins `doc-sync`: every doc listed in [scripts/doc-budgets.manifest.json](../../../../scripts/doc-budgets.manifest.json) must stay under its word ceiling (`wc -w` semantics, whole file), and a budgeted file that is missing fails the gate so a rename cannot silently orphan its budget. Scope is deliberately only the accretion-prone standing docs — the root and subtree `AGENTS.md` files, `architecture.md`, `packages/README.md`, and the standing policy docs they evict content into (`docs/testing.md`, `docs/defensive-patterns.md`). Reference docs, Agent Notes, and package READMEs are unbudgeted: length is legitimate there when every row is a fact, and review plus the slop checklist govern them. - **Ceilings are an enforcement frontier that ratchets.** A ceiling sits at least 5% above the doc's current size — working headroom, so routine wording edits pass while real growth still trips the gate — and ratchets down, keeping that margin, as the doc is brought to its target budget (root `AGENTS.md` ≤ 1,500 words; `architecture.md` ≤ 1,800; subtree `AGENTS.md` ≤ 600; `packages/README.md` ≤ 600) — the same rollout mechanism as the [translation-pairing `required` list](2026-07-02-bilingual-docs-and-pairing-gate.md). When the gate goes red the fix is to relocate or condense per the taxonomy; raising a ceiling is permitted only with explicit justification in the PR description, the manifest diff being the reviewable act. -- **A thin workflow skill, contracts in docs.** [.agents/skills/dsh-doc-standards](../../../../.agents/skills/dsh-doc-standards/SKILL.md) carries the placement/audit/red-gate workflow and defers to the standard as its source of truth, the same split as [dsh-translate-docs](../../../../.agents/skills/dsh-translate-docs/SKILL.md) over the i18n contract. +- **A thin workflow skill, contracts in docs.** [.agents/skills/dsh-doc-standards](../../../skills/dsh-doc-standards/SKILL.md) carries the placement/audit/red-gate workflow and defers to the standard as its source of truth, the same split as [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) over the i18n contract. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md b/.agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md new file mode 100644 index 0000000000..b0f292d4a0 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md @@ -0,0 +1,32 @@ +# Agent Note: Generate the Agent Note index tables + +Status: implemented + +## Problem + +The Agent Note index's per-lifecycle/per-class tables list facts that are fully derivable: an Agent Note's path encodes lifecycle and class, its filename encodes the first-proposed date, and its H1 carries the title. A hand-maintained copy of those facts is also the repo's highest-contention docs hotspot: every proposal wave appends rows to the same few lines, so concurrent Agent Note branches conflict precisely there while agreeing everywhere else, and each conflict is resolved by hand-merging rows whose content the filesystem already knows. [The classification Agent Note](2026-06-20-agent-note-classification.md) originally kept the index hand-written for curation's sake — but the curated part of the README is the prose, and the prose never conflicts; only the mechanical tables do. + +## Decision + +Keep the curated prose; generate the list. The tables live in [`.agents/notes/INDEX.md`](../../INDEX.md), a **fully generated file** — the curated prose stays in README.md, which carries no index rows at all. [`scripts/agent-note-index.ts`](../../../../scripts/agent-note-index.ts) is the shared source of truth — the tree walker (owning the closed lifecycle/class sets and the structure rules, including a parseable-H1 requirement) and the renderer (rows from H1 title with any `Agent Note: ` prefix stripped, plus the filename date, sorted by date then filename, grouped as `### {Class}` sections in canonical class order). Two thin consumers share it: + +- [`scripts/gen-agent-note-index.ts`](../../../../scripts/gen-agent-note-index.ts) (`pnpm run gen-agent-note-index`) rewrites INDEX.md in full from the tree. +- [`scripts/verify-agent-note-classification.ts`](../../../../scripts/verify-agent-note-classification.ts) (a `doc-sync` member) checks structure, asserts the committed INDEX.md byte-matches a fresh render — the `gen-cordis-catalog`/`verify-cordis-catalog` pattern — and rejects an index-shaped row in the curated README. Freshness subsumes the index-completeness check: a generated-from-disk table is definitionally complete and correctly headed. + +Adding, moving, or deleting an Agent Note means editing only the Agent Note file and running the generator; the classification Agent Note's rejected-alternatives record carries the supersession cross-link. + +## Alternatives considered + +### Why not marker-delimited regions inside README.md? + +The first landed shape: the generator spliced the tables into README.md between `gen-agent-note-index` marker comments, under each `## {Lifecycle}` heading. Superseded by the whole-file INDEX.md once the README also absorbed the in-file format contract ([the uniform-format Agent Note](2026-07-05-uniform-agent-note-format.md)): a front-door README hosting hundreds of generated rows dwarfed its curated prose, and splice mechanics (marker pairs, heading checks, outside-region row detection) exist only to protect curated text that a dedicated generated file simply doesn't contain. + +### Why not the verifier-only model? + +It catches mistakes but still makes every proposal edit a shared hotspot in a hand-maintained table, and a failed verifier is strictly more annoying than a generator for a purely mechanical row: the author has already named and placed the file; the index copy adds no information. This is the same hand-list-versus-derivation judgment the [package-inventory proposal](../../proposed/process/2026-06-20-discover-package-inventory.md) applies to tsconfig references and knip stanzas — applied to the one list that demonstrably conflicts. + +## Consequences + +- The generated file is explicit: its banner names the generator, there is no curated region to protect inside it, and the generator refuses to run on a structurally invalid tree. +- A malformed or missing H1 is a hard error in both the generator and the gate — the H1 is now load-bearing as the index title source. +- Concurrent Agent Note branches resolve index conflicts by rerunning the generator, never by hand-merging rows. diff --git a/docs/rfc/implemented/process/2026-07-04-persistence-log-catalog.md b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md similarity index 98% rename from docs/rfc/implemented/process/2026-07-04-persistence-log-catalog.md rename to .agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md index 70a6d60c1a..bd16baf8f6 100644 --- a/docs/rfc/implemented/process/2026-07-04-persistence-log-catalog.md +++ b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md @@ -1,4 +1,4 @@ -# RFC: Generated persistence log event catalog +# Agent Note: Generated persistence log event catalog Status: implemented diff --git a/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md new file mode 100644 index 0000000000..40c2dd6ec2 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md @@ -0,0 +1,28 @@ +# Agent Note: One gated in-file format for Agent Notes + +Status: implemented + +## Problem + +Agent Note paths encoded lifecycle and class, but file contents still mixed headings, status formats, ADR and proposal templates, and proposal-era sections in implemented records. Authors copied whichever neighbor they found, and lifecycle moves could skip the required rewrite because no gate enforced an in-file contract. + +## Decision + +[README.md § The file format](../../README.md#the-file-format) is the in-file contract — the header block (`# Agent Note: <title>` plus a dateless, folder-agreeing `Status:` enum whose only content is the rejection reason), the per-lifecycle body skeleton (`Problem` opener everywhere; `Proposal`/`Acceptance criteria`/`Risks` in `proposed/`; present-tense `Decision`/`Consequences` with proposal-era headings banned in `implemented/`; frozen proposal shape in `rejected/`), a mandatory `Alternatives considered` section, and the canonical section vocabulary between which bespoke technical sections stay free-form. `pnpm run verify-agent-note-format` ([scripts/verify-agent-note-format.ts](../../../../scripts/verify-agent-note-format.ts)) enforces every mechanical clause as part of `doc-sync`, so a lifecycle move that skips its rewrite now fails CI instead of review memory. + +The whole corpus was normalized in the same change that defined the format — the pre-release stance: no transition period, no dual-format tolerance. The one grandfather is content, not format: alternatives are recorded, never invented, so a pre-format Agent Note whose alternatives are not reconstructible from the record carries the exact `agent-note-format: alternatives-not-recorded` comment, which the gate accepts only for files dated before this Agent Note. + +## Alternatives considered + +- **A full rigid template** (one fixed section sequence per lifecycle, every Agent Note restructured to fit) — rejected: the big design Agent Notes carry eight to fifteen bespoke technical sections (package topology, wire contracts, schemas) that are load-bearing content, not drift; a rigid sequence would force destructive rewrites now and template-fighting forever. +- **Header-only normalization** (H1 and Status, bodies untouched) — rejected: the debt markers flagged the *body* genre split, and leaving `Context`/`Decision` beside `Problem`/`Proposal` indefinitely resolves nothing. +- **No Status line** (the folder already is the status; the three newest pre-format Agent Notes (and the zh counterpart of one) omitted the line) — rejected in favor of keeping a self-describing file: the drift risk that motivated dropping it is neutralized by gating the line against the folder instead. +- **Dated status** (`Status: implemented (accepted YYYY-MM-DD)`) — rejected: the acceptance date is narrated history the writing rules keep out of docs; the filename carries first-proposed, git carries the rest, and the gate could check a date's format but never its truth. +- **A bare `# <title>` H1** — rejected: the `Agent Note: ` prefix is the corpus-majority form and self-describes the genre when a file is read outside its tree; the index generator strips it, so index rows are identical either way. +- **`## What we give up` as the implemented closer** (the README's own phrase for what an Agent Note records) — rejected: it names only costs, and an honest consequences section records what the trade-off bought as well. +- **Convention without a gate** (write the contract down, enforce by review) — rejected: the slop checklist already outlawed spec-speak in `implemented/` by convention, and nineteen files show what convention alone achieves here. +- **A standalone `FORMAT.md` contract file** — the first landed home; folded into README.md once the generated index moved out to [INDEX.md](../../INDEX.md): with the tables gone the README regained the room, and one front door carrying layout, classification, and format beats splitting the contract across two files. + +## Consequences + +Every Agent Note now costs slightly more structure, and the mandatory `Alternatives considered` section is deliberate friction: a decision recorded without what it beat invites the re-litigation Agent Notes exist to prevent. Pre-format Agent Notes whose alternatives were not reconstructible carry the grandfather comment permanently — an honest gap on the record rather than fabricated rationale. `doc-sync` gains one gate, and moving an Agent Note between lifecycle folders is now real work at move time (the body rewrite the move always owed) instead of deferred cleanup nothing tracked. The thirty-nine debt markers are gone, resolved by the template they were waiting for. diff --git a/docs/rfc/implemented/process/2026-07-06-export-surface-jsdoc-gate.md b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md similarity index 99% rename from docs/rfc/implemented/process/2026-07-06-export-surface-jsdoc-gate.md rename to .agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md index 6ebb477dea..452c877182 100644 --- a/docs/rfc/implemented/process/2026-07-06-export-surface-jsdoc-gate.md +++ b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md @@ -1,4 +1,4 @@ -# RFC: Export-surface JSDoc gate +# Agent Note: Export-surface JSDoc gate Status: implemented diff --git a/docs/rfc/implemented/process/2026-07-06-generated-config-catalog.md b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.md similarity index 93% rename from docs/rfc/implemented/process/2026-07-06-generated-config-catalog.md rename to .agents/notes/implemented/process/2026-07-06-generated-config-catalog.md index 999ebd8503..82355ab511 100644 --- a/docs/rfc/implemented/process/2026-07-06-generated-config-catalog.md +++ b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.md @@ -1,4 +1,4 @@ -# RFC: Generated plugin config catalog +# Agent Note: Generated plugin config catalog Status: implemented @@ -8,7 +8,7 @@ The repository had no source-backed reference for plugin configuration. Package ## Decision -`scripts/gen-config-catalog.ts` emits [docs/config-catalog.md](../../../config-catalog.md) from each plugin's declared config type and JSDoc, with injection requirements, referenced-type links, and a source pointer. Package-local types are included transitively; workspace and external types are linked or named. Deterministic `--write` and `--check` modes make the committed page a generated artifact. +`scripts/gen-config-catalog.ts` emits [docs/config-catalog.md](../../../../docs/config-catalog.md) from each plugin's declared config type and JSDoc, with injection requirements, referenced-type links, and a source pointer. Package-local types are included transitively; workspace and external types are linked or named. Deterministic `--write` and `--check` modes make the committed page a generated artifact. Pure AST generation is correct here for the same reason it is for the events/services catalog and NOT for the tool catalog: a config type is a static declaration and every schemastery schema in the repo is a static `z.object`/`z.intersect` literal, so the source is the whole truth — nothing about the config surface is runtime-composed. diff --git a/docs/rfc/implemented/process/2026-07-06-node-engine-floor.md b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md similarity index 96% rename from docs/rfc/implemented/process/2026-07-06-node-engine-floor.md rename to .agents/notes/implemented/process/2026-07-06-node-engine-floor.md index af08c96be3..59f4c347eb 100644 --- a/docs/rfc/implemented/process/2026-07-06-node-engine-floor.md +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md @@ -1,4 +1,4 @@ -# RFC: Raise the Node LTS engine floor to 22.19 +# Agent Note: Raise the Node LTS engine floor to 22.19 Status: implemented @@ -24,7 +24,7 @@ Those source features clear on the 22.x line at **22.18**, but the installed Pi - The advertised LTS branch no longer undercuts the Pi adapter dependency floor. - CI proves the Node 22 LTS floor directly with Node 22.19, keeps the Node 24 branch on `node: 24`, and keeps Node 26 for the next even line; each leg typechecks the source graph and launches the unbuilt workflow worker for real. - The built-bin smoke needs no version-conditional flag: at 22.19 type-stripping is already the default, so the test stays the plain `node lib/bin.js` path it documents. -- A future dependency or source API that raises the runtime floor must move `engines.node`, the compatibility matrix, and this RFC in the same change. +- A future dependency or source API that raises the runtime floor must move `engines.node`, the compatibility matrix, and this Agent Note in the same change. ## Alternatives considered diff --git a/docs/rfc/implemented/process/2026-07-06-parallel-github-ci-gates.md b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md similarity index 99% rename from docs/rfc/implemented/process/2026-07-06-parallel-github-ci-gates.md rename to .agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md index be31a439c1..65ad437ca9 100644 --- a/docs/rfc/implemented/process/2026-07-06-parallel-github-ci-gates.md +++ b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md @@ -1,4 +1,4 @@ -# RFC: Parallel GitHub CI gates +# Agent Note: Parallel GitHub CI gates Status: implemented diff --git a/docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md similarity index 94% rename from docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md rename to .agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md index 4e27b111d6..60472e51ec 100644 --- a/docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md +++ b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md @@ -1,4 +1,4 @@ -# RFC: Parallel pre-push gates +# Agent Note: Parallel pre-push gates Status: implemented @@ -14,7 +14,7 @@ Flattening those members directly into `lefthook.yml` solves the local hook only [lefthook.yml](../../../../lefthook.yml) keeps one pre-push job named `full check` and runs `pnpm run check:pre-push`. That package script delegates to [scripts/run-gates.ts](../../../../scripts/run-gates.ts), the same bounded scheduler CI uses. -The `pre-push` mode expands into leaf gates for the unit suite, snapshot suite, build, `hygiene` members, `doc-sync` members, and module-graph freshness. The leaf list keeps the same gate vocabulary as the package scripts, including RFC classification and RFC format, while the runner schedules independent checks with four active top-level workers by default; `DSH_GATE_CONCURRENCY` overrides that bound. +The `pre-push` mode expands into leaf gates for the unit suite, snapshot suite, build, `hygiene` members, `doc-sync` members, and module-graph freshness. The leaf list keeps the same gate vocabulary as the package scripts, including Agent Note classification and Agent Note format, while the runner schedules independent checks with four active top-level workers by default; `DSH_GATE_CONCURRENCY` overrides that bound. The build gate makes the hook self-contained from a clean worktree. `publint`, `verify-node-next-types`, and the pre-push form of `doc-typecheck` wait for that build output, while source-only gates continue in parallel. diff --git a/docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md similarity index 57% rename from docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md rename to .agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md index 6cd8851149..0d294feb0f 100644 --- a/docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md +++ b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md @@ -1,18 +1,18 @@ -# RFC: A gated Known-Limitations section in every package README +# Agent Note: A gated Known-Limitations section in every package README Status: implemented ## Problem -The [documentation standard](../../../AGENTS.md) assigns limitations to package READMEs. Without a shared shape, an omitted section cannot distinguish an audited absence from forgotten documentation, and variant headings prevent a repository-wide search. +The [documentation standard](../../../../docs/AGENTS.md) assigns limitations to package READMEs. Without a shared shape, an omitted section cannot distinguish an audited absence from forgotten documentation, and variant headings prevent a repository-wide search. ## Decision -Every package manifest under `packages/<group>/<pkg>/package.json` has a sibling README with the canonical `## Known Limitations and Deferred Work` section. Its bullets record durable consumer gaps and non-obvious maintainer constraints owned by that package; ordinary cleanup remains in its source TODO or owning RFC. The [`verify-package-readme-limitations` gate](../../../../scripts/verify-package-readme-limitations.ts) derives the package set from manifests, rejects missing READMEs, and requires exactly one canonical h2 with at least one top-level bullet. Near-miss headings such as “Limitations,” “Deferred,” “What is NOT here,” or “Non-goals” fail. +Every package manifest under `packages/<group>/<pkg>/package.json` has a sibling README with the canonical `## Known Limitations and Deferred Work` section. Its bullets record durable consumer gaps and non-obvious maintainer constraints owned by that package; ordinary cleanup remains in its source TODO or owning Agent Note. The [`verify-package-readme-limitations` gate](../../../../scripts/verify-package-readme-limitations.ts) derives the package set from manifests, rejects missing READMEs, and requires exactly one canonical h2 with at least one top-level bullet. Near-miss headings such as “Limitations,” “Deferred,” “What is NOT here,” or “Non-goals” fail. A package with nothing to declare is listed in `NO_LIMITATIONS` and omits the section. Adding a limitation requires removing the entry; renames and removals fail because every entry must name a scanned package. -The gate checks presence, shape, and the allowlist. Review under the documentation and [prose](../../../../.agents/skills/dsh-prose-standard/SKILL.md) standards owns coverage and accuracy. The standing rule lives in [packages/AGENTS.md](../../../../packages/AGENTS.md). +The gate checks presence, shape, and the allowlist. Review under the documentation and [prose](../../../skills/dsh-prose-standard/SKILL.md) standards owns coverage and accuracy. The standing rule lives in [packages/AGENTS.md](../../../../packages/AGENTS.md). ## Alternatives considered diff --git a/docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md similarity index 88% rename from docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md rename to .agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md index d0844f4f3b..dd986f3661 100644 --- a/docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md +++ b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md @@ -1,4 +1,4 @@ -# RFC: Package Model Experience contract +# Agent Note: Package Model Experience contract Status: implemented @@ -8,9 +8,9 @@ A package README can explain APIs and runtime mechanics without answering the qu ## Decision -Every workspace package README with a model-facing or model-adjacent contract ends with the canonical [Model Experience section](../../../cookbook/adding-a-package.md#4-write-the-package-readme), immediately before `## Known Limitations and Deferred Work`; a package on the no-limitations allowlist ends with Model Experience itself. An audited model-agnostic generic package omits the section through `NO_MODEL_EXPERIENCE_SECTION`. +Every workspace package README with a model-facing or model-adjacent contract ends with the canonical [Model Experience section](../../../../docs/cookbook/adding-a-package.md#4-write-the-package-readme), immediately before `## Known Limitations and Deferred Work`; a package on the no-limitations allowlist ends with Model Experience itself. An audited model-agnostic generic package omits the section through `NO_MODEL_EXPERIENCE_SECTION`. -Packages with direct, conditional, capped, lifetime, multi-surface, or auxiliary-model effects use one H3 per context surface. Each surface contains three ordered H4 fields—`What the model sees`, `Token effect`, and `KV Cache effect`—and each field starts with one prose paragraph. The cache field distinguishes append-only growth, a stable repeated prefix, replacement of earlier tokens, and an independent model request; it names every package-owned configuration, scope, lifecycle, compaction, or routing change that can alter the request before newly appended content. “Does not invalidate” means the package preserves an already-reusable prefix, not that a provider promises a cache hit or retention period. Stable package-owned text is quoted exactly: system-prompt prose and other long literals use a titled H5 plus `markdown` fence under the field that introduces them, normally `What the model sees`, while short literals stay inline with named interpolation placeholders. Tool-schema surfaces link their anchored section in the generated [tool catalog](../../../tool-catalog.md) and state only composition or configuration deltas; runtime-only definitions explain why the catalog omits them. Data-dependent and provider-owned text is summarized. Agent-scoped visibility is explicit, and prompt and schema surfaces remain separate when scoping can hide one without the other. +Packages with direct, conditional, capped, lifetime, multi-surface, or auxiliary-model effects use one H3 per context surface. Each surface contains three ordered H4 fields—`What the model sees`, `Token effect`, and `KV Cache effect`—and each field starts with one prose paragraph. The cache field distinguishes append-only growth, a stable repeated prefix, replacement of earlier tokens, and an independent model request; it names every package-owned configuration, scope, lifecycle, compaction, or routing change that can alter the request before newly appended content. “Does not invalidate” means the package preserves an already-reusable prefix, not that a provider promises a cache hit or retention period. Stable package-owned text is quoted exactly: system-prompt prose and other long literals use a titled H5 plus `markdown` fence under the field that introduces them, normally `What the model sees`, while short literals stay inline with named interpolation placeholders. Tool-schema surfaces link their anchored section in the generated [tool catalog](../../../../docs/tool-catalog.md) and state only composition or configuration deltas; runtime-only definitions explain why the catalog omits them. Data-dependent and provider-owned text is summarized. Agent-scoped visibility is explicit, and prompt and schema surfaces remain separate when scoping can hide one without the other. A package with no model-context effect, or one path rendered entirely by another package, uses the verifier's audited short form: one sentence beginning `None, as ` or `Indirectly, through ` followed by a `KV Cache effect` H4 and one prose paragraph. Pure transport and keyless test-support packages use the none form when they create no model-bound content. Provider backends use the indirect form even when they cap or filter data, and wiring bundles use it when named children own every effect. These sections locate the contribution and disclaim direct cache invalidation without restating the consumer. Structured sections likewise document only package-owned inputs, transformations, and deltas. diff --git a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml b/.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml similarity index 59% rename from docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml rename to .agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml index eb411f1158..366faaf6a3 100644 --- a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-14-typescript-program-backed-semantic-gates.md: 3e7a76e86d83080ae1a4f91ca97cc9749c90ef29 -2026-07-14-typescript-program-backed-semantic-gates.zh.md: 0a13452012e7f6cbd3ad7994845ba1985355c089 +2026-07-14-typescript-program-backed-semantic-gates.md: f9c00a4b6a5e9f08c11902e9267e4c1a954cebf8 +2026-07-14-typescript-program-backed-semantic-gates.zh.md: ce1f1edc765f621ca9f650720aa2db43f636e330 diff --git a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md b/.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md similarity index 99% rename from docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md rename to .agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md index 3e7a76e86d..f9c00a4b6a 100644 --- a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md +++ b/.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md @@ -1,4 +1,4 @@ -# RFC: TypeScript Program-backed semantic gates +# Agent Note: TypeScript Program-backed semantic gates Status: implemented diff --git a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md b/.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md similarity index 99% rename from docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md rename to .agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md index 0a13452012..ce1f1edc76 100644 --- a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md +++ b/.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md @@ -1,4 +1,4 @@ -# RFC: 基于 TypeScript Program 的语义门禁 +# Agent Note: 基于 TypeScript Program 的语义门禁 Status: implemented diff --git a/docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml b/.agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml similarity index 62% rename from docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml rename to .agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml index 9424f2aa24..31ec0bdb07 100644 --- a/docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-17-run-ci-examples-from-built-lib.md: aae88ee965b4e2211f3a53aeb9c0ee4944d95c2a -2026-07-17-run-ci-examples-from-built-lib.zh.md: 0cd3822a71b8f7399be93beaac74b2177fcbe7ca +2026-07-17-run-ci-examples-from-built-lib.md: 22f69ed56bfc479281648bfb40df5acbd129ebc0 +2026-07-17-run-ci-examples-from-built-lib.zh.md: 74b985f578dd25f785e556c0cd493a7a9292fc43 diff --git a/docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md b/.agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md similarity index 98% rename from docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md rename to .agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md index aae88ee965..22f69ed56b 100644 --- a/docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md +++ b/.agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md @@ -1,4 +1,4 @@ -# RFC: Run CI examples from built lib +# Agent Note: Run CI examples from built lib Status: implemented diff --git a/docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md b/.agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md similarity index 98% rename from docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md rename to .agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md index 0cd3822a71..74b985f578 100644 --- a/docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md +++ b/.agents/notes/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md @@ -1,4 +1,4 @@ -# RFC: 在 CI 中从构建后的 lib 运行示例 +# Agent Note: 在 CI 中从构建后的 lib 运行示例 Status: implemented diff --git a/docs/rfc/implemented/simplification/2026-06-19-drop-mutable-session-summary.md b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md similarity index 88% rename from docs/rfc/implemented/simplification/2026-06-19-drop-mutable-session-summary.md rename to .agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md index 54f8397fc9..f1a9c9aa3c 100644 --- a/docs/rfc/implemented/simplification/2026-06-19-drop-mutable-session-summary.md +++ b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md @@ -1,4 +1,4 @@ -# RFC: Drop the mutable session summary +# Agent Note: Drop the mutable session summary Status: implemented @@ -20,7 +20,7 @@ Delete the mutable session summary entirely. `SessionSummary` and the `SessionMe Anything the summary was meant to provide is **derivable from the append-only log** when a consumer actually needs it (`firstPrompt` = first `user/message`; recency = the last event's `time` or the file mtime) or already lives in the immutable header (`createdAt`, `cwd`). The one thing *not* derivable — a user-*edited* title — had no implementation and is pure YAGNI; it can return as its own log event or header field if a real feature ever needs it. -This is recorded as a decision because it is **durable** (it narrows a public service contract and an on-disk format across two backends), **contested** (the summary was a deliberate forward-looking design, not an accident), and **surprising** (a future reader finding `SessionHeader` where the original RFC describes `SessionMeta` would otherwise ask why the summary vanished). It also unblocks the [shared persistence write coordinator](../architecture/2026-06-18-shared-persistence-write-coordinator.md): with no mutable summary, the coordinator's hook interface needs no `updateSummary` hook and the JSONL-sidecar-vs-SQLite-column durability divergence disappears, so the two backends' write paths converge. +This is recorded as a decision because it is **durable** (it narrows a public service contract and an on-disk format across two backends), **contested** (the summary was a deliberate forward-looking design, not an accident), and **surprising** (a future reader finding `SessionHeader` where the original Agent Note describes `SessionMeta` would otherwise ask why the summary vanished). It also unblocks the [shared persistence write coordinator](../architecture/2026-06-18-shared-persistence-write-coordinator.md): with no mutable summary, the coordinator's hook interface needs no `updateSummary` hook and the JSONL-sidecar-vs-SQLite-column durability divergence disappears, so the two backends' write paths converge. ## No migration @@ -30,4 +30,4 @@ This is unreleased software (see [root AGENTS.md](../../../../AGENTS.md) § "Pre A future session picker now has to derive its preview/ordering from the log (or reintroduce a typed field) rather than reading a ready-made summary row. That is the correct cost: a cache for a feature that does not exist is dead weight that every backend pays to maintain and every contract test pays to assert. The principle — **a passing test pins current behavior, not necessarily correct behavior; behavior can be an artifact of a past compromise** — is now recorded as a standalone convention in [root AGENTS.md](../../../../AGENTS.md), with this change as its worked example. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md similarity index 96% rename from docs/rfc/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md rename to .agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md index a93e3d3196..4e8a092989 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md +++ b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md @@ -1,4 +1,4 @@ -# RFC: Fold trace-only session facts into load-bearing events +# Agent Note: Fold trace-only session facts into load-bearing events Status: implemented @@ -33,7 +33,7 @@ A consumer can no longer filter the canonical log for standalone `usage` or step ## Implementation note -Shipped as proposed, with one scope refinement (per AGENTS.md "RFCs are proposals, not golden truth"): +Shipped as proposed, with one scope refinement (per AGENTS.md "Agent Notes are proposals, not golden truth"): - **Empty-content `assistant/message` hosts usage with no data loss.** The proof the proposal demanded (no persisted usage chunk becomes unrepresented) lands on the max-tokens path: a step cut off with usage but empty content (e.g. only a dropped tool call) previously emitted a standalone `usage`. It now records an empty-content `assistant/message { content: [], usage }`. To keep that from injecting a spurious content-less assistant turn into the provider transcript, `deriveMessages()` skips empty-content `assistant/message` events. A regression test asserts usage stays represented AND derived history is uncorrupted. diff --git a/docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md similarity index 85% rename from docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md rename to .agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md index 9ce20ff7d4..ecea052387 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md @@ -1,4 +1,4 @@ -# RFC: Drop the unconsumed `llm/adapter-change` event +# Agent Note: Drop the unconsumed `llm/adapter-change` event Status: implemented @@ -6,19 +6,19 @@ Status: implemented `LlmService.registerAdapter()` emits `llm/adapter-change` on registration and disposal ([packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts)). Grepping `llm/adapter-change` across `packages/*/src` and `examples/*/src` finds only the declaration, emit sites, docs, and tests; no production listener subscribes to it. -This differs from `tools/change` and `system-prompt/change`. Those two events are also unconsumed today, but they are plausible registry-change signals for future live tool/prompt UIs. LLM adapter registration is more of a boot-time implementation detail: adapters are not a user-visible palette and the real model-call interception seam is `llm/stream`. Keeping an adapter-change event with no listener repeats the [drop-the-dead-summary](../../implemented/simplification/2026-06-19-drop-mutable-session-summary.md) pattern at a smaller scale. +This differs from `tools/change` and `system-prompt/change`. Those two events are also unconsumed today, but they are plausible registry-change signals for future live tool/prompt UIs. LLM adapter registration is more of a boot-time implementation detail: adapters are not a user-visible palette and the real model-call interception seam is `llm/stream`. Keeping an adapter-change event with no listener repeats the [drop-the-dead-summary](2026-06-19-drop-mutable-session-summary.md) pattern at a smaller scale. The event is not free. `registerAdapter()` yields its rollback disposer before emitting `llm/adapter-change` so a throwing listener unwinds the mutation instead of leaking an adapter entry, and the package carries tests for that listener-throw path. That defensive ordering protects a failure mode only tests can trigger. ## Decision -Only `llm/adapter-change` is removed: the declaration in `dsh-llm`'s `interface Events`, the `ctx.emit('llm/adapter-change')` calls, and the "Emits `llm/adapter-change` on registration and disposal" sentence in `LlmService.registerAdapter`'s JSDoc. `registerAdapter()`'s effect generator keeps the mutation and rollback disposer for HMR/disposal but sheds the listener-throw rollback ordering that existed only for the removed event. The adapter-disposer test asserts the returned disposer removes the adapter without subscribing to the event; the listener-throw rollback test is gone with its subject. The event taxonomy in [docs/architecture.md](../../../architecture.md) and [packages/llm/llm/README.md](../../../../packages/llm/llm/README.md) is updated in the same change. +Only `llm/adapter-change` is removed: the declaration in `dsh-llm`'s `interface Events`, the `ctx.emit('llm/adapter-change')` calls, and the "Emits `llm/adapter-change` on registration and disposal" sentence in `LlmService.registerAdapter`'s JSDoc. `registerAdapter()`'s effect generator keeps the mutation and rollback disposer for HMR/disposal but sheds the listener-throw rollback ordering that existed only for the removed event. The adapter-disposer test asserts the returned disposer removes the adapter without subscribing to the event; the listener-throw rollback test is gone with its subject. The event taxonomy in [docs/architecture.md](../../../../docs/architecture.md) and [packages/llm/llm/README.md](../../../../packages/llm/llm/README.md) is updated in the same change. ## Alternatives considered ### Why not remove every registry change event? -A microkernel where registries announce mutations is a coherent convention. `tools/change` and `system-prompt/change` may become useful when a UI can live-refresh available tools or prompt sections. This RFC leaves that convention intact where it has a plausible user-facing consumer and cuts only the adapter-change event whose current and likely future consumer is unclear. +A microkernel where registries announce mutations is a coherent convention. `tools/change` and `system-prompt/change` may become useful when a UI can live-refresh available tools or prompt sections. This Agent Note leaves that convention intact where it has a plausible user-facing consumer and cuts only the adapter-change event whose current and likely future consumer is unclear. If an LLM adapter browser or dynamic model-picker needs this signal later, reintroduce it with that consumer and a clearer payload than "something changed." diff --git a/docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md similarity index 89% rename from docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md rename to .agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md index 3a5dfcda26..b482a444b5 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md @@ -1,4 +1,4 @@ -# RFC: Drop unconsumed assembled LLM convenience surfaces +# Agent Note: Drop unconsumed assembled LLM convenience surfaces Status: implemented @@ -12,7 +12,7 @@ Status: implemented The only production consumer of the LLM service is the agent loop, and it uses `stream()` exclusively — feeding raw chunks through its own `BlockAssembler` so it can log chunks for replay fidelity while assembling in parallel ([packages/core/agent-loop/src/loop.ts](../../../../packages/core/agent-loop/src/loop.ts), the `ctx.llm.stream(req)` step). Grepping `streamBlocks` and `ctx.llm.generate` across `packages/*/src` and `examples/*/src` finds no production callers. The references are the service methods, docs, and tests; adapter tests use `generate()` as a convenient driver, but they can hand-drain `stream()` through the same assembler helper without preserving a public production API. -This is the [drop-mutable-session-summary](../../implemented/simplification/2026-06-19-drop-mutable-session-summary.md) pattern: assembled-view APIs with tested contracts, consumed by tests rather than production. They were built speculatively for consumers that do not care about token-level deltas, but the one real consumer cares about deltas precisely so it can persist high-fidelity replay data. +This is the [drop-mutable-session-summary](2026-06-19-drop-mutable-session-summary.md) pattern: assembled-view APIs with tested contracts, consumed by tests rather than production. They were built speculatively for consumers that do not care about token-level deltas, but the one real consumer cares about deltas precisely so it can persist high-fidelity replay data. `streamBlocks()` drags a dedicated slice of `BlockAssembler` behind it: `flushReady()` and `flushRemaining()` ([packages/llm/llm/src/assembler.ts:138-168](../../../../packages/llm/llm/src/assembler.ts)) plus the `flushed` cursor field exist only to support incremental in-order yield. `generate()` drags `GenerateResult`, `BlockAssembler.result()`, and the `llm/generate` waterfall as a second interception surface over the same underlying stream. The loop's assembler usage is `push()` / `message()` / `usage` / `finish` — not streaming flush or one-shot service assembly. diff --git a/docs/rfc/implemented/simplification/2026-06-20-prune-dead-seam-methods.md b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md similarity index 77% rename from docs/rfc/implemented/simplification/2026-06-20-prune-dead-seam-methods.md rename to .agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md index ce16ff2ee2..782ffe891e 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-prune-dead-seam-methods.md +++ b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md @@ -1,25 +1,25 @@ -# RFC: Prune dead methods from the persistence seam +# Agent Note: Prune dead methods from the persistence seam Status: implemented -> **Implementation note:** Only `SessionPersistence.has()` and `.delete()` were removed. `BashExecutor.get()` and `.list()` remain because removing their one-line lookup surface required substantially more completion-tracking machinery in consumers. Their id branding is covered by the [branded-ids RFC](../architecture/2026-06-20-branded-ids.md). +> **Implementation note:** Only `SessionPersistence.has()` and `.delete()` were removed. `BashExecutor.get()` and `.list()` remain because removing their one-line lookup surface required substantially more completion-tracking machinery in consumers. Their id branding is covered by the [branded-ids Agent Note](../architecture/2026-06-20-branded-ids.md). ## Problem -A capability seam ([interface / implementation / consumer](../../implemented/architecture/2026-06-13-capability-seams.md)) carries abstract methods that no consumer calls. The seam exists to let implementations and consumers evolve independently — but a method no consumer programs against is not a seam, it is speculative surface every implementation must still implement and test. +A capability seam ([interface / implementation / consumer](../architecture/2026-06-13-capability-seams.md)) carries abstract methods that no consumer calls. The seam exists to let implementations and consumers evolve independently — but a method no consumer programs against is not a seam, it is speculative surface every implementation must still implement and test. ### `SessionPersistence.has()` and `.delete()` The abstract service declared its operations beyond create/append: `load`, `list`, `has`, `delete`. Production consumers of `ctx.sessionPersistence` use only two: the agent-loop resume path calls `load()` ([packages/core/agent-loop/src/index.ts:176](../../../../packages/core/agent-loop/src/index.ts)), and the ACP bridge calls `list()` for `session/list` ([packages/ui/acp/src/index.ts:494](../../../../packages/ui/acp/src/index.ts)). Grepping every `sessionPersistence.*` / `persistence.*` use across `packages/*/src` and `examples/` finds no `has(` and no `delete(` on the service. The `.has(`/`.delete(` calls in `packages/ui/acp/src/index.ts` are on the in-memory `SessionStore` and a local `Set` of loading ids, not persistence. The only callers of `has`/`delete` were the contract suites and per-backend specs. -`has()` was not just unused — it was the most intricate branch in the shared coordinator: a tracked-vs-untracked dual-probe (`loadLive(id, cwd)` for a live-tracked session vs `loadStored(id)` for an untracked one) with a multi-line rationale. `delete()` dragged the `deleteStored` backend hook that every backend had to implement. This is the [drop-mutable-session-summary](../../implemented/simplification/2026-06-19-drop-mutable-session-summary.md) pattern: a contract test exercised both, but no shipping code asks "is this session persisted?" or removes one. +`has()` was not just unused — it was the most intricate branch in the shared coordinator: a tracked-vs-untracked dual-probe (`loadLive(id, cwd)` for a live-tracked session vs `loadStored(id)` for an untracked one) with a multi-line rationale. `delete()` dragged the `deleteStored` backend hook that every backend had to implement. This is the [drop-mutable-session-summary](2026-06-19-drop-mutable-session-summary.md) pattern: a contract test exercised both, but no shipping code asks "is this session persisted?" or removes one. ## Decision The methods nothing consumes are removed — from the abstract seam, the implementation, and the contract/spec suites that existed only to exercise them: -- `SessionPersistence.has()` / `.delete()` are gone: the abstract declarations, the coordinator's `has`/`delete`/`deleteCore`, and the `PersistenceBackend.deleteStored` hook (jsonl + sqlite each implemented `deleteStored` only to satisfy the hook — those implementations went too). The backends are the [dual-backend](../../implemented/architecture/2026-06-14-session-persistence.md) design and otherwise out of scope; removing a hook they implemented for no consumer is part of removing the hook, not a backend redesign. -- Every doc and source-comment reference is updated to the surviving four-method, `list()`-only contract — not only literal `has(`/`delete(`/`deleteStored` spellings but `{@link has}`/`{@link delete}` JSDoc links and "six public methods" counts — across the seam and backend READMEs, [docs/architecture.md](../../../architecture.md), the [session-persistence](../../implemented/architecture/2026-06-14-session-persistence.md) and [write-coordinator](../../implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md) RFCs, and the coordinator/backends JSDoc. +- `SessionPersistence.has()` / `.delete()` are gone: the abstract declarations, the coordinator's `has`/`delete`/`deleteCore`, and the `PersistenceBackend.deleteStored` hook (jsonl + sqlite each implemented `deleteStored` only to satisfy the hook — those implementations went too). The backends are the [dual-backend](../architecture/2026-06-14-session-persistence.md) design and otherwise out of scope; removing a hook they implemented for no consumer is part of removing the hook, not a backend redesign. +- Every doc and source-comment reference is updated to the surviving four-method, `list()`-only contract — not only literal `has(`/`delete(`/`deleteStored` spellings but `{@link has}`/`{@link delete}` JSDoc links and "six public methods" counts — across the seam and backend READMEs, [docs/architecture.md](../../../../docs/architecture.md), the [session-persistence](../architecture/2026-06-14-session-persistence.md) and [write-coordinator](../architecture/2026-06-18-shared-persistence-write-coordinator.md) Agent Notes, and the coordinator/backends JSDoc. ## Alternatives considered diff --git a/docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md similarity index 92% rename from docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md rename to .agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md index 7ed7d10211..c85f644853 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md +++ b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md @@ -1,4 +1,4 @@ -# RFC: Keep one public stop primitive +# Agent Note: Keep one public stop primitive Status: implemented @@ -34,4 +34,4 @@ A future plugin cannot abort only the current model/tool step while preserving q ## Related -This RFC only removes the redundant stop verb. Mid-turn steering remains an intentional message path; quiescence observation remains via `whenIdle()`. The resulting public surface is `send()`, `steer()`, `inject()`, `cancel()`, `whenIdle()`, status, options, session, and identity. +This Agent Note only removes the redundant stop verb. Mid-turn steering remains an intentional message path; quiescence observation remains via `whenIdle()`. The resulting public surface is `send()`, `steer()`, `inject()`, `cancel()`, `whenIdle()`, status, options, session, and identity. diff --git a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md similarity index 82% rename from docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md rename to .agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md index f4b49281ea..910eb46e92 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md +++ b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md @@ -1,4 +1,4 @@ -# RFC: Stop mirroring durable boundaries as agent events +# Agent Note: Stop mirroring durable boundaries as agent events Status: implemented @@ -6,7 +6,7 @@ Status: implemented removed; `agent/steering` and `agent/stream-chunk` were RETAINED here (they are not durable-boundary mirrors — see "Scope: what is and isn't removed"). The original proposal bundled `agent/steering` into the removal; keeping it - out kept this RFC's scope to boundaries. Each retained event was later + out kept this Agent Note's scope to boundaries. Each retained event was later removed by its own decision — see [Stop mirroring the token stream as an agent event](2026-07-02-remove-stream-chunk-mirror.md) and [Remove the `agent/steering` mirror emit](2026-07-04-remove-agent-steering-mirror.md). --> @@ -23,7 +23,7 @@ Make `session/event` the single live boundary/transcript stream. Consumers that The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle at a boundary retains the live target object from `agent/created`/`agent/disposed` and compares its session directly; `dsh-ui-stdio` uses this to label the app-owned agent's `[main turn N]` header while other sessions render their durable id. The canonical record remains the event-sourced session log. -The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it reads `session/event` and retains only its live target object. +The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics Agent Note](../architecture/2026-06-30-event-domain-semantics.md); that Agent Note KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This Agent Note finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it reads `session/event` and retains only its live target object. ## Scope: what is and isn't removed @@ -37,8 +37,8 @@ RETAINED — NOT durable-boundary mirrors, so out of scope for this decision: ## Alternatives considered -- **Bundling `agent/steering` into the removal** — the original proposal's shape; narrowed out as scope creep: it mirrors the durable `steering/message` control record, not a boundary, and was removed by [its own later decision](2026-07-04-remove-agent-steering-mirror.md) (as was `agent/stream-chunk`, by [the stream-chunk-mirror RFC](2026-07-02-remove-stream-chunk-mirror.md)). -- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` plus its live target object instead. +- **Bundling `agent/steering` into the removal** — the original proposal's shape; narrowed out as scope creep: it mirrors the durable `steering/message` control record, not a boundary, and was removed by [its own later decision](2026-07-04-remove-agent-steering-mirror.md) (as was `agent/stream-chunk`, by [the stream-chunk-mirror Agent Note](2026-07-02-remove-stream-chunk-mirror.md)). +- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics Agent Note](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` plus its live target object instead. ## Consequences diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md similarity index 90% rename from docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md rename to .agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 9084befad5..a8a2c375b5 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -1,4 +1,4 @@ -# RFC: Unify the agent id and the session id +# Agent Note: Unify the agent id and the session id Status: implemented @@ -8,7 +8,7 @@ A live agent/session pair needs one identity for registry routing, event sourcin ACP uses the same value for both identities. Stdio and hooks also operate on the session event stream and need the corresponding live agent directly; no production path reattaches one live agent object to several sessions or drives one session through several agent ids. -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) uses one `AgentCreationTransaction` for create and resume, and agent/session entries share the same final-entry collision rule. A second identity would not represent separate liveness, rollback, or quiescence; it would only add API and translation state around the same transaction. +The [agent-scope runtime](../architecture/2026-07-12-agent-scope-runtime-design.md) uses one `AgentCreationTransaction` for create and resume, and agent/session entries share the same final-entry collision rule. A second identity would not represent separate liveness, rollback, or quiescence; it would only add API and translation state around the same transaction. Session identity likewise has one home in `Session.header.id`; `Session.id` is a derived accessor rather than independent state that needs duplicate validation. diff --git a/docs/rfc/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md similarity index 86% rename from docs/rfc/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md rename to .agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md index d2b4c6dc4f..3753fb803a 100644 --- a/docs/rfc/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md +++ b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md @@ -1,10 +1,10 @@ -# RFC: Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin +# Agent Note: Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin Status: implemented ## Problem -The filesystem capability from [filesystem-capability-seam](../../implemented/architecture/2026-06-17-filesystem-capability-seam.md) currently makes one abstract `FileSystem` service own two different jobs: +The filesystem capability from [filesystem-capability-seam](../architecture/2026-06-17-filesystem-capability-seam.md) currently makes one abstract `FileSystem` service own two different jobs: 1. **Provider operations** — resolving targets, stat/version metadata, text reads/streams, atomic writes, and guarded literal edits. 2. **Agent-facing policy** — line windows, literal edit semantics, and read-before-write/edit observed-state. @@ -13,7 +13,7 @@ That makes every future backend reimplement model-facing read semantics and obse This also creates a real UX dead-end: a windowed read records `view: partial`, and partial views cannot authorize `edit`. A model that reads lines 100-150 of a large file therefore cannot edit line 120 unless it first gets a `full` read, which may be impossible for a file past the read cap. Literal edit only needs freshness: the bytes being matched must still be from the version the model read. -The old RFC already deferred a separate `@deepseek-ai/dsh-fs-policy` package. This RFC builds that layer and keeps `ctx.fs` close to fsspec-style storage primitives (`info`/`cat`/`open`), without turning it into full fsspec. +The old Agent Note already deferred a separate `@deepseek-ai/dsh-fs-policy` package. This Agent Note builds that layer and keeps `ctx.fs` close to fsspec-style storage primitives (`info`/`cat`/`open`), without turning it into full fsspec. ## Decision @@ -28,7 +28,7 @@ provider dsh-fs-local local implementation of ctx.fs `dsh-tool-fs` keeps the same model-facing `read`/`write`/`edit` schemas. It is the executor: it injects `fs` (not a policy service) and reaches `ctx.fs` directly, owns read windowing, and dispatches the `fs/*` events so `dsh-fs-policy` can gate and record. -This RFC decided the four-layer split, the provider contract, and the freshness policy. The tool↔policy COUPLING was then refined by [the event-gate RFC](../architecture/2026-06-26-file-context-as-event-gate.md): `dsh-fs-policy` is a gate PLUGIN that participates through the `fs/*` events rather than a `ctx.fileContext` method service, so the tool is not method-coupled to it and read windowing + the fs I/O live in `dsh-tool-fs`. This document describes that landed event-gate shape; the provider's version guard is optional (omit = unconditional bare provider). +This Agent Note decided the four-layer split, the provider contract, and the freshness policy. The tool↔policy COUPLING was then refined by [the event-gate Agent Note](../architecture/2026-06-26-file-context-as-event-gate.md): `dsh-fs-policy` is a gate PLUGIN that participates through the `fs/*` events rather than a `ctx.fileContext` method service, so the tool is not method-coupled to it and read windowing + the fs I/O live in `dsh-tool-fs`. This document describes that landed event-gate shape; the provider's version guard is optional (omit = unconditional bare provider). ## Provider Contract @@ -63,11 +63,11 @@ type FsWriteIntent = This is a *text-storage* seam, deliberately half a level above byte-level fsspec (`cat`/`open` hand back raw bytes). UTF-8 decoding, binary/NUL rejection, guarded full-file writes, and guarded literal text edits live in the provider so the policy layer never touches raw bytes, reimplements cross-chunk decoding, or separates stale checks from the mutation critical section. Model-facing concepts still stay out of the provider: no line windows, numbered lines, rendered footers, or observed-state store leak down. -Deleted from `dsh-fs`: `readPage`, `FsExpectation`, `FsView`, `FsStateSource`, `FsReadRequest`, `FsTextLine`, line/window constants, `formatReadBody`, and the observed-state `WeakMap`. `applyEdit` is replaced by the narrower provider primitive `editText`, whose contract is version-guarded literal text mutation rather than policy-layer read authorization. The `FS_PARTIAL_OBSERVATION` code also leaves the `FsErrorCode` taxonomy: freshness authorization has no partial/full distinction, so nothing can raise it. `FsTargetKey` and `FsVersion` become branded opaque ids under the existing [branded-ids RFC](../../implemented/architecture/2026-06-20-branded-ids.md). +Deleted from `dsh-fs`: `readPage`, `FsExpectation`, `FsView`, `FsStateSource`, `FsReadRequest`, `FsTextLine`, line/window constants, `formatReadBody`, and the observed-state `WeakMap`. `applyEdit` is replaced by the narrower provider primitive `editText`, whose contract is version-guarded literal text mutation rather than policy-layer read authorization. The `FS_PARTIAL_OBSERVATION` code also leaves the `FsErrorCode` taxonomy: freshness authorization has no partial/full distinction, so nothing can raise it. `FsTargetKey` and `FsVersion` become branded opaque ids under the existing [branded-ids Agent Note](../architecture/2026-06-20-branded-ids.md). ## Policy Contract -`@deepseek-ai/dsh-fs-policy` is a plugin, not a service: it registers no `ctx.*` key and injects nothing. It owns the write/edit freshness policy and observed-state that do not belong on the `FileSystem` provider base class (where a sandboxed/remote backend would otherwise inherit model-facing observation policy it has no business carrying). It contributes that policy through the `fs/*` event gate the executor dispatches. (This RFC originally proposed a concrete `ctx.fileContext` service with `read`/`write`/`edit` methods; [the event-gate RFC](../architecture/2026-06-26-file-context-as-event-gate.md) refined it into the plugin described here so the tool is never method-coupled to the policy.) +`@deepseek-ai/dsh-fs-policy` is a plugin, not a service: it registers no `ctx.*` key and injects nothing. It owns the write/edit freshness policy and observed-state that do not belong on the `FileSystem` provider base class (where a sandboxed/remote backend would otherwise inherit model-facing observation policy it has no business carrying). It contributes that policy through the `fs/*` event gate the executor dispatches. (This Agent Note originally proposed a concrete `ctx.fileContext` service with `read`/`write`/`edit` methods; [the event-gate Agent Note](../architecture/2026-06-26-file-context-as-event-gate.md) refined it into the plugin described here so the tool is never method-coupled to the policy.) Observed state lives here as `WeakMap<owner, Map<targetKey, FsVersion>>`. An entry exists iff the owner has read, written, OR edited that target (every success emits `fs/observed`), so its presence *is* the prior-observation record — there is no separate `hasRead` flag. The owner is derived structurally from the opaque event actor (`{ agent?: { session? } }`), a shape that lives in `dsh-fs-policy`, not `dsh-fs`. @@ -97,7 +97,7 @@ Cross-process writes are best-effort freshness plus atomic replacement: `mtime:s ## Supersedes -This RFC reverses two decisions from [filesystem-capability-seam](../../implemented/architecture/2026-06-17-filesystem-capability-seam.md) and narrows a third: +This Agent Note reverses two decisions from [filesystem-capability-seam](../architecture/2026-06-17-filesystem-capability-seam.md) and narrows a third: - Read-before-write/edit policy moves out of `ctx.fs` and into the `dsh-fs-policy` plugin (on the `fs/*` event gate). - Text reads no longer return backend-numbered line records or `full`/`partial` views; authorization is based on version freshness, so a windowed read can authorize edit when the file is unchanged. @@ -111,12 +111,12 @@ It keeps the interface/implementation/consumer discipline, consumer-never-import ## Later extension -The seam was later extended with direct directory listing by [Add direct directory listing to the filesystem seam](../architecture/2026-07-03-filesystem-directory-listing-seam.md). That follow-up is tracked separately so this RFC's acceptance criteria continue to describe the fsspec-style refit that originally shipped. +The seam was later extended with direct directory listing by [Add direct directory listing to the filesystem seam](../architecture/2026-07-03-filesystem-directory-listing-seam.md). That follow-up is tracked separately so this Agent Note's acceptance criteria continue to describe the fsspec-style refit that originally shipped. ## Alternatives considered - **Byte-level fsspec (`cat`/`open` handing back raw bytes)** — rejected: the seam is deliberately text-storage, half a level up, so UTF-8 decoding, binary/NUL rejection, and guarded text mutations live once in the provider and the policy layer never touches raw bytes or separates stale checks from the mutation critical section. -- **A concrete `ctx.fileContext` method service** — this RFC's original policy shape; reworked by [the event-gate RFC](../architecture/2026-06-26-file-context-as-event-gate.md) into the gate plugin, so the tool is never method-coupled to the policy. +- **A concrete `ctx.fileContext` method service** — this Agent Note's original policy shape; reworked by [the event-gate Agent Note](../architecture/2026-06-26-file-context-as-event-gate.md) into the gate plugin, so the tool is never method-coupled to the policy. - **Keeping `readPage` and `full`/`partial` view authorization on the provider** — the pre-refit shape the Supersedes section reverses: view completeness is not what edit safety needs, version freshness is, and the view rule made large files past the read cap impossible to edit. ## Consequences diff --git a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md similarity index 88% rename from docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md rename to .agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md index 6ca85b3d16..c79202b95a 100644 --- a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md +++ b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md @@ -1,4 +1,4 @@ -# RFC: Stop mirroring the token stream as an agent event +# Agent Note: Stop mirroring the token stream as an agent event Status: implemented @@ -17,7 +17,7 @@ ctx.emit('agent/stream-chunk', agent, turn, step, chunk) // ← the mirror The only thing the emit added over the session event was the live `Agent` handle, and the sole consumer discarded it (its handler signature was `(_agent, _turn, _step, chunk)`). -This is the same duplication the [boundary-mirror removal](2026-06-20-remove-agent-boundary-mirror-events.md) eliminated for turn/step boundaries: a consumer had two sources of truth for one durable fact, and every change had to touch both. That RFC deferred the chunk stream ("`assistant/chunk` persistence remains load-bearing, so the chunk stream could later be evaluated as a mirror, but that is a separate decision") rather than bundling it in. This RFC is that separate decision. +This is the same duplication the [boundary-mirror removal](2026-06-20-remove-agent-boundary-mirror-events.md) eliminated for turn/step boundaries: a consumer had two sources of truth for one durable fact, and every change had to touch both. That Agent Note deferred the chunk stream ("`assistant/chunk` persistence remains load-bearing, so the chunk stream could later be evaluated as a mirror, but that is a separate decision") rather than bundling it in. This Agent Note is that separate decision. The premise the deferral hinged on is settled: chunk persistence is authoritative and staying. The proposal to stop persisting chunks and keep only a transient live stream event was [rejected](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.md) — high-fidelity replay, partial failed streams, and snapshot replay all depend on the persisted `assistant/chunk` feed. So `assistant/chunk` on `session/event` is the durable, load-bearing token stream, and `agent/stream-chunk` is a pure redundant mirror of it. @@ -32,7 +32,7 @@ Remove `agent/stream-chunk` from the agent event taxonomy. The token stream is r Removed: `agent/stream-chunk`. Not touched: -- `assistant/chunk` (the durable session event) — the authoritative token stream, kept exactly as-is. This RFC removes the LIVE MIRROR, not the persistence (the persistence-removal proposal was separately rejected — see above). +- `assistant/chunk` (the durable session event) — the authoritative token stream, kept exactly as-is. This Agent Note removes the LIVE MIRROR, not the persistence (the persistence-removal proposal was separately rejected — see above). - `agent/steering` — not touched by THIS decision (a control signal, not the token stream). Its durable twin is `steering/message`, and the mirror emit was removed by its own follow-up: [Remove the `agent/steering` mirror emit](2026-07-04-remove-agent-steering-mirror.md). - `agent/status`, `agent/error`, `agent/created`/`agent/disposed`, `agent/queued`, `agent/session-start` — lifecycle/control events that are not transcript data and have no durable duplicate. diff --git a/docs/rfc/implemented/simplification/2026-07-04-drop-image-content-block.md b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md similarity index 87% rename from docs/rfc/implemented/simplification/2026-07-04-drop-image-content-block.md rename to .agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md index 73645e8fda..df63f2a78f 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-drop-image-content-block.md +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md @@ -1,4 +1,4 @@ -# RFC: Drop the `image` content block until a path can honor it +# Agent Note: Drop the `image` content block until a path can honor it Status: implemented @@ -20,7 +20,7 @@ The recorded fallback, had review landed on keeping the slot: keep `ImageBlock` ## Verification -No harness `ImageBlock` is constructed outside RFC records. ACP's independent inbound-image rejection remains tested, while adapter, codec, and compaction default branches are covered with plugin-defined block types. +No harness `ImageBlock` is constructed outside Agent Note records. ACP's independent inbound-image rejection remains tested, while adapter, codec, and compaction default branches are covered with plugin-defined block types. ## Consequences diff --git a/docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md similarity index 71% rename from docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md rename to .agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md index 95a5a487b5..dadab43f76 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md @@ -1,4 +1,4 @@ -# RFC: Drop `GenerateOptions.prefill` and `ToolSchema.strict` — request knobs with no working end-to-end path +# Agent Note: Drop `GenerateOptions.prefill` and `ToolSchema.strict` — request knobs with no working end-to-end path Status: implemented @@ -13,10 +13,10 @@ Both knobs were adapter-symmetric, so removal shed them from both twins together ## Decision -- `prefill` is removed from `GenerateOptions`, along with both adapters' UNSUPPORTED guards, the tests pinning the throws, the paste line in [core.md](../../../core-data-structures/core.md), and the adapter README rows documenting the rejection. The cookbook's UNSUPPORTED guidance ([adding-an-llm-adapter.md](../../../cookbook/adding-an-llm-adapter.md)) states the rule generically — a `GenerateOptions` field your provider cannot honor throws `LlmError(..., 'UNSUPPORTED')` — instead of using prefill as the example. The [content-block vocabulary RFC](../architecture/2026-06-11-content-block-vocabulary.md)'s consequences record prefill as producer-gated rather than as having a home, per [implemented/AGENTS.md](../AGENTS.md). +- `prefill` is removed from `GenerateOptions`, along with both adapters' UNSUPPORTED guards, the tests pinning the throws, the paste line in [core.md](../../../../docs/core-data-structures/core.md), and the adapter README rows documenting the rejection. The cookbook's UNSUPPORTED guidance ([adding-an-llm-adapter.md](../../../../docs/cookbook/adding-an-llm-adapter.md)) states the rule generically — a `GenerateOptions` field your provider cannot honor throws `LlmError(..., 'UNSUPPORTED')` — instead of using prefill as the example. The [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)'s consequences record prefill as producer-gated rather than as having a home, per [implemented/AGENTS.md](../AGENTS.md). - `strict` is removed from `ToolSchema`, `DefineToolOptions`, `defineTool`, the `schemas()` allowlist, the deepseek serializer branch and its wire-type field, and the tool-catalog renderer's `Strict:` row. The pi-ai payload fixup is simplified to the unconditional scrub of pi-ai's own per-tool strict default (pi-ai stamps `strict: false` on every serialized tool; the hand-rolled twin sends no such field, so the scrub survives for wire parity, pinned by its serializer test). The setter tests and the core.md paste line are gone; both `GenerateOptions` and `ToolSchema` keep their rows in `scripts/type-equiv.manifest.json`, since each type survives minus a field. -This RFC deliberately does NOT touch `temperature`, `stop`, or `maxTokens`: those are honored end-to-end by both adapters and are the natural first targets of a request-mutating hook plugin on `agent/request`. +This Agent Note deliberately does NOT touch `temperature`, `stop`, or `maxTokens`: those are honored end-to-end by both adapters and are the natural first targets of a request-mutating hook plugin on `agent/request`. ## Alternatives considered @@ -26,7 +26,7 @@ This RFC deliberately does NOT touch `temperature`, `stop`, or `maxTokens`: thos ## Verification -`rg prefill` returns only RFC records (this one and the [content-block vocabulary RFC](../architecture/2026-06-11-content-block-vocabulary.md)'s producer-gated consequence); a tool-schema-scoped `rg strict` returns only this RFC, the surviving pi-ai scrub, and unrelated prose such as `strictEqual`. Both adapters' contract tests pass without the guards, and the pi-ai fixup still scrubs the library's strict default — wire parity pinned by its serializer tests. +`rg prefill` returns only Agent Note records (this one and the [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)'s producer-gated consequence); a tool-schema-scoped `rg strict` returns only this Agent Note, the surviving pi-ai scrub, and unrelated prose such as `strictEqual`. Both adapters' contract tests pass without the guards, and the pi-ai fixup still scrubs the library's strict default — wire parity pinned by its serializer tests. ## Consequences diff --git a/docs/rfc/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md similarity index 52% rename from docs/rfc/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md rename to .agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md index 35868be2fd..80faa2ac07 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md @@ -1,4 +1,4 @@ -# RFC: Drop the unconsumed web observation surface — the `providers-change` event and the status methods +# Agent Note: Drop the unconsumed web observation surface — the `providers-change` event and the status methods Status: implemented @@ -7,11 +7,11 @@ Status: implemented `WebService` exposes an observation surface no production code observes: - **`web/providers-change`** (`packages/web/web/src/index.ts`) is declared and emitted on every provider registration and disposal, and each registration effect's rollback yield is ordered BEFORE the emit solely so a throwing change listener unwinds the registration. No listener exists outside the package's own two unit tests (one of which exists to pin that rollback ordering). -- **`searchStatus()` / `fetchStatus()` and the `WebCapabilityStatus` union** (same package) have zero production callers: `dsh-tool-web` executes directly through `ctx.web.search()`/`fetch()` and surfaces unavailability as the structured `WebError` codes the seam throws at execution time (`packages/web/tool-web/src/search.ts`, `packages/web/tool-web/src/fetch.ts`); the only status callers are the web packages' own tests. The prose in `packages/web/tool-web/README.md` and [architecture.md](../../../architecture.md) claims the tool "reads only the aggregated `searchStatus()`/`fetchStatus()`" — drift that survives only because nothing checks prose against call sites. +- **`searchStatus()` / `fetchStatus()` and the `WebCapabilityStatus` union** (same package) have zero production callers: `dsh-tool-web` executes directly through `ctx.web.search()`/`fetch()` and surfaces unavailability as the structured `WebError` codes the seam throws at execution time (`packages/web/tool-web/src/search.ts`, `packages/web/tool-web/src/fetch.ts`); the only status callers are the web packages' own tests. The prose in `packages/web/tool-web/README.md` and [architecture.md](../../../../docs/architecture.md) claims the tool "reads only the aggregated `searchStatus()`/`fetchStatus()`" — drift that survives only because nothing checks prose against call sites. The seam's own design starves both surfaces of consumers: tool registration follows product ENABLEMENT, not provider availability (`packages/web/tool-web/src/index.ts`), and provider selection resolves at execution time, never cached — so there is no cache to invalidate, no registration set to recompute, and no caller that needs an availability probe distinct from executing and routing the structured error. HMR cleanup is carried by the effect disposers themselves. -This mirrors [drop the unconsumed `llm/adapter-change` event](../../implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md), which removed the same notification shape, the same rollback-before-emit machinery, and the same listener-throw test from `LlmService`. That RFC's keep/cut criterion — keep `tools/change` for its plausible user-facing tool-list consumer, cut the boot-time backend-registry signal — puts a web-provider registry squarely on the cut side; the status methods are the same judgment applied to a pull surface instead of a push one. +This mirrors [drop the unconsumed `llm/adapter-change` event](2026-06-20-drop-unconsumed-llm-adapter-change-event.md), which removed the same notification shape, the same rollback-before-emit machinery, and the same listener-throw test from `LlmService`. That Agent Note's keep/cut criterion — keep `tools/change` for its plausible user-facing tool-list consumer, cut the boot-time backend-registry signal — puts a web-provider registry squarely on the cut side; the status methods are the same judgment applied to a pull surface instead of a push one. ## Decision @@ -21,11 +21,11 @@ Remove the registry-change event, aggregated status methods and type, and their ### Why not keep it? -The web seam RFC specified both deliberately — the event as a minimal HMR-visibility signal, the status methods as the tool's aggregated diagnostics — and a future provider-status panel is imaginable. But the same RFC's other choices starved them: derived-on-call selection and enablement-based registration leave no consumer that CAN need either, the shipped tool demonstrates the real pattern (execute and route the structured error), and the drifted README sentence shows the promised consumer never materialized. Per AGENTS.md "RFCs are proposals, not golden truth", these are the parts of that proposal the code has since shown to over-reach; a future observer reintroduces the smallest signal or query it actually consumes, shaped by that consumer. +The web seam Agent Note specified both deliberately — the event as a minimal HMR-visibility signal, the status methods as the tool's aggregated diagnostics — and a future provider-status panel is imaginable. But the same Agent Note's other choices starved them: derived-on-call selection and enablement-based registration leave no consumer that CAN need either, the shipped tool demonstrates the real pattern (execute and route the structured error), and the drifted README sentence shows the promised consumer never materialized. Per AGENTS.md "Agent Notes are proposals, not golden truth", these are the parts of that proposal the code has since shown to over-reach; a future observer reintroduces the smallest signal or query it actually consumes, shaped by that consumer. ## Verification -No `providers-change`, `searchStatus`, `fetchStatus`, or `WebCapabilityStatus` spelling survives outside RFC history; the catalog is fresh (`verify-cordis-catalog` green); registration/disposal HMR-safety tests prove cleanup through execution behavior; and the tool-web README plus the architecture paragraph describe the execution-time error-routing contract the tool actually has. +No `providers-change`, `searchStatus`, `fetchStatus`, or `WebCapabilityStatus` spelling survives outside Agent Note history; the catalog is fresh (`verify-cordis-catalog` green); registration/disposal HMR-safety tests prove cleanup through execution behavior; and the tool-web README plus the architecture paragraph describe the execution-time error-routing contract the tool actually has. ## Consequences diff --git a/docs/rfc/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md similarity index 98% rename from docs/rfc/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md rename to .agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md index 43f35ee770..bde3efcc75 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md +++ b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md @@ -1,4 +1,4 @@ -# RFC: Fold the stdio UI helper into the stdio app +# Agent Note: Fold the stdio UI helper into the stdio app Status: implemented diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md new file mode 100644 index 0000000000..aa61e859d2 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md @@ -0,0 +1,31 @@ +# Agent Note: Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger) + +Status: implemented + +## Problem + +The merge-extensible vocabulary maps are designed to grow by declaration merging, and the codebase already states the admission policy on `TurnEndReasonMap` (`packages/core/session/src/types.ts`): a variant like `refusal` is "deliberately omitted until" an adapter or loop first emits it. Three declared vocabulary items violated that policy — each had no producer and no consumer, and two had not even a test: + +- **`CacheHint` and its `cache?: CacheHint` block fields** on `TextBlock`/`ToolResultBlock` (`packages/llm/llm/src/types.ts`; the image block carried a third such field, which left with it — see [the drop-image Agent Note](2026-07-04-drop-image-content-block.md)). Nothing constructed a block with `cache:` anywhere — src, tests, and doc pastes all came up empty — and neither adapter read `.cache`: DeepSeek prompt caching is automatic, so the adapters map `prompt_cache_hit_tokens` OUT of responses without ever sending a hint IN. This was Anthropic-style `cache_control` surface with no provider that could honor it. +- **`MessageSourceMap.agent`** (`{ kind: 'agent'; agentId: string }`, same file). Zero constructors, tests included. Its intended producer shipped without it: the subagent backends send the parent's prompt to the child with no `source`, so it logs as `{ kind: 'user' }`, and the generic envelope renderer interpolates `source.kind` without ever routing on it. +- **`TurnTriggerMap.continuation`** (`packages/core/session/src/types.ts`). The loop structurally cannot emit it — continuation happens *within* a turn as further steps, never as a new turn — and it constructs only `message` and `injection` triggers. The only writer was one hand-built test fixture needing an arbitrary non-message trigger (`packages/support/llm-replay/tests/llm-replay.spec.ts`), which an `injection` trigger serves equally; the only production trigger reader, the ACP bridge, filters on `kind === 'message'`. + +## Decision + +`CacheHint`, its `cache?` block fields, the `agent` message-source variant, and the `continuation` turn-trigger variant are deleted: the shipped vocabulary carries none of them. The llm-replay fixture uses an `injection` trigger (any non-`message` trigger serves its purpose). The type-equiv pastes in [core.md](../../../../docs/core-data-structures/core.md) and [session.md](../../../../docs/core-data-structures/session.md) match the pruned maps — both symbols keep their rows in `scripts/type-equiv.manifest.json`, since each map survives minus a member — and the [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)'s consequences record cache hints as producer-gated rather than as having a home, per [implemented/AGENTS.md](../AGENTS.md). + +Each variant returns the day it gains a real producer, exactly as the maps are designed to grow: a caching feature re-adds `cache` together with the adapter that transmits it; subagent attribution re-adds `agent` together with the backend that stamps it and a consumer that routes on it; an auto-continue feature that genuinely starts new turns re-adds `continuation` with the plugin that emits it. + +## Alternatives considered + +### Why not keep them? + +The [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md) listed "cache hints … have a home" as a design consequence, and reserved slots do advertise intent. But an empty slot is contract surface every implementation and consumer must consider (must my adapter honor `cache`? must my renderer route `agent` sources?), and the sibling map's own JSDoc already rejects reservation-without-emitter — `refusal` and `max_turn_requests` are named as variants to add *when something first emits them*, not declared in advance. Holding already-declared dead variants to the same standard makes the vocabulary mean something: if it is in the map, something produces it. + +## Verification + +`rg` for `CacheHint`, the `agent` message-source spelling, and the `continuation` trigger spelling returns only Agent Note records (this one, and [the drop-image Agent Note](2026-07-04-drop-image-content-block.md)'s account of the image block's own `cache` field); the llm-replay fixture asserts the same replay behavior with an `injection` trigger; the core-data-structures pastes and the type-equiv manifest are in sync. + +## Consequences + +Nothing operational changed — nothing could construct these values. The mirror-event removals ([the boundary-mirror Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md), [the stream-chunk Agent Note](2026-07-02-remove-stream-chunk-mirror.md)) touch only transient `agent/*` events, never the durable vocabulary, so there is no collision. Elsewhere the admission policy already holds: `rejected`, `prompt/blocked`, and `hook/invoked`/`hook/result` each have live producers — this Agent Note extends the same bar to the three variants that lacked one. The image block's own `cache?` field belongs to [the drop-image Agent Note](2026-07-04-drop-image-content-block.md), which removed it together with the block; this Agent Note covers the two fields on the block types that remain. diff --git a/docs/rfc/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md similarity index 94% rename from docs/rfc/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md rename to .agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md index 0de8f5732c..97652ef50c 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md @@ -1,4 +1,4 @@ -# RFC: Prune write-only fields and a dead routing knob from the fs seam +# Agent Note: Prune write-only fields and a dead routing knob from the fs seam Status: implemented @@ -13,7 +13,7 @@ The [fs seam split](2026-06-26-fsspec-style-fs-seam.md) moved read routing and p ## Decision -Delete the fs-local constant, its re-export, and the `streamMinSize` knob (the remaining `FsIoInternals` knobs are genuinely used by the atomic-write tests); drop `inputPath` from `FsTarget`; shrink `FsEditOutcome` to `{ version, before, after }` and pass `replaceAll` to `formatEditOutput` from the parsed args; drop `limit`/`version` from `FileReadOutcome`. The [filesystem.md](../../../core-data-structures/filesystem.md) pastes, `packages/fs/fs/README.md`, and the test fakes that had to fabricate the removed fields shrink with the types. +Delete the fs-local constant, its re-export, and the `streamMinSize` knob (the remaining `FsIoInternals` knobs are genuinely used by the atomic-write tests); drop `inputPath` from `FsTarget`; shrink `FsEditOutcome` to `{ version, before, after }` and pass `replaceAll` to `formatEditOutput` from the parsed args; drop `limit`/`version` from `FileReadOutcome`. The [filesystem.md](../../../../docs/core-data-structures/filesystem.md) pastes, `packages/fs/fs/README.md`, and the test fakes that had to fabricate the removed fields shrink with the types. ## Alternatives considered diff --git a/docs/rfc/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md similarity index 62% rename from docs/rfc/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md rename to .agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md index 6591aab8f3..ebfc774792 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md +++ b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md @@ -1,4 +1,4 @@ -# RFC: Remove the `agent/steering` mirror emit +# Agent Note: Remove the `agent/steering` mirror emit Status: implemented @@ -12,19 +12,19 @@ Steering carries real production traffic — the hook bridges' turn-continuation ## Decision -`agent/steering` is removed from the agent event taxonomy: the declaration in `packages/core/agent/src/types.ts` (and its mention in the live-events JSDoc list there), the emit in `drainSteering` (whose then-unused `ctx` parameter went with it), the row in `packages/core/agent/README.md`, and the emit line in the loop-pseudocode blocks (the `packages/core/agent-loop/src/loop.ts` module doc and [architecture.md](../../../architecture.md)); the cordis catalog is regenerated without it. The one regression test pins source preservation on the durable `steering/message` event — the fact it pins lives on the log. +`agent/steering` is removed from the agent event taxonomy: the declaration in `packages/core/agent/src/types.ts` (and its mention in the live-events JSDoc list there), the emit in `drainSteering` (whose then-unused `ctx` parameter went with it), the row in `packages/core/agent/README.md`, and the emit line in the loop-pseudocode blocks (the `packages/core/agent-loop/src/loop.ts` module doc and [architecture.md](../../../../docs/architecture.md)); the cordis catalog is regenerated without it. The one regression test pins source preservation on the durable `steering/message` event — the fact it pins lives on the log. -Three implemented RFCs stated the retention, and each is amended per [implemented/AGENTS.md](../AGENTS.md) to point here as the record of the removal: the [boundary RFC](2026-06-20-remove-agent-boundary-mirror-events.md)'s retained-list entry, the [stream-chunk RFC](2026-07-02-remove-stream-chunk-mirror.md)'s scope clause, and the [event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s transient-emit enumeration. +Three implemented Agent Notes stated the retention, and each is amended per [implemented/AGENTS.md](../AGENTS.md) to point here as the record of the removal: the [boundary Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md)'s retained-list entry, the [stream-chunk Agent Note](2026-07-02-remove-stream-chunk-mirror.md)'s scope clause, and the [event-domain-semantics Agent Note](../architecture/2026-06-30-event-domain-semantics.md)'s transient-emit enumeration. ## Alternatives considered ### Why not keep it? -"It is a control signal, not a boundary" — but the taxonomy's operative distinction is mirrored-vs-live-only, not control-vs-boundary, and this event mirrored. A consumer that wants enqueue-time notification has `agent/queued` (with its steering flag); a consumer that wants drain-time notification is by definition asking for the moment `steering/message` is appended, which `session/event` delivers with the same payload plus durability. The rejected [retire-mid-turn-steering RFC](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md) defended the steering *capability* — `steer()`, the durable event, continuation forcing — all of which this removal keeps untouched. +"It is a control signal, not a boundary" — but the taxonomy's operative distinction is mirrored-vs-live-only, not control-vs-boundary, and this event mirrored. A consumer that wants enqueue-time notification has `agent/queued` (with its steering flag); a consumer that wants drain-time notification is by definition asking for the moment `steering/message` is appended, which `session/event` delivers with the same payload plus durability. The rejected [retire-mid-turn-steering Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md) defended the steering *capability* — `steer()`, the durable event, continuation forcing — all of which this removal keeps untouched. ## Verification -The `agent/steering` spelling survives only in RFC prose (this RFC, the three amended RFCs above, and the frozen [rejected steering-capability RFC](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md), whose text records the proposal it declined); the catalog is regenerated; the retargeted test pins source preservation on `steering/message`. +The `agent/steering` spelling survives only in Agent Note prose (this Agent Note, the three amended Agent Notes above, and the frozen [rejected steering-capability Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md), whose text records the proposal it declined); the catalog is regenerated; the retargeted test pins source preservation on `steering/message`. ## Consequences diff --git a/docs/rfc/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md similarity index 76% rename from docs/rfc/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md rename to .agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md index 79abfab2a0..f054f168a2 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md +++ b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md @@ -1,4 +1,4 @@ -# RFC: Share the app bins' boot glue instead of maintaining twin copies +# Agent Note: Share the app bins' boot glue instead of maintaining twin copies Status: implemented @@ -10,13 +10,13 @@ The stdio and ACP bins duplicated environment loading, fail-loud handling, entry The helpers live once, in [`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot) (`packages/ui/app-boot`, in the `ui` group because the bins are published artifacts whose runtime dependency must itself be published, not `support/`): `resolveConfigPath` (snapshot-aware, the single path resolver for both bins), `loadEnv`, `installFailLoud`, `assertEntriesLoaded`, and `boot`, each parameterized by the bin's diagnostic prefix and injectable at its side-effect seams (the warn sink, the process slice) so the unit suite covers every branch — including `boot()` driven in-process against the real Loader with relative-specifier configs, both the settled-tree happy path and the fiber-less-entry rejection. The package carries the per-file 100% coverage gate; the loader-failure lore has one home. -Each `bin.ts` is a thin self-executing composition over the shared helpers plus its app-specific lifecycle (the ACP bin: replay-mode env skipping and the stdin-EOF dispose; the stdio bin: nothing extra). The bins stay coverage-excluded and export nothing; the published-artifact guards are unchanged — the built-bin smokes still run each bin under plain node in a node_modules-shaped temp dir (now symlinking `ui/app-boot` too) and still assert the missing-config non-zero exit, per the "real entry path means the published artifact" defensive pattern. The [extract-example-app-packages RFC](../architecture/2026-06-20-extract-example-app-packages.md)'s bin-ownership facts are amended accordingly. +Each `bin.ts` is a thin self-executing composition over the shared helpers plus its app-specific lifecycle (the ACP bin: replay-mode env skipping and the stdin-EOF dispose; the stdio bin: nothing extra). The bins stay coverage-excluded and export nothing; the published-artifact guards are unchanged — the built-bin smokes still run each bin under plain node in a node_modules-shaped temp dir (now symlinking `ui/app-boot` too) and still assert the missing-config non-zero exit, per the "real entry path means the published artifact" defensive pattern. The [extract-example-app-packages Agent Note](../architecture/2026-06-20-extract-example-app-packages.md)'s bin-ownership facts are amended accordingly. ## Alternatives considered ### Why not keep the duplication? -The bins were framed as independently-owned published artifacts, and a new package carries fixed overhead (manifest, README, tsconfig reference, publint surface) comparable to the deduplicated line count. But app-vs-app sharing was never weighed by the RFC that created the bins — it consolidated three example `start.ts` copies INTO the bins and stopped there; the drift was observed fact; and the coverage-gap argument is independent of the dedup argument: this was the only nontrivial runtime logic in the repo exempt from the per-file 100% gate. The recorded fallback (extracting only the pure logic into per-app modules) would have ended the exemption but kept two homes for the lore. +The bins were framed as independently-owned published artifacts, and a new package carries fixed overhead (manifest, README, tsconfig reference, publint surface) comparable to the deduplicated line count. But app-vs-app sharing was never weighed by the Agent Note that created the bins — it consolidated three example `start.ts` copies INTO the bins and stopped there; the drift was observed fact; and the coverage-gap argument is independent of the dedup argument: this was the only nontrivial runtime logic in the repo exempt from the per-file 100% gate. The recorded fallback (extracting only the pure logic into per-app modules) would have ended the exemption but kept two homes for the lore. ## Consequences diff --git a/docs/rfc/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md similarity index 85% rename from docs/rfc/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md rename to .agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md index 7cbf67043f..82830b1366 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md +++ b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md @@ -1,12 +1,12 @@ -# RFC: Tighten the hook-protocol contract — dialect, discarded fields, double defaults, and lib-owned `hook/result` semantics +# Agent Note: Tighten the hook-protocol contract — dialect, discarded fields, double defaults, and lib-owned `hook/result` semantics Status: implemented ## Problem -Four pieces of the `dsh-hook-protocol`/bridge contract missed the discipline the [subagent-observe-enrich RFC](../feature/2026-06-30-subagent-observe-enrich.md) records — it dropped an `agentType` lifecycle field for lacking a consumer, and these failed the same test: +Four pieces of the `dsh-hook-protocol`/bridge contract missed the discipline the [subagent-observe-enrich Agent Note](../feature/2026-06-30-subagent-observe-enrich.md) records — it dropped an `agentType` lifecycle field for lacking a consumer, and these failed the same test: -1. **`HookDialect`'s `'native'` variant** (`packages/hooks/hook-protocol/src/types.ts`) had zero producers — the bridges stamp `'claude'` and `'codex'`; the only `'native'` constructor anywhere was the lib's own unit test. The field's own JSDoc defines `dialect` as "the bridge that ran it", and native is not a bridge: the [interception-seams RFC](../feature/2026-06-30-interception-seams.md) records that native hooks are not a package and that "a native plugin can already use the typed Decisions" without the durable hook log, and the flagship native-plugin worked example asserts exactly that (no `hook/*` events at all). +1. **`HookDialect`'s `'native'` variant** (`packages/hooks/hook-protocol/src/types.ts`) had zero producers — the bridges stamp `'claude'` and `'codex'`; the only `'native'` constructor anywhere was the lib's own unit test. The field's own JSDoc defines `dialect` as "the bridge that ran it", and native is not a bridge: the [interception-seams Agent Note](../feature/2026-06-30-interception-seams.md) records that native hooks are not a package and that "a native plugin can already use the typed Decisions" without the durable hook log, and the flagship native-plugin worked example asserts exactly that (no `hook/*` events at all). 2. **`HookOutput.suppressOutput`** (same file) was parsed by the codec and discarded on every path: no bridge branch, no merge fold, no warn, no deferred-list row — uniquely among its parsed-but-unhonored siblings, each of which carries a stated deferral (`updatedInput` → a logged warn plus the [pre-tool-input-rewrite proposal](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md); `systemMessage` → a logged warn plus a README deferred row; `continue`/`stopReason` → a `TODO(hook-continue-false)` anchor plus the `'stop'` decision record). Structurally there is nothing to suppress: hook stdout never enters any transcript (context flows only via `additionalContext`; the log records only `decision`/`stderrSummary`), so a hook author setting `suppressOutput: true` got silent nothing with no warn. 3. **`defaultTimeoutMs` was double-defaulted in both bridge configs with a floating literal** — a schema `.default(600_000)` AND a `?? 600_000` fallback (`packages/hooks/hooks-claude/src/index.ts`, `packages/hooks/hooks-codex/src/index.ts`), two homes per bridge for one protocol-level constant, so the bridges could silently drift apart on the shared default. *The proposal's original remedy — delete the knob outright — was overtaken by the no-hardcoded-tunables audit, which kept the knob as the explicit bridge-owned config (and added `stderrSummaryMaxChars` beside it); what remained to fix was the literal's home.* 4. **The `hook/result` semantics lived in the bridges, twice, not in the lib that owns the event.** `summarize()` — the stderr truncation rule — was byte-identical in `packages/hooks/hooks-claude/src/index.ts` and `packages/hooks/hooks-codex/src/index.ts`, and so was the decision-string rule `output.decision ?? (output.continue === false ? 'stop' : 'pass')`; yet `dsh-hook-protocol` declared `hook/result`, documented `stderrSummary` as "truncated" without owning the truncation, and documented the decision values without owning the mapping. If one bridge drifted (a different cap, a different fallback), the shared durable event's semantics would fork silently. diff --git a/docs/rfc/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md similarity index 96% rename from docs/rfc/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md rename to .agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md index 39edd8fee9..7d1065d250 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md +++ b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md @@ -1,4 +1,4 @@ -# RFC: Trim unreachable ACP bridge surface — the branding knobs and the kind-sniffing fallback +# Agent Note: Trim unreachable ACP bridge surface — the branding knobs and the kind-sniffing fallback Status: implemented diff --git a/docs/rfc/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md similarity index 91% rename from docs/rfc/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md rename to .agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md index 0907a63417..a719e20f1e 100644 --- a/docs/rfc/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md +++ b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md @@ -1,4 +1,4 @@ -# RFC: Drop unconsumed skill provider events +# Agent Note: Drop unconsumed skill provider events Status: implemented @@ -14,7 +14,7 @@ Skill discovery reads the current provider map on demand, provider registration The skill registry declares and emits no provider-membership events. Provider registration and disposal remain direct effect-owned state changes that synchronously invalidate completed catalogs; lookup and discovery read the current provider map on demand. Tests observe cleanup through provider lookup and collected output rather than lifecycle notifications. -The generated event catalog, API catalog, and producer/consumer matrix omit the deleted notifications. The skill-system RFC and package documentation describe registration through its direct effect-owned state and cache-invalidation contract. +The generated event catalog, API catalog, and producer/consumer matrix omit the deleted notifications. The skill-system Agent Note and package documentation describe registration through its direct effect-owned state and cache-invalidation contract. ## Alternatives considered diff --git a/docs/rfc/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md similarity index 98% rename from docs/rfc/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md rename to .agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md index 8ece4214b7..68ced83876 100644 --- a/docs/rfc/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md +++ b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md @@ -1,4 +1,4 @@ -# RFC: Prune unused web seam fields +# Agent Note: Prune unused web seam fields Status: implemented diff --git a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md similarity index 98% rename from docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md rename to .agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md index 7bf44c6c06..97a89e5be7 100644 --- a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md +++ b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md @@ -1,4 +1,4 @@ -# RFC: Simplify session-log representation +# Agent Note: Simplify session-log representation Status: implemented diff --git a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml similarity index 62% rename from docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml rename to .agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml index b86d9405e0..2b0b5c067d 100644 --- a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-retire-subagent-mock-package.md: 47174d22eaf27c5a5509280793dd50d70c542d00 -2026-07-19-retire-subagent-mock-package.zh.md: bfad78e1912f9d5153196df3fea2494c88436a91 +2026-07-19-retire-subagent-mock-package.md: 4a7fa32fdb0d8e656d61c39491a49bbd85e0adf3 +2026-07-19-retire-subagent-mock-package.zh.md: 7de72abb18050fb737000a2013e514dde3dae521 diff --git a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.md b/.agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.md similarity index 98% rename from docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.md rename to .agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.md index 47174d22ea..4a7fa32fdb 100644 --- a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.md +++ b/.agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.md @@ -1,4 +1,4 @@ -# RFC: Retire the standalone subagent mock package +# Agent Note: Retire the standalone subagent mock package Status: implemented diff --git a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md b/.agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md similarity index 98% rename from docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md rename to .agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md index bfad78e191..7de72abb18 100644 --- a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md @@ -1,4 +1,4 @@ -# RFC: 撤销独立的 subagent mock 包 +# Agent Note: 撤销独立的 subagent mock 包 Status: implemented diff --git a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml similarity index 61% rename from docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml rename to .agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml index 55a113d22b..cd03e02285 100644 --- a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-use-one-session-surface-manager.md: 0c0fd70717ff4b49e8817e88592d0781d9ccbd09 -2026-07-19-use-one-session-surface-manager.zh.md: 6d11c9bb475b0ee5a568f96678d0251f1160dda3 +2026-07-19-use-one-session-surface-manager.md: dee1a2a1cb6642730c87035de071d77ad38bd238 +2026-07-19-use-one-session-surface-manager.zh.md: ce538f1569c91e317af347d2ac20db624215eac8 diff --git a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.md b/.agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.md similarity index 98% rename from docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.md rename to .agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.md index 0c0fd70717..dee1a2a1cb 100644 --- a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.md +++ b/.agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.md @@ -1,4 +1,4 @@ -# RFC: Use one surface manager per session +# Agent Note: Use one surface manager per session Status: implemented diff --git a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md b/.agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md similarity index 97% rename from docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md rename to .agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md index 6d11c9bb47..ce538f1569 100644 --- a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md @@ -1,4 +1,4 @@ -# RFC: 每个会话只使用一个表层管理器 +# Agent Note: 每个会话只使用一个表层管理器 Status: implemented diff --git a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.md similarity index 95% rename from docs/rfc/implemented/testing/2026-06-11-property-based-testing.md rename to .agents/notes/implemented/testing/2026-06-11-property-based-testing.md index db7a9c8a79..06350753cd 100644 --- a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md +++ b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.md @@ -1,4 +1,4 @@ -# RFC: Property-based testing for protocol-shaped code +# Agent Note: Property-based testing for protocol-shaped code Status: implemented @@ -24,4 +24,4 @@ Adopt `fast-check` (a root devDependency) with one `tests/properties.spec.ts` pe - A property flake from a timeout is a finding, not something to retry away. The loop properties are deterministic by construction (settle on `agent/status`), so a hang is a real defect. - Property tests supplement, not replace, the example tests that pin specific branches for the 100%-coverage gate. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md similarity index 86% rename from docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md rename to .agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md index 2f7c0dbd8e..5fc7479eaf 100644 --- a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -1,14 +1,14 @@ -# RFC: ACP snapshot tests — record-once / replay-deterministic +# Agent Note: ACP snapshot tests — record-once / replay-deterministic Status: implemented ## Problem -Unit tests do not exercise the complete ACP subprocess transcript, while real-API tests are nondeterministic and key-gated. Editor-facing `session/update` output can therefore regress despite green unit coverage, as the [default-export postmortem](../../../postmortem/0001-acp-default-export-drops-inject.md) demonstrated. +Unit tests do not exercise the complete ACP subprocess transcript, while real-API tests are nondeterministic and key-gated. Editor-facing `session/update` output can therefore regress despite green unit coverage, as the [default-export postmortem](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) demonstrated. The blocker for a full-transcript test is the model: the agent's output is driven by a non-deterministic LLM, and a key-gated test that hits the real API on every run is neither deterministic nor CI-runnable. We want the fidelity of a real run with the determinism of a fixture. -This RFC records the decision to add a third test tier — **snapshot tests** — and the design choices that make it deterministic, keyless-in-CI, and cheap to maintain. +This Agent Note records the decision to add a third test tier — **snapshot tests** — and the design choices that make it deterministic, keyless-in-CI, and cheap to maintain. ## Decision @@ -42,14 +42,14 @@ Replay is positional and therefore permits only one in-flight model stream per s Recording runs the scenario with the real `llm-deepseek` adapter and the JSONL persistence backend, then copies the produced `.jsonl` into the scenario dir. Per-event appends are durable, but the harness shuts the subprocess down gracefully (close stdin → `await ctx.dispose()`) before harvesting so the final events are flushed. `llm-replay` itself does no recording — it is replay-only. -Replay uses a `cordis.snapshot.yml` overlay that replaces the real adapter with `llm-replay` while retaining the live composition. Recording uses the ordinary config and a harness-supplied persistence root. Replay mode skips `.env` loading, so a stray API key cannot trigger a live call. See the [single-source config RFC](2026-07-04-single-source-acp-replay-config.md). +Replay uses a `cordis.snapshot.yml` overlay that replaces the real adapter with `llm-replay` while retaining the live composition. Recording uses the ordinary config and a harness-supplied persistence root. Replay mode skips `.env` loading, so a stray API key cannot trigger a live call. See the [single-source config Agent Note](2026-07-04-single-source-acp-replay-config.md). ### Two surfaces: normalize, then compare A snapshot run asserts **two** normalized surfaces, because the harness's external surfaces are distinct: 1. The **stdout transcript** — the framed `session/update` JSON-RPC the editor sees. Catches regressions in the ACP bridge's event→update translation (`streamSessionEventUpdate`). Compared against a committed `stdout.expected.jsonl`. -2. The **re-persisted session JSONL**, normalized and compared with `session.jsonl`. The same fixture is both replay source and expected log. Prompt text is scrubbed; one scenario per header class pins readable prompt and tool content as described in the [header-pinning RFC](2026-07-06-pin-request-header-content-in-one-scenario.md). Override scenarios derive model behavior solely from their sidecar. +2. The **re-persisted session JSONL**, normalized and compared with `session.jsonl`. The same fixture is both replay source and expected log. Prompt text is scrubbed; one scenario per header class pins readable prompt and tool content as described in the [header-pinning Agent Note](2026-07-06-pin-request-header-content-in-one-scenario.md). Override scenarios derive model behavior solely from their sidecar. The surfaces are complementary: stdout covers bridge projection, while JSONL covers loop, tool, and boundary structure that the projection omits. @@ -77,4 +77,4 @@ Tool determinism comes from a temporary cwd, scrubbed environment, fresh non-log The new tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures. Workspace seeds are copied into the temporary cwd for both record and replay. In return the tier provides deterministic keyless transcript coverage through the real Loader and tool composition. The subprocess, input, workspace, normalization, and replay harness can support examples beyond ACP. -This RFC relates to but does not supersede the [proposed determinism RFC](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md): that proposal's "universal replay fixture" re-derives session *message history* after every test (an internal-consistency invariant), whereas snapshot tests pin the *external protocol output*. They are complementary — one guards the event-sourcing invariant, the other guards the editor-facing contract. +This Agent Note relates to but does not supersede the [proposed determinism Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md): that proposal's "universal replay fixture" re-derives session *message history* after every test (an internal-consistency invariant), whereas snapshot tests pin the *external protocol output*. They are complementary — one guards the event-sourcing invariant, the other guards the editor-facing contract. diff --git a/docs/rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md similarity index 90% rename from docs/rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md rename to .agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md index ea2eb6964a..36160de354 100644 --- a/docs/rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md +++ b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md @@ -1,14 +1,14 @@ -# RFC: Real-API e2e in CI against the external DeepSeek API +# Agent Note: Real-API e2e in CI against the external DeepSeek API Status: implemented ## Problem -The harness leans hard on real-API tests by policy: [docs/testing.md](../../../testing.md) argues that a no-key suite proves the plumbing but not the product, and the [ACP inject postmortem](../../../postmortem/0001-acp-default-export-drops-inject.md) is the standing proof — 178 keyless tests stayed green while a real editor session crashed instantly. The real-API e2e suite (`pnpm run test:e2e`, the `*.e2e.ts` files) exists precisely to close that gap: it drives the agent against the live DeepSeek API — real model calls, real bash tools, multi-turn, resume, ACP-over-stdio. +The harness leans hard on real-API tests by policy: [docs/testing.md](../../../../docs/testing.md) argues that a no-key suite proves the plumbing but not the product, and the [ACP inject postmortem](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) is the standing proof — 178 keyless tests stayed green while a real editor session crashed instantly. The real-API e2e suite (`pnpm run test:e2e`, the `*.e2e.ts` files) exists precisely to close that gap: it drives the agent against the live DeepSeek API — real model calls, real bash tools, multi-turn, resume, ACP-over-stdio. The default gate ([.github/workflows/ci.yml](../../../../.github/workflows/ci.yml)) is deliberately keyless: it carries no secret and runs for forks. `test:e2e` self-skips without a key (`describe.skipIf(!process.env.DEEPSEEK_API_KEY)`), so adding it there would report green without exercising the real suite. A separate secret-bearing workflow is required to make real-API coverage a merge signal. -This RFC records the decision to add a **second, secret-consuming workflow** that runs the real-API suite in CI, and — because introducing the first CI secret into a repo that may later go public is a security/isolation decision — the threat model it relies on and what changes when the repo becomes public. +This Agent Note records the decision to add a **second, secret-consuming workflow** that runs the real-API suite in CI, and — because introducing the first CI secret into a repo that may later go public is a security/isolation decision — the threat model it relies on and what changes when the repo becomes public. ## Decision @@ -20,7 +20,7 @@ ci.yml's value is that it is keyless, forkable, and always-green: any contributo ### Cost is not the constraint; reliability is -Internal inference cost is not the limiting constraint, so the workflow optimizes for coverage and signal. It runs every matching `*.e2e.ts` file on multiple triggers and every trusted PR, implementing the [docs/testing.md](../../../testing.md) with-key policy. +Internal inference cost is not the limiting constraint, so the workflow optimizes for coverage and signal. It runs every matching `*.e2e.ts` file on multiple triggers and every trusted PR, implementing the [docs/testing.md](../../../../docs/testing.md) with-key policy. ### Triggers: trusted events only @@ -93,6 +93,6 @@ None of these require changing the workflow to go public; they are operational s A second CI workflow and the first repo secret to maintain. The real-API suite now gates merges (pre-merge on trusted PRs, post-merge on the main branch) and runs nightly, so a real break in the agent's interaction with the external API surfaces in CI rather than only in a developer's local run — at the cost of real (but internally free) API calls on every trusted PR and merge. The preflight makes secret misconfiguration self-announcing instead of silently disabling the net. -The design carries a documented constraint surface: the `pull_request` trigger's key-exposure tradeoff (drop it to harden), the `if:` gate's dependence on the author-based Dependabot test, and the hard prohibition on `pull_request_target`. The going-public checklist above is the operational companion — this RFC is the place a future maintainer should re-read before changing the trigger set or flipping repo visibility, rather than re-deriving the fork/secret model from scratch. +The design carries a documented constraint surface: the `pull_request` trigger's key-exposure tradeoff (drop it to harden), the `if:` gate's dependence on the author-based Dependabot test, and the hard prohibition on `pull_request_target`. The going-public checklist above is the operational companion — this Agent Note is the place a future maintainer should re-read before changing the trigger set or flipping repo visibility, rather than re-deriving the fork/secret model from scratch. The scheduled trigger auto-disables after 60 days of repo inactivity (a GitHub behavior); push/PR/dispatch are backstops, and an active monorepo will not hit it. Runner egress to `https://api.deepseek.com` is assumed — GitHub-hosted `ubuntu-latest` has it; an egress-restricted self-hosted runner would need connectivity confirmed before relying on the nightly. diff --git a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md similarity index 94% rename from docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md rename to .agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md index ef0d3bd4ab..b17ecad098 100644 --- a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md +++ b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md @@ -1,4 +1,4 @@ -# RFC: Use `session.jsonl` as the only snapshot session-log artifact +# Agent Note: Use `session.jsonl` as the only snapshot session-log artifact Status: implemented @@ -24,7 +24,7 @@ Stdout expected outputs remain unchanged; they are the editor-facing projection ## Verification -`session.expected.jsonl` appears nowhere in the snapshot harness, fixtures, orphan guards, or docs; the snapshot test derives the expected session log from `session.jsonl` for every model scenario; authored sidecar scenarios commit their expected produced log as `session.jsonl` with `replay.override.json` as the model-behavior override; and the orphan-fixture guards know which files each scenario kind requires. The [ACP snapshot tests RFC](../../implemented/testing/2026-06-19-acp-snapshot-tests.md) describes the reduced fixture set. +`session.expected.jsonl` appears nowhere in the snapshot harness, fixtures, orphan guards, or docs; the snapshot test derives the expected session log from `session.jsonl` for every model scenario; authored sidecar scenarios commit their expected produced log as `session.jsonl` with `replay.override.json` as the model-behavior override; and the orphan-fixture guards know which files each scenario kind requires. The [ACP snapshot tests Agent Note](2026-06-19-acp-snapshot-tests.md) describes the reduced fixture set. ## Consequences diff --git a/docs/rfc/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md similarity index 90% rename from docs/rfc/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md rename to .agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md index 14db415b1b..93280ed62e 100644 --- a/docs/rfc/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md +++ b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md @@ -1,10 +1,10 @@ -# RFC: Persist the seed boundary so fork-child replay routes correctly +# Agent Note: Persist the seed boundary so fork-child replay routes correctly Status: implemented ## Problem -The [per-session snapshot replay RFC](2026-06-22-subagent-snapshot-replay.md) made the snapshot tier express a nested-agent shape: a parent plus one recorded log per in-process subagent, each replayed as its own script keyed by calling session. It noted (§ Scope, final bullet) that a fork snapshot was "a trivial future addition, not a gap in the keying." That was wrong about a fork child specifically — not the keying, but the *script derivation*. +The [per-session snapshot replay Agent Note](2026-06-22-subagent-snapshot-replay.md) made the snapshot tier express a nested-agent shape: a parent plus one recorded log per in-process subagent, each replayed as its own script keyed by calling session. It noted (§ Scope, final bullet) that a fork snapshot was "a trivial future addition, not a gap in the keying." That was wrong about a fork child specifically — not the keying, but the *script derivation*. A subagent script is derived from a recorded session log by [`deriveReplayScript`](../../../../packages/support/llm-replay): it groups the log's `assistant/chunk` events by `(turn, step)` into one replay entry per `stream()` call. This is correct for a **spawn** child, whose log contains only its own model calls. diff --git a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md similarity index 69% rename from docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md rename to .agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md index 34bebd1194..272e62ba77 100644 --- a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md +++ b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md @@ -1,10 +1,10 @@ -# RFC: Record fork and mixed spawn+fork snapshot scenarios +# Agent Note: Record fork and mixed spawn+fork snapshot scenarios Status: implemented ## Problem -The [seed-boundary RFC](2026-06-22-fork-child-replay-seed-boundary.md) made fork-child replay route correctly: `dsh-llm-replay` derives a child's script from the events at or after its persisted `seedLength` boundary, so a fork child's inherited parent prefix is not replayed as the child's own model calls. But it shipped with **no recorded fork scenario** — the slice was exercised only by `llm-replay`'s unit tests (a synthetic child fixture) and a persistence round-trip test. The full-transcript snapshot tier, the one net that boots the real `acp-agent` and replays an end-to-end nested transcript, had only spawn children (`subagent-spawn`, `subagent-multi`). A fork-routing regression that left the unit tests green would still have escaped the tier built to catch transcript regressions. +The [seed-boundary Agent Note](2026-06-22-fork-child-replay-seed-boundary.md) made fork-child replay route correctly: `dsh-llm-replay` derives a child's script from the events at or after its persisted `seedLength` boundary, so a fork child's inherited parent prefix is not replayed as the child's own model calls. But it shipped with **no recorded fork scenario** — the slice was exercised only by `llm-replay`'s unit tests (a synthetic child fixture) and a persistence round-trip test. The full-transcript snapshot tier, the one net that boots the real `acp-agent` and replays an end-to-end nested transcript, had only spawn children (`subagent-spawn`, `subagent-multi`). A fork-routing regression that left the unit tests green would still have escaped the tier built to catch transcript regressions. The snapshot infrastructure to express a fork scenario was already in place — both in-process backends are wired into `cordis.yml` / `cordis.snapshot.yml` as two model-facing tools (`subagent` → spawn, `subagent_fork` → fork), the harness harvests every child log, and replay forwards per-child fixtures keyed by `seedLength`. What was missing was a *recorded scenario* that drives a fork child through it. @@ -13,7 +13,7 @@ The snapshot infrastructure to express a fork scenario was already in place — Record two scenarios against the real API, both replayed keyless in the default gate: - **`subagent-fork`** — the parent completes a turn that establishes a fact, then delegates one subtask via `subagent_fork`. The fork child inherits the conversation (its log carries a non-zero `seedLength`), so it can answer from the parent's context. This is the focused regression: the child fixture's `seedLength` is the boundary the replay slice depends on, recorded from a real fork rather than hand-synthesized. -- **`subagent-mixed`** — the parent completes a turn, then delegates once via `subagent` (a fresh spawn child, `seedLength` 0) and once via `subagent_fork` (a fork child, non-zero `seedLength`) in one transcript. This is the mixed spawn+fork scenario the seed-boundary and per-session-replay RFCs both named as a future addition: one transcript exercises both transports and both branches of the slice (`seedLength` 0 = no-op, `seedLength > 0` = trim the inherited prefix), with the two children ordered spawn-then-fork by `createdAt`. +- **`subagent-mixed`** — the parent completes a turn, then delegates once via `subagent` (a fresh spawn child, `seedLength` 0) and once via `subagent_fork` (a fork child, non-zero `seedLength`) in one transcript. This is the mixed spawn+fork scenario the seed-boundary and per-session-replay Agent Notes both named as a future addition: one transcript exercises both transports and both branches of the slice (`seedLength` 0 = no-op, `seedLength > 0` = trim the inherited prefix), with the two children ordered spawn-then-fork by `createdAt`. ### Why a completed turn-1 is required @@ -26,4 +26,4 @@ The fork backend seeds the child with the parent's **balanced completed-turn pre - Out-of-process (ACP) subagent replay remains a different shape (each child is its own process with its own replay) and is still tracked as `TODO(acp-subagent-replay)` — these scenarios are in-process only. - Re-recording (`pnpm run test:snapshot:record`) regenerates all four fork/spawn fixtures from the live API; the two new scenarios self-skip without a key like every recorded scenario. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/testing/2026-06-22-subagent-snapshot-replay.md b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md similarity index 94% rename from docs/rfc/implemented/testing/2026-06-22-subagent-snapshot-replay.md rename to .agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md index 811930af00..d21a081f9b 100644 --- a/docs/rfc/implemented/testing/2026-06-22-subagent-snapshot-replay.md +++ b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md @@ -1,4 +1,4 @@ -# RFC: Per-session snapshot replay for nested agents +# Agent Note: Per-session snapshot replay for nested agents Status: implemented @@ -11,7 +11,7 @@ It was built for ONE session per process, and that assumption is wired into two - **`dsh-llm-replay` keyed nothing.** It served the Nth `llm/stream` call the Nth recorded entry from a single global cursor. With a parent agent AND an in-process subagent both streaming on one context, the calls interleave and the single cursor hands the child the parent's script (and vice versa). - **The harness harvested one log.** `findSessionLog` walked the sessions root and returned the FIRST `.jsonl` it found. A subagent runs as a second `Session` with its own log in the same cwd bucket, so the child's transcript was silently dropped. -This was the `TODO(subagent-snapshots)` deferral recorded in the [subagent seam RFC](../../implemented/feature/2026-06-21-subagent-capability-seam.md): the in-process backends (PR2) shipped with unit + e2e coverage, but the full-transcript snapshot tier could not express a nested-agent shape until this infrastructure landed. This RFC is that stacked follow-up. +This was the `TODO(subagent-snapshots)` deferral recorded in the [subagent seam Agent Note](../feature/2026-06-21-subagent-capability-seam.md): the in-process backends (PR2) shipped with unit + e2e coverage, but the full-transcript snapshot tier could not express a nested-agent shape until this infrastructure landed. This Agent Note is that stacked follow-up. ## Decision diff --git a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md similarity index 97% rename from docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md rename to .agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 0ba04c4abb..7c2c33460c 100644 --- a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -1,4 +1,4 @@ -# RFC: Hook snapshot matrix — end-to-end expected outputs for both bridges +# Agent Note: Hook snapshot matrix — end-to-end expected outputs for both bridges Status: implemented @@ -47,4 +47,4 @@ The matrix therefore covers every hook point that has a DETERMINISTIC, OBSERVABL - The prove-red discipline holds: tampering a hook config's output (e.g. changing a deny reason) turns its scenario red on replay — the hook process runs FOR REAL during replay (only the model is replayed), so the expected output guards the actual hook→seam→loop path, not a mock of it. - The `acp-agent` demo now loads a Codex bridge it will usually no-op (no `codex-hooks.json` in a typical project), which is the intended fail-soft behavior, not a cost. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md similarity index 91% rename from docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md rename to .agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md index 03c25572d4..3de645deeb 100644 --- a/docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md +++ b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md @@ -1,10 +1,10 @@ -# RFC: Single-source the acp-agent replay config +# Agent Note: Single-source the acp-agent replay config Status: implemented ## Problem -`examples/acp-agent` shipped two hand-maintained configs: `cordis.yml` (the live tree) and a `cordis.snapshot.yml` that mirrored it entry-for-entry with only the llm backend swapped — stripped of comments, the entire difference was the eight-line `llm-deepseek` stanza versus the two-line `llm-replay` stanza. Every app-shape change had to be made twice, and nothing gated the symmetry: if the copies drifted, the snapshot tier would silently exercise a different app than the one that ships — the ["green units, broken product" class of gap](../../../postmortem/0001-acp-default-export-drops-inject.md) the snapshot tier exists to close, reintroduced one level up, with reviewer vigilance as the only defense. +`examples/acp-agent` shipped two hand-maintained configs: `cordis.yml` (the live tree) and a `cordis.snapshot.yml` that mirrored it entry-for-entry with only the llm backend swapped — stripped of comments, the entire difference was the eight-line `llm-deepseek` stanza versus the two-line `llm-replay` stanza. Every app-shape change had to be made twice, and nothing gated the symmetry: if the copies drifted, the snapshot tier would silently exercise a different app than the one that ships — the ["green units, broken product" class of gap](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) the snapshot tier exists to close, reintroduced one level up, with reviewer vigilance as the only defense. ## Decision diff --git a/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md similarity index 94% rename from docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md rename to .agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md index 68f7fce66a..1dcfc2e085 100644 --- a/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md +++ b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md @@ -1,4 +1,4 @@ -# RFC: Pin request-header content in one snapshot scenario +# Agent Note: Pin request-header content in one snapshot scenario Status: implemented @@ -22,7 +22,7 @@ One pin covers the whole suite because every session — parent, spawn child, fo - **Scrub at compare time only, keeping fixtures raw** — lets compares pass while committed fixtures retain stale duplicate content and rewrite wholesale on the next recording. Stored tokens state honestly what each JSONL does not pin. - **Scrub everywhere, pin nowhere** — loses the only end-to-end record of the composed header as actually sent (prompt assembly, registered-tool order, full schemas). The generated tool catalog documents each tool in isolation; only a real fixture pins the composed set. - **Keep the one full pin entirely in JSONL** — removes suite-wide duplication but leaves prompt and schema changes as one escaped line. Markdown and structured JSON give each surface its natural review format without weakening the reconstructed-header assertion. -- **Slim the session log itself (log a content digest, store the header elsewhere)** — violates the reconstructability contract: the product log must reproduce each request bit-for-bit ([reconstructable-requests RFC](../architecture/2026-07-05-reconstructable-requests.md)). Header bulk is a test-artifact concern, solved in test normalization; the live log is untouched. +- **Slim the session log itself (log a content digest, store the header elsewhere)** — violates the reconstructability contract: the product log must reproduce each request bit-for-bit ([reconstructable-requests Agent Note](../architecture/2026-07-05-reconstructable-requests.md)). Header bulk is a test-artifact concern, solved in test normalization; the live log is untouched. ## Verification diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md similarity index 81% rename from docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md rename to .agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index ecdd40f313..aadeaeea30 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -1,10 +1,10 @@ -# RFC: Extract the ACP snapshot suite into a support package +# Agent Note: Extract the ACP snapshot suite into a support package Status: implemented ## Problem -The ACP snapshot tier ([snapshot RFC](2026-06-19-acp-snapshot-tests.md)) was built from three modules living inside one example's test directory: `snapshot-harness.ts` (boot the real bin subprocess, drive it over ACP JSON-RPC, harvest the persisted logs), `snapshot-normalize.ts` (the pure expected-output normalizers), and the ~150-line scenario body plus fixture guards in `acp.snapshot.ts` (record/replay modes, the stdout expected-output and log comparisons, the pinned-header uniformity guard, the orphan/required-file/single-pin meta-tests). +The ACP snapshot tier ([snapshot Agent Note](2026-06-19-acp-snapshot-tests.md)) was built from three modules living inside one example's test directory: `snapshot-harness.ts` (boot the real bin subprocess, drive it over ACP JSON-RPC, harvest the persisted logs), `snapshot-normalize.ts` (the pure expected-output normalizers), and the ~150-line scenario body plus fixture guards in `acp.snapshot.ts` (record/replay modes, the stdout expected-output and log comparisons, the pinned-header uniformity guard, the orphan/required-file/single-pin meta-tests). A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was also triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness. Location decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all. @@ -18,11 +18,11 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. -**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). A scenario directory's `session.jsonl` plus contiguous `session.<n>.jsonl` siblings are its ordered primary/child inventory, so the scenario table declares policy without duplicating a child count. The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.expected.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`sessionFixtureNames`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. +**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). A scenario directory's `session.jsonl` plus contiguous `session.<n>.jsonl` siblings are its ordered primary/child inventory, so the scenario table declares policy without duplicating a child count. The pinned-header contract ([pinned-header Agent Note](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.expected.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`sessionFixtureNames`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. ## Alternatives considered -- **Copy the modules into each example** — the fork this RFC exists to prevent: the record/guard logic is exactly the code that must stay byte-identical across suites, and examples are outside the coverage gate, so each copy is also unmeasured. +- **Copy the modules into each example** — the fork this Agent Note exists to prevent: the record/guard logic is exactly the code that must stay byte-identical across suites, and examples are outside the coverage gate, so each copy is also unmeasured. - **A shared module directory under `examples/`** — keeps the code outside the coverage gate and forces relative imports across example boundaries, against the package-name import convention; `examples/` leaves stay thin by design. - **A `/testing` subpath export of `dsh-acp-demo`** — couples test infrastructure into a product package's surface and dependency set; `packages/support/` exists precisely for real-but-lower-compatibility dev/test packages, with `dsh-llm-replay` as the precedent this package completes. - **Export raw test-body functions instead of a suite factory** — each example would re-own the `describe`/`it` skeleton (~80 lines of registration boilerplate per suite) for no flexibility gain; the factory keeps consumers to a scenario table plus one call, and the exported pure helpers preserve unit-testability inside the factory design. diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml b/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml similarity index 62% rename from docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml rename to .agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml index 6f3df04716..c208a1e553 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml +++ b/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-18-tui-terminal-state-snapshots.md: a609e7c167ddf7ebe594f6793e34a48c555c10a9 -2026-07-18-tui-terminal-state-snapshots.zh.md: 8690a6f83a827619682b82c2df56d360e104c53b +2026-07-18-tui-terminal-state-snapshots.md: 192e872ab63cf4ff8a121ea0a2ee9345379cfa26 +2026-07-18-tui-terminal-state-snapshots.zh.md: 9766a8087632daa1be0dcfb191696dbad354ff68 diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md b/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md similarity index 99% rename from docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md rename to .agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md index a609e7c167..192e872ab6 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md +++ b/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md @@ -1,4 +1,4 @@ -# RFC: Snapshot semantic terminal state for the TUI +# Agent Note: Snapshot semantic terminal state for the TUI Status: implemented diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md b/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md similarity index 99% rename from docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md rename to .agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md index 8690a6f83a..9766a80876 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md +++ b/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md @@ -1,4 +1,4 @@ -# RFC: TUI 语义终端状态快照 +# Agent Note: TUI 语义终端状态快照 Status: implemented diff --git a/docs/rfc/proposed/architecture/2026-06-16-typed-event-schemas.md b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md similarity index 91% rename from docs/rfc/proposed/architecture/2026-06-16-typed-event-schemas.md rename to .agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md index 9eb4c585a4..91679a0a6c 100644 --- a/docs/rfc/proposed/architecture/2026-06-16-typed-event-schemas.md +++ b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md @@ -1,10 +1,10 @@ -# RFC: Runtime schemas for the event vocabulary (Zod vs the merge-extensible-map pattern) +# Agent Note: Runtime schemas for the event vocabulary (Zod vs the merge-extensible-map pattern) Status: proposed ## Problem -The harness models its core vocabulary — content blocks, message sources, finish reasons, turn triggers, turn-end reasons, and session events — as **merge-extensible maps**: a TypeScript `interface` (e.g. `SessionEventMap`, `ContentBlockMap`) that plugins augment via declaration merging, with the public union derived as `Map[keyof Map]`. This is the repo's universal extension pattern, documented in [docs/architecture.md](../../../architecture.md) ("The same merge-extensible-map pattern is used for `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`") and relied on by the `defineTool` `InferArgs` DSL and the `assertNever` exhaustiveness convention. +The harness models its core vocabulary — content blocks, message sources, finish reasons, turn triggers, turn-end reasons, and session events — as **merge-extensible maps**: a TypeScript `interface` (e.g. `SessionEventMap`, `ContentBlockMap`) that plugins augment via declaration merging, with the public union derived as `Map[keyof Map]`. This is the repo's universal extension pattern, documented in [docs/architecture.md](../../../../docs/architecture.md) ("The same merge-extensible-map pattern is used for `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`") and relied on by the `defineTool` `InferArgs` DSL and the `assertNever` exhaustiveness convention. The pattern is **compile-time only**. The types vanish at runtime: there is no schema object to validate an incoming value against, parse untrusted input with, or enumerate at runtime. The [session-persistence contract](../../implemented/architecture/2026-06-14-session-persistence.md) exposes two consequences: @@ -13,7 +13,7 @@ The pattern is **compile-time only**. The types vanish at runtime: there is no s This raises whether the event vocabulary should move to **Zod** or another runtime-schema library so durable and plugin boundaries have runtime schemas rather than erased types. -This RFC scopes that question without proposing an implementation. +This Agent Note scopes that question without proposing an implementation. ## Why this is not a persistence change @@ -30,7 +30,7 @@ A migration of the event/vocabulary surface to runtime schemas touches, at minim - **The event producers** — 16 `session.append(...)` call sites in the loop — unchanged in shape but now validated at the boundary. - **~7 switch-consumers** that branch on these unions: `deriveMessages` (`dsh-session`), `BlockAssembler` (`dsh-llm`), the `dsh-invariants` plugin, both LLM adapters (`dsh-llm-deepseek`, `dsh-llm-pi-ai`), and the tool schema layer (`dsh-tools`). The `assertNever`-on-closed-unions vs fall-through-on-extensible-unions convention (a documented lint rule) would need rethinking — runtime variants are not statically exhaustive. - **The `defineTool` `InferArgs` DSL** (`dsh-tools`), which derives zero-cast `execute` arg types from a compile-time schema spec — the showcase of the current approach. -- **Docs**: architecture.md (the pattern is described as foundational), [dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md), and any RFC that references the pattern. +- **Docs**: architecture.md (the pattern is described as foundational), [dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md), and any Agent Note that references the pattern. This is a repository-wide vocabulary redesign, not a persistence implementation detail. @@ -56,11 +56,11 @@ Replace the merge-extensible maps with a runtime registry the producers contribu ## Proposal -Defer. If runtime validation is wanted at the durable boundary, **Option B** (schemastery on closed header and metadata shapes) is the proportionate step within the existing convention. **Option C** is an architecture decision that requires its own implementation RFC, including a choice between Zod and schemastery. +Defer. If runtime validation is wanted at the durable boundary, **Option B** (schemastery on closed header and metadata shapes) is the proportionate step within the existing convention. **Option C** is an architecture decision that requires its own implementation Agent Note, including a choice between Zod and schemastery. ## Acceptance criteria -- Option C proceeds only through its own implementation RFC, never as a persistence side effect. +- Option C proceeds only through its own implementation Agent Note, never as a persistence side effect. - If Option B is taken up, the closed header/metadata shapes (the JSONL `isHeaderLine` guard and kin) validate through schemastery in place of hand-rolled guards, with the merge-extensible maps untouched. ## Risks diff --git a/docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.i18n.yaml similarity index 61% rename from docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.i18n.yaml rename to .agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.i18n.yaml index 6e301ee06a..83a2d4d788 100644 --- a/docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-sdk-project-editing-architecture.md: 985cc22c159c68801b78262aa96c7422bdfa1318 -2026-07-15-sdk-project-editing-architecture.zh.md: 6a194e8e5f193e62bfc283fd93a5fde0367fe196 +2026-07-15-sdk-project-editing-architecture.md: 8335af516dbaa85f4adb85286f976ce9be2c9da8 +2026-07-15-sdk-project-editing-architecture.zh.md: bec39cc896887678b2d3f74832a9d13d7b354d6e diff --git a/docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md b/.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md similarity index 99% rename from docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md rename to .agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md index 985cc22c15..8335af516d 100644 --- a/docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md +++ b/.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md @@ -1,4 +1,4 @@ -# RFC: SDK project editing architecture +# Agent Note: SDK project editing architecture Status: proposed @@ -16,7 +16,7 @@ Structured files are modified through document objects, while one-shot text arti ## Terminology -| Term | Usage in this RFC | Meaning | +| Term | Usage in this Agent Note | Meaning | |---|---|---| | Feature | feature | A product unit curated and managed by the SDK; one feature may contain several feature options and contribute several Cordis config entries, npm dependencies, environment placeholders, and owned files | | Feature option | feature option | A finite selectable implementation or configuration shape within one feature; feature rules may make options fixed, exclusive, or additive | diff --git a/docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.zh.md b/.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.zh.md similarity index 99% rename from docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.zh.md rename to .agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.zh.md index 6a194e8e5f..bec39cc896 100644 --- a/docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.zh.md @@ -1,4 +1,4 @@ -# RFC: SDK 工程编辑架构 +# Agent Note: SDK 工程编辑架构 Status: proposed diff --git a/docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md similarity index 88% rename from docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md rename to .agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md index 9657512082..e6c5d9eb1e 100644 --- a/docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md +++ b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md @@ -1,10 +1,10 @@ -# RFC: Pre-tool input rewrite — a consistent design +# Agent Note: Pre-tool input rewrite — a consistent design Status: proposed ## Problem -The [interception-seams RFC](../../implemented/feature/2026-06-30-interception-seams.md) defines `tools/pre-execute` as an allow/deny/ask gate over an execution whose identity is already protected and whose arguments are deeply frozen. Claude Code's `PreToolUse` hook also offers `updatedInput`, so a faithful bridge needs an explicit rewrite mechanism. A rewrite cannot be a mutation escape hatch on the existing execution object: it must keep the durable history, audit record, presentation, and executed value consistent. +The [interception-seams Agent Note](../../implemented/feature/2026-06-30-interception-seams.md) defines `tools/pre-execute` as an allow/deny/ask gate over an execution whose identity is already protected and whose arguments are deeply frozen. Claude Code's `PreToolUse` hook also offers `updatedInput`, so a faithful bridge needs an explicit rewrite mechanism. A rewrite cannot be a mutation escape hatch on the existing execution object: it must keep the durable history, audit record, presentation, and executed value consistent. ## The problem: three readers of pre-execution arguments diff --git a/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.md similarity index 96% rename from docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md rename to .agents/notes/proposed/feature/2026-07-06-recallable-compaction.md index 6e28e8a31e..3f54030f9d 100644 --- a/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md +++ b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.md @@ -1,4 +1,4 @@ -# RFC: Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall +# Agent Note: Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall Status: proposed @@ -58,7 +58,7 @@ The design ships as a new backend `dsh-compact-recallable` on the existing `ctx. - **Tool-result pruning** (the in-flight pruning service): its replacement nodes carry `sourceEventSeqs`; the same registry fold lists pruned results as recallable. Follow-up scope; neither blocks the other. - **Provider-usage token accounting** (the in-flight move of compaction pressure onto provider-reported usage): supplies the guard's accounting; the implementation stacks after it. -- **"Query sessions" backlog item**: the cross-session generalization; this RFC scopes to the live session with tool names and rendering chosen so that work extends rather than collides. +- **"Query sessions" backlog item**: the cross-session generalization; this Agent Note scopes to the live session with tool names and rendering chosen so that work extends rather than collides. - **Training**: when to recall is a learned behavior. The deterministic footers and keyword anchors give training a stable target, and recall usage is fully visible in the session log for trajectory export; benchmark and RL design proceed with the post-training side. ### Follow-ups @@ -96,7 +96,7 @@ Specified during review, deferred until observation calls for them: - Nothing commits before all summaries exist and the guard passes on like-for-like accounting; a guard failure commits nothing and does not fail the turn; a mid-commit kill resumed at the next pre-step completes the pass with the state region committed unconditionally, merge base read from the log; a legacy head checkpoint is adopted as state-class. - `history_read` renders any logged checkpoint's span under budget with a working cursor; `history_search` covers every shadowed span with checkpoint-id snippets and coverage metadata, asserted in particular by finding content that exists only in a span shadowed by a superseded state checkpoint — the regression pin for trailing-slice reachability; both reject non-agent callers and never-existing ids or orphaned `compact/start` with typed errors; recalled content appears as ordinary `tool/result`s; request-reconstruction invariants pass over sessions with compaction plus recall; one keyless snapshot scenario covers compact-then-recall end to end; tool schemas and the prompt section are byte-identical across passes. - On the long-horizon bench suite: task success does not regress against `compact-basic` at equal budgets; a handoff-fidelity probe (restate K known decisions and constraints after a pass) scores no worse; recall usage frequency and hit usefulness are reported per run via the dsh bench report pipeline, alongside the stub-directory attention measurement and cache-hit telemetry. -- Seam JSDoc, the compaction capability-seam RFC, `architecture.md`, and the generated tool, config, persistence, and module-graph catalogs update in the same change; all budgets live in config; new source directories hold per-file 100% coverage with HMR disposal tests. +- Seam JSDoc, the compaction capability-seam Agent Note, `architecture.md`, and the generated tool, config, persistence, and module-graph catalogs update in the same change; all budgets live in config; new source directories hold per-file 100% coverage with HMR disposal tests. ## Risks diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md similarity index 90% rename from docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md rename to .agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index c05ae8d67f..620f39c4a4 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -1,10 +1,10 @@ -# RFC: Claude Code and Codex subagent backends (out-of-process delegation to external coding agents) +# Agent Note: Claude Code and Codex subagent backends (out-of-process delegation to external coding agents) Status: proposed ## Problem -The subagent seam ([the seam RFC](../../implemented/feature/2026-06-21-subagent-capability-seam.md)) hosts multiple named providers on `ctx.subagents`, and the ACP backend ([the ACP backend RFC](../../implemented/feature/2026-06-22-acp-subagent-backend.md)) proved the seam generalizes across a process boundary; its Future-providers section explicitly named the Codex app-server and the Claude Code Agent SDK as mechanically similar siblings. Those two are the engines actually worth delegating to today: a harness turn should be able to hand a self-contained task to a real Claude Code or a real Codex — a separate product with its own model, tools, and sandbox — and get back one final answer, without the parent deployment leaking its secrets into the child or the child's behavior silently depending on whatever `~/.claude` / `~/.codex` state exists on the host machine. +The subagent seam ([the seam Agent Note](../../implemented/feature/2026-06-21-subagent-capability-seam.md)) hosts multiple named providers on `ctx.subagents`, and the ACP backend ([the ACP backend Agent Note](../../implemented/feature/2026-06-22-acp-subagent-backend.md)) proved the seam generalizes across a process boundary; its Future-providers section explicitly named the Codex app-server and the Claude Code Agent SDK as mechanically similar siblings. Those two are the engines actually worth delegating to today: a harness turn should be able to hand a self-contained task to a real Claude Code or a real Codex — a separate product with its own model, tools, and sandbox — and get back one final answer, without the parent deployment leaking its secrets into the child or the child's behavior silently depending on whatever `~/.claude` / `~/.codex` state exists on the host machine. ## Proposal @@ -49,7 +49,7 @@ Named at every tier per the root AGENTS.md rule, and de-risked up front: - **Keyless unit/integration**, mirroring the ACP spec list per backend (round-trip and output accumulation, every stop mapping, both cancel paths, already-aborted, permission auto-answer under both policies, unknown-message tolerance, bad-command spawn failure, HMR provider cleanup, export shape, isolation assertions on child env and temp-dir removal; Codex adds the auth-precheck failure path). Claude Code's harness is a scripted fake `claude` executable behind `pathToClaudeCodeExecutable` driven by the REAL SDK — a spike already passed end-to-end keyless in 24ms (the fake CLI answers one `control_request/initialize` and speaks plain stream-json, ~40 lines). Codex's harness is a scripted mock app-server subprocess speaking the verified wire protocol, the `mock-acp-server.ts` shape. - **With-key e2e** per backend: the real engine does real file work verified on disk, under a pinned opened-up config so acceptance and the do-no-harm defaults don't collide — `permissionMode: 'acceptEdits'` for Claude Code, `sandboxMode: 'workspace-write'` + `approvalPolicy: 'never'` for Codex; self-skips report exactly what is missing (binary vs key). CI has no secrets, so these run locally per the with-key policy. -- **Snapshot**: deferred as `TODO(claude-code-subagent-replay)` / `TODO(codex-subagent-replay)` — the same distinct replay shape the ACP backend deferred ([the per-session replay RFC](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md)); the keyless suites carry deterministic coverage meanwhile. +- **Snapshot**: deferred as `TODO(claude-code-subagent-replay)` / `TODO(codex-subagent-replay)` — the same distinct replay shape the ACP backend deferred ([the per-session replay Agent Note](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md)); the keyless suites carry deterministic coverage meanwhile. ## Alternatives considered @@ -59,7 +59,7 @@ The dispose ladder and env scrub require owning the child process (spawn args, e ### Why not a model-visible `subagent_type` parameter (one Task-style tool)? -Claude Code's own Task tool puts the subagent type in the model-facing schema, selecting a prompt-plus-toolset persona. Here the choice is between EXECUTION ENGINES, and only the deployer knows which engines have credentials configured — so selection stays deployment config, preserving `dsh-tool-subagent`'s documented one-provider-per-tool contract. A persona-style type selector would be a separate RFC against the tool, not the backends. +Claude Code's own Task tool puts the subagent type in the model-facing schema, selecting a prompt-plus-toolset persona. Here the choice is between EXECUTION ENGINES, and only the deployer knows which engines have credentials configured — so selection stays deployment config, preserving `dsh-tool-subagent`'s documented one-provider-per-tool contract. A persona-style type selector would be a separate Agent Note against the tool, not the backends. ### Why not login-state credentials and the user's own config? @@ -71,7 +71,7 @@ Injecting a fake `query()` would mock our own boundary and leave the real SDK lo ### Why not ACP adapters (e.g. `claude-code-acp`) reusing the existing backend? -Community shims wrap both engines in ACP, which would make them "just config" on `dsh-subagent-acp`. But that inserts an unofficial third-party layer between the harness and the engine, erases the native control surfaces this RFC exposes (permissionMode, sandboxMode/approvalPolicy, config-dir isolation, apiKey RPC), and trades first-party protocol stability for a shim's release cadence. First-party surfaces — the Agent SDK and the app-server — are the supported integration points. +Community shims wrap both engines in ACP, which would make them "just config" on `dsh-subagent-acp`. But that inserts an unofficial third-party layer between the harness and the engine, erases the native control surfaces this Agent Note exposes (permissionMode, sandboxMode/approvalPolicy, config-dir isolation, apiKey RPC), and trades first-party protocol stability for a shim's release cadence. First-party surfaces — the Agent SDK and the app-server — are the supported integration points. ## Acceptance criteria diff --git a/docs/rfc/proposed/feature/2026-07-08-interactive-side-sessions.md b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md similarity index 95% rename from docs/rfc/proposed/feature/2026-07-08-interactive-side-sessions.md rename to .agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md index 7caceed4ba..f2e3e74ca1 100644 --- a/docs/rfc/proposed/feature/2026-07-08-interactive-side-sessions.md +++ b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md @@ -1,4 +1,4 @@ -# RFC: Interactive side sessions and merge-back +# Agent Note: Interactive side sessions and merge-back Status: proposed @@ -13,7 +13,7 @@ A **side session** is an ordinary live session forked at the source's last compl - **Fork and attach:** create the child with the parent's balanced completed-turn prefix and stamp `parentSession` and `seedLength` in its metadata. This composes `ctx.agents.create({ seed, meta })`; it adds no core service or session-store method. - **Advisor framing:** inject one plugin-sourced `context/message` after creation that tells the child to explain without mutating or continuing the task. Keeping the system prompt byte-identical preserves the provider prefix cache over inherited history. - **Merge-back:** ask the child for a length-capped handback, then inject one plugin-sourced `context/message` into the parent. The next parent request sees it at its logged position, preserving replay and [request reconstructability](../../implemented/architecture/2026-07-05-reconstructable-requests.md) without a new session event. -- **Presentation:** invocation, session switching, and handback rendering belong to the first client-owned surface. This RFC specifies only the surface-independent mechanics. +- **Presentation:** invocation, session switching, and handback rendering belong to the first client-owned surface. This Agent Note specifies only the surface-independent mechanics. Rewind productization, session-tree views, a model-facing side-session tool, and `forkName`/`mergedInto` metadata are out of scope. A live-adapter spike validated source-log isolation, inherited context, a multi-turn child exchange, and merge-back visibility in the parent's next turn. diff --git a/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md b/.agents/notes/proposed/feature/2026-07-10-sqlite-session-query-provider.md similarity index 97% rename from docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md rename to .agents/notes/proposed/feature/2026-07-10-sqlite-session-query-provider.md index 36216f74d8..d643d223dd 100644 --- a/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md +++ b/.agents/notes/proposed/feature/2026-07-10-sqlite-session-query-provider.md @@ -1,4 +1,4 @@ -# RFC: SQLite FTS5 session search +# Agent Note: SQLite FTS5 session search Status: proposed @@ -44,7 +44,7 @@ Reconciliation may use stable fingerprints to avoid rewriting unchanged persiste - Tests cover both search scopes, content-bearing results, chainable result filters, surface defaults, snippets, escaping, deterministic ties, pagination, scoped stale cursors, cancellation, dynamic persistence mount/unmount, and recovery after a failed transaction. - A schema mismatch resets only the derived database. - A keyless end-to-end test combines a real persistence backend with the real SQLite search package. -- The RFC is amended to the measured tokenizer and public API actually implemented before moving to `implemented/`. +- The Agent Note is amended to the measured tokenizer and public API actually implemented before moving to `implemented/`. ## Risks diff --git a/docs/rfc/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md similarity index 99% rename from docs/rfc/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md rename to .agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md index 200ed50b1e..0c6516080a 100644 --- a/docs/rfc/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md +++ b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md @@ -1,4 +1,4 @@ -# RFC: Stream workflow progress through tool calls +# Agent Note: Stream workflow progress through tool calls Status: proposed diff --git a/docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.i18n.yaml b/.agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.i18n.yaml similarity index 64% rename from docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.i18n.yaml rename to .agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.i18n.yaml index 36bb26161f..c876ddc68f 100644 --- a/docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.i18n.yaml +++ b/.agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-14-sdk-developer-projects.md: 0b5fe876f92153e1ccf5bd8fe383464f5087f4b1 -2026-07-14-sdk-developer-projects.zh.md: ec08f323acba1b9dc049182937fda34bfb50d4ee +2026-07-14-sdk-developer-projects.md: 1be9abcad1e51a1b9a1406f21ce60073427576e0 +2026-07-14-sdk-developer-projects.zh.md: a8ba1d658f78484a46a7148a4e2ff1b073a3e9f2 diff --git a/docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.md b/.agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.md similarity index 99% rename from docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.md rename to .agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.md index 0b5fe876f9..1be9abcad1 100644 --- a/docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.md +++ b/.agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.md @@ -1,4 +1,4 @@ -# RFC: Developer-owned SDK projects +# Agent Note: Developer-owned SDK projects Status: proposed diff --git a/docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.zh.md b/.agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.zh.md similarity index 99% rename from docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.zh.md rename to .agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.zh.md index ec08f323ac..a8ba1d658f 100644 --- a/docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.zh.md +++ b/.agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.zh.md @@ -1,4 +1,4 @@ -# RFC: 开发者拥有的 SDK 工程 +# Agent Note: 开发者拥有的 SDK 工程 Status: proposed diff --git a/docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.i18n.yaml b/.agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.i18n.yaml similarity index 63% rename from docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.i18n.yaml rename to .agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.i18n.yaml index 933cff9cb5..8b70484312 100644 --- a/docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.i18n.yaml +++ b/.agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-17-sdk-follow-up-capabilities.md: dac859f95e4ee4c628c50be72b3a18720f2b19fb -2026-07-17-sdk-follow-up-capabilities.zh.md: 55648a368b4f9aa865129f3e0501e417d15f09ed +2026-07-17-sdk-follow-up-capabilities.md: 0f3ada6bdbb4ce933d14602cf59be9a51640e61c +2026-07-17-sdk-follow-up-capabilities.zh.md: d0d0b3e6bcdf192e64f003dc9f6e90cc2bdb060b diff --git a/docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.md b/.agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.md similarity index 96% rename from docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.md rename to .agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.md index dac859f95e..0f3ada6bdb 100644 --- a/docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.md +++ b/.agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.md @@ -1,4 +1,4 @@ -# RFC: SDK follow-up capabilities +# Agent Note: SDK follow-up capabilities Status: proposed @@ -6,7 +6,7 @@ English | [中文](2026-07-17-sdk-follow-up-capabilities.zh.md) ## Problem -The first SDK release creates and edits developer-owned Cordis projects through the shared model defined by the [developer-project RFC](2026-07-14-sdk-developer-projects.md) and the [project-editing architecture](../architecture/2026-07-15-sdk-project-editing-architecture.md). Its create and config workflows are interactive, external Cordis plugins require manual dependency and configuration edits, command-line telemetry has no owning boundary, and interactive branches lack a stable test strategy. +The first SDK release creates and edits developer-owned Cordis projects through the shared model defined by the [developer-project Agent Note](2026-07-14-sdk-developer-projects.md) and the [project-editing architecture](../architecture/2026-07-15-sdk-project-editing-architecture.md). Its create and config workflows are interactive, external Cordis plugins require manual dependency and configuration edits, command-line telemetry has no owning boundary, and interactive branches lack a stable test strategy. These gaps are coupled. Create and config already share questions, feature configuration, and `ProjectEditSession`; adding separate automation paths would duplicate that domain logic. External-plugin installation must update both the package manager's files and `cordis.yml`. Telemetry must observe commands such as create and build that do not boot Cordis. Interactive testing must exercise Harness behavior without making terminal rendering a brittle product contract. diff --git a/docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.zh.md b/.agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.zh.md similarity index 95% rename from docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.zh.md rename to .agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.zh.md index 55648a368b..d0d0b3e6bc 100644 --- a/docs/rfc/proposed/feature/2026-07-17-sdk-follow-up-capabilities.zh.md +++ b/.agents/notes/proposed/feature/2026-07-17-sdk-follow-up-capabilities.zh.md @@ -1,4 +1,4 @@ -# RFC: SDK 后续功能 +# Agent Note: SDK 后续功能 Status: proposed @@ -6,7 +6,7 @@ Status: proposed ## 问题 -首个 SDK 版本通过[开发者工程 RFC](2026-07-14-sdk-developer-projects.md) 和 [SDK 工程编辑架构](../architecture/2026-07-15-sdk-project-editing-architecture.md)定义的共享模型创建和编辑开发者拥有的 Cordis 工程。create 和 config 工作流仅支持交互调用，接入外部 Cordis 插件需要手工修改依赖和配置，命令行遥测没有明确的所属边界，交互分支也缺少稳定的测试策略。 +首个 SDK 版本通过[开发者工程 Agent Note](2026-07-14-sdk-developer-projects.md) 和 [SDK 工程编辑架构](../architecture/2026-07-15-sdk-project-editing-architecture.md)定义的共享模型创建和编辑开发者拥有的 Cordis 工程。create 和 config 工作流仅支持交互调用，接入外部 Cordis 插件需要手工修改依赖和配置，命令行遥测没有明确的所属边界，交互分支也缺少稳定的测试策略。 这些缺口彼此关联。create 和 config 已经共享问题、功能配置和 `ProjectEditSession`；若另建自动化路径，就会复制领域逻辑。安装外部插件必须同时修改包管理器文件和 `cordis.yml`。遥测需要观察 create、build 等不会启动 Cordis 的命令。交互测试需要覆盖 Harness 自身行为，同时避免把终端渲染固化成脆弱的产品契约。 diff --git a/docs/rfc/proposed/process/2026-06-11-api-extractor-reports.md b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.md similarity index 81% rename from docs/rfc/proposed/process/2026-06-11-api-extractor-reports.md rename to .agents/notes/proposed/process/2026-06-11-api-extractor-reports.md index a6f3bfb14c..b32dc7e2af 100644 --- a/docs/rfc/proposed/process/2026-06-11-api-extractor-reports.md +++ b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.md @@ -1,8 +1,8 @@ -# RFC: API extractor reports +# Agent Note: API extractor reports Status: proposed -> Split out from the original "Doc-sync and API reports" RFC (2026-06-11). Parts 1-2 (doc-block typechecking, event-taxonomy verification) shipped — see [doc-sync enforcement](../../implemented/process/2026-06-11-doc-sync-enforcement.md). This is the deferred part 3, kept as a standalone proposal. +> Split out from the original "Doc-sync and API reports" Agent Note (2026-06-11). Parts 1-2 (doc-block typechecking, event-taxonomy verification) shipped — see [doc-sync enforcement](../../implemented/process/2026-06-11-doc-sync-enforcement.md). This is the deferred part 3, kept as a standalone proposal. ## Problem diff --git a/docs/rfc/proposed/process/2026-06-11-architectural-conformance.md b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.md similarity index 93% rename from docs/rfc/proposed/process/2026-06-11-architectural-conformance.md rename to .agents/notes/proposed/process/2026-06-11-architectural-conformance.md index e0d16b455d..006aa76ad1 100644 --- a/docs/rfc/proposed/process/2026-06-11-architectural-conformance.md +++ b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.md @@ -1,4 +1,4 @@ -# RFC: Architectural conformance — dependency rules and the adapter kit +# Agent Note: Architectural conformance — dependency rules and the adapter kit Status: proposed @@ -31,4 +31,4 @@ dependency-cruiser config + CI step first (an hour of work, permanent guarantee) Dep-cruiser rule maintenance as packages are added — keep rules pattern-based (`dsh-*`) rather than enumerated. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md similarity index 97% rename from docs/rfc/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md rename to .agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md index e787133026..a79f719751 100644 --- a/docs/rfc/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md +++ b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md @@ -1,4 +1,4 @@ -# RFC: Supply chain checks and vendor drift verification +# Agent Note: Supply chain checks and vendor drift verification Status: proposed diff --git a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.md similarity index 95% rename from docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md rename to .agents/notes/proposed/process/2026-06-20-discover-package-inventory.md index 8e4f4cce13..fa544d6ddb 100644 --- a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md +++ b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.md @@ -1,4 +1,4 @@ -# RFC: Discover package inventories instead of maintaining static lists +# Agent Note: Discover package inventories instead of maintaining static lists Status: proposed @@ -30,4 +30,4 @@ One cataloged item needs no generator at all: folding the e2e entry glob into kn Discovery scripts can become too clever. The implementation should stay boring: read manifests, filter on explicit fields, print the resolved list, and fail loud. The payoff is removing manual inventory drift, not inventing a build system. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/proposed/process/2026-07-13-human-review-skill-maintenance.md b/.agents/notes/proposed/process/2026-07-13-human-review-skill-maintenance.md similarity index 96% rename from docs/rfc/proposed/process/2026-07-13-human-review-skill-maintenance.md rename to .agents/notes/proposed/process/2026-07-13-human-review-skill-maintenance.md index 8098247fdf..6d4de215c9 100644 --- a/docs/rfc/proposed/process/2026-07-13-human-review-skill-maintenance.md +++ b/.agents/notes/proposed/process/2026-07-13-human-review-skill-maintenance.md @@ -1,4 +1,4 @@ -# RFC: Periodic human-review maintenance for dsh-code-review +# Agent Note: Periodic human-review maintenance for dsh-code-review Status: proposed @@ -8,7 +8,7 @@ The `dsh-code-review` skill records failure modes that require reviewer judgment ## Proposal -Periodic out-of-repo maintenance. A private tool, kept on the skill maintainer's machine rather than committed to this repository, runs against a clean full-history checkout at refreshed `origin/master`. The intended scheduler runs daily with a two-UTC-day overlap; manual runs accept another `--since` duration or repeated `--pr` arguments for an explicit set. The scan is idempotent against the current skill and stores no repository cursor. The only repository file changed by promotion is [.agents/skills/dsh-code-review/SKILL.md](../../../../.agents/skills/dsh-code-review/SKILL.md); the draft PR carries a provenance summary so reviewers can audit the source feedback and adoption evidence without the private adapter logs. +Periodic out-of-repo maintenance. A private tool, kept on the skill maintainer's machine rather than committed to this repository, runs against a clean full-history checkout at refreshed `origin/master`. The intended scheduler runs daily with a two-UTC-day overlap; manual runs accept another `--since` duration or repeated `--pr` arguments for an explicit set. The scan is idempotent against the current skill and stores no repository cursor. The only repository file changed by promotion is [.agents/skills/dsh-code-review/SKILL.md](../../../skills/dsh-code-review/SKILL.md); the draft PR carries a provenance summary so reviewers can audit the source feedback and adoption evidence without the private adapter logs. ```mermaid flowchart TD @@ -50,7 +50,7 @@ The promote helper starts from a clean checkout at refreshed `origin/master` and ### Where the mechanism lives -The tool source, adapter binaries, provider credentials, and intended daily scheduler are kept private to the maintainer's machine rather than committed to this repository. This document specifies the protocol; the reference implementation is private infrastructure. The mechanism serves a single skill maintained by a single operator, so the ongoing cost of vetting mechanism edits through repository review outweighs any provenance benefit. If the mechanism is ever handed off to a second maintainer, that handoff is a follow-up RFC that revises this decision — the operator doc at [docs/cookbook/maintaining-dsh-code-review.md](../../../cookbook/maintaining-dsh-code-review.md) is the entry point for anyone taking over. +The tool source, adapter binaries, provider credentials, and intended daily scheduler are kept private to the maintainer's machine rather than committed to this repository. This document specifies the protocol; the reference implementation is private infrastructure. The mechanism serves a single skill maintained by a single operator, so the ongoing cost of vetting mechanism edits through repository review outweighs any provenance benefit. If the mechanism is ever handed off to a second maintainer, that handoff is a follow-up Agent Note that revises this decision — the operator doc at [docs/cookbook/maintaining-dsh-code-review.md](../../../../docs/cookbook/maintaining-dsh-code-review.md) is the entry point for anyone taking over. ## Alternatives considered @@ -80,4 +80,4 @@ Promotion from `proposed/` to `implemented/` requires all of the following to be - **Two-non-candidate classifications routed to `excluded` without a dispute round.** When both classifiers say "not a candidate" but disagree on which non-candidate reason applies (for example `covered` vs `specific`), the item is excluded rather than re-evaluated. Both classifiers agree the item does not become new reviewer behavior, so a dispute round would not change the outcome. - **Dual-reviewer independence beyond byte-hash distinctness is a deployment contract.** The tool refuses to run when the two commands resolve to byte-identical executables, but cannot verify that two distinct wrappers back different providers or models. Operators must configure independent primary and secondary adapters. - **Best-effort compare-and-swap for candidate writes and rollback.** File-based CAS on POSIX is not truly atomic; the window is one event-loop tick. The tool targets single-user periodic maintenance and a truly concurrent editor is out of scope. -- **Single-maintainer bus factor.** Because the mechanism lives on one machine, its interruption stops skill maintenance entirely until the operator restores service or hands off to a new maintainer through a follow-up RFC. +- **Single-maintainer bus factor.** Because the mechanism lives on one machine, its interruption stops skill maintenance entirely until the operator restores service or hands off to a new maintainer through a follow-up Agent Note. diff --git a/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md similarity index 87% rename from docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md rename to .agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md index f874784a6d..1f52bfac25 100644 --- a/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md +++ b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md @@ -1,4 +1,4 @@ -# RFC: Prune dead public and result surface +# Agent Note: Prune dead public and result surface Status: proposed @@ -6,14 +6,14 @@ Status: proposed Several package-root exports, result fields, and convenience methods have no production consumer. They survive because tests import internals through public entry points or because a type anticipated a caller that never arrived. Each item is small in isolation, but together they enlarge the SDK contract, generated catalogs, documentation, and regression matrix without enabling a shipped path. -The production corpus is `packages/*/*/src`, example sources/config, and runtime scripts. Tests, package READMEs, and RFC prose are evidence of publication but not fixed callers. `cordis_inspect` makes `packages/cordis/tool-cordis/src/api-catalog.ts` model-visible, and `cordis_mount` can invoke injected services through guarded real-service proxies, so catalogued service methods and returned shapes are a genuine dynamic product surface. The table therefore distinguishes absence of a fixed repository caller from unreachability: rows touching catalogued vocabulary intentionally contract what model-written mounts can discover and call, while package-root implementation helpers are not reached through that service façade. Exact-symbol searches produce the following inventory: +The production corpus is `packages/*/*/src`, example sources/config, and runtime scripts. Tests, package READMEs, and Agent Note prose are evidence of publication but not fixed callers. `cordis_inspect` makes `packages/cordis/tool-cordis/src/api-catalog.ts` model-visible, and `cordis_mount` can invoke injected services through guarded real-service proxies, so catalogued service methods and returned shapes are a genuine dynamic product surface. The table therefore distinguishes absence of a fixed repository caller from unreachability: rows touching catalogued vocabulary intentionally contract what model-written mounts can discover and call, while package-root implementation helpers are not reached through that service façade. Exact-symbol searches produce the following inventory: | Surface | Production evidence | Simplification | | --- | --- | --- | | `SurfaceManager.invalidate()` | Only its unit test calls it; seeding completes before the lazily-created manager exists and the session never replaces its log reference. | Delete it and its impossible wholesale-replacement contract. | | `ToolExecutionResult.callId` | Every hook already receives the immutable `ToolExecution`; the loop and ACP correlate through the call/session event. No consumer reads the duplicate result field. | Remove the field, copy/mismatch guards, and tests that prove the duplicate cannot disagree. | | `ReactLoopAgent` root export | Outside-package named imports are tests; production programs against `Agent` and creates/resumes through `ctx.agents`. | Return/interface-type `Agent` and make the concrete loop class package-internal; keep the deliberate synchronous config-only `AgentLoop.create()` path. | -| `workflow-workerthread` protocol/runtime/session re-exports and named `WorkerWorkflowEngine` | Every package-name consumer uses the default engine; the workflow RFC already defines the worker wire protocol as private. | Keep the default plugin class/config contract; drop the duplicate named class export and keep protocol modules source-private. | +| `workflow-workerthread` protocol/runtime/session re-exports and named `WorkerWorkflowEngine` | Every package-name consumer uses the default engine; the workflow Agent Note already defines the worker wire protocol as private. | Keep the default plugin class/config contract; drop the duplicate named class export and keep protocol modules source-private. | | `code-runtime-worker` protocol/bootstrap re-exports | Outside-package production/e2e consumers use `WorkerCodeRuntime` and config, not `BootstrapPort`, `PatchableStream`, or worker message/boot types. | Keep the runtime class/config contract and make its wire/bootstrap vocabulary source-private. | | ACP translation/presenter root exports | `agentOptions`, `streamSessionEventUpdate`, `todosToPlan`, `ToolPresenter`, `nullToolPresenter`, and `TerminalRendering` have only same-file or ACP-test consumers; the sole outside-package production consumer mounts the plugin namespace. | Keep `name`, `inject`, `Config`, `AcpConfig`, and `apply`; make translation/presentation helpers source-private and test them in-package. | | `providerWording` and `completedTurnPrefix` root exports | Each has one same-package production caller; only the balanced-prefix helper has a same-package white-box test. | Make them source-private and test provider behavior. | @@ -23,7 +23,7 @@ The production corpus is `packages/*/*/src`, example sources/config, and runtime | `BlockAssembler.push()` return value | Both production callers ignore the returned completed block. | Return `void`; keep the deliberately public `blocks()`/`message()` contract. | | `compactRegion`'s separate `session` argument | The fixed caller passes the same object already present as `agent.session`; the model-visible mount API can also call the method, but accepting two identities permits a mounted plugin to provide an incoherent pair. | Keep the manual-region seam while deliberately narrowing it to `agent.session` as the one source of truth. | | `CompactionResult.startSeq`, `summarySeq`, `endSeq`, and `summary` | The production consumer reads only shadowed range/seq/token accounting; the durable log owns summary and event identity. | Remove the four result echoes while keeping both shared transcript renderers. | -| `BasicCompactService` estimation/summarization visibility | No outside production caller invokes the five methods; the implemented RFC names only `estimateContentTokens()` and `summarize()` as subclass hooks. | Make those two `protected` and the three orchestration-only estimators private. | +| `BasicCompactService` estimation/summarization visibility | No outside production caller invokes the five methods; the implemented Agent Note names only `estimateContentTokens()` and `summarize()` as subclass hooks. | Make those two `protected` and the three orchestration-only estimators private. | | `CodeLogEntry.source`/`level` and `RunCodeMeta.dispatches` | Every production consumer maps logs to text; no presenter/model path reads the other fields or the persisted dispatch count. | Make code-runtime logs strings (or text-only entries) and remove result-meta dispatch plumbing; keep the local counter that mints deterministic dispatch ids. | | `CodeRuntime.language` and `CodeRuntime.isolation` | The worker backend supplies the only production values, while Code Mode and every other production caller invoke only `run()`. | Remove the unread descriptors while preserving the worker's language, isolation, budgets, cancellation, and disposal behavior. | | `ToolNotFoundError.toolName`, `SystemPrompt.config`, and `BashTask.command` | Each stored public value has no production reader. | Drop the unread field while retaining error messages, resolved configuration behavior, and task lifecycle. | @@ -51,8 +51,8 @@ Remove or demote every row as one bounded coordinated public-surface cleanup. Up ## Acceptance criteria -- Exact-symbol searches show no removed surface outside this RFC and any implemented-RFC amendments. -- Every surface listed in this RFC is absent or demoted as specified; deliberately retained extension/test contracts outside the inventory are unchanged. +- Exact-symbol searches show no removed surface outside this Agent Note and any implemented-Agent Note amendments. +- Every surface listed in this Agent Note is absent or demoted as specified; deliberately retained extension/test contracts outside the inventory are unchanged. - Tool execution, compaction, both LLM adapters, both persistence backends, workflow isolation, and agent creation/resume retain their shipped behavior. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml similarity index 63% rename from docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml rename to .agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml index e04aed96a6..50dfd13aab 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml +++ b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-make-jsonrpc-directional.md: 2a9579c53c111887e9d93cf02cc832304a496795 -2026-07-19-make-jsonrpc-directional.zh.md: 4f3793f1b4de3b4f69c4219c10fe5b3b360c8692 +2026-07-19-make-jsonrpc-directional.md: 74de3c960a415a9a2601e57ec75f244ca753193d +2026-07-19-make-jsonrpc-directional.zh.md: 76228ba56cfbd4fb86f39d0d0873d49edb13309b diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md similarity index 98% rename from docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md rename to .agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md index 2a9579c53c..74de3c960a 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md +++ b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md @@ -1,4 +1,4 @@ -# RFC: Make JSON-RPC completion and transport directional +# Agent Note: Make JSON-RPC completion and transport directional Status: proposed diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md similarity index 98% rename from docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md rename to .agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md index 4f3793f1b4..76228ba56c 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md +++ b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md @@ -1,4 +1,4 @@ -# RFC: 让 JSON-RPC 完成结果与传输方向单一化 +# Agent Note: 让 JSON-RPC 完成结果与传输方向单一化 Status: proposed diff --git a/docs/rfc/proposed/testing/2026-06-11-deterministic-and-stress-testing.md b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md similarity index 92% rename from docs/rfc/proposed/testing/2026-06-11-deterministic-and-stress-testing.md rename to .agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md index 2a30969ba4..c3b17c401a 100644 --- a/docs/rfc/proposed/testing/2026-06-11-deterministic-and-stress-testing.md +++ b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md @@ -1,4 +1,4 @@ -# RFC: Deterministic tests, the replay invariant fixture, and race stress +# Agent Note: Deterministic tests, the replay invariant fixture, and race stress Status: proposed @@ -28,4 +28,4 @@ Land 1 and 2 together (they touch the same helpers); add the nightly job after t Fake timers interact subtly with Promise scheduling in the loop — prefer event-driven waits; reserve fake timers for timer-service behavior itself. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/proposed/testing/2026-06-11-mutation-testing.md b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.md similarity index 93% rename from docs/rfc/proposed/testing/2026-06-11-mutation-testing.md rename to .agents/notes/proposed/testing/2026-06-11-mutation-testing.md index 8c68ccf09f..35df228b85 100644 --- a/docs/rfc/proposed/testing/2026-06-11-mutation-testing.md +++ b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.md @@ -1,4 +1,4 @@ -# RFC: Mutation testing as the coverage counterweight +# Agent Note: Mutation testing as the coverage counterweight Status: proposed @@ -31,4 +31,4 @@ Stryker (`@stryker-mutator/vitest-runner`) over `packages/*/src`: Runtime: mutation testing is expensive; per-file 100% coverage helps (every mutant is at least reached). If PR-scoped runs stay too slow, keep them nightly-only and rely on the score ratchet. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/architecture/2026-06-11-immutable-public-surfaces.md b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md similarity index 95% rename from docs/rfc/rejected/architecture/2026-06-11-immutable-public-surfaces.md rename to .agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md index 3eedd92a2d..0c6652a94d 100644 --- a/docs/rfc/rejected/architecture/2026-06-11-immutable-public-surfaces.md +++ b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md @@ -1,4 +1,4 @@ -# RFC: Deep-readonly public surfaces +# Agent Note: Deep-readonly public surfaces Status: rejected — the pervasive `DeepReadonly<T>` type flip is replaced by source-owned runtime immutability in `Session` plus relational development assertions. See [source-owned session immutability and dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md). @@ -24,4 +24,4 @@ Introduce `DeepReadonly`, flip the session read paths, and fix the resulting com `DeepReadonly` types can produce noisy errors at waterfall boundaries where mutation IS the API — keep the mutable/readonly boundary exactly at "logged vs in-flight" and document it in the session README. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/architecture/2026-06-20-providerless-example-base.md b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md similarity index 90% rename from docs/rfc/rejected/architecture/2026-06-20-providerless-example-base.md rename to .agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md index 0fd4ca27f7..81dbe40ee4 100644 --- a/docs/rfc/rejected/architecture/2026-06-20-providerless-example-base.md +++ b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md @@ -1,4 +1,4 @@ -# RFC: Make the shared example base providerless +# Agent Note: Make the shared example base providerless Status: rejected — superseded by [Extract example apps into packages](../../implemented/architecture/2026-06-20-extract-example-app-packages.md), which moves the spine into a `dsh-agent-spine-demo` bundle and deletes the `base*.yml` files, so there is no shared base YAML left to rename. @@ -20,10 +20,10 @@ The shared base should contain only provider-neutral services and tools: `llm`, - `examples/base-core.yml` is deleted. - Real demo configs explicitly add the DeepSeek adapter. - Snapshot replay config includes the same providerless base and its replay adapter. -- The [examples README](../../../../examples/README.md), example-specific READMEs, and RFC references stop explaining "base = base-core plus adapter". +- The [examples README](../../../../examples/README.md), example-specific READMEs, and Agent Note references stop explaining "base = base-core plus adapter". ## What we give up Real demos lose one layer of convenience: each must opt into the adapter. That is the right default for examples, because adapter choice is the variable part and providerless wiring is the shared product core. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md similarity index 84% rename from docs/rfc/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md rename to .agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md index 088fa8d25d..62dd7609e8 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md +++ b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md @@ -1,10 +1,10 @@ -# RFC: Persist assembled assistant messages, not stream chunks +# Agent Note: Persist assembled assistant messages, not stream chunks Status: rejected — high-fidelity chunk replay, partial failed streams, and snapshot replay currently depend on persisted `assistant/chunk` events. Dropping chunks is only viable with a no-information-loss replay/artifact replacement. ## Problem -The canonical session log currently persists every `assistant/chunk` exactly as streamed by the model. The [session persistence RFC](../../implemented/architecture/2026-06-14-session-persistence.md) chose this for token-level replay fidelity and contiguous `seq`, but the cost has grown: JSONL fixtures are dominated by tiny delta records, snapshot scenarios replay the model by grouping chunk events, ACP load reconstructs prior assistant output from chunks, and any future log reader must distinguish durable message history from token-level trace. +The canonical session log currently persists every `assistant/chunk` exactly as streamed by the model. The [session persistence Agent Note](../../implemented/architecture/2026-06-14-session-persistence.md) chose this for token-level replay fidelity and contiguous `seq`, but the cost has grown: JSONL fixtures are dominated by tiny delta records, snapshot scenarios replay the model by grouping chunk events, ACP load reconstructs prior assistant output from chunks, and any future log reader must distinguish durable message history from token-level trace. For successful steps that assemble completed content, the loop already appends an `assistant/message`. That is the event `deriveMessages()` uses for the next model request. In other words, the normal resumable conversation state is already present without the chunks; chunks are a live rendering and deterministic-test artifact, not required conversation history. Failed or aborted streams are different: partial assistant output may exist only as chunks, and empty max-token steps may produce no `assistant/message` at all. @@ -31,4 +31,4 @@ The canonical user session no longer reconstructs the exact token stream of an o This supersedes the chunk-persistence choice in [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md) and affects [ACP snapshot tests](../../implemented/testing/2026-06-19-acp-snapshot-tests.md), whose current replay plugin derives its script from `assistant/chunk` events. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-drop-acp-session-load.md b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md similarity index 93% rename from docs/rfc/rejected/simplification/2026-06-20-drop-acp-session-load.md rename to .agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md index 18cd6e981d..b8b9b29987 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-drop-acp-session-load.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md @@ -1,4 +1,4 @@ -# RFC: Drop ACP session/load until resume has a product shape +# Agent Note: Drop ACP session/load until resume has a product shape Status: rejected — Zed is the current target ACP client, advertises and exercises load-capable sessions, and keeps pending-load state for concurrent `session/load`. The bridge should keep `session/load` and make the resume contract solid. @@ -24,4 +24,4 @@ For now, ACP starts fresh sessions only. `initialize` advertises `loadSession: f An editor cannot reopen a prior persisted session through ACP. That is a real product feature, but the current implementation is ahead of the UX and ties the bridge to token-level log replay. Keeping persistence while dropping editor load narrows the bridge to the workflow it can currently present cleanly. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md similarity index 68% rename from docs/rfc/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md rename to .agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md index 2f1408dc4c..8ce4803f73 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md @@ -1,10 +1,10 @@ -# RFC: Drop ACP terminal `_meta` rendering +# Agent Note: Drop ACP terminal `_meta` rendering Status: rejected — Zed is the current target client, and the terminal `_meta` convention is intentional Zed UX with a plain ACP fallback for other clients. ## Problem -The ACP bridge implements a Zed-specific terminal-card convention through `_meta.terminal_info`, `_meta.terminal_output`, and `_meta.terminal_exit`. The implemented [rich ACP bash rendering RFC](../../implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) deliberately avoided ACP's client-side `terminal/create` because bash execution belongs in the harness, but still adopted the reference agents' display-only `_meta` convention. That gives a nicer Zed card at the cost of bridge state, capability negotiation, terminal ids, special update mapping, text fallback tests, and exit-pill parsing in `dsh-tool-bash`. +The ACP bridge implements a Zed-specific terminal-card convention through `_meta.terminal_info`, `_meta.terminal_output`, and `_meta.terminal_exit`. The implemented [rich ACP bash rendering Agent Note](../../implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) deliberately avoided ACP's client-side `terminal/create` because bash execution belongs in the harness, but still adopted the reference agents' display-only `_meta` convention. That gives a nicer Zed card at the cost of bridge state, capability negotiation, terminal ids, special update mapping, text fallback tests, and exit-pill parsing in `dsh-tool-bash`. The fallback path already exists: render the tool call and completed output as normal ACP content blocks. Non-Zed clients rely on that path anyway, but the Zed terminal card is a current target-client feature rather than speculative decoration. @@ -20,10 +20,10 @@ This proposal is narrower than [collapsing tool-owned UI presentation](2026-06-2 - `TerminalRendering`, terminal ids, terminal cwd resolution, and `_meta.terminal_*` update mapping disappear from `@deepseek-ai/dsh-acp`. - `ToolTerminal` disappears from `@deepseek-ai/dsh-tools`, or is unused and deleted with the presentation cleanup. - Bash result presentation no longer parses exit status for terminal pills. -- The implemented [rich ACP bash rendering RFC](../../implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) stays in `implemented/` as shipped history and is cross-linked from this proposal if superseded. +- The implemented [rich ACP bash rendering Agent Note](../../implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) stays in `implemented/` as shipped history and is cross-linked from this proposal if superseded. ## What we give up Zed users lose the dedicated terminal card: no cwd header, terminal display, or exit pill. They still see the command and output as plain content. That is a reasonable simplification while the ACP bridge is still unreleased and the `_meta` keys are a convention rather than a standard. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md similarity index 88% rename from docs/rfc/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md rename to .agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md index 859bd6f23d..939255f91e 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md @@ -1,4 +1,4 @@ -# RFC: Drop bash full-output spill files +# Agent Note: Drop bash full-output spill files Status: rejected — full-output recovery is a real bash behavior. A future artifact/blob service may generalize it, but dropping spill files before that replacement would lose useful command output. @@ -20,10 +20,10 @@ This proposal can land independently of [a generic long-running tool runtime](.. - `OutputCollector` keeps bounded buffers only and deletes the temp-file machinery. - `renderResult()` reports truncation without a filesystem path. - Tests cover tail truncation and no longer assert full-output file contents. -- Security guidance in [docs/defensive-patterns.md](../../../defensive-patterns.md) stops treating private spill files as a model-visible interface. +- Security guidance in [docs/defensive-patterns.md](../../../../docs/defensive-patterns.md) stops treating private spill files as a model-visible interface. ## What we give up A model or user cannot recover the omitted prefix of a huge command output from a temp file. That is acceptable until there is a real artifact service. The current spill path is too much bespoke machinery for a feature whose lifecycle and permissions are not designed. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md similarity index 90% rename from docs/rfc/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md rename to .agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md index 2aad598f6d..b2bf42a348 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md @@ -1,4 +1,4 @@ -# RFC: Drop durable step boundary events +# Agent Note: Drop durable step boundary events Status: rejected — `step/end` is the durable indication that a model step finished, and keeping the symmetric `step/start` / `step/end` pair makes crash repair, invariants, and transcript inspection clearer than inferring completion from adjacent step-scoped events. @@ -20,11 +20,11 @@ The invariants plugin should enforce that step-scoped events have valid positive - The loop has no `closeStep()` finalization path. - ACP snapshots and persistence contract fixtures stop expecting step-boundary lines. - `deriveMessages()` and replay derive the same message history from step-scoped events. -- The [event taxonomy docs](../../../architecture.md) describe turns as the durable boundary and steps as a field on step-scoped records. +- The [event taxonomy docs](../../../../docs/architecture.md) describe turns as the durable boundary and steps as a field on step-scoped records. - The session format version and recorded fixtures are refreshed; non-current stored logs are rejected per the pre-release format policy. ## What we give up The log no longer records "a model request started but produced no event before the process died" as a durable fact, and no longer has an explicit "this step completed" marker. That loss is not acceptable while the session log is the durable replay and audit surface. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-drop-unused-session-lineage.md b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md similarity index 94% rename from docs/rfc/rejected/simplification/2026-06-20-drop-unused-session-lineage.md rename to .agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md index fc06cc76c9..c85e943476 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-drop-unused-session-lineage.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md @@ -1,4 +1,4 @@ -# RFC: Drop unused session lineage metadata +# Agent Note: Drop unused session lineage metadata Status: rejected — `parentSession` is part of the documented fork/sub-agent seam and is already preserved by the agent/session resume path. The field is future-facing, but it is not accidental dead state. @@ -26,4 +26,4 @@ If lineage returns, decide then whether it belongs in the immutable header, a se The codebase loses a ready-made lineage hook for future fork/sub-agent UX. That is intentional. The field is easy to reintroduce when the feature exists, and the unreleased stance lets the format change without migrations. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-fold-session-persistence-interface.md b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md similarity index 94% rename from docs/rfc/rejected/simplification/2026-06-20-fold-session-persistence-interface.md rename to .agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md index a59c992b0d..8e5d59172f 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-fold-session-persistence-interface.md +++ b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md @@ -1,4 +1,4 @@ -# RFC: Fold the persistence interface into dsh-session +# Agent Note: Fold the persistence interface into dsh-session Status: rejected — the separate persistence interface package is the intended modular capability seam for durable backends. Folding it into `dsh-session` would reduce package count at the cost of a cleaner backend boundary. @@ -26,4 +26,4 @@ The implementing PR should update the [capability seams](../../implemented/archi `dsh-session` becomes heavier: it owns both the in-memory log and the persistence interface. That is the trade. If third-party persistence backends were already a public ecosystem, the separate interface package would be a cleaner SDK boundary; pre-release, the extra package looks like abstraction before there is an external consumer. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-generic-tool-rendering.md b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md similarity index 93% rename from docs/rfc/rejected/simplification/2026-06-20-generic-tool-rendering.md rename to .agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md index 87d739ba54..dbc6ffed44 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-generic-tool-rendering.md +++ b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md @@ -1,4 +1,4 @@ -# RFC: Collapse tool-owned UI presentation +# Agent Note: Collapse tool-owned UI presentation Status: rejected — tool-owned presentation should wait for more real tools before being generalized or deleted. Bash and ACP currently need the existing richer presentation path. @@ -30,4 +30,4 @@ Bash loses its custom terminal-looking card and model-written description placem ## Related -This is the broad version of [dropping ACP terminal metadata](2026-06-20-drop-acp-terminal-meta.md). If this RFC is accepted, that narrower RFC becomes unnecessary. +This is the broad version of [dropping ACP terminal metadata](2026-06-20-drop-acp-terminal-meta.md). If this Agent Note is accepted, that narrower Agent Note becomes unnecessary. diff --git a/docs/rfc/rejected/simplification/2026-06-20-retire-mid-turn-steering.md b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md similarity index 96% rename from docs/rfc/rejected/simplification/2026-06-20-retire-mid-turn-steering.md rename to .agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md index fd1a4687b3..b26243f197 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-retire-mid-turn-steering.md +++ b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md @@ -1,4 +1,4 @@ -# RFC: Retire mid-turn steering +# Agent Note: Retire mid-turn steering Status: rejected — mid-turn steering is an intentional agent capability for between-step user/plugin input and future goal/loop workflows. It is complexity with a product direction, not an accidental duplicate of `send()`. @@ -32,4 +32,4 @@ A user cannot add same-turn steering content while a model is between tool steps This pairs naturally with [dropping durable step boundaries](2026-06-20-drop-durable-step-boundaries.md), because removing same-turn steering and `agent/turn-continuation` leaves tool calls as the only reason a turn contains multiple model steps. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-single-session-acp-bridge.md b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md similarity index 88% rename from docs/rfc/rejected/simplification/2026-06-20-single-session-acp-bridge.md rename to .agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md index 8f1d4e4531..83c6f598d4 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-single-session-acp-bridge.md +++ b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md @@ -1,10 +1,10 @@ -# RFC: Return the ACP bridge to one live session per connection +# Agent Note: Return the ACP bridge to one live session per connection Status: rejected — Zed is the current target ACP client and its ACP implementation is explicitly multi-session: it stores live sessions in a `HashMap<SessionId, AcpSession>`, tracks `pending_sessions`, joins concurrent loads for the same id, and tests close-during-load behavior. ## Problem -The ACP bridge now supports multiple live sessions on one JSON-RPC connection. That capability brings multi-entry session maps, reverse session/agent lookups, per-session prompt state, loading ids, demux for every event, cross-session teardown, and isolation concerns for future permission prompts and background tasks. The older [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) still tracks the unfinished permission-ownership piece; this RFC is the competing simplification path. +The ACP bridge now supports multiple live sessions on one JSON-RPC connection. That capability brings multi-entry session maps, reverse session/agent lookups, per-session prompt state, loading ids, demux for every event, cross-session teardown, and isolation concerns for future permission prompts and background tasks. The older [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) still tracks the unfinished permission-ownership piece; this Agent Note is the competing simplification path. The product target has proven it needs concurrent editor conversations over one harness process: Zed's ACP connection owns multiple sessions and load states. The snapshot replay tier still avoids concurrent model streams because its replay entries are positional; that is a test-fixture limitation, not a reason to remove bridge multiplexing. @@ -20,10 +20,10 @@ Remove the multi-session maps and demux where a single `SessionRecord | undefine - `session/new` and `session/load` reject while that record exists. - Event handlers no longer demux across a `Map<sessionId, record>`. - Multi-session tests are removed or moved under the proposal that continues to defend multiplexing. -- The existing [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) is updated to link this RFC and remains the live direction. +- The existing [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) is updated to link this Agent Note and remains the live direction. ## What we give up An ACP client cannot host several concurrent conversations on one server process. That is a meaningful capability cut. The simpler model is still reasonable for an unreleased harness: one editor conversation maps to one agent process, and cross-session permission/background-task isolation stops being a live correctness burden. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-06-20-truncate-interrupted-turns.md b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md similarity index 96% rename from docs/rfc/rejected/simplification/2026-06-20-truncate-interrupted-turns.md rename to .agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md index 1ed26c66f8..a685765197 100644 --- a/docs/rfc/rejected/simplification/2026-06-20-truncate-interrupted-turns.md +++ b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md @@ -1,4 +1,4 @@ -# RFC: Truncate interrupted final turns on load +# Agent Note: Truncate interrupted final turns on load Status: rejected — a single turn can contain substantial real work, including many steps and large tool output. Preserving interrupted turns is preferable to silently dropping that tail on load. @@ -31,4 +31,4 @@ A crash can lose real work from the final turn: assistant text, tool calls, and This is a direct simplification of [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md) and [turn enclosure](../../implemented/architecture/2026-06-15-turn-enclosure-invariant.md). It also removes much of the motivation for durable step boundary events, making [drop durable step boundary events](2026-06-20-drop-durable-step-boundaries.md) smaller. -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/docs/rfc/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md similarity index 65% rename from docs/rfc/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md rename to .agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md index 266a1d911d..582673f185 100644 --- a/docs/rfc/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md +++ b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md @@ -1,4 +1,4 @@ -# RFC: Prune the unimplemented subagent seam vocabulary +# Agent Note: Prune the unimplemented subagent seam vocabulary Status: rejected — the deferred capability vocabulary (`outputSchema`/`structured`, `toolFilter`, `sendMessage`/`resume`) is intentionally reserved surface: the seam advertises the full intended contract ahead of its implementations by design, so providers and consumers grow into a stable shape rather than re-negotiating it per capability. The consumer-evidence analysis below records the decision-time state. @@ -13,11 +13,11 @@ The only reason `dsh-subagent` depends on `dsh-tools` at all is `outputSchema`'s ## Proposal -Remove `outputSchema`/`structured`, `toolFilter`, `sendMessage`, and `resume` from the seam; shrink `SubagentCapabilities` to `{ depthLimit }`; drop the two capability-assert rows, the all-false flags on the three providers, the scripted fixture's structured branch and capability knobs, and the tests that exist to pin the removed surface. Drop the `dsh-tools` peer/dev dependency from `packages/subagent/subagent/package.json`. Update the [subagent.md](../../../core-data-structures/subagent.md) pastes and the type-equiv manifest, plus the affected provider READMEs. The implementing PR amends the seam RFC's capability catalog per [implemented/AGENTS.md](../../implemented/AGENTS.md). +Remove `outputSchema`/`structured`, `toolFilter`, `sendMessage`, and `resume` from the seam; shrink `SubagentCapabilities` to `{ depthLimit }`; drop the two capability-assert rows, the all-false flags on the three providers, the scripted fixture's structured branch and capability knobs, and the tests that exist to pin the removed surface. Drop the `dsh-tools` peer/dev dependency from `packages/subagent/subagent/package.json`. Update the [subagent.md](../../../../docs/core-data-structures/subagent.md) pastes and the type-equiv manifest, plus the affected provider READMEs. The implementing PR amends the seam Agent Note's capability catalog per [implemented/AGENTS.md](../../implemented/AGENTS.md). **Keep** `depthLimit`/`maxDepth` and capability checks. The in-process backend enforces the limit, although the shipping tool does not yet set it. Recursion is a known seam risk, so the appropriate follow-up is to supply a tool default rather than delete working enforcement. -Adjacent surface examined and deliberately left alone: `SubagentService.getProvider()`/`list()` have test-harness consumers only, but the [prune-dead-seam-methods implementation note](../../implemented/simplification/2026-06-20-prune-dead-seam-methods.md) records precisely this shape being removed from the bash executor and reverted — a test harness IS a consumer for a one-line accessor over an already-tracked map. `SubagentRunEndInfo.lastAssistantMessage` is a recorded keep (the [subagent-observe-enrich RFC](../../implemented/feature/2026-06-30-subagent-observe-enrich.md)'s review dropped `agentType` and kept it deliberately, as the only final-message channel for out-of-process children); its currently-unwired bridge forwarding is a gap to close or a consumer to document, not surface for this RFC to cut. +Adjacent surface examined and deliberately left alone: `SubagentService.getProvider()`/`list()` have test-harness consumers only, but the [prune-dead-seam-methods implementation note](../../implemented/simplification/2026-06-20-prune-dead-seam-methods.md) records precisely this shape being removed from the bash executor and reverted — a test harness IS a consumer for a one-line accessor over an already-tracked map. `SubagentRunEndInfo.lastAssistantMessage` is a recorded keep (the [subagent-observe-enrich Agent Note](../../implemented/feature/2026-06-30-subagent-observe-enrich.md)'s review dropped `agentType` and kept it deliberately, as the only final-message channel for out-of-process children); its currently-unwired bridge forwarding is a gap to close or a consumer to document, not surface for this Agent Note to cut. This is the seam-vocabulary echo of [prune dead methods from the persistence seam](../../implemented/simplification/2026-06-20-prune-dead-seam-methods.md): members every implementation must declare for nobody — weaker even, since here zero implementations exist. @@ -25,13 +25,13 @@ This is the seam-vocabulary echo of [prune dead methods from the persistence sea ### Why not keep it? -The two-kinds-of-capability design is the seam RFC's headline, and re-adding `outputSchema` later touches several files. But the design survives with `depthLimit` as its live example and the RFCs as its record, and the seam RFC itself concedes the shipped `toolFilter` shape is wrong (real enforcement needs a `tools/pre-execute` deny in the child's context, not schema filtering) — that deny primitive exists on the interception seams, so re-adding against a real implementing provider will pin a better contract than the current speculative one. +The two-kinds-of-capability design is the seam Agent Note's headline, and re-adding `outputSchema` later touches several files. But the design survives with `depthLimit` as its live example and the Agent Notes as its record, and the seam Agent Note itself concedes the shipped `toolFilter` shape is wrong (real enforcement needs a `tools/pre-execute` deny in the child's context, not schema filtering) — that deny primitive exists on the interception seams, so re-adding against a real implementing provider will pin a better contract than the current speculative one. ## Acceptance criteria -- The removed spellings appear only in this RFC and the amended seam RFCs; `SubagentCapabilities` is `{ depthLimit: boolean }`; the `dsh-tools` dependency edge is gone (`hygiene` green). +- The removed spellings appear only in this Agent Note and the amended seam Agent Notes; `SubagentCapabilities` is `{ depthLimit: boolean }`; the `dsh-tools` dependency edge is gone (`hygiene` green). - Depth-enforcement tests are unchanged and green. ## Risks -The subagent lifecycle events carry `lastAssistantMessage` on the end payload — that enrichment lives in the service module, not the seam vocabulary this RFC shrinks, and the observe-enrich RFC records dropping an `agentType` sibling for lacking a consumer: the judgment this RFC extends. The CC hooks bridge, the first outside consumer of those lifecycle events, reads only the event payloads and touches none of the surface removed here; the observe-enrich RFC's deferred control-flow redesign names implementing `resume` as its own future work — exactly the re-add trigger this RFC's pattern anticipates. +The subagent lifecycle events carry `lastAssistantMessage` on the end payload — that enrichment lives in the service module, not the seam vocabulary this Agent Note shrinks, and the observe-enrich Agent Note records dropping an `agentType` sibling for lacking a consumer: the judgment this Agent Note extends. The CC hooks bridge, the first outside consumer of those lifecycle events, reads only the event payloads and touches none of the surface removed here; the observe-enrich Agent Note's deferred control-flow redesign names implementing `resume` as its own future work — exactly the re-add trigger this Agent Note's pattern anticipates. diff --git a/docs/rfc/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md similarity index 91% rename from docs/rfc/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md rename to .agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md index 7624629d41..dcfdfa13e6 100644 --- a/docs/rfc/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md +++ b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md @@ -1,4 +1,4 @@ -# RFC: Collapse workflows to the exercised foreground core +# Agent Note: Collapse workflows to the exercised foreground core Status: rejected — Workflow progress is an intentional observation surface; make it useful through a consumer instead of deleting it. @@ -18,7 +18,7 @@ Cancellation also has two public channels for one synchronous start. `WorkflowSt Keep the exercised core: `agent(prompt, { schema, model })`, `parallel`, `pipeline`, `args`, concurrency/agent caps, cancellation, bounded disposal, structured results, worker isolation, and foreground tool collection. Remove all `workflow/*` events and their event-only info/outcome types; remove `phase()`, `log()`, agent `label`/`phase`, phase declarations, `whenToUse`, and their worker messages/host observers; collapse workflow metadata to the name the tool actually uses; remove event-only run ids/meta snapshots and the synthesized agent-end ledger. Shrink `WorkflowRun` to `result`, `cancel()`, and `dispose()`; the tool renders the request-owned name. Remove `WorkflowStartRequest.signal` and the worker host's input-signal listener/disarm state, retaining the caller-owned bridge from its abort signal to `run.cancel()`. Make `WorkflowError` one fatal error class without a boolean mode or `isFatalWorkflowError()` helper. -Amend the implemented dynamic-workflow RFC and update the seam/tool/worker READMEs, tool schema, generated catalogs and package graph, worker type-equivalence records, unit tests, and workflow snapshot/header fixtures. Progress UI work, if commissioned, starts from a correlation contract that names the parent agent/session/tool call instead of reviving this protocol unchanged. +Amend the implemented dynamic-workflow Agent Note and update the seam/tool/worker READMEs, tool schema, generated catalogs and package graph, worker type-equivalence records, unit tests, and workflow snapshot/header fixtures. Progress UI work, if commissioned, starts from a correlation contract that names the parent agent/session/tool call instead of reviving this protocol unchanged. ## Alternatives considered diff --git a/docs/rfc/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md similarity index 76% rename from docs/rfc/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md rename to .agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md index cafd50e8a5..e96215a651 100644 --- a/docs/rfc/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md +++ b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md @@ -1,4 +1,4 @@ -# RFC: Prune unused skill registry surface +# Agent Note: Prune unused skill registry surface Status: rejected — Direct runtime skill registration is an intentional extension path for third-party plugins. @@ -10,11 +10,11 @@ The skill service's embedded-runtime subsystem has zero production caller of `ct Remove `SkillService.register()`, `SkillRegistration`, the runtime pseudo-provider and reserved-name rules, runtime revisions/cache branches, and runtime-only source/rank normalization. Tests that need an embedded skill register a small real provider. Retain `providerRevision` as the in-flight discovery epoch, but key completed catalogs by cwd alone: every provider mutation synchronously clears the cache, and the post-await revision comparison already prevents inserting stale work. Remove `whenToUse`, `SkillCandidate.path`, and `SkillDefinition.path` from the skill contract and local-provider copies while retaining provider locator/root paths; retain `metadata`, `disableModelInvocation`, `source`, `provider`, `locator`, and `resourceBase` as either deliberate extension vocabulary or production-consumed fields. -Amend the skill-system RFC, README, JSDoc, catalogs, and tests. Agent-scoped system-prompt sections, tool providers, and variables are explicitly outside this proposal: the [agent-scope contributor contract](../../implemented/architecture/2026-07-08-agent-scope-contexts.md) intentionally allows all three to be registered during `setup(agentCtx)` through the agent-owned context, so absence of a fixed in-repo scoped registration is not evidence of non-consumption. +Amend the skill-system Agent Note, README, JSDoc, catalogs, and tests. Agent-scoped system-prompt sections, tool providers, and variables are explicitly outside this proposal: the [agent-scope contributor contract](../../implemented/architecture/2026-07-08-agent-scope-contexts.md) intentionally allows all three to be registered during `setup(agentCtx)` through the agent-owned context, so absence of a fixed in-repo scoped registration is not evidence of non-consumption. ## Alternatives considered -**Keep runtime skill registration for embedders.** It is a deliberate synchronous direct-definition convenience in the implemented skill RFC. A small provider wrapper can expose the same embedded data under effect-owned lifetime, but it must implement async `list()`/`get()`, carry provider identity, and accept provider duplicate semantics. The proposal chooses that one regular path over preserving a second ranking, validation, cache-invalidation, and lookup path. +**Keep runtime skill registration for embedders.** It is a deliberate synchronous direct-definition convenience in the implemented skill Agent Note. A small provider wrapper can expose the same embedded data under effect-owned lifetime, but it must implement async `list()`/`get()`, carry provider identity, and accept provider duplicate semantics. The proposal chooses that one regular path over preserving a second ranking, validation, cache-invalidation, and lookup path. ## Acceptance criteria diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml b/.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml similarity index 62% rename from docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml rename to .agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml index d2a15cc2c2..98acc791c3 100644 --- a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml +++ b/.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-fold-compaction-package-split.md: 7c7a2da85beb956f8d6c24f813fc33aa350b5c0e -2026-07-19-fold-compaction-package-split.zh.md: 37d75671d57226742608a525ea711b34780e65c6 +2026-07-19-fold-compaction-package-split.md: 47c9feb6bb0dd06fec0f002b7c1e930b288abe5e +2026-07-19-fold-compaction-package-split.zh.md: 53717ff10d1210bd2072f322d1936ac6c389afcd diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md b/.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.md similarity index 97% rename from docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md rename to .agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.md index 7c7a2da85b..47c9feb6bb 100644 --- a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md +++ b/.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.md @@ -1,4 +1,4 @@ -# RFC: Fold the single compaction backend into its service package +# Agent Note: Fold the single compaction backend into its service package Status: rejected — More compaction backends are planned, so the interface and basic implementation packages remain separate. diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md b/.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md similarity index 98% rename from docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md rename to .agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md index 37d75671d5..53717ff10d 100644 --- a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md +++ b/.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md @@ -1,4 +1,4 @@ -# RFC: 将唯一的压缩后端并入服务包 +# Agent Note: 将唯一的压缩后端并入服务包 Status: rejected — 计划增加更多压缩后端，因此接口包与 basic 实现包继续分离。 diff --git a/.agents/skills/dsh-code-review/SKILL.md b/.agents/skills/dsh-code-review/SKILL.md index e1493d04f2..c980ad444c 100644 --- a/.agents/skills/dsh-code-review/SKILL.md +++ b/.agents/skills/dsh-code-review/SKILL.md @@ -13,8 +13,8 @@ description: Use when reviewing a pull request in the deepseek-harness repo — - [docs/defensive-patterns.md](../../../docs/defensive-patterns.md): subprocess, callback, async-state, and disposal bug classes. - [docs/AGENTS.md](../../../docs/AGENTS.md): documentation placement and prose discipline. - [dsh-prose-standard](../dsh-prose-standard/SKILL.md): required coverage and editorial judgment for comments, docs, prompts, and visible strings. -- [docs/testing.md](../../../docs/testing.md) and the [quality-gates RFC](../../../docs/rfc/implemented/process/2026-06-11-quality-gates.md): required test tiers and gates. -- [RFC index](../../../docs/rfc/README.md): design rationale. Treat disagreement with an RFC as a design discussion, not an automatic veto. +- [docs/testing.md](../../../docs/testing.md) and the [quality-gates Agent Note](../../notes/implemented/process/2026-06-11-quality-gates.md): required test tiers and gates. +- [Agent Note index](../../notes/README.md): design rationale. Treat disagreement with an Agent Note as a design discussion, not an automatic veto. - For bilingual changes, read [translation-rules.md](../../../docs/i18n/translation-rules.md), [terminology.md](../../../docs/i18n/terminology.md), and [dsh-translate-docs](../dsh-translate-docs/SKILL.md). ## Blocking requirements @@ -27,7 +27,7 @@ description: Use when reviewing a pull request in the deepseek-harness repo — ## Manual checks -- **Intent and seam contracts:** trace both sides of every changed interface. Confirm the implementation matches the PR and any RFC, including errors, cancellation, ownership, and disposal. +- **Intent and seam contracts:** trace both sides of every changed interface. Confirm the implementation matches the PR and any Agent Note, including errors, cancellation, ownership, and disposal. - **Lifecycle and concurrency:** for async setup, callbacks, processes, or teardown, apply [defensive-patterns.md](../../../docs/defensive-patterns.md). Check races before publication, cancellation during awaits, independent error reporting, callback containment, ownership before reentry, complete detach cleanup, and quiescent disposal. - **Capability and consumer fit:** trace every current consumer, then flag consumer-specific behavior leaking into the interface under [the package contract](../../../packages/AGENTS.md). - **Scope, ownership, and necessity:** map each abstraction, state machine, option, defensive copy, and compatibility path to its current contract, production consumer, and owning plugin or service. Challenge unrelated features and speculative generality, then test the PR's coherence against [the root contract](../../../AGENTS.md#conventions). @@ -39,7 +39,7 @@ description: Use when reviewing a pull request in the deepseek-harness repo — - **Real entry path:** tests exercise the shipped Loader, bin, worker, ACP bridge, or subprocess where relevant. A hand-mounted plugin does not catch Loader export-shape failures; a function plugin must named-export its namespace and have no default export. - **Test strength:** assertions fail on the intended regression and verify external state, logs, events, or disposal rather than restating the implementation or trusting an agent's report. Coverage is necessary but not evidence that the scenario is correct. - **Mechanized invariants and negative controls:** trace each new or changed check through the executed top-level gate and its deliberately invalid case; confirm the real runner fails for the intended rule. -- **Implemented RFCs match shipped reality:** when a PR implements a proposed RFC, move and rewrite it as present-tense shipped state in the same diff, then verify paths, names, and mechanisms against the implementation. +- **Implemented Agent Notes match shipped reality:** when a PR implements a proposed Agent Note, move and rewrite it as present-tense shipped state in the same diff, then verify paths, names, and mechanisms against the implementation. - **Transcript changes:** editor-visible or model-visible changes update snapshots or explain why no snapshot applies. Review expected-output diffs as behavior changes, not formatting noise. - **Bilingual changes:** compare meaning and terminology on both sides; a green pairing hash does not prove translation quality. diff --git a/.agents/skills/dsh-doc-standards/SKILL.md b/.agents/skills/dsh-doc-standards/SKILL.md index 6ad8902d66..2a5458db7f 100644 --- a/.agents/skills/dsh-doc-standards/SKILL.md +++ b/.agents/skills/dsh-doc-standards/SKILL.md @@ -10,7 +10,7 @@ The contract lives in [docs/AGENTS.md](../../../docs/AGENTS.md). This workflow c ## Sources of truth (read, don't re-summarize) - [docs/AGENTS.md](../../../docs/AGENTS.md) — the taxonomy ("one home per fact"), budgets, slop checklist. -- [docs/rfc/README.md](../../../docs/rfc/README.md) — when a decision earns an RFC, how to file it, and what goes inside one (the header block, per-lifecycle skeleton, and Alternatives-considered mandate, gated by `verify-rfc-format`); [docs/postmortem/README.md](../../../docs/postmortem/README.md) — when an incident earns a postmortem. +- [.agents/notes/README.md](../../notes/README.md) — when a decision earns an Agent Note, how to file it, and what goes inside one (the header block, per-lifecycle skeleton, and Alternatives-considered mandate, gated by `verify-agent-note-format`); [docs/postmortem/README.md](../../../docs/postmortem/README.md) — when an incident earns a postmortem. - [docs/i18n/README.md](../../../docs/i18n/README.md) — the bilingual pairing contract; editing either side of a pair obligates the counterpart in the same change. - Root [AGENTS.md](../../../AGENTS.md) — the standing orders whose budget discipline this skill protects. @@ -32,8 +32,8 @@ The audit is a hunt for the standard's slop checklist, cheapest probes first. Es 3. Inspect long comments for reasoning transcripts: control-flow narration, test walkthroughs, proof of obvious branches, review findings, rejected local alternatives, and the same rationale repeated beside sibling methods. Preserve only a non-obvious contract or durable rationale; otherwise delete the comment. 4. Hunt duplication by grepping distinctive phrases. Keep one home and replace other copies with links. 5. Replace hand-written catalogs, test/status inventories, and JSDoc restatements with the authoritative tree, script, or generated reference. -6. In `implemented/` RFCs, remove migration plans, acceptance-task checklists, and future-tense spec language. Keep concise verification contracts that identify the behaviors and tiers pinning the shipped decision, plus named coverage gaps. -7. If removing prose changes a promised behavior rather than its explanation, use a proposed RFC first (follow [dsh-find-simplifications](../dsh-find-simplifications/SKILL.md)). +6. In `implemented/` Agent Notes, remove migration plans, acceptance-task checklists, and future-tense spec language. Keep concise verification contracts that identify the behaviors and tiers pinning the shipped decision, plus named coverage gaps. +7. If removing prose changes a promised behavior rather than its explanation, use a proposed Agent Note first (follow [dsh-find-simplifications](../dsh-find-simplifications/SKILL.md)). Keep every load-bearing rule, preferably as one to three lines plus a link to its rationale. Cut stories, duplicates, status notes, and the path used to derive the rule. Do not create a new explanation merely to relocate disposable reasoning. diff --git a/.agents/skills/dsh-find-simplifications/SKILL.md b/.agents/skills/dsh-find-simplifications/SKILL.md index 623cdf18e2..ae1f3b60d1 100644 --- a/.agents/skills/dsh-find-simplifications/SKILL.md +++ b/.agents/skills/dsh-find-simplifications/SKILL.md @@ -1,17 +1,17 @@ --- name: dsh-find-simplifications -description: 'Use when working in the deepseek-harness repo to find non-obvious simplification candidates and write proposed RFCs or inline TODO/FIXME/XXX notes for dead, duplicated, speculative, or over-built code surfaces; especially for requests like "find simplification RFCs", "look for unnecessary complexity", "audit for removal-style cleanups", or "fold worthwhile simplification ideas from another PR".' +description: 'Use when working in the deepseek-harness repo to find non-obvious simplification candidates and write proposed Agent Notes or inline TODO/FIXME/XXX notes for dead, duplicated, speculative, or over-built code surfaces; especially for requests like "find simplification Agent Notes", "look for unnecessary complexity", "audit for removal-style cleanups", or "fold worthwhile simplification ideas from another PR".' --- # Finding DeepSeek Harness Simplifications -This skill helps turn a broad "find things to simplify" request into evidence-backed RFCs that remove or collapse existing harness surface area. It is guidance, not a checklist: follow the code, keep judgment active, and prefer a few well-proven candidates over a pile of thin guesses. +This skill helps turn a broad "find things to simplify" request into evidence-backed Agent Notes that remove or collapse existing harness surface area. It is guidance, not a checklist: follow the code, keep judgment active, and prefer a few well-proven candidates over a pile of thin guesses. ## Start With Repo Context -- Read `AGENTS.md`, especially the pre-release stance and the conventions (including the tests-are-not-golden-truth and RFCs-are-not-golden-truth doctrines), plus [docs/defensive-patterns.md](../../../docs/defensive-patterns.md) and [docs/testing.md](../../../docs/testing.md). +- Read `AGENTS.md`, especially the pre-release stance and the conventions (including the tests-are-not-golden-truth and Agent Notes-are-not-golden-truth doctrines), plus [docs/defensive-patterns.md](../../../docs/defensive-patterns.md) and [docs/testing.md](../../../docs/testing.md). - Skim [docs/architecture.md](../../../docs/architecture.md) before judging anything under `packages/`; simplifications that fight the service map or event taxonomy need extra evidence. -- Use the RFC index ([docs/rfc/README.md](../../../docs/rfc/README.md)) to understand intentional architecture. The most relevant implemented examples are [drop mutable session summary](../../../docs/rfc/implemented/simplification/2026-06-19-drop-mutable-session-summary.md), [shared persistence write coordinator](../../../docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md), [capability seams](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md), and the twin adapter / dual persistence backend RFCs. +- Use the Agent Note index ([.agents/notes/README.md](../../notes/README.md)) to understand intentional architecture. The most relevant implemented examples are [drop mutable session summary](../../notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md), [shared persistence write coordinator](../../notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md), [capability seams](../../notes/implemented/architecture/2026-06-13-capability-seams.md), and the twin adapter / dual persistence backend Agent Notes. - Treat dual LLM adapters and dual persistence backends as intentional by default. Do not propose deleting either twin/backend as "low effort" unless the user explicitly overrides that constraint. Removing an unused method or hook inside a protected seam can still be valid if it does not collapse the protected design. ## What Counts As A Strong Candidate @@ -27,7 +27,7 @@ A strong simplification removes, folds, or demotes something real and has clear - An invariant, rollback path, set of expected outputs, or special-case test exists only to protect an unused surface. - The simplified behavior may differ slightly, but the new behavior is still reasonable and easier to explain. -Thin candidates are usually not enough for an RFC: deleting one typo, running `knip` once, removing an intentionally documented backend/adapter, or flagging "this looks complex" without call-site proof. +Thin candidates are usually not enough for an Agent Note: deleting one typo, running `knip` once, removing an intentionally documented backend/adapter, or flagging "this looks complex" without call-site proof. ## Survey Broadly @@ -54,7 +54,7 @@ For complex asynchronous code, draw the ownership graph and map each sentinel, r For every symbol or behavior, classify consumers before writing: - Production corpus: `packages/*/src`, `examples/*/src`, `examples/**/*.yml`, runtime scripts, and loader/config paths. -- Non-production corpus: tests, README/docs, RFCs, snapshots, generated expected outputs, and comments. +- Non-production corpus: tests, README/docs, Agent Notes, snapshots, generated expected outputs, and comments. - Ambiguous corpus: examples and scripts that may be product smoke paths. Inspect usage before classifying. Use `rg` first. Good searches include the exact symbol, event name, package name, config key, method name with both `.name(` and `name(`, and any wire strings. Then read the call sites. `knip` can help, but it is not a substitute for understanding public interfaces, dynamic event names, tests, docs, and Cordis loader paths. @@ -62,17 +62,17 @@ Use `rg` first. Good searches include the exact symbol, event name, package name Reject or downgrade a candidate when: - A production caller exists and the simplification would be a feature decision rather than a cleanup. -- The surface is explicitly justified by an implemented RFC or a hard-won defensive pattern, and the new evidence does not beat that reason. +- The surface is explicitly justified by an implemented Agent Note or a hard-won defensive pattern, and the new evidence does not beat that reason. - The removal would force unrelated churn without actually making the contract smaller. - The idea is correct but tiny. Add a targeted TODO/FIXME/XXX instead, using the urgency semantics in [docs/development.md](../../../docs/development.md). -## Write The RFC +## Write The Agent Note -Create one file per durable proposal under `docs/rfc/<lifecycle>/<class>/yyyy-mm-dd-topic.md`, following the lifecycle/classification contract in `docs/rfc/README.md`. Regenerate `docs/rfc/INDEX.md`; never add a manual RFC table to the README. Keep prose paragraphs on one physical line and use relative Markdown links. +Create one file per durable proposal under `.agents/notes/<lifecycle>/<class>/yyyy-mm-dd-topic.md`, following the lifecycle/classification contract in `.agents/notes/README.md`. Regenerate `.agents/notes/INDEX.md`; never add a manual Agent Note table to the README. Keep prose paragraphs on one physical line and use relative Markdown links. Prefer this shape, adjusting when the idea needs it: -- `# RFC: <action-oriented title>` +- `# Agent Note: <action-oriented title>` - `Status: proposed` - `## Problem`: name the current surface, cite the relevant files, and state the consumer evidence. Separate production callers from tests/docs. - `## Proposal`: say exactly what to remove, fold, demote, or rehome. Include tests, docs, READMEs, JSDoc, event-taxonomy, snapshot, and generated-file cleanup when relevant. @@ -80,7 +80,7 @@ Prefer this shape, adjusting when the idea needs it: - `## Acceptance criteria`: observable end state and gates. - `## Risks`: public API changes, behavior changes, future product wants, and why the tradeoff is still reasonable. -Be concrete enough that an implementing PR can follow the trail. Avoid vague "simplify this package" RFCs. When a proposal overlaps an existing RFC, consolidate the useful details into the existing one rather than creating a duplicate. +Be concrete enough that an implementing PR can follow the trail. Avoid vague "simplify this package" Agent Notes. When a proposal overlaps an existing Agent Note, consolidate the useful details into the existing one rather than creating a duplicate. ## Inline TODO Notes @@ -88,25 +88,25 @@ Use inline TODO/FIXME/XXX only for small, local cleanups that are clearly useful - Name the smell with a stable tag, e.g. `TODO(double-default)` or `XXX(unused-default)`. - Explain why it is safe to revisit and what action would simplify it. -- Do not add TODOs for speculative complaints or for behavior that needs an RFC-level decision. +- Do not add TODOs for speculative complaints or for behavior that needs an Agent Note-level decision. ## When Folding Another PR Or Branch Diff the sibling branch against `origin/master`, not against the current PR branch, so you see its independent contribution. For each item: -- Port non-overlapping RFCs or TODOs that meet the quality bar. -- Consolidate overlapping material into the existing RFC that owns the topic. +- Port non-overlapping Agent Notes or TODOs that meet the quality bar. +- Consolidate overlapping material into the existing Agent Note that owns the topic. - Do not port duplicate or lower-confidence proposals just to preserve the count. - Update the PR body so reviewers see the true candidate count and scope. - Close the duplicate PR only when the user asked you to, or when you clearly own that housekeeping. ## Validation And PR Hygiene -For docs-only RFC work, run at least `pnpm run doc-sync`, `pnpm run lint`, and `git diff --check`. For code comments or skill changes, also run the relevant validator when one exists. Before pushing, expect the pre-push hook to run module graph freshness, unit tests, snapshots, doc-sync, and hygiene. +For docs-only Agent Note work, run at least `pnpm run doc-sync`, `pnpm run lint`, and `git diff --check`. For code comments or skill changes, also run the relevant validator when one exists. Before pushing, expect the pre-push hook to run module graph freshness, unit tests, snapshots, doc-sync, and hygiene. When opening or updating a PR, summarize: -- How many RFCs and inline notes were added. +- How many Agent Notes and inline notes were added. - The main areas surveyed. - What was intentionally excluded. - Which checks passed. diff --git a/.agents/skills/dsh-pre-push-checks/SKILL.md b/.agents/skills/dsh-pre-push-checks/SKILL.md index 433aa38942..5c51209113 100644 --- a/.agents/skills/dsh-pre-push-checks/SKILL.md +++ b/.agents/skills/dsh-pre-push-checks/SKILL.md @@ -41,7 +41,7 @@ Why `test:coverage`, not only `test`: CI enforces per-file 100% coverage. A bran ## Add Gates By Touched Surface -Run `pnpm run doc-sync` and `pnpm run verify-module-graph` when the diff touches Markdown docs, package manifests, package imports/exports, generated catalogs, RFCs, architecture docs, translation pairs, Mermaid diagrams, or comments that cite docs/packages. +Run `pnpm run doc-sync` and `pnpm run verify-module-graph` when the diff touches Markdown docs, package manifests, package imports/exports, generated catalogs, Agent Notes, architecture docs, translation pairs, Mermaid diagrams, or comments that cite docs/packages. Run `pnpm run build` and `pnpm run hygiene` when the diff touches any package `package.json`, dependency graph, public exports, build config, declaration surface, bundled runtime path, or code that will be consumed from built `lib/`. diff --git a/.agents/skills/dsh-prose-standard/SKILL.md b/.agents/skills/dsh-prose-standard/SKILL.md index b4cc300f14..faf234ae7c 100644 --- a/.agents/skills/dsh-prose-standard/SKILL.md +++ b/.agents/skills/dsh-prose-standard/SKILL.md @@ -45,7 +45,7 @@ This is not a one-way shortening pass. Add or restore prose when code, types, an - **Tests:** explain only non-obvious test design—why a fixture, assertion, platform accommodation, real entry path, or indirect observation is necessary. Delete walkthroughs and inventories. - **Cookbooks:** include prerequisites, required actions, the real entry path, observable verification, and concise warnings. - **READMEs:** include the consumer contract: configuration, semantics, failures, limitations, extension points, and model-visible effects. Quote stable model-visible text owned by the package; link generated catalogs and cross-package owners. Keep durable gaps and maintainer traps, not ordinary cleanup inventories. Follow the [package README contract](../../../docs/cookbook/adding-a-package.md#4-write-the-package-readme). -- **RFCs:** retain unique rationale, mechanisms, alternatives, consequences, shipped verification contracts, and named coverage gaps. Implemented RFCs state shipped reality in the present tense; remove planning checklists, not evidence of what pins the decision. +- **Agent Notes:** retain unique rationale, mechanisms, alternatives, consequences, shipped verification contracts, and named coverage gaps. Implemented Agent Notes state shipped reality in the present tense; remove planning checklists, not evidence of what pins the decision. - **Postmortems:** retain the incident sequence, evidence, causal chain, impact, and prevention. Remove repeated persuasion or implementation detail that does not establish causality. - **Skills and agent instructions:** state behavioral guardrails and explicit scope limitations such as “guidance, not a script/checklist.” Keep the workflow concise and link its source of truth. - **Examples and configuration comments:** explain boundaries, non-obvious wiring or load order, security stance, replay behavior, exceptions, and likely misuse. Do not narrate entries that the configuration already shows. diff --git a/.agents/skills/dsh-prose-standard/references/examples.md b/.agents/skills/dsh-prose-standard/references/examples.md index 7edb01af3d..c4270ecc98 100644 --- a/.agents/skills/dsh-prose-standard/references/examples.md +++ b/.agents/skills/dsh-prose-standard/references/examples.md @@ -56,7 +56,7 @@ Event order and its current-request consequence are caller-visible behavior, not **Over-trimmed:** “Worker realm support.” -**Balanced:** “Owns the worker realm and its host bridge. Realm initialization is single-shot; disposal terminates the worker and rejects later calls. See the worker-isolation RFC for the protocol rationale.” +**Balanced:** “Owns the worker realm and its host bridge. Realm initialization is single-shot; disposal terminates the worker and rejects later calls. See the worker-isolation Agent Note for the protocol rationale.” **Over-detailed:** A paragraph-by-paragraph preview of the classes and helper functions below. @@ -84,17 +84,17 @@ Keep mapping details that explain an abstraction boundary or intentional informa ## Link rationale while keeping the local contract -**Over-trimmed:** “Disposal is documented in the lifecycle RFC.” +**Over-trimmed:** “Disposal is documented in the lifecycle Agent Note.” -**Balanced:** “Disposal aborts the run and waits for provider quiescence. See the lifecycle RFC for ownership and race handling.” +**Balanced:** “Disposal aborts the run and waits for provider quiescence. See the lifecycle Agent Note for ownership and race handling.” -**Over-detailed:** Repeating the RFC's promise choreography and rejected ownership models beside every disposer. +**Over-detailed:** Repeating the Agent Note's promise choreography and rejected ownership models beside every disposer. Keep the behavior and completion guarantee where callers need them. Link aggressively for the algorithm and rationale; a link cannot replace the local contract. -## Implemented RFCs retain verification contracts +## Implemented Agent Notes retain verification contracts -**Over-trimmed:** Deleting the entire Testing section because the RFC has already shipped. +**Over-trimmed:** Deleting the entire Testing section because the Agent Note has already shipped. **Balanced:** “Unit tests cover cancellation before and after publication, disposal quiescence, and provider reload. A built-entry smoke covers the real loader path; snapshot coverage is deferred because the transport is process-specific.” @@ -162,6 +162,6 @@ Know what the generator extracts. That fragment must preserve the contract neede **Over-detailed:** Listing private helper cleanup and unused test-only accessors with no caller or maintainer consequence. -**Balanced:** “Provider selection is cached for the plugin lifetime; installing or repairing a provider requires reload.” Keep ordinary cleanup in its TODO or RFC. +**Balanced:** “Provider selection is cached for the plugin lifetime; installing or repairing a provider requires reload.” Keep ordinary cleanup in its TODO or Agent Note. Retain gaps and non-obvious constraints that affect use or safe maintenance. A package README is not a backlog dump. diff --git a/.github/workflows/build-exe-for-python-sdk.yml b/.github/workflows/build-exe-for-python-sdk.yml index 198e7b4e09..48c96e4d20 100644 --- a/.github/workflows/build-exe-for-python-sdk.yml +++ b/.github/workflows/build-exe-for-python-sdk.yml @@ -1,7 +1,7 @@ name: Build single-exe # Native builds for the release targets; see -# docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md. +# .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md. # A full target run retains one SDK wheel and three runtime wheels; subset # dispatch retains the SDK wheel and selected runtime wheels. Bare executables # and source closures are test inputs. Run manually or label a PR diff --git a/.github/workflows/e2e.yml b/.github/workflows/e2e.yml index dd3965f5cd..3d1bba6c17 100644 --- a/.github/workflows/e2e.yml +++ b/.github/workflows/e2e.yml @@ -23,7 +23,7 @@ name: E2E (real DeepSeek API) # in the BASE repo's context WITH secrets while still able to check out untrusted # fork code — a textbook key-leak vector, especially once this repo is public. # The fork/secret model and its public-repo implications are recorded in -# docs/rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md. +# .agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md. # # Note: scheduled triggers are auto-disabled after 60 days of repo inactivity; # push/pull_request/workflow_dispatch act as backstops. diff --git a/.github/workflows/sandbox.yml b/.github/workflows/sandbox.yml index 561d74b587..51dfe06f1c 100644 --- a/.github/workflows/sandbox.yml +++ b/.github/workflows/sandbox.yml @@ -19,7 +19,7 @@ permissions: contents: read jobs: - # Keyless real-kernel sandbox proofs (sandbox RFC § Testing): each ladder + # Keyless real-kernel sandbox proofs (sandbox Agent Note § Testing): each ladder # rung is only provable on a host where it enforces, so this job fans out # an OS×runner matrix — bwrap and Landlock on Linux (separate legs: the # Landlock files force the bwrap rung off, so each leg proves exactly one diff --git a/AGENTS.md b/AGENTS.md index cd3505ea8b..7ceeb69dd2 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -33,7 +33,8 @@ packages/ @deepseek-ai/dsh-<pkg> workspaces at packages/<group>/<pkg>/ util/ zero-dependency utilities python/ Python SDK and bundled runtime (see python/README.md) examples/ Runnable cordis.yml leaves over packages/examples bundles (see examples/AGENTS.md) -docs/ architecture, generated catalogs, RFCs, postmortems, cookbook (see docs/AGENTS.md) +.agents/ Agent workflows and Agent Notes (`notes/`) +docs/ architecture, generated catalogs, postmortems, cookbook (see docs/AGENTS.md) scripts/ repo gates and generators website/ VitePress docs site (zh-CN); api/ pages generated from source ``` @@ -116,7 +117,7 @@ Real-API tests and demos read `DEEPSEEK_API_KEY`, optional `DEEPSEEK_BASE_URL`, - **An empty `catch` names what it swallows** and why nothing else can reach it; keep the `try` to one statement. - **Prefer symmetry for parallel values**; unexplained asymmetry usually signals a missed extraction. - **Tests describe behavior, not correctness.** Change obsolete behavior with its tests; explain why in the PR. -- **Validate RFC premises against current code**; friction may expose overreach, so amend proposals before moving them to `implemented/`. +- **Validate Agent Note premises against current code**; friction may expose overreach, so amend proposals before moving them to `implemented/`. - **Testing policy** — [docs/testing.md](docs/testing.md). Transcript changes need snapshots or a PR note. Fixtures must replay on macOS/Linux; fix fixtures, not normalizers. - **A tool's ACP render intent is part of its design**, decided up front (`generic`/`terminal`/`diff`, `locations`); presentation methods are pure functions of `args` ([cookbook](docs/cookbook/adding-a-tool.md)). - **Plan unit, e2e, and snapshot coverage** for new seams, lifecycle shapes, and transcript surfaces, and schedule any missing harness support before implementation. diff --git a/docs/AGENTS.md b/docs/AGENTS.md index a0c30c5545..010fb126b7 100644 --- a/docs/AGENTS.md +++ b/docs/AGENTS.md @@ -1,6 +1,6 @@ # AGENTS.md — The documentation standard -This file defines Markdown tiers, writing rules, and `verify-doc-budgets` ceilings. Use [dsh-doc-standards](../.agents/skills/dsh-doc-standards/SKILL.md) for placement and validation, and [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for required coverage and editorial judgment; the [doc-tiers RFC](rfc/implemented/process/2026-07-04-doc-tiers-and-budgets.md) owns rationale. +This file defines Markdown tiers, writing rules, and `verify-doc-budgets` ceilings. Use [dsh-doc-standards](../.agents/skills/dsh-doc-standards/SKILL.md) for placement and validation, and [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for required coverage and editorial judgment; the [doc-tiers Agent Note](../.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md) owns rationale. ## The tier taxonomy: one home per fact @@ -9,23 +9,23 @@ Each fact has one home: the tier whose job it is. Elsewhere, link to that home; | Tier | Job | Does NOT belong there | |---|---|---| | Root `AGENTS.md` | Standing orders: rules an agent needs in context in every session, one to three lines each, linking its home | Stories, worked examples, situational procedures, anything restated from a linked home | -| Subtree `AGENTS.md` (`packages/`, `examples/`, `docs/`) | Orders specific to that subtree | Repo-wide rules the root file already carries | -| [architecture.md](architecture.md) | The system map: services, the loop, extension seams — read before changing `packages/` | Type shapes (→ core-data-structures), per-package detail (→ package READMEs), decision rationale (→ RFCs), implementation-status annotations | +| Subtree `AGENTS.md` (`packages/`, `examples/`, `docs/`, `.agents/notes/`) | Orders specific to that subtree | Repo-wide rules the root file already carries | +| [architecture.md](architecture.md) | The system map: services, the loop, extension seams — read before changing `packages/` | Type shapes (→ core-data-structures), per-package detail (→ package READMEs), decision rationale (→ Agent Notes), implementation-status annotations | | [core-data-structures/](core-data-structures/core.md) | The type catalog: literal shapes and semantics of the spine and seam vocabulary | Behavior narration (→ architecture.md) | -| [rfc/](rfc/README.md) | Decision records: the why, what-was-given-up, and concise verification contract; `implemented/` RFCs describe shipped reality in present tense | Migration plans, acceptance-task checklists, fixture walkthroughs, and spec-speak ("should…") once the decision has shipped | +| [Agent Notes](../.agents/notes/README.md) | Decision records: the why, what-was-given-up, and concise verification contract; `implemented/` notes describe shipped reality in present tense | Migration plans, acceptance-task checklists, fixture walkthroughs, and spec-speak ("should…") once the decision has shipped | | [postmortem/](postmortem/README.md) | Incident stories — the only tier where war-story narrative belongs | — | -| [cookbook/](cookbook/adding-a-package.md) | Step-by-step how-tos with numbered verify steps | Design rationale (→ the RFC each guide links) | +| [cookbook/](cookbook/adding-a-package.md) | Step-by-step how-tos with numbered verify steps | Design rationale (→ the Agent Note each guide links) | | Package README | The per-package contract: config, semantics, limitations, extension points, and [Model Experience](cookbook/adding-a-package.md#4-write-the-package-readme) | JSDoc restatement, generated-catalog restatement (event/tool tables), other packages' concerns | -| [development.md](development.md) | First-stop contributor onboarding: local setup, daily workflow, and CI shape at summary level; a bilingual pair under the [i18n contract](i18n/README.md) | Runtime/version rationale (→ RFCs), gate-by-gate enumerations that drift from `package.json` scripts | +| [development.md](development.md) | First-stop contributor onboarding: local setup, daily workflow, and CI shape at summary level; a bilingual pair under the [i18n contract](i18n/README.md) | Runtime/version rationale (→ Agent Notes), gate-by-gate enumerations that drift from `package.json` scripts | | Generated catalogs: [cordis events](cordis-catalog/events.md), [cordis services](cordis-catalog/services.md), [tool-catalog](tool-catalog.md), [config-catalog](config-catalog.md), [persistence-catalog](persistence-catalog.md), [module-graph.md](module-graph.md) | Exhaustive enumerations regenerated from source, freshness-gated | Hand edits of any kind | | Skills (`.agents/skills/`) | Reusable workflows and specialized decision standards | Product and runtime contracts (→ docs or source) | -Placement: bugs → postmortems; rationale → RFCs; procedures → cookbooks; type shapes → core data; package contracts → READMEs; standing orders → root `AGENTS.md` with a rationale link. +Placement: bugs → postmortems; rationale → Agent Notes; procedures → cookbooks; type shapes → core data; package contracts → READMEs; standing orders → root `AGENTS.md` with a rationale link. ## Writing rules -- **Document current state, not change history.** Avoid "previously/now/no longer", PRs, commits, and stack positions in durable prose; name the live mechanism. Put change stories in commits, PRs, RFCs, or postmortems. -- **Write an RFC in the same PR for decisions a maintainer may reasonably revisit.** Mechanical or self-evident changes need none ([when to write one](rfc/README.md)). +- **Document current state, not change history.** Avoid "previously/now/no longer", PRs, commits, and stack positions in durable prose; name the live mechanism. Put change stories in commits, PRs, Agent Notes, or postmortems. +- **Write an Agent Note in the same PR for decisions a maintainer may reasonably revisit.** Mechanical or self-evident changes need none ([when to write one](../.agents/notes/README.md)). - **One physical line per paragraph** (`verify-md-wrap`): use editor soft-wrap. Code blocks, tables, and list structure keep their formatting; code comments stay under the linter's column limit. - **Fenced `ts` blocks must compile** (`doc-typecheck`); a pasted type declaration and its original JSDoc use ` ```ts type-equiv `, while a body-stripped public class declaration uses ` ```ts public-api `; register either in the manifest so neither can drift ([mechanics](development.md#documenting-types-verbatim-ts-type-equiv)). - **The [core-data-structures catalog](core-data-structures/core.md) updates in the same change** that reshapes a documented type. `verify-type-equiv` catches drifted pastes, not never-documented new types ([what counts as core](core-data-structures/core.md#what-counts-as-core)). @@ -50,8 +50,8 @@ Ceilings are guardrails, not reduction targets. Retain at least 5% headroom; low Hunt these in any doc; the [dsh-doc-standards](../.agents/skills/dsh-doc-standards/SKILL.md) skill runs this list as an audit: - The same rule stated in more than one home. Grep a distinctive phrase; keep one home, convert the rest to links. -- Narrated history: "previously", "now", "no longer", "used to", "renamed", "was moved", references to PRs or commits. State the current fact; the why belongs in an RFC, the story in a postmortem or git. -- A war story told inline where a one-line rule plus a postmortem/RFC link would do. +- Narrated history: "previously", "now", "no longer", "used to", "renamed", "was moved", references to PRs or commits. State the current fact; the why belongs in an Agent Note, the story in a postmortem or git. +- A war story told inline where a one-line rule plus a postmortem/Agent Note link would do. - Implementation-status annotations in prose or diagrams ("implemented!", "future: …"). Status rots; the repo layout and package manifests carry it. - Hand-restating a generated catalog or JSDoc: event tables, tool arg tables, method signatures. Link instead. - Hand-maintained inventories of tests, packages, or implementation status when the tree or a generator is authoritative. @@ -59,10 +59,10 @@ Hunt these in any doc; the [dsh-doc-standards](../.agents/skills/dsh-doc-standar - The same rationale repeated beside sibling methods. State it once at the owning seam or shared helper. - Paragraph walls: one paragraph carrying several rules and parenthetical asides. Split it, or demote the detail to the linked home. - Emphasis inflation: bold, CAPS, or "critically" everywhere means nothing stands out. Reserve emphasis for the clause that changes behavior. -- Spec-speak in `implemented/` RFCs: "should", migration plans, acceptance checklists. An implemented RFC describes what is, per [rfc/implemented/AGENTS.md](rfc/implemented/AGENTS.md). +- Spec-speak in `implemented/` Agent Notes: "should", migration plans, acceptance checklists. An implemented Agent Note describes what is, per the [implemented-note instructions](../.agents/notes/implemented/AGENTS.md). ## Cross-reference with machine-checkable links, never free prose -Link repository references with relative Markdown paths, never bare filenames or RFC numbers. `verify-md-links` catches missing targets; the [cross-link RFC](rfc/implemented/process/2026-06-18-markdown-cross-link-lint.md) owns the rationale. +Link repository references with relative Markdown paths, never bare filenames or Agent Note numbers. `verify-md-links` catches missing targets; the [cross-link Agent Note](../.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md) owns the rationale. The gate checks file existence, not `#anchor` validity — verify anchors yourself when linking to one. diff --git a/docs/architecture.md b/docs/architecture.md index fd21648dd2..7cd9b34a2c 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -106,11 +106,11 @@ forever: checkpoint persistence and notify idle/running status ``` -Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). +Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt ownership](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). Tool-time context—including async `agent.inject()` notices and post-tool `additionalContexts`—settles, then follows recorded results. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering before signal closure. Leftovers become queued input. Terminal `agent/turn-stop` runs after continuation and steering folding, stays authoritative through turn close and flush, and discards later steering but preserves queued prompts. -`dsh-compact-basic` handles pressure and canonical overflow at these checkpoints; retry requires a balanced surface replacement ([RFC](rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)). +`dsh-compact-basic` handles pressure and canonical overflow at checkpoints; retry requires a balanced surface replacement ([decision](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)). ### Failure Boundaries @@ -126,7 +126,7 @@ Every session event is turn-enclosed. Reloading preserves an interrupted tail an ### Agent Scope -Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, receive only that agent's dispatches, and unwind with it; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. Typed resolvers derive carrier checks from merged `Events` signatures and `scopeTarget` ([semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md)). See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md) and [subagent composition controls](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). `AgentLoop` runs drivers inside `ctx.agents.withInitiator()`; private orchestration derives `agent.session`; other identities stay explicit ([RFC](rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md)). +Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, receive only that agent's dispatches, and unwind with it; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. Typed resolvers derive carrier checks from merged `Events` signatures and `scopeTarget` ([semantic gates](../.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md)). See [agent scope](../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md) and [subagent composition controls](../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). `AgentLoop` runs drivers inside `ctx.agents.withInitiator()`; private orchestration derives `agent.session`; other identities stay explicit ([decision](../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md)). ## State @@ -134,7 +134,7 @@ Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, re The session log is the source of truth. `deriveMessages()` projects session events into the `Message[]` sent to the model; raw `assistant/chunk` events stay in the log for replay and UI fidelity. Replay, fork, resume, transcript rendering, telemetry, and persistence all derive from the same event stream. -**Model-visible ⟺ logged**: the log reconstructs every request — messages at `step/start` fronted by the header's session prefix, headers by folding `request/header` — and dev invariants assert this ([reconstructability RFC](rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). +**Model-visible ⟺ logged**: the log reconstructs every request — messages at `step/start` fronted by the header's session prefix, headers by folding `request/header` — and dev invariants assert this ([reconstructability](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)). Durability is a plugin concern. Persistence backends buffer synchronous `session/event` notifications and the loop awaits a turn-end checkpoint before moving on. The `SessionPersistence` seam stores `SessionEvent` directly, with metadata in `SessionHeader`; JSONL and SQLite share one contract suite. @@ -152,7 +152,7 @@ A swappable capability usually splits into **interface / implementation / consum Some seams bend the template deliberately: LLM combines interface and consumer because adapters implement it; filesystem wraps provider primitives with policy; web keeps search/fetch provider registries behind one service; skills and subagents use named providers. Subagents spawn fresh, fork a completed-turn prefix, or use ACP children ([subagent.md](core-data-structures/subagent.md)). -`dsh-workspace-context` composes baselines on `agent/session-prefix` and appends `ctx.fs`-discovered nested changes on `tools/post-execute`; its [RFC](rfc/implemented/feature/2026-06-24-workspace-context.md) records isolation. `dsh-paths` owns shared paths. +`dsh-workspace-context` composes baselines on `agent/session-prefix` and appends `ctx.fs`-discovered nested changes on `tools/post-execute`; its [decision](../.agents/notes/implemented/feature/2026-06-24-workspace-context.md) records isolation. `dsh-paths` owns shared paths. ### Bundles And Apps @@ -185,4 +185,4 @@ The [extension cookbook](cookbook/extension-cookbook.md) carries plugin skeleton - Exact event and service signatures in [events](cordis-catalog/events.md) - [services](cordis-catalog/services.md) catalogs - package contracts in the [package map](../packages/README.md) -- [RFCs](rfc/README.md) +- [Agent Notes](../.agents/notes/README.md) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index f595e6574b..74d0c6ba7e 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1040,7 +1040,7 @@ export interface Config { /** * Milliseconds the SYNCHRONOUS portion of mount code may run in the vm * before evaluation is aborted (default 5000). An async body escapes this - * bound — see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md for the trust stance. + * bound — see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md for the trust stance. */ vmTimeoutMs?: number } @@ -1476,7 +1476,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co ## Seam packages (not directly loadable) -Abstract service classes — a deployment loads a concrete implementation package instead ([capability seams](rfc/implemented/architecture/2026-06-13-capability-seams.md)). +Abstract service classes — a deployment loads a concrete implementation package instead ([capability seams](../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)). - `@deepseek-ai/dsh-bash` — abstract `BashExecutor` ([`packages/bash/bash/src/index.ts`](../packages/bash/bash/src/index.ts)) - `@deepseek-ai/dsh-code-runtime` — abstract `CodeRuntime` ([`packages/code-runtime/code-runtime/src/index.ts`](../packages/code-runtime/code-runtime/src/index.ts)) diff --git a/docs/cookbook/adding-a-package.i18n.yaml b/docs/cookbook/adding-a-package.i18n.yaml index 854acc2750..6fd3feebbd 100644 --- a/docs/cookbook/adding-a-package.i18n.yaml +++ b/docs/cookbook/adding-a-package.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -adding-a-package.md: 404492a9903d823feb011ec2536e4b66ef110e32 -adding-a-package.zh.md: 4be67137d416f373bf3477e30785055fedc5ac6f +adding-a-package.md: 556a48493af4452c178634c0abb4e23e2419dd8e +adding-a-package.zh.md: 5f7e4692233448c746d25e4808c078c390cf39e6 diff --git a/docs/cookbook/adding-a-package.md b/docs/cookbook/adding-a-package.md index 404492a990..556a48493a 100644 --- a/docs/cookbook/adding-a-package.md +++ b/docs/cookbook/adding-a-package.md @@ -44,7 +44,7 @@ For a swappable capability, split interface / implementation / consumer into sep ## 4. Write the package README -Keep package-specific service API, config, events, extension points, and design notes first. The limitations section records durable consumer gaps and non-obvious maintainer constraints owned by this package; ordinary cleanup stays in its source TODO or RFC. An indirect Model Experience sentence may name the consumer that surfaces this package's contribution, but it does not restate that consumer's implementation. End a package README with this canonical sequence: +Keep package-specific service API, config, events, extension points, and design notes first. The limitations section records durable consumer gaps and non-obvious maintainer constraints owned by this package; ordinary cleanup stays in its source TODO or Agent Note. An indirect Model Experience sentence may name the consumer that surfaces this package's contribution, but it does not restate that consumer's implementation. End a package README with this canonical sequence: ````markdown ## Model Experience @@ -76,7 +76,7 @@ Append-only, prefix-stable, replacing, or independent behavior, including the ex Fill Model Experience from the implementation. Use one H3 per direct, conditional, capped, lifetime, or auxiliary-model surface, with the three ordered H4 fields shown above and one prose paragraph under each. Quote stable text owned by the package: system-prompt prose goes in a titled H5 plus `markdown` fence under the field that introduces it—normally `What the model sees`—other short literals stay inline with named placeholders, and other long literals use the same nested form. Summarize only data-dependent or provider-owned text. A tool-schema surface links its anchored section in the generated [tool catalog](../tool-catalog.md) and states only deltas absent there. Keep prompt and schema surfaces separate when scoping can hide one without the other. In `KV Cache effect`, distinguish append-only growth, a stable repeated prefix, replacement of earlier request tokens, and an independent model request, then name the package-owned changes that can invalidate reuse. “Does not invalidate” means the package preserves an already-reusable prefix; provider cache availability and eviction remain outside the package contract. The [prose standard](../../.agents/skills/dsh-prose-standard/SKILL.md) governs completeness and ownership; the verifier enforces the mechanical shape. -A package with no context effect or one consumer-owned path uses the audited `None, as ` or `Indirectly, through ` sentence in [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts), followed by a `KV Cache effect` H4 and one non-empty paragraph; a model-agnostic generic package may instead join `NO_MODEL_EXPERIENCE_SECTION`. Do not expand either case into a description of another package's work. The limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) is independent. The [Model Experience RFC](../rfc/implemented/process/2026-07-12-package-model-experience-contract.md) records the rationale. +A package with no context effect or one consumer-owned path uses the audited `None, as ` or `Indirectly, through ` sentence in [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts), followed by a `KV Cache effect` H4 and one non-empty paragraph; a model-agnostic generic package may instead join `NO_MODEL_EXPERIENCE_SECTION`. Do not expand either case into a description of another package's work. The limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) is independent. The [Model Experience Agent Note](../../.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md) records the rationale. ## 5. Verify diff --git a/docs/cookbook/adding-a-package.zh.md b/docs/cookbook/adding-a-package.zh.md index 4be67137d4..5f7e469223 100644 --- a/docs/cookbook/adding-a-package.zh.md +++ b/docs/cookbook/adding-a-package.zh.md @@ -44,7 +44,7 @@ package.json 不变式（由 `pnpm run constraints` / `scripts/check-workspace-c ## 4. 编写包 README -将包特有的服务 API、配置、事件、扩展点和设计说明放在前面。limitations 部分记录持久的消费方缺口和本包拥有的非显而易见的维护者约束；日常清理事项留在源码 TODO 或 RFC 中。间接的 Model Experience 语句可以点名暴露本包贡献的消费方，但不重述该消费方的实现。包 README 以如下规范序列结尾： +将包特有的服务 API、配置、事件、扩展点和设计说明放在前面。limitations 部分记录持久的消费方缺口和本包拥有的非显而易见的维护者约束；日常清理事项留在源码 TODO 或 Agent Note 中。间接的 Model Experience 语句可以点名暴露本包贡献的消费方，但不重述该消费方的实现。包 README 以如下规范序列结尾： ````markdown ## Model Experience @@ -76,7 +76,7 @@ Append-only, prefix-stable, replacing, or independent behavior, including the ex 根据实现填写 Model Experience。每个直接、条件、上限、生命周期或辅助模型的 surface 使用一个 H3，包含上述三个有序 H4 字段，每个字段下有一个正文段落。引用包拥有的稳定文本：系统提示词放在引出它的字段下，用带标题的 H5 加 `markdown` 围栏表示，通常归入 `What the model sees`；其他短文本以命名占位符内联，其他长文本使用相同的嵌套形式。仅概述数据依赖或提供方拥有的文本。tool-schema surface 链接到生成的[工具目录](../tool-catalog.md)中对应的锚定章节，仅说明该处缺失的差异。当作用域可以隐藏 prompt 或 schema 其中之一而不影响另一个时，将二者分开。填写 `KV Cache effect` 时，应区分仅追加增长、稳定重复的前缀、替换既有请求 token 和独立模型请求，并列出会使缓存复用失效、且由本包拥有的变化。“不使缓存失效”仅表示本包保留了已有的可复用前缀；缓存是否可用以及何时淘汰不属于本包契约。[行文标准](../../.agents/skills/dsh-prose-standard/SKILL.md)约束完整性与归属；验证器强制执行机械形状。 -没有上下文效果或仅有消费方拥有路径的包使用 [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts) 中经过审计的 `None, as ` 或 `Indirectly, through ` 语句，随后添加 `KV Cache effect` H4 和一个非空正文段落；与模型无关的通用包可以改为加入 `NO_MODEL_EXPERIENCE_SECTION`。两种情况都不要展开为对另一个包工作的描述。limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) 独立管理。[Model Experience RFC](../rfc/implemented/process/2026-07-12-package-model-experience-contract.md) 记录了设计动机。 +没有上下文效果或仅有消费方拥有路径的包使用 [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts) 中经过审计的 `None, as ` 或 `Indirectly, through ` 语句，随后添加 `KV Cache effect` H4 和一个非空正文段落；与模型无关的通用包可以改为加入 `NO_MODEL_EXPERIENCE_SECTION`。两种情况都不要展开为对另一个包工作的描述。limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) 独立管理。[Model Experience Agent Note](../../.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md) 记录了设计动机。 ## 5. 验证 diff --git a/docs/cookbook/adding-a-tool.i18n.yaml b/docs/cookbook/adding-a-tool.i18n.yaml index 6ec964c335..5bcb3bac1d 100644 --- a/docs/cookbook/adding-a-tool.i18n.yaml +++ b/docs/cookbook/adding-a-tool.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -adding-a-tool.md: da214702939e01fedf3d0d69be7560bbafe0696a -adding-a-tool.zh.md: b216d18b1593cd7e6074685bd39684f1b9694eac +adding-a-tool.md: 68a8449bc189497b917efe678837d757f85aaf75 +adding-a-tool.zh.md: 003534e04550bfbee6740aa3b6bee02ac2cdc237 diff --git a/docs/cookbook/adding-a-tool.md b/docs/cookbook/adding-a-tool.md index da21470293..68a8449bc1 100644 --- a/docs/cookbook/adding-a-tool.md +++ b/docs/cookbook/adding-a-tool.md @@ -35,7 +35,7 @@ Registration is effect-based: disposing the plugin fiber unregisters the tool (w ## Rules of the execute() contract -- **Args are validated for you.** `defineTool` validates the model-generated `arguments` against the `SchemaSpec` before `execute` runs (type, required keys, enum membership, nested objects/arrays — [runtime arg validation](../rfc/implemented/architecture/2026-06-11-runtime-arg-validation.md)), so inside `execute` the args already match `InferArgs`. You still hand-check value constraints the DSL can't express (non-empty strings, positive numbers, cross-field rules); throw a descriptive Error for those. Raw JSON-Schema tools registered directly (MCP) are NOT validated by the harness — they validate their own input. +- **Args are validated for you.** `defineTool` validates the model-generated `arguments` against the `SchemaSpec` before `execute` runs (type, required keys, enum membership, nested objects/arrays — [runtime arg validation](../../.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md)), so inside `execute` the args already match `InferArgs`. You still hand-check value constraints the DSL can't express (non-empty strings, positive numbers, cross-field rules); throw a descriptive Error for those. Raw JSON-Schema tools registered directly (MCP) are NOT validated by the harness — they validate their own input. - **Registration borrows your readonly definition.** A typed same-process contribution is not a serialization boundary; do not mutate its schema or replace callbacks after registration. `schemas()` materializes only the explicit model-facing projection. To hot-swap a tool, dispose its owning effect and register the replacement; mutable state inside the callback's closure remains ordinary plugin state. - **Execution identity is protected.** The registry materializes `arguments` as detached lossless JSON in one recursive pass, freezes that value before policy starts, and assigns an opaque `exec.token`; `callId`, `name`, `arguments`, `agent`, `token`, and an optional enclosing-transport `parent` token stay immutable through dispatch. `parent` is identity-only and exposes no live outer execution. Treat `args` as readonly input. An around-dispatch wrapper may add, replace, or remove only `exec.signal` to impose cancellation or a deadline. - **Throwing or returning non-JSON data means `isError`.** The registry catches throws and materializes the final result before observers run. A malformed or non-JSON result becomes `{ isError: true }`, preventing a live success that cannot be logged. Throw for infrastructure failures; report domain failures in result text when the model must interpret them. @@ -47,11 +47,11 @@ Registration is effect-based: disposing the plugin fiber unregisters the tool (w Gate `run_in_background` with producer config, reject a pre-aborted call, then register through `ctx.tasks.start({ kind, label, owner: exec.agent, run })`. The runtime validates ownership and control-surface availability before `run()` starts work, then supplies the id, session fence, generic control tools, notices, and owner cleanup. -The producer supplies synchronous `cancel`, non-rejecting `done` that settles after resource cleanup, and optional consuming `readOutput` with bounded-output formatting. Once the id is returned, use a task-owned cancellation signal rather than `exec.signal`. See the [background task runtime RFC](../rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md) and `dsh-tool-bash` for a stream producer. +The producer supplies synchronous `cancel`, non-rejecting `done` that settles after resource cleanup, and optional consuming `readOutput` with bounded-output formatting. Once the id is returned, use a task-owned cancellation signal rather than `exec.signal`. See the [background task runtime Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md) and `dsh-tool-bash` for a stream producer. ## Execution policy and observation -Prefer not to build deployment policy into the tool. Use `tools/pre-execute` for extensible allow/deny/ask policy (the [permission-gate example](./extension-cookbook.md#a-hook-plugin-permission-gate-example)), `ctx.tools.guard()` for a final monotonic deny that later listeners cannot undo, `tools/execute` to wrap core dispatch with a deadline/retry/metrics scope, `tools/post-execute` to transform or attach model-facing context, and `tools/result` to observe the immutable normalized outcome without changing it. A sandboxing implementation can also sit behind the tool's executor capability seam; the exact contracts are in the [`dsh-tools` README](../../packages/core/tools/README.md#extension-points). +Prefer not to build deployment policy into the tool. Use `tools/pre-execute` for extensible allow/deny/ask policy (the [permission-gate example](extension-cookbook.md#a-hook-plugin-permission-gate-example)), `ctx.tools.guard()` for a final monotonic deny that later listeners cannot undo, `tools/execute` to wrap core dispatch with a deadline/retry/metrics scope, `tools/post-execute` to transform or attach model-facing context, and `tools/result` to observe the immutable normalized outcome without changing it. A sandboxing implementation can also sit behind the tool's executor capability seam; the exact contracts are in the [`dsh-tools` README](../../packages/core/tools/README.md#extension-points). ## Code Mode reaches your tool for free @@ -78,8 +78,8 @@ Hard rules (they bite if broken): - **UI-only formatting stays out of the model result.** A fenced ` ```console ` block, a diff, a relativized path — none of these may appear in what `execute` returns to the model; they live only in the presentation. (A `terminal` result view carries RAW `output`; the bridge adds the fences.) - **`defineTool` soft-validates the display path.** A malformed/older logged arg shape makes the wrapper return `undefined` (a generic fallback) rather than throw — display must never crash a replay. -The neutral vocabulary lives in `dsh-tools` (never import an ACP type into a tool); the ACP bridge maps each `card` to the wire. The design and the why are in [the render-intent-union RFC](../rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md); `dsh-tool-fs` (generic/diff) and `dsh-tool-bash` (terminal) are the reference implementations. +The neutral vocabulary lives in `dsh-tools` (never import an ACP type into a tool); the ACP bridge maps each `card` to the wire. The design and the why are in [the render-intent-union Agent Note](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md); `dsh-tool-fs` (generic/diff) and `dsh-tool-bash` (terminal) are the reference implementations. ## Tests every tool needs -Cover argument rejection, every result shape, and HMR disposal. For a side-effecting tool, drive the real tool through the agent loop with a scripted `MockAdapter` and assert its `tool/call` and `tool/result` session events. For an editor card, assert the exact `presentCall` and `presentResult` views and add an [ACP snapshot](../rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) through the real bridge; a terminal card's scenario sets `terminalOutput: true` to exercise the capable-client path. +Cover argument rejection, every result shape, and HMR disposal. For a side-effecting tool, drive the real tool through the agent loop with a scripted `MockAdapter` and assert its `tool/call` and `tool/result` session events. For an editor card, assert the exact `presentCall` and `presentResult` views and add an [ACP snapshot](../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) through the real bridge; a terminal card's scenario sets `terminalOutput: true` to exercise the capable-client path. diff --git a/docs/cookbook/adding-a-tool.zh.md b/docs/cookbook/adding-a-tool.zh.md index b216d18b15..003534e045 100644 --- a/docs/cookbook/adding-a-tool.zh.md +++ b/docs/cookbook/adding-a-tool.zh.md @@ -35,7 +35,7 @@ export function apply(ctx: Context) { ## execute() 契约的规则 -- **参数已为你校验。** `defineTool` 在 `execute` 运行前，会根据 `SchemaSpec` 校验模型生成的 `arguments`（类型、必填键、枚举成员、嵌套对象/数组——见[运行时参数校验](../rfc/implemented/architecture/2026-06-11-runtime-arg-validation.md)），因此 `execute` 内部的 args 已匹配 `InferArgs`。你仍需手动检查 DSL 无法表达的值约束（非空字符串、正数、跨字段规则），对这些情况抛出描述性 Error。直接注册的原始 JSON-Schema 工具（MCP）不由 harness 校验，它们自行校验输入。 +- **参数已为你校验。** `defineTool` 在 `execute` 运行前，会根据 `SchemaSpec` 校验模型生成的 `arguments`（类型、必填键、枚举成员、嵌套对象/数组——见[运行时参数校验](../../.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md)），因此 `execute` 内部的 args 已匹配 `InferArgs`。你仍需手动检查 DSL 无法表达的值约束（非空字符串、正数、跨字段规则），对这些情况抛出描述性 Error。直接注册的原始 JSON-Schema 工具（MCP）不由 harness 校验，它们自行校验输入。 - **注册借用你的只读定义。** 类型化的同进程贡献不是序列化边界；注册后不要修改其 schema 或替换回调。`schemas()` 只物化显式的模型可见投影。如需热替换工具，请 dispose 其所属副作用并注册替代品；回调闭包内的可变状态仍是普通的插件状态。 - **执行身份受保护。** 注册表在一次递归遍历中将 `arguments` 物化为分离的无损 JSON，在策略开始前冻结该值，并分配一个不透明的 `exec.token`；`callId`、`name`、`arguments`、`agent`、`token` 以及可选的外层传输 `parent` token 在整个分发过程中保持不可变。`parent` 仅用于身份标识，不暴露活跃的外层执行。请将 `args` 视为只读输入。around-dispatch 包装器只能添加、替换或移除 `exec.signal`，以施加取消或截止时间。 - **抛出异常或返回非 JSON 数据意味着 `isError`。** 注册表捕获异常，并在观察者运行前物化最终结果。格式错误或非 JSON 的结果变为 `{ isError: true }`，防止出现无法记录的活跃成功。基础设施故障请抛异常；当模型需要解读领域失败时，请在结果文本中报告。 @@ -47,11 +47,11 @@ export function apply(ctx: Context) { 通过 producer 配置控制 `run_in_background`，拒绝已预先中止的调用，然后使用 `ctx.tasks.start({ kind, label, owner: exec.agent, run })` 注册任务。运行时会在 `run()` 启动工作前校验 owner 和控制面是否可用，随后提供 id、会话围栏、通用控制工具、通知和 owner cleanup。 -producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的 `done`，以及可选的消费式 `readOutput`（负责有界输出的格式化）。返回 id 后，应使用 task 自有的取消信号，而不是 `exec.signal`。流式 producer 的示例和完整契约见[后台 task 运行时 RFC](../rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md)与 `dsh-tool-bash`。 +producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的 `done`，以及可选的消费式 `readOutput`（负责有界输出的格式化）。返回 id 后，应使用 task 自有的取消信号，而不是 `exec.signal`。流式 producer 的示例和完整契约见[后台 task 运行时 Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md)与 `dsh-tool-bash`。 ## 执行策略与观测 -尽量不要把部署策略内建到工具中。使用 `tools/pre-execute` 实现可扩展的允许/拒绝/询问策略（见[权限门禁示例](./extension-cookbook.md#a-hook-plugin-permission-gate-example)）；使用 `ctx.tools.guard()` 设置最终的单调拒绝（后续监听器无法撤销）；使用 `tools/execute` 为核心分发包装截止时间/重试/指标作用域；使用 `tools/post-execute` 转换或附加模型可见的上下文；使用 `tools/result` 观测不可变的归一化结果而不改变它。沙箱实现也可以位于工具执行器的能力 seam 之后；确切契约见 [`dsh-tools` README](../../packages/core/tools/README.md#extension-points)。 +尽量不要把部署策略内建到工具中。使用 `tools/pre-execute` 实现可扩展的允许/拒绝/询问策略（见[权限门禁示例](extension-cookbook.md#a-hook-plugin-permission-gate-example)）；使用 `ctx.tools.guard()` 设置最终的单调拒绝（后续监听器无法撤销）；使用 `tools/execute` 为核心分发包装截止时间/重试/指标作用域；使用 `tools/post-execute` 转换或附加模型可见的上下文；使用 `tools/result` 观测不可变的归一化结果而不改变它。沙箱实现也可以位于工具执行器的能力 seam 之后；确切契约见 [`dsh-tools` README](../../packages/core/tools/README.md#extension-points)。 ## Code Mode 自动触达你的工具 @@ -78,8 +78,8 @@ producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的 - **UI 格式不进入模型结果。** 围栏 ` ```console ` 块、diff、相对化路径——这些都不得出现在 `execute` 返回给模型的内容中；它们只存在于展示层。（`terminal` 结果视图携带原始 `output`；桥接层添加围栏。） - **`defineTool` 对展示路径做软校验。** 格式错误或旧版日志中的 arg 形态会使包装器返回 `undefined`（通用回退）而非抛异常——展示绝不能导致回放崩溃。 -中性词汇定义在 `dsh-tools` 中（绝不在工具中导入 ACP 类型）；ACP 桥接层将每个 `card` 映射到协议格式（wire format）。设计与原因见[渲染意图联合体 RFC](../rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md)；`dsh-tool-fs`（generic/diff）和 `dsh-tool-bash`（terminal）是参考实现。 +中性词汇定义在 `dsh-tools` 中（绝不在工具中导入 ACP 类型）；ACP 桥接层将每个 `card` 映射到协议格式（wire format）。设计与原因见[渲染意图联合体 Agent Note](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md)；`dsh-tool-fs`（generic/diff）和 `dsh-tool-bash`（terminal）是参考实现。 ## 每个工具必须的测试 -覆盖参数拒绝、每种结果形态和 HMR dispose。对于有副作用的工具，使用脚本化的 `MockAdapter` 驱动真实工具通过 agent loop（智能体循环），并断言其 `tool/call` 和 `tool/result` 会话事件。对于编辑器卡片，断言 `presentCall` 和 `presentResult` 的精确视图，并通过真实桥接层添加一个 [ACP 快照](../rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)；终端卡片的场景设置 `terminalOutput: true` 以覆盖 capable-client 路径。 +覆盖参数拒绝、每种结果形态和 HMR dispose。对于有副作用的工具，使用脚本化的 `MockAdapter` 驱动真实工具通过 agent loop（智能体循环），并断言其 `tool/call` 和 `tool/result` 会话事件。对于编辑器卡片，断言 `presentCall` 和 `presentResult` 的精确视图，并通过真实桥接层添加一个 [ACP 快照](../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md)；终端卡片的场景设置 `terminalOutput: true` 以覆盖 capable-client 路径。 diff --git a/docs/cookbook/adding-a-vendored-package.i18n.yaml b/docs/cookbook/adding-a-vendored-package.i18n.yaml index 0a359ead84..b3ca7ca791 100644 --- a/docs/cookbook/adding-a-vendored-package.i18n.yaml +++ b/docs/cookbook/adding-a-vendored-package.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -adding-a-vendored-package.md: d7b5b93b59fb39d8369be6eb42fb0a8b977c68b4 -adding-a-vendored-package.zh.md: 86b1e6c959180ba15b6fcb56b6dfe5a3be791b47 +adding-a-vendored-package.md: 1b82f2e582ca5cd040a7f3237505848dbb304fae +adding-a-vendored-package.zh.md: 7245682ef8b7d85ace2c626f8d47aa36f739506b diff --git a/docs/cookbook/adding-a-vendored-package.md b/docs/cookbook/adding-a-vendored-package.md index d7b5b93b59..1b82f2e582 100644 --- a/docs/cookbook/adding-a-vendored-package.md +++ b/docs/cookbook/adding-a-vendored-package.md @@ -2,7 +2,7 @@ English | [中文](adding-a-vendored-package.zh.md) -When the harness needs another upstream Cordis package (e.g. `@cordisjs/plugin-http`), it is **vendored** as pinned source under `vendor/`, not added as an npm dependency — see [the vendoring decision](../rfc/implemented/process/2026-06-11-vendor-cordis-as-source.md) for why. [vendor/README.md](../../vendor/README.md) covers *updating* an already-vendored package; this guide is the file-by-file checklist for adding a **new** one. (Verified against the existing vendored set; if it drifts, fix it here.) +When the harness needs another upstream Cordis package (e.g. `@cordisjs/plugin-http`), it is **vendored** as pinned source under `vendor/`, not added as an npm dependency — see [the vendoring decision](../../.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md) for why. [vendor/README.md](../../vendor/README.md) covers *updating* an already-vendored package; this guide is the file-by-file checklist for adding a **new** one. (Verified against the existing vendored set; if it drifts, fix it here.) ## 1. Copy the source in diff --git a/docs/cookbook/adding-a-vendored-package.zh.md b/docs/cookbook/adding-a-vendored-package.zh.md index 86b1e6c959..7245682ef8 100644 --- a/docs/cookbook/adding-a-vendored-package.zh.md +++ b/docs/cookbook/adding-a-vendored-package.zh.md @@ -2,7 +2,7 @@ [English](adding-a-vendored-package.md) | 中文 -当 harness 需要引入另一个上游 Cordis 包（如 `@cordisjs/plugin-http`）时，应将其作为固定版本的源码 **vendor** 到 `vendor/` 下，而非作为 npm 依赖添加——原因见[vendoring 决策](../rfc/implemented/process/2026-06-11-vendor-cordis-as-source.md)。[vendor/README.md](../../vendor/README.md) 介绍如何*更新*已有的 vendored 包；本指南是添加**新** vendored 包的逐文件清单。（已对照现有 vendored 集合验证；如有偏差，请在此修正。） +当 harness 需要引入另一个上游 Cordis 包（如 `@cordisjs/plugin-http`）时，应将其作为固定版本的源码 **vendor** 到 `vendor/` 下，而非作为 npm 依赖添加——原因见[vendoring 决策](../../.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md)。[vendor/README.md](../../vendor/README.md) 介绍如何*更新*已有的 vendored 包；本指南是添加**新** vendored 包的逐文件清单。（已对照现有 vendored 集合验证；如有偏差，请在此修正。） ## 1. 复制源码 diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 313cb8489b..5b7f226916 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: c6bf6ddd4bf0da8bd7377ab57e779750b72bd25e -extension-cookbook.zh.md: dcc188b7d3ac44f5d86253c20147e95da0bea648 +extension-cookbook.md: 37793e4e76bf5171c759ca78be473912101bd9f4 +extension-cookbook.zh.md: 8f170f225b55721c78ef27c0e87e481b5cb00f64 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index c6bf6ddd4b..37793e4e76 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -4,11 +4,11 @@ English | [中文](extension-cookbook.zh.md) > FIXME: This important guide has not received sufficient human design review; complete that review before the first release. -The three plugin shapes you write against the harness extension surface, as illustrative snippets (elided imports and helper stubs — not copy-paste-complete). For the full step-by-step guides see [adding a package](./adding-a-package.md), [adding a tool](./adding-a-tool.md), and [adding an LLM adapter](./adding-an-llm-adapter.md); for the seams these hook into see [docs/architecture.md](../architecture.md). +The three plugin shapes you write against the harness extension surface, as illustrative snippets (elided imports and helper stubs — not copy-paste-complete). For the full step-by-step guides see [adding a package](adding-a-package.md), [adding a tool](adding-a-tool.md), and [adding an LLM adapter](adding-an-llm-adapter.md); for the seams these hook into see [docs/architecture.md](../architecture.md). ## A tool plugin -A tool registers on `ctx.tools`. The annotated `defineTool` example (typed `execute` args, result shaping, the `run_in_background` pattern) lives in [adding-a-tool.md](./adding-a-tool.md) — that guide is the source of truth for the tool shape. Raw JSON-Schema `ToolDefinition`s are also accepted by `ctx.tools.register()` directly (that is how MCP-sourced tools arrive); `defineTool` is the typed sugar for first-party tools. +A tool registers on `ctx.tools`. The annotated `defineTool` example (typed `execute` args, result shaping, the `run_in_background` pattern) lives in [adding-a-tool.md](adding-a-tool.md) — that guide is the source of truth for the tool shape. Raw JSON-Schema `ToolDefinition`s are also accepted by `ctx.tools.register()` directly (that is how MCP-sourced tools arrive); `defineTool` is the typed sugar for first-party tools. ## A hook plugin (permission-gate example) @@ -32,7 +32,7 @@ export function apply(ctx: Context) { } ``` -This waterfall is the reorderable policy layer. Use `ctx.tools.guard()` when an invariant needs a monotonic final denial, `tools/execute` when a plugin must wrap the actual dispatch lifetime (timeouts/retries/metrics; only `exec.signal` is replaceable), `tools/post-execute` for explicit result transformation, and `tools/result` for contained observation of the immutable final outcome. The [adding-a-tool guide](./adding-a-tool.md#execution-policy-and-observation) gives the selection rule. +This waterfall is the reorderable policy layer. Use `ctx.tools.guard()` when an invariant needs a monotonic final denial, `tools/execute` when a plugin must wrap the actual dispatch lifetime (timeouts/retries/metrics; only `exec.signal` is replaceable), `tools/post-execute` for explicit result transformation, and `tools/result` for contained observation of the immutable final outcome. The [adding-a-tool guide](adding-a-tool.md#execution-policy-and-observation) gives the selection rule. ## A UI plugin @@ -91,7 +91,7 @@ Six runnable leaves load their plugin trees from `cordis.yml`: [`examples/echo-a ## The feature → mechanism map -Every product feature maps to a listener on a documented extension seam — the microkernel claim made checkable ([microkernel RFC](../rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md)). No row modifies the loop. +Every product feature maps to a listener on a documented extension seam — the microkernel claim made checkable ([microkernel Agent Note](../../.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md)). No row modifies the loop. `system-prompt/assemble` is an expert cooperative whole-assembly transform: its returned assembly is authoritative, so listener authors own preserving active Code Mode and structured-output protocol contributions. Prefer `ctx.tools.restrict()` for tool filtering that must stay aligned across presentation, lookup, and execution. @@ -102,7 +102,7 @@ Every product feature maps to a listener on a documented extension seam — the | `/loop` | on the `turn/end` session event, `send()` the next iteration; or force-continue | | Dynamic workflow | `ctx.workflows` + the worker-thread engine + the `workflow` tool; structured in-process children enforce output with scoped prompt/tool registrations, a monotonic tool guard, final `tools/result` commit (including enclosing `run_code`), and terminal `agent/turn-stop` | | Queued + steering messages | core `Agent.send()` / `Agent.steer()` | -| Context compaction (auto + manual) | the `ctx.compact` seam + `dsh-compact-basic`; automatic pressure runs on serial `agent/post-step`, canonical overflow recovery runs on `agent/request-error`, and manual callers use the same compact service ([compaction RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) | +| Context compaction (auto + manual) | the `ctx.compact` seam + `dsh-compact-basic`; automatic pressure runs on serial `agent/post-step`, canonical overflow recovery runs on `agent/request-error`, and manual callers use the same compact service ([compaction Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) | | System prompt configurability | `ctx.systemPrompt.section()` with ordering and scope-local shadowing | | AGENTS.md (root) | a section provider reading the file | | AGENTS.md (subdir, on-touch) + file-change notices | `agent.inject()` from a watcher / tool-result listener | diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index dcc188b7d3..8f170f225b 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -4,11 +4,11 @@ > FIXME：这篇重要指南尚未经过充分的人工设计审查；请在首次发布前完成审查。 -针对 harness 扩展表面编写的三种插件形态，以示意性代码片段呈现（省略了 import 和辅助桩——不可直接复制运行）。完整的分步指南见[添加包（package）](./adding-a-package.md)、[添加工具](./adding-a-tool.md)和[添加 LLM（大语言模型）适配器](./adding-an-llm-adapter.md)；这些插件所挂接的 seam 见 [docs/architecture.md](../architecture.md)。 +针对 harness 扩展表面编写的三种插件形态，以示意性代码片段呈现（省略了 import 和辅助桩——不可直接复制运行）。完整的分步指南见[添加包（package）](adding-a-package.md)、[添加工具](adding-a-tool.md)和[添加 LLM（大语言模型）适配器](adding-an-llm-adapter.md)；这些插件所挂接的 seam 见 [docs/architecture.md](../architecture.md)。 ## 工具插件 -工具在 `ctx.tools` 上注册。带注解的 `defineTool` 示例（类型化的 `execute` 参数、结果塑形、`run_in_background` 模式）见 [adding-a-tool.md](./adding-a-tool.md)——该指南是工具形态的真源。`ctx.tools.register()` 也直接接受原始 JSON-Schema `ToolDefinition`（MCP 来源的工具就是这样到达的）；`defineTool` 是为第一方工具提供的类型化语法糖。 +工具在 `ctx.tools` 上注册。带注解的 `defineTool` 示例（类型化的 `execute` 参数、结果塑形、`run_in_background` 模式）见 [adding-a-tool.md](adding-a-tool.md)——该指南是工具形态的真源。`ctx.tools.register()` 也直接接受原始 JSON-Schema `ToolDefinition`（MCP 来源的工具就是这样到达的）；`defineTool` 是为第一方工具提供的类型化语法糖。 ## 钩子插件（以权限门禁为例） @@ -32,7 +32,7 @@ export function apply(ctx: Context) { } ``` -这个 waterfall（瀑布式事件）是可重排的策略层。当不变式需要单调的最终拒绝时使用 `ctx.tools.guard()`；当插件需要包裹实际分发生命周期时（超时/重试/指标；仅 `exec.signal` 可替换）使用 `tools/execute`；显式结果变换使用 `tools/post-execute`；对不可变最终结果的受限观察使用 `tools/result`。选择规则见[添加工具指南](./adding-a-tool.md#execution-policy-and-observation)。 +这个 waterfall（瀑布式事件）是可重排的策略层。当不变式需要单调的最终拒绝时使用 `ctx.tools.guard()`；当插件需要包裹实际分发生命周期时（超时/重试/指标；仅 `exec.signal` 可替换）使用 `tools/execute`；显式结果变换使用 `tools/post-execute`；对不可变最终结果的受限观察使用 `tools/result`。选择规则见[添加工具指南](adding-a-tool.md#execution-policy-and-observation)。 ## UI 插件 @@ -91,7 +91,7 @@ export function apply(ctx: Context) { ## 功能→机制映射 -每个产品功能都映射到一个文档化扩展 seam 上的监听器——微内核声明由此可验证（[微内核 RFC](../rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md)）。没有任何一行修改循环本身。 +每个产品功能都映射到一个文档化扩展 seam 上的监听器——微内核声明由此可验证（[微内核 Agent Note](../../.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md)）。没有任何一行修改循环本身。 `system-prompt/assemble` 是一个专家协作式的整体装配变换：其返回的装配结果具有权威性，因此监听器作者有责任保留活跃的 Code Mode 和结构化输出协议的贡献。对于需要在展示、查找和执行之间保持对齐的工具过滤，优先使用 `ctx.tools.restrict()`。 @@ -102,7 +102,7 @@ export function apply(ctx: Context) { | `/loop` | 在 `turn/end` 会话事件上 `send()` 下一次迭代；或强制继续 | | 动态工作流 | `ctx.workflows` + worker-thread 引擎 + `workflow` 工具；结构化的进程内子任务通过作用域化的 prompt/工具注册、单调工具守卫、最终 `tools/result` 提交（包括外层 `run_code`）和终端 `agent/turn-stop` 来强制输出 | | 排队消息 + steering（中途引导） | 核心 `Agent.send()` / `Agent.steer()` | -| 上下文压缩（context compaction）（自动 + 手动） | `ctx.compact` seam + `dsh-compact-basic`；自动压力检查运行在串行 `agent/post-step`，规范化溢出恢复运行在 `agent/request-error`，手动调用方使用同一个压缩服务（[压缩 RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟） | +| 上下文压缩（context compaction）（自动 + 手动） | `ctx.compact` seam + `dsh-compact-basic`；自动压力检查运行在串行 `agent/post-step`，规范化溢出恢复运行在 `agent/request-error`，手动调用方使用同一个压缩服务（[压缩 Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟） | | 系统提示词可配置性 | `ctx.systemPrompt.section()`，支持排序与作用域局部覆盖 | | AGENTS.md（根目录） | 一个读取该文件的 section provider | | AGENTS.md（子目录，按需触发）+ 文件变更通知 | 从 watcher / tool-result 监听器调用 `agent.inject()` | diff --git a/docs/cookbook/maintaining-dsh-code-review.md b/docs/cookbook/maintaining-dsh-code-review.md index 5a6c2df120..8af449b749 100644 --- a/docs/cookbook/maintaining-dsh-code-review.md +++ b/docs/cookbook/maintaining-dsh-code-review.md @@ -1,6 +1,6 @@ # Maintaining the dsh-code-review skill -The [`dsh-code-review`](../../.agents/skills/dsh-code-review/SKILL.md) skill is kept current by a single designated operator running a private periodic maintenance tool. This cookbook is the entry point for that operator — and for anyone taking over the role — and for repo contributors who want to understand why skill updates arrive as small periodic PRs rather than one-off audits. The workflow itself is specified in the [human-review skill-maintenance RFC](../rfc/proposed/process/2026-07-13-human-review-skill-maintenance.md). +The [`dsh-code-review`](../../.agents/skills/dsh-code-review/SKILL.md) skill is kept current by a single designated operator running a private periodic maintenance tool. This cookbook is the entry point for that operator — and for anyone taking over the role — and for repo contributors who want to understand why skill updates arrive as small periodic PRs rather than one-off audits. The workflow itself is specified in the [human-review skill-maintenance Agent Note](../../.agents/notes/proposed/process/2026-07-13-human-review-skill-maintenance.md). ## What the maintainer receives @@ -55,8 +55,8 @@ The mechanism lives on one machine. Interruptions the operator handles as they a - **Daily run missed.** The two-day overlap window catches one skipped day automatically; longer gaps recover by running the wrapper manually with `DSH_CODE_REVIEW_SINCE=<Nd>`. Overlapping windows are idempotent: guidance already in the current skill is classified `covered` and does not re-enter as a candidate. - **Adapter provider outage.** The tool refuses to run when the two reviewer commands resolve to byte-identical executables. A single batch whose adapter response fails schema or id validation is failed closed at the batch level (every item in the batch marked unclear) and the run continues; the raw output is preserved for debugging. If either adapter produces no valid result for any nonempty batch in an operation, the run fails, writes a failure record, and notifies the operator; it never collapses a total-provider outage into "no candidate." -- **Handoff to another maintainer.** Open a follow-up RFC that supersedes the current one: either move the mechanism into the repository or record the new operator's private setup. Do not silently transfer the tool — the "single-maintainer bus factor" in the RFC's Risks section is the reason the handoff needs a documented decision. +- **Handoff to another maintainer.** Open a follow-up Agent Note that supersedes the current one: either move the mechanism into the repository or record the new operator's private setup. Do not silently transfer the tool — the "single-maintainer bus factor" in the Agent Note's Risks section is the reason the handoff needs a documented decision. ## Where the operator's private setup lives -The tool source, reviewer adapters, provider credentials, and scheduler are the operator's private infrastructure and are outside this repository by design (see the RFC's "Where the mechanism lives" section). This cookbook and the RFC describe **what the workflow guarantees**; **how** those guarantees are implemented is a private-infrastructure concern. If you are the new operator, the RFC's `## Proposal` sections are the specification you build against. +The tool source, reviewer adapters, provider credentials, and scheduler are the operator's private infrastructure and are outside this repository by design (see the Agent Note's "Where the mechanism lives" section). This cookbook and the Agent Note describe **what the workflow guarantees**; **how** those guarantees are implemented is a private-infrastructure concern. If you are the new operator, the Agent Note's `## Proposal` sections are the specification you build against. diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 7d7472a33e..5d6c627751 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -463,7 +463,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t * adapter's stream, or yield your own chunks to short-circuit. * @param options - the full request. A LOOP-built request arrives * deep-frozen (mutation throws): its content is a pure function of the - * session log (the reconstructability RFC), so listeners read it, never + * session log (the reconstructability Agent Note), so listeners read it, never * rewrite it. A hand-built one-shot (compaction summarize) is the * caller's own object and stays mutable here. * @mode waterfall diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index 060d249eb7..c1c7754dd2 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -105,7 +105,7 @@ interface BashExecSpec { } ``` -`stdin` and `env` are trusted in-process plugin inputs and are not exposed by `dsh-tool-bash`. The local executor scrubs ambient credentials before merging explicit caller-supplied env. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +`stdin` and `env` are trusted in-process plugin inputs and are not exposed by `dsh-tool-bash`. The local executor scrubs ambient credentials before merging explicit caller-supplied env. See [the bash-stdin-env Agent Note](../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). `stdoutMaxBytes` is also trusted-plugin-only. It lets a foreground consumer request complete stdout up to a bounded parser budget without changing stderr, background tasks, or the model-facing bash tool's ordinary output cap. @@ -125,7 +125,7 @@ interface BashRunResult { * short. Mutually exclusive with {@link aborted}: one fused deadline drives * both the timeout and the caller's cancellation, so a timeout and an abort * racing before process close report the single first-abort cause, not both - * (see the [timeout-library RFC](../../../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md)). + * (see the [timeout-library Agent Note](../../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md)). */ timedOut: boolean /** @@ -181,7 +181,7 @@ interface BashSandboxInfo { } ``` -One more piece completes the vocabulary: the `SANDBOX_UNAVAILABLE` error code (owned by the [sandbox seam](sandbox.md)) is what the `ctx.sandbox` provider throws — and the executor propagates — when a confined mode has no usable backend. A selected runner refusing its profile reaches the same fail-closed foreground error; a settled background task records `runnerFailed`. The model receives denial/runner facts in results, learns the effective mode only when a denial marker names it, and can request a one-shot strictly wider retry through `sandbox_permissions` plus `justification`; `ctx.approval` must grant that exact call before anything executes. The complete policy and switching design is the [sandbox RFC](../rfc/implemented/feature/2026-07-06-sandbox.md). +One more piece completes the vocabulary: the `SANDBOX_UNAVAILABLE` error code (owned by the [sandbox seam](sandbox.md)) is what the `ctx.sandbox` provider throws — and the executor propagates — when a confined mode has no usable backend. A selected runner refusing its profile reaches the same fail-closed foreground error; a settled background task records `runnerFailed`. The model receives denial/runner facts in results, learns the effective mode only when a denial marker names it, and can request a one-shot strictly wider retry through `sandbox_permissions` plus `justification`; `ctx.approval` must grant that exact call before anything executes. The complete policy and switching design is the [sandbox Agent Note](../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). ## Background processes: `BashProcess` diff --git a/docs/core-data-structures/code-runtime.md b/docs/core-data-structures/code-runtime.md index cea69180af..af3fdbc649 100644 --- a/docs/core-data-structures/code-runtime.md +++ b/docs/core-data-structures/code-runtime.md @@ -1,6 +1,6 @@ # Code Runtime -The code-execution seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) whose interface ([dsh-code-runtime](../../packages/code-runtime/code-runtime), `ctx.codeRuntime`) runs one model-written program against host-provided async bindings and reports what it printed and returned. Code execution is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). Backends differ by execution substrate and source language, both readonly descriptors on the service; the worker-thread backend and the tool-registry consumer (Code Mode) are specified in the [Code Mode RFC](../rfc/implemented/feature/2026-06-15-code-mode.md). +The code-execution seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) whose interface ([dsh-code-runtime](../../packages/code-runtime/code-runtime), `ctx.codeRuntime`) runs one model-written program against host-provided async bindings and reports what it printed and returned. Code execution is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). Backends differ by execution substrate and source language, both readonly descriptors on the service; the worker-thread backend and the tool-registry consumer (Code Mode) are specified in the [Code Mode Agent Note](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md). Source: [`packages/code-runtime/code-runtime/src/types.ts`](../../packages/code-runtime/code-runtime/src/types.ts) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index f6cdfd5b8b..a511b2f93d 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -1,17 +1,17 @@ # Compaction -The compaction seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). +The compaction seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)). Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) ## The `compact/*` session events -Compaction extends [`SessionEventMap`](session.md) with three event types via declaration merging. All three are **log-only** — they record the compaction lock and its provenance, and never join the surface. `SurfaceEventType` is deliberately NOT extended (only message-producing events reach the model), so the summary itself rides on a separate `user/message` with `surfaceOp: { op: 'replace', start, end }` — the only surface mutation. See the RFC for why reusing `user/message` is honest rather than a workaround. +Compaction extends [`SessionEventMap`](session.md) with three event types via declaration merging. All three are **log-only** — they record the compaction lock and its provenance, and never join the surface. `SurfaceEventType` is deliberately NOT extended (only message-producing events reach the model), so the summary itself rides on a separate `user/message` with `surfaceOp: { op: 'replace', start, end }` — the only surface mutation. See the Agent Note for why reusing `user/message` is honest rather than a workaround. | Event | Payload | Role | |---|---|---| | `compact/start` | `{ turn }` | acquires the log-recorded lock | -| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`provider`, `model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability RFC) | +| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`provider`, `model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability Agent Note) | | `compact/end` | `{ turn, error? }` | releases the lock (`error` set when summarization threw) | The lock brackets the **whole** operation: `compact/start` is appended first, then summarization, the `compact/summary` provenance record, and the `user/message` replacement all land, and only then `compact/end`. Releasing the lock last turns a crash mid-operation into a detectable orphaned lock (a `compact/start` with no matching `compact/end`) rather than a `compact/end` that falsely claims compaction finished. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 1d45f3814a..1b87513e11 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -264,7 +264,7 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition` ### The request envelope: `LlmCallConfig` and the logged header -The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset), and session prefix through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md). +The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset), and session prefix through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability Agent Note](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md). `agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, or sampling. `agent/session-prefix` composes request-only prefix messages once per loop instance, and the header records the exact result used. Requests reaching `llm/stream` are deep-frozen, so mutation throws. @@ -403,7 +403,7 @@ The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, che ## Initiating Agent -The process-local initiator carried by `ctx.agents` is the exact `Agent` above, not a separate frame or copied identity. Ambient presence is neither liveness proof nor authorization; the [initiator-scope decision](../rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns its lifetime and boundary rules. +The process-local initiator carried by `ctx.agents` is the exact `Agent` above, not a separate frame or copied identity. Ambient presence is neither liveness proof nor authorization; the [initiator-scope decision](../../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns its lifetime and boundary rules. ## Interception decisions diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index 3526687f3e..41ce6427e6 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -46,7 +46,7 @@ This contract was pinned down by two deliberately independent implementations: ` ## `AppIdentity` — app attribution -The static public application identity every adapter sends to providers ([`packages/llm/llm/src/attribution.ts`](../../packages/llm/llm/src/attribution.ts)). `attributionHeaders(identity?)` maps it to the standard `User-Agent` header only; OpenRouter-specific app attribution headers are intentionally not supported by this contract. The default `APP_IDENTITY` sources its version from the package manifest; every field is a public product fact - no secrets, paths, session ids, or per-user identifiers, and nothing per-request may influence the values. Rationale: [Mandatory `User-Agent` attribution](../rfc/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md). +The static public application identity every adapter sends to providers ([`packages/llm/llm/src/attribution.ts`](../../packages/llm/llm/src/attribution.ts)). `attributionHeaders(identity?)` maps it to the standard `User-Agent` header only; OpenRouter-specific app attribution headers are intentionally not supported by this contract. The default `APP_IDENTITY` sources its version from the package manifest; every field is a public product fact - no secrets, paths, session ids, or per-user identifiers, and nothing per-request may influence the values. Rationale: [Mandatory `User-Agent` attribution](../../.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md). ```ts type-equiv /** diff --git a/docs/core-data-structures/persistence.md b/docs/core-data-structures/persistence.md index 72ebcc5852..a80b9bc896 100644 --- a/docs/core-data-structures/persistence.md +++ b/docs/core-data-structures/persistence.md @@ -2,7 +2,7 @@ The **durability seam** for the event log. [session.md](session.md) describes the in-memory `Session` — the append-only `SessionEvent` log that is the source of truth. This page describes how that log is made durable: the abstract `SessionPersistence` service, its backends, the flush checkpoint, crash recovery, and the metadata header that travels alongside the log. The event vocabulary the log carries is enumerated, member by member, in the generated [persistence log event catalog](../persistence-catalog.md). -The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining locate/create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence RFC](../rfc/implemented/architecture/2026-06-14-session-persistence.md). +The seam is a textbook [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining locate/create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence Agent Note](../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md). ## The flush checkpoint @@ -98,4 +98,4 @@ Both implement the same abstract `SessionPersistence` (locate/create/append/load - **[dsh-session-persistence-jsonl](../../packages/session-persistence/session-persistence-jsonl)** — an append-only JSONL log per session with crash-safe atomic writes, the interrupted-turn crash recovery above, and a read/replay path. - **[dsh-session-persistence-sqlite](../../packages/session-persistence/session-persistence-sqlite)** — `node:sqlite`, one row per `SessionEvent`. The row shape `(session_id, seq, type, time, data, source_event_seqs, surface_op)` maps 1:1 onto the event, including optional surface metadata, so there is no parallel persisted schema to keep in sync. -Multiple backends sharing one on-disk session coordinate writes through the [shared persistence write-coordinator](../rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md). +Multiple backends sharing one on-disk session coordinate writes through the [shared persistence write-coordinator](../../.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md). diff --git a/docs/core-data-structures/scope.md b/docs/core-data-structures/scope.md index d79f464b3e..93e6d76598 100644 --- a/docs/core-data-structures/scope.md +++ b/docs/core-data-structures/scope.md @@ -1,6 +1,6 @@ # Scoped Registration -The [scope package](../../packages/core/scope) supplies the identity and carrier vocabulary that makes one registration context mean both per-agent visibility and shared lifetime ownership. It is a library primitive rather than a Cordis service; the [agent-scope runtime-design RFC](../rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#scope-routing-one-opaque-key-selects-one-layer) owns the implementation rationale, while the package [README](../../packages/core/scope/README.md) owns the callable API and filtering semantics. +The [scope package](../../packages/core/scope) supplies the identity and carrier vocabulary that makes one registration context mean both per-agent visibility and shared lifetime ownership. It is a library primitive rather than a Cordis service; the [agent-scope runtime-design Agent Note](../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#scope-routing-one-opaque-key-selects-one-layer) owns the implementation rationale, while the package [README](../../packages/core/scope/README.md) owns the callable API and filtering semantics. Source: [`packages/core/scope/src/index.ts`](../../packages/core/scope/src/index.ts). diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 3668191fb2..263d991f86 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -101,7 +101,7 @@ interface SessionEventMap { ### `TodoItem` — one todo-list entry -The unit of the `todo/write` event's whole-list snapshot. Deliberately minimal — a `content` line and a three-state `status` (no id, priority, or `activeForm`): the list is replaced wholesale on every write, so entries need no stable identity, and the status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally requires). See the [todo_write RFC](../rfc/implemented/feature/2026-06-29-todo-write-tool.md). +The unit of the `todo/write` event's whole-list snapshot. Deliberately minimal — a `content` line and a three-state `status` (no id, priority, or `activeForm`): the list is replaced wholesale on every write, so entries need no stable identity, and the status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally requires). See the [todo_write Agent Note](../../.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md). ```ts type-equiv /** @@ -125,7 +125,7 @@ interface TodoItem { ### The request header event: `request/header` -The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas + the session prefix) — is logged session state, so every conversation request is a pure function of the log (the reconstructability RFC). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message. +The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas + the session prefix) — is logged session state, so every conversation request is a pure function of the log (the reconstructability Agent Note). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message. ```ts type-equiv /** @@ -200,7 +200,7 @@ For `assistant/message`, a present `sourceEventSeqs: []` is a complete known-emp ## Surface types -The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the ordered derived surface. See the [session surface RFC](../rfc/implemented/architecture/2026-06-18-session-surface.md). +The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the ordered derived surface. See the [session surface Agent Note](../../.agents/notes/implemented/architecture/2026-06-18-session-surface.md). ### `SurfaceEventType` — the message-producing subset of event types @@ -414,7 +414,7 @@ declare class Session { * The per-node pure function {@link deriveMessages} folds over the surface; * an external reconstructor (or the dev invariant) folds the same function * over a log prefix's surface to rebuild the exact messages any request was - * built from (the reconstructability RFC). The returned message wrapper is + * built from (the reconstructability Agent Note). The returned message wrapper is * fresh; its content reuses the logged event's already deep-frozen durable * data, so changing the wrapper cannot rewrite the log and changing content * throws. @@ -502,13 +502,13 @@ interface TurnEndReasonMap { ## The turn-enclosure invariant -Every session event lives **inside** a turn (between a `turn/start` and its `turn/end`). The loop appends queued `user/message` events *after* `turn/start`, and an idle `agent.inject()` wraps its `context/message` in a one-shot `injection` turn. This makes the turn the single durability/replay boundary: a backend can treat anything after the last `turn/end` as an interrupted-crash tail without risking the loss of legitimately-recorded between-turn context. The `dsh-invariants` plugin enforces it in dev (a message event outside an open turn throws). See [the turn-enclosure invariant RFC](../rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md). +Every session event lives **inside** a turn (between a `turn/start` and its `turn/end`). The loop appends queued `user/message` events *after* `turn/start`, and an idle `agent.inject()` wraps its `context/message` in a one-shot `injection` turn. This makes the turn the single durability/replay boundary: a backend can treat anything after the last `turn/end` as an interrupted-crash tail without risking the loss of legitimately-recorded between-turn context. The `dsh-invariants` plugin enforces it in dev (a message event outside an open turn throws). See [the turn-enclosure invariant Agent Note](../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md). ## Plugin-contributed log-only events A plugin may declaration-merge extra `SessionEventMap` types. These are **log-only**: NOT `SurfaceEventType`s (they carry no `surfaceOp` and contribute nothing to derived history), but, like every event, they must sit inside an open turn. The full per-event enumeration — core and plugin-contributed alike, with payloads and provenance — is the generated [persistence log event catalog](../persistence-catalog.md); the compaction seam's `compact/*` semantics are discussed on [compaction.md](compaction.md). -The hook bridges' `hook/invoked` / `hook/result` provenance pairs (from `@deepseek-ai/dsh-hook-protocol`) correlate by `handlerId`. The mid-turn hook points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn, so their `hook/*` records are turn-enclosed by construction. `SessionStart` gets no `hook/*` record — its injected `context/message` is the durable evidence — because it has no open turn to enclose one (see [the hook-bridges RFC](../rfc/implemented/feature/2026-06-30-hook-bridges.md)). +The hook bridges' `hook/invoked` / `hook/result` provenance pairs (from `@deepseek-ai/dsh-hook-protocol`) correlate by `handlerId`. The mid-turn hook points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn, so their `hook/*` records are turn-enclosed by construction. `SessionStart` gets no `hook/*` record — its injected `context/message` is the durable evidence — because it has no open turn to enclose one (see [the hook-bridges Agent Note](../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md)). ## Durability contract diff --git a/docs/core-data-structures/skills.md b/docs/core-data-structures/skills.md index daccb38550..e367adf006 100644 --- a/docs/core-data-structures/skills.md +++ b/docs/core-data-structures/skills.md @@ -152,6 +152,6 @@ interface Config { ## Session catalog and tool contract -`dsh-tool-skill` contributes a user-role `<system-reminder>` through `agent/session-prefix`. The catalog contains sorted skill `name` and normalized, XML-escaped `description` only; it omits bodies, paths, sources, providers, and routing hints. Prefix discovery forwards the caller's abort signal through `SkillLookupOptions`. `catalogDescriptionMaxLength` is the consumer config for the description bound, with default `500` and integer minimum `3`. Its request-only, header-logged lifecycle is defined by the [session-prefix RFC](../rfc/implemented/feature/2026-07-07-session-prefix.md). +`dsh-tool-skill` contributes a user-role `<system-reminder>` through `agent/session-prefix`. The catalog contains sorted skill `name` and normalized, XML-escaped `description` only; it omits bodies, paths, sources, providers, and routing hints. Prefix discovery forwards the caller's abort signal through `SkillLookupOptions`. `catalogDescriptionMaxLength` is the consumer config for the description bound, with default `500` and integer minimum `3`. Its request-only, header-logged lifecycle is defined by the [session-prefix Agent Note](../../.agents/notes/implemented/feature/2026-07-07-session-prefix.md). The model-facing `skill({ name })` tool validates the kebab-case name, loads the complete definition for the calling agent cwd, reports an unresolved skill as unknown or no longer available, rejects `disableModelInvocation` skills, and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` resolves explicitly referenced scripts, references, and assets only as needed; the loaded result does not enumerate a skill directory. The tool result is the model-visible path for complete instructions. diff --git a/docs/core-data-structures/spill.md b/docs/core-data-structures/spill.md index d046874b0e..a964064912 100644 --- a/docs/core-data-structures/spill.md +++ b/docs/core-data-structures/spill.md @@ -1,6 +1,6 @@ # Spill Storage -The spill storage seam — a [capability seam](../rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md) that persists a tool's oversized text and returns a model-facing locator plus retrieval guidance, split across packages: interface ([dsh-spill](../../packages/spill/spill), `ctx.spillStore`), implementation ([dsh-spill-local](../../packages/spill/spill-local), private session-scoped files on the host filesystem), and consumer ([dsh-spill-policy](../../packages/spill/spill-policy), the `tools/post-execute` policy). Spill is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). Preview mechanics stay in [dsh-retention](../../packages/util/retention); this seam only saves the final text the policy hands it. +The spill storage seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md) that persists a tool's oversized text and returns a model-facing locator plus retrieval guidance, split across packages: interface ([dsh-spill](../../packages/spill/spill), `ctx.spillStore`), implementation ([dsh-spill-local](../../packages/spill/spill-local), private session-scoped files on the host filesystem), and consumer ([dsh-spill-policy](../../packages/spill/spill-policy), the `tools/post-execute` policy). Spill is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). Preview mechanics stay in [dsh-retention](../../packages/util/retention); this seam only saves the final text the policy hands it. Source: [`packages/spill/spill/src/types.ts`](../../packages/spill/spill/src/types.ts) diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index d279f26a9d..54e79aca68 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -2,7 +2,7 @@ The subagent seam — an agent delegating work to a child agent. Like [bash](bash.md) it is **one optional capability**, not part of the agent-loop spine, so its vocabulary lives here rather than in [core.md](core.md). But it differs from every other seam on one axis: **multiple provider implementations coexist** in one context, registered by name (`ctx.subagents`), where bash allows only one executor. The registry shape mirrors the [LLM adapter registry](llm-streaming.md), not the single-service bash executor. -Interface: [dsh-subagent](../../packages/subagent/subagent) (`ctx.subagents` + the vocabulary below). Implementations are sibling packages (`dsh-subagent-spawn`, `-fork`, `-acp`); the model-facing consumer is [dsh-tool-subagent](../../packages/subagent/tool-subagent). The proposal and rationale: [the subagent RFC](../rfc/implemented/feature/2026-06-21-subagent-capability-seam.md). +Interface: [dsh-subagent](../../packages/subagent/subagent) (`ctx.subagents` + the vocabulary below). Implementations are sibling packages (`dsh-subagent-spawn`, `-fork`, `-acp`); the model-facing consumer is [dsh-tool-subagent](../../packages/subagent/tool-subagent). The proposal and rationale: [the subagent Agent Note](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md). Source: [`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts) @@ -94,7 +94,7 @@ interface SubagentStartRequest { } ``` -`signal` is the single cancellation channel before and after readiness. The [subagent composition-controls RFC](../rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns the persona, live global-tool filter, absolute-depth, and visibility-not-authority rationale. +`signal` is the single cancellation channel before and after readiness. The [subagent composition-controls Agent Note](../../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns the persona, live global-tool filter, absolute-depth, and visibility-not-authority rationale. ## The terminal result: `SubagentResult` diff --git a/docs/core-data-structures/tasks.md b/docs/core-data-structures/tasks.md index ebe2062a84..491f380166 100644 --- a/docs/core-data-structures/tasks.md +++ b/docs/core-data-structures/tasks.md @@ -1,6 +1,6 @@ # Background Task Runtime -Types shared by long-running producers, `ctx.tasks`, and task control surfaces. The [runtime RFC](../rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md) owns the design; this page records the literal shapes from [`packages/tasks/tasks/src/types.ts`](../../packages/tasks/tasks/src/types.ts). +Types shared by long-running producers, `ctx.tasks`, and task control surfaces. The [runtime Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md) owns the design; this page records the literal shapes from [`packages/tasks/tasks/src/types.ts`](../../packages/tasks/tasks/src/types.ts). ## Ids and status diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 7cc0910d90..30ec86213a 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -28,7 +28,7 @@ interface ToolDefinition extends ToolSchema { * Opted-in executions must not mutate parent-owned state. Shared state must * tolerate concurrent dispatch; recorder races are permitted only when they * commute or fail closed. See the - * [parallel-tool-call RFC](../../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) + * [parallel-tool-call Agent Note](../../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) * for the full contract. * @param args - parsed arguments; `defineTool` validates before calling. * @returns Whether this call may join a parallel group. @@ -346,6 +346,6 @@ How a tool wants its call shown in a UI (an editor tool-call card, a CLI log lin - `ToolCallView` (pending): `{ card: 'generic', title, kind?, rawInput?, content?, locations? }` (the default card; `locations` is `{ path, line? }[]` files the call reads/modifies, for editor follow-along), `{ card: 'terminal', title, description?, cwd? }` (a shell command → a terminal card), or `{ card: 'diff', title, diffs, locations? }` (a file create/modify → an inline diff card; `diffs` is `{ path, oldText, newText }[]`, `oldText: null` for a new file). - `ToolResultView` (completed): `{ card: 'generic', title?, content? }`, `{ card: 'terminal', title?, output?, exitCode?, signal? }` (the captured run output + exit; a capable UI shows an exit-status pill, an incapable one gets a fenced ` ```console ` fallback the bridge derives from `output`), or `{ card: 'diff', title?, diffs }` (a completed file mutation → the change to show, typically the applied hunks with context lines computed from the before/after content, or a whole-file diff when there is no before-image — e.g. a file create. A `tool_call_update`'s content REPLACES the call's content, so a mutation tool returns this even when it duplicates the call-time snippet, to keep the result from clobbering the diff with result text). -`ToolCallKind` (`'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'`) picks an icon on a generic card. `FileLocation` (`{ path, line? }`) and `FileDiff` (`{ path, oldText, newText }`) are the shared file-card vocabulary. The design is pinned in [the render-intent-union RFC](../rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md); the ACP bridge maps a `diff` card to a `{ type: 'diff' }` content block, a `terminal` card to the `_meta` terminal convention, and relativizes a file card's title against the session cwd. +`ToolCallKind` (`'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'`) picks an icon on a generic card. `FileLocation` (`{ path, line? }`) and `FileDiff` (`{ path, oldText, newText }`) are the shared file-card vocabulary. The design is pinned in [the render-intent-union Agent Note](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md); the ACP bridge maps a `diff` card to a `{ type: 'diff' }` content block, a `terminal` card to the `_meta` terminal convention, and relativizes a file card's title against the session cwd. The full presentation field docs live in [`packages/core/tools/src/presentation.ts`](../../packages/core/tools/src/presentation.ts). The `bash` schema and executor are on [bash.md](bash.md); generic background controls are on [tasks.md](tasks.md). diff --git a/docs/core-data-structures/web.md b/docs/core-data-structures/web.md index af14f54466..22909b8dfb 100644 --- a/docs/core-data-structures/web.md +++ b/docs/core-data-structures/web.md @@ -1,6 +1,6 @@ # Web Access -The web access seam — a [capability seam](../rfc/implemented/architecture/2026-06-24-web-capability-seam.md) that spans **two capabilities** (search and fetch) on one `ctx.web` service, split across packages: interface ([dsh-web](../../packages/web/web), `ctx.web` + the provider registries), implementations ([dsh-web-search-exa](../../packages/web/web-search-exa), [dsh-web-search-perplexity](../../packages/web/web-search-perplexity), [dsh-web-search-deepseek](../../packages/web/web-search-deepseek), [dsh-web-fetch-local](../../packages/web/web-fetch-local)), and consumer ([dsh-tool-web](../../packages/web/tool-web), the `web_search`/`web_fetch` tool schemas). Web is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A search-provider swap does not change how the model asks for a query, and a fetch-implementation swap does not change how the model asks for a URL. +The web access seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md) that spans **two capabilities** (search and fetch) on one `ctx.web` service, split across packages: interface ([dsh-web](../../packages/web/web), `ctx.web` + the provider registries), implementations ([dsh-web-search-exa](../../packages/web/web-search-exa), [dsh-web-search-perplexity](../../packages/web/web-search-perplexity), [dsh-web-search-deepseek](../../packages/web/web-search-deepseek), [dsh-web-fetch-local](../../packages/web/web-fetch-local)), and consumer ([dsh-tool-web](../../packages/web/tool-web), the `web_search`/`web_fetch` tool schemas). Web is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A search-provider swap does not change how the model asks for a query, and a fetch-implementation swap does not change how the model asks for a URL. Source: [`packages/web/web/src/types.ts`](../../packages/web/web/src/types.ts) diff --git a/docs/core-data-structures/workflow.md b/docs/core-data-structures/workflow.md index 40b17a3112..26e337c4c6 100644 --- a/docs/core-data-structures/workflow.md +++ b/docs/core-data-structures/workflow.md @@ -2,7 +2,7 @@ The workflow seam — an agent running a model-written orchestration SCRIPT that fans out subagents. Like [subagent](subagent.md) it is **one optional capability**, not part of the agent-loop spine, so its vocabulary lives here rather than in [core.md](core.md). Unlike the subagent registry it takes the bash shape: ONE engine implementation per context provides `ctx.workflows`; there is no named-provider registry (a second engine is a plugin swap, not a co-resident). -Interface: [dsh-workflow](../../packages/workflow/workflow) (`ctx.workflows` + the vocabulary below). The implementation is [dsh-workflow-workerthread](../../packages/workflow/workflow-workerthread) (a `node:worker_threads` engine — one worker per run, the script's vm context inside it); the model-facing consumer is [dsh-tool-workflow](../../packages/workflow/tool-workflow). The proposal and rationale: [the dynamic-workflows RFC](../rfc/implemented/feature/2026-07-05-dynamic-workflows.md). +Interface: [dsh-workflow](../../packages/workflow/workflow) (`ctx.workflows` + the vocabulary below). The implementation is [dsh-workflow-workerthread](../../packages/workflow/workflow-workerthread) (a `node:worker_threads` engine — one worker per run, the script's vm context inside it); the model-facing consumer is [dsh-tool-workflow](../../packages/workflow/tool-workflow). The proposal and rationale: [the dynamic-workflows Agent Note](../../.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md). Source: [`packages/workflow/workflow/src/types.ts`](../../packages/workflow/workflow/src/types.ts) diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index d7f82d7e92..8036d11e0b 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: a3268164cd06fb8bf66f52391bc42c2dc3ca9396 -development.zh.md: f8f29c64aa6e49e3ed6d7ef12df2a4911c9182b0 +development.md: 31d9f76b6f32b1d26e7b61cdbc2a09aa3504fd6a +development.zh.md: 57d9ca376ed85c212cfd075e1b056882f6449e05 diff --git a/docs/development.md b/docs/development.md index a3268164cd..31d9f76b6f 100644 --- a/docs/development.md +++ b/docs/development.md @@ -2,11 +2,11 @@ English | [中文](development.zh.md) -This onboarding guide helps project contributors get started with the local environment, daily workflow, and CI flow; see the RFCs for design rationale and technical trade-offs. +This onboarding guide helps project contributors get started with the local environment, daily workflow, and CI flow; see the Agent Notes for design rationale and technical trade-offs. ## Prerequisites -- Node.js supports 22.19+ and 24+. CI covers 22.19, 24, and 26; see the [Node engine floor RFC](rfc/implemented/process/2026-07-06-node-engine-floor.md). +- Node.js supports 22.19+ and 24+. CI covers 22.19, 24, and 26; see the [Node engine floor Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md). - Corepack-enabled pnpm. The repo pins `pnpm@11.7.0` in `package.json`; run `corepack enable` if `pnpm --version` does not resolve through Corepack. - Git. - Optional: a DeepSeek API key for the REPL/ACP agent demos and real-API e2e tests. @@ -86,7 +86,7 @@ pnpm run verify-cordis-catalog # fail if either cordis catalog is stale pnpm run verify-export-jsdoc # fail if a module-level package export lacks complete JSDoc pnpm run gen-doc-graphs # regenerate generated relationship docs from source and curated graph definitions pnpm run verify-doc-graphs # fail if generated relationship docs are stale -pnpm run gen-rfc-index # regenerate the docs/rfc/README.md index tables from the RFC tree +pnpm run gen-agent-note-index # regenerate .agents/notes/INDEX.md from the Agent Note tree pnpm run verify-md-wrap # fail on hard-wrapped prose paragraphs in docs/README markdown pnpm run verify-mermaid # fail if a ```mermaid diagram has invalid Mermaid syntax pnpm run verify-type-equiv # fail if a ```ts type-equiv doc block drifts from its source type diff --git a/docs/development.zh.md b/docs/development.zh.md index f8f29c64aa..57d9ca376e 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -2,11 +2,11 @@ [English](development.md) | 中文 -本指南覆盖参与 DeepSeek Harness 开发所需的本地环境搭建、日常工作流与 CI 流程；设计动机与技术权衡请查阅相应 RFC。 +本指南覆盖参与 DeepSeek Harness 开发所需的本地环境搭建、日常工作流与 CI 流程；设计动机与技术权衡请查阅相应 Agent Note。 ## 前置条件 -- Node.js 支持 22.19+ 与 24+。CI 覆盖 22.19、24 和 26；见 [Node 引擎下限 RFC](rfc/implemented/process/2026-07-06-node-engine-floor.md)。 +- Node.js 支持 22.19+ 与 24+。CI 覆盖 22.19、24 和 26；见 [Node 引擎下限 Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md)。 - 启用了 Corepack 的 pnpm。仓库在 `package.json` 中固定使用 `pnpm@11.7.0`；如果 `pnpm --version` 无法通过 Corepack 解析，请先运行 `corepack enable`。 - Git。 - 可选：一个 DeepSeek API key，用于 REPL/ACP（Agent Client Protocol） agent（智能体）演示和真实 API 的 e2e 测试。 @@ -86,7 +86,7 @@ pnpm run verify-cordis-catalog # fail if either cordis catalog is stale pnpm run verify-export-jsdoc # fail if a module-level package export lacks complete JSDoc pnpm run gen-doc-graphs # regenerate generated relationship docs from source and curated graph definitions pnpm run verify-doc-graphs # fail if generated relationship docs are stale -pnpm run gen-rfc-index # regenerate the docs/rfc/README.md index tables from the RFC tree +pnpm run gen-agent-note-index # regenerate .agents/notes/INDEX.md from the Agent Note tree pnpm run verify-md-wrap # fail on hard-wrapped prose paragraphs in docs/README markdown pnpm run verify-mermaid # fail if a ```mermaid diagram has invalid Mermaid syntax pnpm run verify-type-equiv # fail if a ```ts type-equiv doc block drifts from its source type diff --git a/docs/glossary.md b/docs/glossary.md index 81b9b4f84a..5392773dc9 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -1,6 +1,6 @@ # Glossary -Domain vocabulary for the DeepSeek Harness SDK uses one canonical term per concept. Terms link to their entries with standard Markdown anchors; implementation detail stays in package READMEs and RFCs. +Domain vocabulary for the DeepSeek Harness SDK uses one canonical term per concept. Terms link to their entries with standard Markdown anchors; implementation detail stays in package READMEs and Agent Notes. FIXME(glossary-completeness): Expand this glossary before the first release so it covers the SDK's other core and capability subsystems, not only agent scope. diff --git a/docs/graph-atlas.md b/docs/graph-atlas.md index 0e6401fdc0..d477bd6d62 100644 --- a/docs/graph-atlas.md +++ b/docs/graph-atlas.md @@ -5,7 +5,7 @@ These diagrams are the relationship layer above the generated catalogs. Use them to navigate package topology, capability seams, event flow, model-facing tools, app composition, and runtime lifecycle paths. Exact signatures and type shapes still live in the generated [events](cordis-catalog/events.md) / [services](cordis-catalog/services.md) catalogs, [tool-catalog.md](tool-catalog.md), and [core-data-structures/](core-data-structures/core.md). -The process decision behind this index is recorded in [the documentation graph RFC](rfc/implemented/process/2026-07-03-documentation-graph-atlas.md). +The process decision behind this index is recorded in [the documentation graph Agent Note](../.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md). | Graph | Mode | | --- | --- | diff --git a/docs/i18n/README.i18n.yaml b/docs/i18n/README.i18n.yaml index ab1c9024ad..401813b088 100644 --- a/docs/i18n/README.i18n.yaml +++ b/docs/i18n/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 17bb1eeb67b4f5119a698fca23f12490c9378a7f -README.zh.md: c957a82bf420a942e2249942a2d9afc54ad950cf +README.md: bd5d8c08a4c474a13342b6b60800cfe0d31e110b +README.zh.md: a53ab8d9d6053b39def34505038504fefc80a3f9 diff --git a/docs/i18n/README.md b/docs/i18n/README.md index 17bb1eeb67..bd5d8c08a4 100644 --- a/docs/i18n/README.md +++ b/docs/i18n/README.md @@ -2,11 +2,11 @@ English | [中文](README.zh.md) -This repo's documentation is read by people and agents both inside and outside the company, so the README and the docs tree are maintained in English and Simplified Chinese. This page defines the pairing contract, the enforcement gate, and the rollout policy; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md). +This repo's documentation is read by people and agents both inside and outside the company, so the README, Agent Notes, and docs tree are maintained in English and Simplified Chinese. This page defines the pairing contract, the enforcement gate, and the rollout policy; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md). ## The pairing contract -- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first RFC is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing. +- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first Agent Note is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing. - **A pair is three sibling files.** The English `foo.md`, the Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`, all in the same directory. No locale directories, no separate translation repo, no interleaved bilingual files. Pairs merge whole: a PR never lands one language without the other two files. - **The consistency record.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last time the two were confirmed to say the same thing: @@ -26,7 +26,7 @@ This repo's documentation is read by people and agents both inside and outside t 1. Every file listed as `required` in [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) has a complete pair. 2. Every pair that exists at all — required or not — is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher. 3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all. -4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new date-named RFCs merge bilingual from birth. +4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new date-named Agent Notes merge bilingual from birth. `pnpm run verify-translation-pairing --list` prints the current pairing state of every document in scope — missing, out-of-sync, or ok — and is the work list for translation batches. It never fails; it reports. @@ -36,16 +36,16 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co ## Scope, exclusions, and rollout -**Scope**: the root `README.md`, everything under `docs/**`, and everything under `python/**`. Package READMEs (`packages/**`) join the scope in a later batch. +**Scope**: the root `README.md`, everything under `.agents/notes/**`, `docs/**`, and `python/**`. Package READMEs (`packages/**`) join the scope in a later batch. **Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them): - `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/config-catalog.md`, `docs/persistence-catalog.md`, and `docs/module-graph.md` — generated files; their generators emit English only today, so a hand-written translation would go stale on every regeneration. The planned follow-up is to teach the generators to emit Chinese alongside English, at which point these leave the exclusion list. -- `docs/AGENTS.md` — agent instructions, maintained in English only like the root `AGENTS.md`. +- `docs/AGENTS.md` and `.agents/notes/**/AGENTS.md` — agent instructions, maintained in English only like the root `AGENTS.md`. - `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction. - [translation-prompt.md](translation-prompt.md) — the automated pipeline's prompt template; its body is machine-consumed verbatim, so a paired translation would change pipeline behavior. -**Rollout**: a date-named document (`yyyy-mm-dd-*.md`, i.e. an RFC) dated on or after the manifest's `requiredSince` cutoff must merge with its pair. Earlier dates are backlog, including files created on the cutoff's eve. An RFC filename records its first-proposed date, so backdating past the cutoff is a review-visible violation. The manifest's `required` list is the current enforcement frontier, not the goal of full coverage. Translation batches add paths to `required`, ratcheting the gate forward. Unlisted documents remain visible in `--list`, while every existing pair is governed by the full contract. Because later edits must update both sides, expand `required` only as fast as translation review can support. +**Rollout**: a date-named document (`yyyy-mm-dd-*.md`, i.e. an Agent Note) dated on or after the manifest's `requiredSince` cutoff must merge with its pair. Earlier dates are backlog, including files created on the cutoff's eve. An Agent Note filename records its first-proposed date, so backdating past the cutoff is a review-visible violation. The manifest's `required` list is the current enforcement frontier, not the goal of full coverage. Translation batches add paths to `required`, ratcheting the gate forward. Unlisted documents remain visible in `--list`, while every existing pair is governed by the full contract. Because later edits must update both sides, expand `required` only as fast as translation review can support. ## Division of labor diff --git a/docs/i18n/README.zh.md b/docs/i18n/README.zh.md index c957a82bf4..a53ab8d9d6 100644 --- a/docs/i18n/README.zh.md +++ b/docs/i18n/README.zh.md @@ -2,11 +2,11 @@ [English](README.md) | 中文 -本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此 README 与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。 +本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此 README、Agent Note 与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。 ## 配对契约 -- **两种语言同权。**一篇文档可以先用任一语言撰写和评审——先写中文的 RFC 与先写英文的一样正当——另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。 +- **两种语言同权。**一篇文档可以先用任一语言撰写和评审——先写中文的 Agent Note 与先写英文的一样正当——另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。 - **一对文档是三个同目录文件。**英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对整体合入：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。 - **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash： @@ -26,7 +26,7 @@ 1. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 中 `required` 列出的每个文件都有完整配对。 2. 任何已存在的配对——无论是否 required——都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致——标题深度、逐字节一致的代码块（信息字符串与内容）、表格行列数、列表类型、有序列表起始编号、列表项数量，以及除切换行之外的每个链接目标。 3. 列为 `excluded` 的文件完全没有 `.zh.md`，也没有 `.i18n.yaml`。 -4. 凡文件名符合 `yyyy-mm-dd-*.md` 且日期不早于 manifest（元数据清单）中 `requiredSince` 分界日期的文档，都必须有完整配对——新建的日期命名 RFC 从创建起便须配齐中英文。 +4. 凡文件名符合 `yyyy-mm-dd-*.md` 且日期不早于 manifest（元数据清单）中 `requiredSince` 分界日期的文档，都必须有完整配对——新建的日期命名 Agent Note 从创建起便须配齐中英文。 `pnpm run verify-translation-pairing --list` 打印范围内每篇文档的当前配对状态——missing、out-of-sync 或 ok——是翻译批次的工作清单。它从不失败；它只报告。 @@ -36,16 +36,16 @@ ## 范围、排除与推进 -**范围**：根 `README.md`、`docs/**` 下的全部内容，以及 `python/**` 下的全部内容。package README（`packages/**`）在后续批次加入范围。 +**范围**：根 `README.md`，以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部内容。package README（`packages/**`）在后续批次加入范围。 **排除**（永不配对，门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`）： - `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/config-catalog.md`、`docs/persistence-catalog.md` 与 `docs/module-graph.md`——生成文件；生成器目前只输出英文，手写译文在每次重新生成时必然陈旧。计划中的后续工作是让生成器同时输出中文，届时这些文件移出排除清单。 -- `docs/AGENTS.md`——agent 指令，与根 `AGENTS.md` 一样只以英文维护。 +- `docs/AGENTS.md` 与 `.agents/notes/**/AGENTS.md`——agent 指令，与根 `AGENTS.md` 一样只以英文维护。 - `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md)——二者本身即为中英对照文档。 - [translation-prompt.md](translation-prompt.md)——自动翻译流水线的 prompt 模板；正文逐字进入模型请求，配对翻译会改变流水线行为。 -**推进**：以日期命名的文档（`yyyy-mm-dd-*.md`，即 RFC），只要标注日期等于或晚于 manifest 的 `requiredSince` 分界日期，合入时就必须配齐双语文件。更早日期的文件属于 backlog（待翻清单），包括分界前夜创建的文件。RFC 文件名记录首次提出日期，因此倒填日期绕过分界属于评审可见的违规。manifest 中的 `required` 列表是当前执行红线，并非全量覆盖这一最终目标。翻译批次将路径加入 `required`，使门禁只向前收紧。未列入的文档仍可通过 `--list` 查看，而任何已存在的配对都受完整契约约束。后续修改必须同步更新两侧，因此 `required` 的扩展速度不能超过翻译评审的承载能力。 +**推进**：以日期命名的文档（`yyyy-mm-dd-*.md`，即 Agent Note），只要标注日期等于或晚于 manifest 的 `requiredSince` 分界日期，合入时就必须配齐双语文件。更早日期的文件属于 backlog（待翻清单），包括分界前夜创建的文件。Agent Note 文件名记录首次提出日期，因此倒填日期绕过分界属于评审可见的违规。manifest 中的 `required` 列表是当前执行红线，并非全量覆盖这一最终目标。翻译批次将路径加入 `required`，使门禁只向前收紧。未列入的文档仍可通过 `--list` 查看，而任何已存在的配对都受完整契约约束。后续修改必须同步更新两侧，因此 `required` 的扩展速度不能超过翻译评审的承载能力。 ## 分工 diff --git a/docs/i18n/style-samples.md b/docs/i18n/style-samples.md index 786ebea0df..2d9de63bc6 100644 --- a/docs/i18n/style-samples.md +++ b/docs/i18n/style-samples.md @@ -62,7 +62,7 @@ 门禁的边界很明确：通过门禁只说明两侧文件当前的 blob hash 与伴随记录吻合，并且结构签名一致，也就是说，这组内容曾被确认一致；它不代表这次确认可靠。门禁无法判断两种语言是否真正表达了相同的意思；这部分契约要由评审人把关。即使译文粗糙、表意有误，重新记录配对后仍能通过门禁，但绝不能通过人工评审。 -## ⑥ RFC 论证 +## ⑥ Agent Note 论证 > Comparing git timestamps of the pair (no record) — rejected: formatting-only edits would false-positive, and a counterpart committed after an unrelated edit would false-negative; content identity is the only signal that means what the gate claims. @@ -70,9 +70,9 @@ ## ⑦ 推进策略（长段拆分示范） -> **Rollout**: date-named RFCs don't wait for a batch — one dated on or after the manifest's `requiredSince` cutoff must merge with its pair, so each new date-named RFC is bilingual from birth. For the back-catalog, the `required` list in the manifest is the enforcement frontier, not the goal. […] Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so grow the frontier at the pace translation review is actually resourced, not ahead of it. +> **Rollout**: date-named Agent Notes don't wait for a batch — one dated on or after the manifest's `requiredSince` cutoff must merge with its pair, so each new date-named Agent Note is bilingual from birth. For the back-catalog, the `required` list in the manifest is the enforcement frontier, not the goal. […] Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so grow the frontier at the pace translation review is actually resourced, not ahead of it. -**推进**：日期命名的 RFC 无需等待批量翻译。只要文件名中的日期不早于 manifest（元数据清单）的 `requiredSince` 分界日期，合入时就必须配齐中英文，因此此类 RFC 从创建起就要求双语齐备。对于存量文档，manifest 中的 `required` 列表只是当前的执行红线，并非最终目标。（……）一旦文档完成配对，后续修改任一侧都必须同步更新另一侧。因此，应根据实际可投入的翻译评审能力逐步扩展执行红线，不能超前。 +**推进**：日期命名的 Agent Note 无需等待批量翻译。只要文件名中的日期不早于 manifest（元数据清单）的 `requiredSince` 分界日期，合入时就必须配齐中英文，因此此类 Agent Note 从创建起就要求双语齐备。对于存量文档，manifest 中的 `required` 列表只是当前的执行红线，并非最终目标。（……）一旦文档完成配对，后续修改任一侧都必须同步更新另一侧。因此，应根据实际可投入的翻译评审能力逐步扩展执行红线，不能超前。 ## 从样例提炼的要点 diff --git a/docs/i18n/terminology.md b/docs/i18n/terminology.md index f11a1ff19e..3e7527429b 100644 --- a/docs/i18n/terminology.md +++ b/docs/i18n/terminology.md @@ -33,6 +33,7 @@ | English | 中文 | 首次出现 | 不要译作 | 备注 | |---|---|---|---|---| | agent | agent | agent（智能体） | | | +| Agent Note | Agent Note | Agent Note（agent 决策记录） | 智能体注记、智能体笔记 | 本仓库中由 agent 撰写的提案与决策记录 | | agent harness | agent harness | agent harness（智能体框架） | | agent 组合词（agent harness/workflow/loop/skill 等）整体保留英文；未括注过 agent 时首现按对应组合词或 agent 行处理 | | agent loop | agent loop | agent loop（智能体循环） | | | | backlog | backlog | backlog（待翻清单） | | 仅在双语翻译语境里括注`待翻清单` | diff --git a/docs/i18n/translation-prompt.md b/docs/i18n/translation-prompt.md index cd87c161de..bfbb583303 100644 --- a/docs/i18n/translation-prompt.md +++ b/docs/i18n/translation-prompt.md @@ -27,7 +27,7 @@ - `docs/development.md` ↔ `docs/development.zh.md` - `docs/i18n/README.md` ↔ `docs/i18n/README.zh.md` - `docs/i18n/translation-rules.md` ↔ `docs/i18n/translation-rules.zh.md` -- `docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md` ↔ 对应 `.zh.md` +- `.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md` ↔ 对应 `.zh.md` 注入时按当前翻译方向选择每组的源侧与目标侧：user 消息包含源文档全文，assistant 消息采用模板正文规定的 XML 协议；`translation` 与 `final` 都放入目标文档全文，`review` 填 `- [None] No corrections.`。CDATA 遵循上文的 `]]>` 拆分规则。上下文不足时，按上列顺序从后往前删减示例组数。这 5 组也是评审校准锚点；改动任何一组都会改变流水线行为。 diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 3bc15253a5..688d3b545c 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -5,7 +5,7 @@ Every event type that can appear in a session's durable event log: the complete persisted `SessionEvent` envelope and each member of the merge-extensible `SessionEventMap` — the owning vocabulary in `@deepseek-ai/dsh-session` plus every plugin declaration merge in this repo — with source JSDoc, full payload declaration, surface badge, and declaration site. It complements [session.md](core-data-structures/session.md) (surface ordering and the `deriveMessages()` projection), [persistence.md](core-data-structures/persistence.md) (how the log is made durable), and the [cordis events catalog](cordis-catalog/events.md) (the live bus wiring — a log event is NOT a cordis event; it reaches listeners via the single `session/event` emit). -This file is GENERATED from source (`scripts/gen-persistence-catalog.ts`) and verified fresh by `pnpm run verify-persistence-catalog` (part of `doc-sync`) — do not edit it by hand. Declaration blocks retain the source declaration and nested property JSDoc, removing only the indentation imposed by a containing interface/module, and use a `ts persistence-catalog` fence (skipped by doc-typecheck because declarations reference types from their owning modules). Type names in a payload link to the page that documents them. See [the persistence-log-catalog RFC](rfc/implemented/process/2026-07-04-persistence-log-catalog.md). +This file is GENERATED from source (`scripts/gen-persistence-catalog.ts`) and verified fresh by `pnpm run verify-persistence-catalog` (part of `doc-sync`) — do not edit it by hand. Declaration blocks retain the source declaration and nested property JSDoc, removing only the indentation imposed by a containing interface/module, and use a `ts persistence-catalog` fence (skipped by doc-typecheck because declarations reference types from their owning modules). Type names in a payload link to the page that documents them. See [the persistence-log-catalog Agent Note](../.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md). The envelope declarations below compose each event's `type`, monotonic `seq`, epoch-ms `time`, `data`, and the conditional `surfaceOp`/`sourceEventSeqs` fields. **surface** marks a `SurfaceEventType` member: it produces an LLM message and declares how it joins the surface list. **log-only** marks everything else: a durable, replayable record with no derived-history contribution. Every payload is JSON-serializable (enforced at `Session.append`), and the whole format is pinned at `SESSION_FORMAT_VERSION = 0` — pre-release, no compatibility implied ([the version stance](core-data-structures/persistence.md)). Scope: the packages in this repo; a downstream plugin can merge further event types, which are outside this catalog by construction. @@ -224,7 +224,7 @@ Source: [`packages/compact/compact/src/types.ts:15`](../packages/compact/compact * The model that wrote the summary — the summarize call's envelope, * reported by the backend that made the call, logged so the one-shot * request is reconstructable from log + code and "which model wrote - * this summary" has a durable answer (the reconstructability RFC). + * this summary" has a durable answer (the reconstructability Agent Note). */ model: string /** The generation cap the summarize call sent, when one applied. */ diff --git a/docs/postmortem/README.md b/docs/postmortem/README.md index 743433a827..7114f65916 100644 --- a/docs/postmortem/README.md +++ b/docs/postmortem/README.md @@ -2,7 +2,7 @@ Incident write-ups: a bug reached a place it shouldn't have (a real user, a merged PR, a release), and the interesting part is *why our process let it through*, not just the one-line fix. -A post-mortem is NOT an [RFC](../rfc/README.md) (which records a deliberate design decision and its rejected alternatives, or proposes future work). It is a backward-looking record of a failure: what broke, the mechanism, why every safety net missed it, and the concrete guardrails added so the same class of bug fails loudly next time. +A post-mortem is NOT an [Agent Note](../../.agents/notes/README.md) (which records a deliberate design decision and its rejected alternatives, or proposes future work). It is a backward-looking record of a failure: what broke, the mechanism, why every safety net missed it, and the concrete guardrails added so the same class of bug fails loudly next time. Write one when a bug is **subtle** (the mechanism is non-obvious and a careful engineer would re-derive it the hard way), **systemic** (the reason it escaped is a gap in tests/tooling/conventions, not a one-off typo), and **costly to rediscover** (it cost real debugging time, and would cost it again). Link the guardrails (tests, AGENTS.md rules, ADRs) the post-mortem motivated. diff --git a/docs/rfc/README.md b/docs/rfc/README.md deleted file mode 100644 index a6fe4dbfa2..0000000000 --- a/docs/rfc/README.md +++ /dev/null @@ -1,109 +0,0 @@ -# RFCs - -One kind of design doc lives here. An **RFC** records a decision or proposal that shapes this codebase — the *why* and *what we gave up*, the parts code and docs can't carry. The full list is the generated [INDEX.md](INDEX.md); this file is the contract — where RFCs live, when to write one, and [the in-file format](#the-file-format). - -## Layout and naming - -Every RFC has two axes, both encoded in its **path** — `{lifecycle}/{class}/yyyy-mm-dd-topic-title.md`: - -- **Lifecycle** (the top-level folder) is the RFC's status, and an RFC moves between folders as that status changes: - - **`proposed/`** — proposals reviewed before implementation; not yet built (or only partly). - - **`implemented/`** — the decision shipped. The file records what was decided and what was rejected, and is **kept current with what actually shipped**: when the code later moves a file, renames a package, or changes a key/default, the RFC is updated in the same change to match (facts only — paths, names, structure — not the decision itself). See [implemented/AGENTS.md](implemented/AGENTS.md). - - **`rejected/`** — the proposal was considered and declined. Kept for the record so the rejection isn't re-litigated. -- **Class** (the nested folder) is the *kind* of decision — see [Classification](#classification) below. - -The date in the filename is when the topic was **first proposed** (per git history). Cross-references between RFCs use relative markdown links (`[topic](../../implemented/architecture/2026-…-….md)`) — never bare prose or numbers — so they are mechanically checkable and survive moves between folders. - -## Classification - -Each RFC belongs to one path-encoded class from the closed set in `scripts/rfc-index.ts`; the classification gate rejects other folders. [INDEX.md](INDEX.md) is generated from paths, titles, and filename dates, and its freshness is gated. Adding a class requires updating the canonical set and this section. See the [classification](implemented/process/2026-06-20-rfc-classification.md) and [index-generation](implemented/process/2026-07-04-generate-rfc-index-tables.md) RFCs. - -| Class | What it covers | -|---|---| -| `feature` | A new user- or model-facing capability. | -| `bug-fix` | Corrects a defect or closes a gap a postmortem surfaced. | -| `simplification` | Removes code, behavior, or surface area without adding a capability. | -| `architecture` | A structural decision about the **shipped source** — how packages relate, what the runtime vocabulary is. | -| `process` | Tooling, policy, or workflow **around** the code — gates, the package manager, vendoring — not runtime behavior. | -| `testing` | Test infrastructure and strategy. | - -The `architecture` / `process` line: **architecture** is about the source we ship; **process** is the surrounding tooling and workflow. (`refactor` is deliberately absent — it overlaps `simplification`, whose discriminator, "does observable behavior change?", already covers it.) - -## When to write one - -Write an RFC when a decision is **durable** (it shapes the codebase beyond a single function or package), **contested** (there was a real alternative a reasonable engineer might have chosen), and **surprising** (a future reader would otherwise ask "why on earth is it done this way?"). A proposal for substantial future work starts in `proposed/`; a decision already made starts in `implemented/`. Pick the class folder that matches the decision (see [Classification](#classification)). - -Do NOT write one for a mechanical or local choice (a variable name, a one-file refactor), for anything already enforced and explained by a gate or a convention in AGENTS.md, or for a still-provisional decision tagged `TODO(...)` in the code — record those as TODOs and promote to an RFC only once they settle. An RFC is never edited into a *different decision*: supersede it with a new one and cross-link. (Editing an `implemented/` RFC to track where its already-made decision now *lives* — a moved file, a renamed package — is not a different decision and is required, not forbidden; see [implemented/AGENTS.md](implemented/AGENTS.md).) - -## The file format - -Every RFC follows one in-file format, enforced by `pnpm run verify-rfc-format` ([scripts/verify-rfc-format.ts](../../scripts/verify-rfc-format.ts), part of `doc-sync`); the rationale for the format — and the alternatives it rejected — is [the uniform-format RFC](implemented/process/2026-07-05-uniform-rfc-format.md). - -### The header block - -The first three lines of every RFC are exactly: - -```markdown -# RFC: <title> - -Status: <status> -``` - -followed by a blank line. The `Status:` value is one of three forms, and must agree with the lifecycle folder the file sits in — the gate cross-checks them: - -- `Status: proposed` -- `Status: implemented` -- `Status: rejected — <why, in one line>` - -The status carries no dates and no parentheticals: the filename holds the first-proposed date, git holds everything else, and an "accepted in amended form" note is body content (state the amendment where the decision is stated). The rejection reason is the one status with content, because a rejected RFC's verdict is the fact readers come for. - -### The body skeleton - -Every RFC opens its body with `## Problem` — the motivation, written to stand without the solution. What follows depends on the lifecycle; recurring sections use these canonical names and nothing else, while genuinely bespoke technical sections (package topology, wire contracts, schemas) remain free-form between the required ones. - -#### `proposed/` - -```markdown -## Problem -## Proposal -…bespoke sections… -## Alternatives considered -## Acceptance criteria -## Risks -``` - -`## Proposal` is the intended change and may legitimately speak in the future tense — plans, migration steps, and open questions belong here while the work is unbuilt. `## Acceptance criteria` says what observable state means done. `## Risks` covers both what could go wrong and what the change knowingly gives up. - -#### `implemented/` - -```markdown -## Problem -## Decision -…bespoke sections… -## Alternatives considered -## Consequences -``` - -`## Decision` describes shipped reality in the present tense, and the whole file is kept current with it per [implemented/AGENTS.md](implemented/AGENTS.md). `## Consequences` records what the trade-off cost **and** bought. Proposal-era headings are spec-speak here and the gate rejects them: `## Proposal`, `## Plan`, `## Migration plan`, and `## Acceptance criteria` may not appear in an implemented RFC (the [slop checklist](../AGENTS.md) names why). A `## Testing`, `## Deferred`, or `## Related` section is fine where it states present-tense fact. - -#### `rejected/` - -A rejected RFC is the proposal, frozen: it keeps whatever proposal-time sections it had (including `## Acceptance criteria` or `## Plan`), and the verdict lives on the `Status:` line. Only the header block, the `## Problem` opener, a `## Proposal` section, and the Alternatives-considered mandate below apply. - -### Alternatives considered — mandatory - -Every RFC carries an `## Alternatives considered` section: each genuine alternative and why it lost, one bold-led paragraph per alternative or a `### Why not <X>?` subsection per contested one. A decision recorded without what it beat invites re-litigation — the failure RFCs exist to prevent. - -Alternatives are recorded, never invented. An RFC dated before 2026-07-05 whose alternatives are not reconstructible from the record carries this exact comment in place of the section, which the gate accepts for pre-format files only: - -```markdown -<!-- rfc-format: alternatives-not-recorded (pre-format RFC) --> -``` - -### Moving between lifecycles - -Moving a file between lifecycle folders means updating the `Status:` line and re-satisfying that folder's skeleton in the same change — the gate fails the move otherwise. Concretely, `proposed/` → `implemented/` rewrites `## Proposal` into a present-tense `## Decision`, folds `## Acceptance criteria` and `## Risks` into `## Consequences` (or a present-tense `## Testing`/`## Verification` section for what now pins the behavior), and drops plans in favor of what shipped — the rewrite [implemented/AGENTS.md](implemented/AGENTS.md) requires, made mechanical. `proposed/` → `rejected/` only adds the reason to the `Status:` line and freezes the file. - -### Chinese counterparts - -A `.zh.md` counterpart mirrors its English sibling's structure section-for-section under the [i18n contract](../i18n/README.md); the machine-checked header tokens (`# RFC: ` and the `Status:` line) stay in English verbatim. The format gate skips `.zh.md` files — the pairing gate owns their consistency. diff --git a/docs/rfc/implemented/AGENTS.md b/docs/rfc/implemented/AGENTS.md deleted file mode 100644 index 639415ba70..0000000000 --- a/docs/rfc/implemented/AGENTS.md +++ /dev/null @@ -1,11 +0,0 @@ -# AGENTS.md — Implemented RFCs - -These RFCs describe shipped decisions. Follow the [root instructions](../../../AGENTS.md), [documentation standard](../../AGENTS.md), and [RFC format](../README.md#the-file-format); `verify-rfc-format` gates the lifecycle-specific structure. - -## Keep an implemented RFC current with what actually shipped - -Keep paths, symbols, defaults, and mechanisms current in the same change that alters them. Rewrite stale facts in place; do not append change history. - -### This is not a license to rewrite the *decision* - -Update factual realization in place. A reversal of the decision or its rationale requires a new RFC and cross-link; see [rfc/README.md](../README.md). diff --git a/docs/rfc/implemented/process/2026-06-20-rfc-classification.md b/docs/rfc/implemented/process/2026-06-20-rfc-classification.md deleted file mode 100644 index 2162687225..0000000000 --- a/docs/rfc/implemented/process/2026-06-20-rfc-classification.md +++ /dev/null @@ -1,46 +0,0 @@ -# RFC: Classify RFCs by kind via path-encoded subdirectories - -Status: implemented - -## Problem - -`docs/rfc/` grouped RFCs by **lifecycle** only — `proposed/` / `implemented/` / `rejected/`. Nothing recorded what *kind* of decision each RFC was. The index was one flat list per lifecycle, with no way to scan "show me every simplification" or "every testing-strategy decision." A wave of simplification RFCs landing on the same day made the gap concrete: a reader skimming `proposed/` could not tell a new capability from a removal from a tooling-policy change without opening each file. - -The repo's standing bias is [mechanical quality gates over prose guidelines](2026-06-11-quality-gates.md): a convention that isn't machine-checked rots. So a classification scheme here had to be enforceable, not an honor-system header. - -## Decision - -Add a second axis — the RFC's **class** — and encode it in the path: `{lifecycle}/{class}/yyyy-mm-dd-topic.md`. The folder *is* the label. A file's location declares its class, the closed set is "these folders and no others," and the existing [verify-md-links](2026-06-18-markdown-cross-link-lint.md) gate already protects the path rewrites the move required. - -### The closed set of six classes - -| Class | Covers | -|---|---| -| `feature` | A new user- or model-facing capability. | -| `bug-fix` | Corrects a defect or closes a gap a postmortem surfaced. | -| `simplification` | Removes code, behavior, or surface area without adding a capability. | -| `architecture` | A structural decision about the **shipped source** — how packages relate, what the runtime vocabulary is. | -| `process` | Tooling, policy, or workflow **around** the code, not runtime behavior. | -| `testing` | Test infrastructure and strategy. | - -The `architecture` / `process` line: **architecture** is about the source we ship; **process** is the surrounding tooling and workflow. This RFC is itself a `process` decision — it changes how the repo is organized and gated, not what the harness does at runtime — so it lives under `implemented/process/`. - -### Two gates - -Both are `doc-sync` members, in the `verify-md-wrap` style (tsx ESM, verify-don't-generate, exit non-zero on the first violation): - -- **`scripts/verify-rfc-classification.ts`** — the closed set and index freshness. It asserts every file under a lifecycle folder lives in a class folder from the canonical set (a loose `.md` at a lifecycle root, or an unknown class folder, fails), and that the generated [INDEX.md](../../INDEX.md) byte-matches a fresh render from the tree (see [generate the RFC index tables](2026-07-04-generate-rfc-index-tables.md)). The canonical class set lives as a `const` in `scripts/rfc-index.ts` — the machine source of truth shared with the generator — and [the README](../../README.md) documents it in prose; the class *descriptions* stay hand-written, the index is generated. -- **`scripts/verify-doc-refs.ts`** — source comments that cite docs. RFC paths are referenced not only from Markdown but from TypeScript doc comments (root-relative prose like `docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md`). `verify-md-links` never saw those, so the reorg could have silently orphaned them. This gate scans repo-authored `.ts` under `packages/**` and `examples/**` (excluding built `lib/` and `vendor/`) for `docs/….md` tokens, resolves each root-relative, and asserts it exists. It requires the `.md` extension so extensionless prose (`docs/postmortem/0001`, `docs/architecture.md § Extending The Harness`) is left alone. - -## Alternatives considered - -- **A `Classification:` prose line** in each file (next to `Status:`), parsed by the gate. Workable, but it duplicates into the file a fact the path can already carry, and a line can disagree with its folder. Path-encoding makes the label and its storage the same thing — there is nothing to keep in sync. -- **A `refactor` class.** It overlaps `simplification` almost entirely; the only discriminator anyone reached for was "does observable behavior change?", which `simplification` already encodes (it does not). One class, not two. -- **Auto-generating the index** from the filesystem. Rejected here to keep the index hand-written; superseded by [generate the RFC index tables](2026-07-04-generate-rfc-index-tables.md) once stacked proposal waves made the hand-written tables the repo's most conflict-prone docs region — the list is now the fully generated [INDEX.md](../../INDEX.md) while the README prose stays curated. - -## Consequences - -- Every RFC now sits under a class folder, and the index groups by class within each lifecycle. A reader scans one heading to see all simplifications, or all testing decisions. -- Two more fast tsx scripts in the `doc-sync` chain; no new dependency (the mdast/GFM stack was already present for `verify-md-wrap`/`verify-md-links`). -- Adding a class is a deliberate act: amend the `const` in `scripts/rfc-index.ts` and the [Classification section](../../README.md#classification), not just `mkdir` a folder. The gate rejects an unknown folder, so an ad-hoc class can't slip in. -- Source-comment doc references are now gated too — a moved or renamed doc that a `.ts` comment cites fails the pre-push hook, closing a drift class `verify-md-links` structurally could not see. diff --git a/docs/rfc/implemented/process/2026-07-04-generate-rfc-index-tables.md b/docs/rfc/implemented/process/2026-07-04-generate-rfc-index-tables.md deleted file mode 100644 index d854991ad9..0000000000 --- a/docs/rfc/implemented/process/2026-07-04-generate-rfc-index-tables.md +++ /dev/null @@ -1,32 +0,0 @@ -# RFC: Generate the RFC index tables - -Status: implemented - -## Problem - -The RFC index's per-lifecycle/per-class tables list facts that are fully derivable: an RFC's path encodes lifecycle and class, its filename encodes the first-proposed date, and its H1 carries the title. A hand-maintained copy of those facts is also the repo's highest-contention docs hotspot: every proposal wave appends rows to the same few lines, so concurrent RFC branches conflict precisely there while agreeing everywhere else, and each conflict is resolved by hand-merging rows whose content the filesystem already knows. [The classification RFC](2026-06-20-rfc-classification.md) originally kept the index hand-written for curation's sake — but the curated part of the README is the prose, and the prose never conflicts; only the mechanical tables do. - -## Decision - -Keep the curated prose; generate the list. The tables live in [`docs/rfc/INDEX.md`](../../INDEX.md), a **fully generated file** — the curated prose stays in README.md, which carries no index rows at all. [`scripts/rfc-index.ts`](../../../../scripts/rfc-index.ts) is the shared source of truth — the tree walker (owning the closed lifecycle/class sets and the structure rules, including a parseable-H1 requirement) and the renderer (rows from H1 title with any `RFC: ` prefix stripped, plus the filename date, sorted by date then filename, grouped as `### {Class}` sections in canonical class order). Two thin consumers share it: - -- [`scripts/gen-rfc-index.ts`](../../../../scripts/gen-rfc-index.ts) (`pnpm run gen-rfc-index`) rewrites INDEX.md in full from the tree. -- [`scripts/verify-rfc-classification.ts`](../../../../scripts/verify-rfc-classification.ts) (a `doc-sync` member) checks structure, asserts the committed INDEX.md byte-matches a fresh render — the `gen-cordis-catalog`/`verify-cordis-catalog` pattern — and rejects an index-shaped row in the curated README. Freshness subsumes the index-completeness check: a generated-from-disk table is definitionally complete and correctly headed. - -Adding, moving, or deleting an RFC means editing only the RFC file and running the generator; the classification RFC's rejected-alternatives record carries the supersession cross-link. - -## Alternatives considered - -### Why not marker-delimited regions inside README.md? - -The first landed shape: the generator spliced the tables into README.md between `gen-rfc-index` marker comments, under each `## {Lifecycle}` heading. Superseded by the whole-file INDEX.md once the README also absorbed the in-file format contract ([the uniform-format RFC](2026-07-05-uniform-rfc-format.md)): a front-door README hosting hundreds of generated rows dwarfed its curated prose, and splice mechanics (marker pairs, heading checks, outside-region row detection) exist only to protect curated text that a dedicated generated file simply doesn't contain. - -### Why not the verifier-only model? - -It catches mistakes but still makes every proposal edit a shared hotspot in a hand-maintained table, and a failed verifier is strictly more annoying than a generator for a purely mechanical row: the author has already named and placed the file; the index copy adds no information. This is the same hand-list-versus-derivation judgment the [package-inventory proposal](../../proposed/process/2026-06-20-discover-package-inventory.md) applies to tsconfig references and knip stanzas — applied to the one list that demonstrably conflicts. - -## Consequences - -- The generated file is explicit: its banner names the generator, there is no curated region to protect inside it, and the generator refuses to run on a structurally invalid tree. -- A malformed or missing H1 is a hard error in both the generator and the gate — the H1 is now load-bearing as the index title source. -- Concurrent RFC branches resolve index conflicts by rerunning the generator, never by hand-merging rows. diff --git a/docs/rfc/implemented/process/2026-07-05-uniform-rfc-format.md b/docs/rfc/implemented/process/2026-07-05-uniform-rfc-format.md deleted file mode 100644 index d5ce28066d..0000000000 --- a/docs/rfc/implemented/process/2026-07-05-uniform-rfc-format.md +++ /dev/null @@ -1,28 +0,0 @@ -# RFC: One gated in-file format for RFCs - -Status: implemented - -## Problem - -RFC paths encoded lifecycle and class, but file contents still mixed headings, status formats, ADR and proposal templates, and proposal-era sections in implemented records. Authors copied whichever neighbor they found, and lifecycle moves could skip the required rewrite because no gate enforced an in-file contract. - -## Decision - -[README.md § The file format](../../README.md#the-file-format) is the in-file contract — the header block (`# RFC: <title>` plus a dateless, folder-agreeing `Status:` enum whose only content is the rejection reason), the per-lifecycle body skeleton (`Problem` opener everywhere; `Proposal`/`Acceptance criteria`/`Risks` in `proposed/`; present-tense `Decision`/`Consequences` with proposal-era headings banned in `implemented/`; frozen proposal shape in `rejected/`), a mandatory `Alternatives considered` section, and the canonical section vocabulary between which bespoke technical sections stay free-form. `pnpm run verify-rfc-format` ([scripts/verify-rfc-format.ts](../../../../scripts/verify-rfc-format.ts)) enforces every mechanical clause as part of `doc-sync`, so a lifecycle move that skips its rewrite now fails CI instead of review memory. - -The whole corpus was normalized in the same change that defined the format — the pre-release stance: no transition period, no dual-format tolerance. The one grandfather is content, not format: alternatives are recorded, never invented, so a pre-format RFC whose alternatives are not reconstructible from the record carries the exact `rfc-format: alternatives-not-recorded` comment, which the gate accepts only for files dated before this RFC. - -## Alternatives considered - -- **A full rigid template** (one fixed section sequence per lifecycle, every RFC restructured to fit) — rejected: the big design RFCs carry eight to fifteen bespoke technical sections (package topology, wire contracts, schemas) that are load-bearing content, not drift; a rigid sequence would force destructive rewrites now and template-fighting forever. -- **Header-only normalization** (H1 and Status, bodies untouched) — rejected: the debt markers flagged the *body* genre split, and leaving `Context`/`Decision` beside `Problem`/`Proposal` indefinitely resolves nothing. -- **No Status line** (the folder already is the status; the three newest pre-format RFCs (and the zh counterpart of one) omitted the line) — rejected in favor of keeping a self-describing file: the drift risk that motivated dropping it is neutralized by gating the line against the folder instead. -- **Dated status** (`Status: implemented (accepted YYYY-MM-DD)`) — rejected: the acceptance date is narrated history the writing rules keep out of docs; the filename carries first-proposed, git carries the rest, and the gate could check a date's format but never its truth. -- **A bare `# <title>` H1** — rejected: the `RFC: ` prefix is the corpus-majority form and self-describes the genre when a file is read outside its tree; the index generator strips it, so index rows are identical either way. -- **`## What we give up` as the implemented closer** (the README's own phrase for what an RFC records) — rejected: it names only costs, and an honest consequences section records what the trade-off bought as well. -- **Convention without a gate** (write the contract down, enforce by review) — rejected: the slop checklist already outlawed spec-speak in `implemented/` by convention, and nineteen files show what convention alone achieves here. -- **A standalone `FORMAT.md` contract file** — the first landed home; folded into README.md once the generated index moved out to [INDEX.md](../../INDEX.md): with the tables gone the README regained the room, and one front door carrying layout, classification, and format beats splitting the contract across two files. - -## Consequences - -Every RFC now costs slightly more structure, and the mandatory `Alternatives considered` section is deliberate friction: a decision recorded without what it beat invites the re-litigation RFCs exist to prevent. Pre-format RFCs whose alternatives were not reconstructible carry the grandfather comment permanently — an honest gap on the record rather than fabricated rationale. `doc-sync` gains one gate, and moving an RFC between lifecycle folders is now real work at move time (the body rewrite the move always owed) instead of deferred cleanup nothing tracked. The thirty-nine debt markers are gone, resolved by the template they were waiting for. diff --git a/docs/rfc/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md b/docs/rfc/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md deleted file mode 100644 index 5d40b166bd..0000000000 --- a/docs/rfc/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md +++ /dev/null @@ -1,31 +0,0 @@ -# RFC: Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger) - -Status: implemented - -## Problem - -The merge-extensible vocabulary maps are designed to grow by declaration merging, and the codebase already states the admission policy on `TurnEndReasonMap` (`packages/core/session/src/types.ts`): a variant like `refusal` is "deliberately omitted until" an adapter or loop first emits it. Three declared vocabulary items violated that policy — each had no producer and no consumer, and two had not even a test: - -- **`CacheHint` and its `cache?: CacheHint` block fields** on `TextBlock`/`ToolResultBlock` (`packages/llm/llm/src/types.ts`; the image block carried a third such field, which left with it — see [the drop-image RFC](2026-07-04-drop-image-content-block.md)). Nothing constructed a block with `cache:` anywhere — src, tests, and doc pastes all came up empty — and neither adapter read `.cache`: DeepSeek prompt caching is automatic, so the adapters map `prompt_cache_hit_tokens` OUT of responses without ever sending a hint IN. This was Anthropic-style `cache_control` surface with no provider that could honor it. -- **`MessageSourceMap.agent`** (`{ kind: 'agent'; agentId: string }`, same file). Zero constructors, tests included. Its intended producer shipped without it: the subagent backends send the parent's prompt to the child with no `source`, so it logs as `{ kind: 'user' }`, and the generic envelope renderer interpolates `source.kind` without ever routing on it. -- **`TurnTriggerMap.continuation`** (`packages/core/session/src/types.ts`). The loop structurally cannot emit it — continuation happens *within* a turn as further steps, never as a new turn — and it constructs only `message` and `injection` triggers. The only writer was one hand-built test fixture needing an arbitrary non-message trigger (`packages/support/llm-replay/tests/llm-replay.spec.ts`), which an `injection` trigger serves equally; the only production trigger reader, the ACP bridge, filters on `kind === 'message'`. - -## Decision - -`CacheHint`, its `cache?` block fields, the `agent` message-source variant, and the `continuation` turn-trigger variant are deleted: the shipped vocabulary carries none of them. The llm-replay fixture uses an `injection` trigger (any non-`message` trigger serves its purpose). The type-equiv pastes in [core.md](../../../core-data-structures/core.md) and [session.md](../../../core-data-structures/session.md) match the pruned maps — both symbols keep their rows in `scripts/type-equiv.manifest.json`, since each map survives minus a member — and the [content-block vocabulary RFC](../architecture/2026-06-11-content-block-vocabulary.md)'s consequences record cache hints as producer-gated rather than as having a home, per [implemented/AGENTS.md](../AGENTS.md). - -Each variant returns the day it gains a real producer, exactly as the maps are designed to grow: a caching feature re-adds `cache` together with the adapter that transmits it; subagent attribution re-adds `agent` together with the backend that stamps it and a consumer that routes on it; an auto-continue feature that genuinely starts new turns re-adds `continuation` with the plugin that emits it. - -## Alternatives considered - -### Why not keep them? - -The [content-block vocabulary RFC](../architecture/2026-06-11-content-block-vocabulary.md) listed "cache hints … have a home" as a design consequence, and reserved slots do advertise intent. But an empty slot is contract surface every implementation and consumer must consider (must my adapter honor `cache`? must my renderer route `agent` sources?), and the sibling map's own JSDoc already rejects reservation-without-emitter — `refusal` and `max_turn_requests` are named as variants to add *when something first emits them*, not declared in advance. Holding already-declared dead variants to the same standard makes the vocabulary mean something: if it is in the map, something produces it. - -## Verification - -`rg` for `CacheHint`, the `agent` message-source spelling, and the `continuation` trigger spelling returns only RFC records (this one, and [the drop-image RFC](2026-07-04-drop-image-content-block.md)'s account of the image block's own `cache` field); the llm-replay fixture asserts the same replay behavior with an `injection` trigger; the core-data-structures pastes and the type-equiv manifest are in sync. - -## Consequences - -Nothing operational changed — nothing could construct these values. The mirror-event removals ([the boundary-mirror RFC](2026-06-20-remove-agent-boundary-mirror-events.md), [the stream-chunk RFC](2026-07-02-remove-stream-chunk-mirror.md)) touch only transient `agent/*` events, never the durable vocabulary, so there is no collision. Elsewhere the admission policy already holds: `rejected`, `prompt/blocked`, and `hook/invoked`/`hook/result` each have live producers — this RFC extends the same bar to the three variants that lacked one. The image block's own `cache?` field belongs to [the drop-image RFC](2026-07-04-drop-image-content-block.md), which removed it together with the block; this RFC covers the two fields on the block types that remain. diff --git a/docs/testing.md b/docs/testing.md index 1a2d6cb192..84629aae45 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -1,13 +1,13 @@ # Testing policy -How this repo tests, tier by tier, and the rules that keep a green suite meaningful. Commands live in root [AGENTS.md](../AGENTS.md); linked RFCs carry the rationale. +How this repo tests, tier by tier, and the rules that keep a green suite meaningful. Commands live in root [AGENTS.md](../AGENTS.md); linked Agent Notes carry the rationale. ## Tiers - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. -- **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless expected outputs cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized JSON-RPC plus the re-persisted log ([ACP snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)); the headless suite independently pins `stream-json` through its real one-shot subprocess. TUI completed journeys replay recorded primary/child JSONL through the real agent loop and tools before projecting ANSI into semantic terminal-state expected outputs; package-local snapshots retain transient renderer states, and a real PTY conversation covers the process boundary ([TUI snapshot RFC](rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when committed replay input remains correct; review every JSONL and expected-output diff. System-prompt/tool-schema content is pinned by one ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e Agent Note](../.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md)). +- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless expected outputs cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized JSON-RPC plus the re-persisted log ([ACP snapshot Agent Note](../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md)); the headless suite independently pins `stream-json` through its real one-shot subprocess. TUI completed journeys replay recorded primary/child JSONL through the real agent loop and tools before projecting ANSI into semantic terminal-state expected outputs; package-local snapshots retain transient renderer states, and a real PTY conversation covers the process boundary ([TUI snapshot Agent Note](../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when committed replay input remains correct; review every JSONL and expected-output diff. System-prompt/tool-schema content is pinned by one ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header Agent Note](../.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index dfb97deef3..6d991e621b 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -5,7 +5,7 @@ Every model-facing tool a shipped plugin contributes to `ctx.tools`: the `name`, `description`, and JSON-Schema `parameters` the model receives via the system-prompt assembly. It complements the cordis [events](cordis-catalog/events.md) & [services](cordis-catalog/services.md) catalogs (the wiring a plugin listens to and calls) and [core-data-structures/](core-data-structures/core.md) (the types those signatures move) — this page is the *tools* the agent is offered. -This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator's boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md). +This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator's boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog Agent Note](../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md). Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog's packages-only scope. @@ -16,9 +16,9 @@ This table connects model-visible tool names to the plugin package and service s | Tool package | Model-visible names | Requires | Writes / affects | Shipped aliases | Deployment note | | --- | --- | --- | --- | --- | --- | | `@deepseek-ai/dsh-tool-ask-user` | `ask_user_question` | `ctx.tools`, `ctx.userInteraction` | `tool/call`, `tool/result after a UI/provider answers the question` | - | ask_user_question pauses the tool call until the active UI provider returns a human answer. | -| `@deepseek-ai/dsh-tools` | `run_code` | `ctx.tools`, `ctx.codeRuntime (execution time)`, `ctx.systemPrompt` | `tool/call`, `one tool/code-dispatch per bridged sub-call`, `tool/result` | - | Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result. | +| `@deepseek-ai/dsh-tools` | `run_code` | `ctx.tools`, `ctx.codeRuntime (execution time)`, `ctx.systemPrompt` | `tool/call`, `one tool/code-dispatch per bridged sub-call`, `tool/result` | - | Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode Agent Note). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result. | | `@deepseek-ai/dsh-tool-bash` | `bash` | `ctx.tools`, `ctx.bash`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The bash tool is the model-facing consumer of the bash executor seam. A `run_in_background` run registers with the generic `ctx.tasks` runtime and is collected/stopped through the `task_*` tools from `@deepseek-ai/dsh-tool-tasks`; the `enableRunInBackground` config (default true) removes the parameter entirely when disabled. | -| `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. | +| `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. | | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. | | `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are bash-backed discovery tools: they run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | | `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - | @@ -121,7 +121,7 @@ Execute a TypeScript program against the available tools. Write the BODY of an a Source: [`packages/core/tools/src/code-mode.ts`](../packages/core/tools/src/code-mode.ts) -Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result. +Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode Agent Note). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result. ## `@deepseek-ai/dsh-tool-bash` @@ -239,7 +239,7 @@ Dispose a plugin previously mounted with cordis_mount, by id. All its registrati Source: [`packages/cordis/tool-cordis/src/index.ts`](../packages/cordis/tool-cordis/src/index.ts) -Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. +Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. ## `@deepseek-ai/dsh-tool-fs` diff --git a/examples/README.md b/examples/README.md index c06bb791df..6524a36f7f 100644 --- a/examples/README.md +++ b/examples/README.md @@ -41,7 +41,7 @@ An unattended coding agent driven through the Python SDK: JSON-RPC stdio, foregr The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one `cordis-dynamic` fiber subtree. The `ctx.fs`/`ctx.web` services ride along provider-only, as the capabilities those plugins build on. -Run with: `pnpm run demo:cordis` (needs `DEEPSEEK_API_KEY`). See [cordis-agent/README.md](cordis-agent/README.md) for the staged demo script and [the toolset RFC](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md) for the design and sandbox caveats. +Run with: `pnpm run demo:cordis` (needs `DEEPSEEK_API_KEY`). See [cordis-agent/README.md](cordis-agent/README.md) for the staged demo script and [the toolset Agent Note](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md) for the design and sandbox caveats. ## acp-agent diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index 000017dd90..ab559388e7 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -29,15 +29,15 @@ Add to your Zed `settings.json` under `agent_servers`: } ``` -The editor sets each session's `cwd` to the project it opens, and bash uses that directory as its workdir. The current sandbox write boundary is nevertheless fixed when the server starts (`workspaceRoot: process.cwd()`), so launch the server from the workspace it should be allowed to modify; making that root session-scoped is deferred in the [sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). Filesystem tools are omitted from the confined default because they execute in-process and do not ride the bash sandbox. +The editor sets each session's `cwd` to the project it opens, and bash uses that directory as its workdir. The current sandbox write boundary is nevertheless fixed when the server starts (`workspaceRoot: process.cwd()`), so launch the server from the workspace it should be allowed to modify; making that root session-scoped is deferred in the [sandbox Agent Note](../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). Filesystem tools are omitted from the confined default because they execute in-process and do not ride the bash sandbox. ## Snapshot tests (record-once / replay-deterministic) -This example hosts the ACP snapshot suite. It replays through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. +This example hosts the ACP snapshot suite. It replays through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot Agent Note](../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. ## Permissions and sandboxing -The default tree composes [`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/), [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/), [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/), and [`@deepseek-ai/dsh-permission`](../../packages/ui/permission/). Bash starts in `workspace-write`; a denied operation returns a structured marker, and a retry with `sandbox_permissions` plus `justification` becomes a one-shot `session/request_permission` prompt in the editor. "Allow once" runs exactly that retry under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). +The default tree composes [`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/), [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/), [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/), and [`@deepseek-ai/dsh-permission`](../../packages/ui/permission/). Bash starts in `workspace-write`; a denied operation returns a structured marker, and a retry with `sandbox_permissions` plus `justification` becomes a one-shot `session/request_permission` prompt in the editor. "Allow once" runs exactly that retry under the wider mode ([sandbox Agent Note § Escalation](../../.agents/notes/implemented/feature/2026-07-06-sandbox.md)). - **One session config option is live**: a capable client shows one `Permissions` select. `workspace-write` means workspace-confined bash plus `ask`; `danger-full-access` means unconfined bash plus `never`. Switching writes one `permission/preset` event through to the sandbox-mode and approval-policy events, and `session/load` reports the resumed value. - **Every approval is one-shot**: the choices are `Allow once` and `Reject`; a dismissal, rejection, missing editor, or unavailable runner fails closed. diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 37b420378c..4bb08db20e 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -9,8 +9,8 @@ import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from * uniformity guard, the fixture guards). Fixtures live under `snapshots/<name>/`; * `pnpm run test:snapshot:record` re-records model transcripts against the real * API; `pnpm run test:snapshot:refresh` rewrites current replay expected outputs keyless. - * See the package README (packages/support/acp-snapshot) and the snapshot RFC, - * docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md. + * See the package README (packages/support/acp-snapshot) and the snapshot Agent Note, + * .agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md. */ // The dsh-acp-demo bin (the demo:acp entry), this example's cordis.yml, and @@ -138,7 +138,7 @@ const SCENARIOS: Scenario[] = [ // (the model's reaction to a deny/block/force-continue is part of the captured transcript). // SessionStart/SubagentStart are excluded because detached injection races log // order; SubagentStop writes no transcript, so an expected output could not prove it ran. - // Unit tests cover those points; the hook-snapshot-matrix RFC owns the rationale. + // Unit tests cover those points; the hook-snapshot-matrix Agent Note owns the rationale. { name: 'hook-cc-promptsubmit-context', hasModelTurn: true, recorded: true }, { name: 'hook-cc-pretool-deny', hasModelTurn: true, recorded: true }, { name: 'hook-cc-pretool-ask', hasModelTurn: true, recorded: true }, diff --git a/examples/cordis-agent/README.md b/examples/cordis-agent/README.md index 5900d6a0f0..310fbb30af 100644 --- a/examples/cordis-agent/README.md +++ b/examples/cordis-agent/README.md @@ -1,6 +1,6 @@ # cordis-agent -The self-referential harness demo: the coding spine (DeepSeek V4 + local bash on the stdio chat app) plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which hands the model three tools over the **live cordis runtime it is running inside** — inspect it, mount new plugins into it, and dispose them again. The `ctx.fs` and `ctx.web` services are mounted (provider-only, no model-facing file/web tools) so the plugins the agent writes have real capabilities to build on; Node built-ins are trapped in the sandbox and redirect to those services. The design (sandbox semantics, mount lifecycle, cross-mount composition, caveats) lives in [the toolset RFC](../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). +The self-referential harness demo: the coding spine (DeepSeek V4 + local bash on the stdio chat app) plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which hands the model three tools over the **live cordis runtime it is running inside** — inspect it, mount new plugins into it, and dispose them again. The `ctx.fs` and `ctx.web` services are mounted (provider-only, no model-facing file/web tools) so the plugins the agent writes have real capabilities to build on; Node built-ins are trapped in the sandbox and redirect to those services. The design (sandbox semantics, mount lifecycle, cross-mount composition, caveats) lives in [the toolset Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). ## Run it diff --git a/examples/cordis-agent/cordis.yml b/examples/cordis-agent/cordis.yml index a567705cbd..7c7c010c3a 100644 --- a/examples/cordis-agent/cordis.yml +++ b/examples/cordis-agent/cordis.yml @@ -5,7 +5,7 @@ # Trust stance: the vm and context façade limit accidental global/framework # access but are not a security boundary; mounted code can reach live capabilities # such as `ctx.bash`. Grant this toolset like bash access. See -# ../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md. +# ../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md. # Hot-module reload for the dev/demo loop (needs `node --expose-internals`). - id: hmr diff --git a/examples/repl-agent/README.md b/examples/repl-agent/README.md index 7145873e9a..53cc68bb1a 100644 --- a/examples/repl-agent/README.md +++ b/examples/repl-agent/README.md @@ -27,7 +27,7 @@ The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_ ## Code Mode -[`code-mode.cordis.yml`](code-mode.cordis.yml) overlays the same tree with the worker-thread runtime and `tools: { mode: code }`. The model receives one `run_code` transport plus a generated TypeScript SDK for the visible tools; only program output returns to model context. Use `mode: both` to expose native calls alongside `run_code`. See the [Code Mode RFC](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) for the execution contract. +[`code-mode.cordis.yml`](code-mode.cordis.yml) overlays the same tree with the worker-thread runtime and `tools: { mode: code }`. The model receives one `run_code` transport plus a generated TypeScript SDK for the visible tools; only program output returns to model context. Use `mode: both` to expose native calls alongside `run_code`. See the [Code Mode Agent Note](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md) for the execution contract. ```sh pnpm run demo:code-mode # this overlay under the REPL (default UI) diff --git a/examples/tui-agent/README.md b/examples/tui-agent/README.md index 6646649b1b..fb8b10e7f4 100644 --- a/examples/tui-agent/README.md +++ b/examples/tui-agent/README.md @@ -20,4 +20,4 @@ Run `pnpm run demo:code-mode tui` for the sibling Code Mode overlay. ## Snapshot tests -`tests/snapshots/<scenario>/session.jsonl` supplies recorded user prompts and model chunks; sibling child logs drive subagents and workflows. The keyless suite executes those scripts through the real loop and tool implementations, then compares readable expected terminal cell/style output. Use `pnpm run test:snapshot:refresh` for presentation-only changes and `pnpm run test:snapshot:record` with a DeepSeek key when a recorded model journey changes. The implemented [TUI snapshot RFC](../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns the scenario matrix and the split between recorded journeys, transient package snapshots, and PTY coverage. +`tests/snapshots/<scenario>/session.jsonl` supplies recorded user prompts and model chunks; sibling child logs drive subagents and workflows. The keyless suite executes those scripts through the real loop and tool implementations, then compares readable expected terminal cell/style output. Use `pnpm run test:snapshot:refresh` for presentation-only changes and `pnpm run test:snapshot:record` with a DeepSeek key when a recorded model journey changes. The implemented [TUI snapshot Agent Note](../../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns the scenario matrix and the split between recorded journeys, transient package snapshots, and PTY coverage. diff --git a/package.json b/package.json index e736e3f8d1..42988ca5ad 100644 --- a/package.json +++ b/package.json @@ -42,8 +42,8 @@ "verify-package-paths": "tsx scripts/verify-package-paths.ts", "verify-package-readme-model-experience": "tsx scripts/verify-package-readme-model-experience.ts", "verify-mermaid": "tsx scripts/verify-mermaid.ts", - "verify-rfc-classification": "tsx scripts/verify-rfc-classification.ts", - "verify-rfc-format": "tsx scripts/verify-rfc-format.ts", + "verify-agent-note-classification": "tsx scripts/verify-agent-note-classification.ts", + "verify-agent-note-format": "tsx scripts/verify-agent-note-format.ts", "verify-type-equiv": "tsx scripts/verify-type-equiv.ts", "verify-translation-prompt": "tsx scripts/verify-translation-prompt.ts", "verify-translation-pairing": "tsx scripts/verify-translation-pairing.ts", @@ -53,7 +53,7 @@ "verify-runtime-closure": "tsx scripts/verify-runtime-closure.ts", "verify-cordis-config": "tsx scripts/verify-cordis-config.ts", "gen-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts", - "gen-rfc-index": "tsx scripts/gen-rfc-index.ts", + "gen-agent-note-index": "tsx scripts/gen-agent-note-index.ts", "verify-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts --check", "gen-cordis-api": "tsx scripts/gen-cordis-api.ts", "verify-cordis-api": "tsx scripts/gen-cordis-api.ts --check", @@ -76,7 +76,7 @@ "website:dev": "pnpm --filter @deepseek-ai/website run dev", "website:build": "pnpm --filter @deepseek-ai/website run build", "constraints": "tsx scripts/check-workspace-constraints.ts", - "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-events && pnpm run verify-website-api && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-package-readme-model-experience && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-prompt && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-package-readme-limitations && pnpm run verify-website-yaml", + "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-events && pnpm run verify-website-api && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-package-readme-model-experience && pnpm run verify-mermaid && pnpm run verify-agent-note-classification && pnpm run verify-agent-note-format && pnpm run verify-type-equiv && pnpm run verify-translation-prompt && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-package-readme-limitations && pnpm run verify-website-yaml", "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/repl-agent/cordis.yml", diff --git a/packages/AGENTS.md b/packages/AGENTS.md index c41c25b7a5..400436a9f1 100644 --- a/packages/AGENTS.md +++ b/packages/AGENTS.md @@ -6,9 +6,9 @@ These package-specific rules supplement the repo-wide [conventions](../AGENTS.md - **Optional services use `ctx.get(name)`.** Reserve `ctx.<name>` for declared injections; the property proxy is topology-sensitive, while strict `ctx.get` reads the global service store ([postmortem](../docs/postmortem/0001-acp-default-export-drops-inject.md)). - **Product-visible plugins require a non-unit REAL-composition test.** Hand-built `ctx.plugin(...)` suites are insufficient. Boot test-only `cordis.yml` through the Loader and app/process; mock only external/nondeterministic boundaries and assert model-visible, durable, or user-visible output. Keep opt-ins out of shipped defaults. [Policy](../docs/testing.md). - **Typed same-process service and plugin calls are contracts, not serialization boundaries.** Prefer readonly borrowed values; materialize or defensively validate only at parser/config, queued, model/tool JSON, durable/file, worker, process, or wire boundaries. -- **Initiator-owned private chains derive, then capture.** Under `ctx.agents.withInitiator()`, recover the Agent at each orchestration entry, derive `agent.session`, and let operation-local helpers close over it. Keep `Agent` and `Session` explicit at lifecycle, session-log, service, authority, worker/process, persistence, and wire interfaces; do not widen a leaf helper from `Session` to `Context` merely to hide a parameter ([rationale](../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md)). +- **Initiator-owned private chains derive, then capture.** Under `ctx.agents.withInitiator()`, recover the Agent at each orchestration entry, derive `agent.session`, and let operation-local helpers close over it. Keep `Agent` and `Session` explicit at lifecycle, session-log, service, authority, worker/process, persistence, and wire interfaces; do not widen a leaf helper from `Session` to `Context` merely to hide a parameter ([rationale](../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md)). - **Represent one asynchronous operation with one lifecycle controller or transaction.** Separate readiness, cancellation, disposal, reservation, or sentinel state requires an independent owner or settlement boundary; otherwise fold it while preserving rollback, callback containment, and quiescence. -- **Shape capability interfaces around all current consumers.** Keep tool-schema, Loader, UI, transport, and backend-specific behavior in the consumer or adapter; do not let one consumer dictate the interface ([capability-seam rationale](../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)). +- **Shape capability interfaces around all current consumers.** Keep tool-schema, Loader, UI, transport, and backend-specific behavior in the consumer or adapter; do not let one consumer dictate the interface ([capability-seam rationale](../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)). - **Require a current owner and need.** Tie each abstraction, state machine, option, defensive copy, and compatibility path to a current contract or production consumer, and keep behavior in its owning plugin or service. - **Require evidence for public choices.** Configurability does not justify an unsupported default, public operation set, format, or imported external concept. Use current-consumer evidence or relevant prior art; otherwise require an explicit value or defer the choice. - **Write model-facing contracts from the model's perspective.** Prompts, tool schemas, results, and diagnostics contain only task-relevant concepts, not UI, transport, or implementation vocabulary. Pin stable model-visible text verbatim and dynamic behavior through snapshots or end-to-end coverage. @@ -23,4 +23,4 @@ Naming notes: - Tests live at package level under `tests/`, not `src/__tests__/`. - A package's README and JSDoc are part of the change: altered behavior (config keys, defaults, error codes, wire fields) updates them in the same commit. `doc-sync` gates what it can; apply [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for complete, concise prose and verify accuracy against code. - Package READMEs document model, token, and KV-cache effects using the [canonical Model Experience format](../docs/cookbook/adding-a-package.md#4-write-the-package-readme). -- Package READMEs put durable consumer gaps and non-obvious maintainer constraints under `## Known Limitations and Deferred Work`; ordinary cleanup stays in its TODO or RFC. Packages with none use a justified [allowlist entry](../scripts/verify-package-readme-limitations.ts) ([rationale](../docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md)). +- Package READMEs put durable consumer gaps and non-obvious maintainer constraints under `## Known Limitations and Deferred Work`; ordinary cleanup stays in its TODO or Agent Note. Packages with none use a justified [allowlist entry](../scripts/verify-package-readme-limitations.ts) ([rationale](../.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md)). diff --git a/packages/README.md b/packages/README.md index 61a1e994c8..9c6a979d61 100644 --- a/packages/README.md +++ b/packages/README.md @@ -25,7 +25,7 @@ Packages live at `packages/<group>/<pkg>/`; groups are containers, while names r | [`todo/`](todo/README.md) | Todo/planning family: the model-facing `todo_write` tool | Product — stable surface | | [`timeout/`](timeout/README.md) | Tool-call timeout policy: the `tools/execute` deadline enforcer | Product — stable surface | | [`guard/`](guard/README.md) | Loop-hygiene guards: advisory repeat-call reminders | Product — stable surface | -| [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface | +| [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface | | [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface | | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface | | [`session-query/`](session-query/README.md) | Session retrieval: logical corpus, bounded reads, lineage, and event relationships | Product — stable surface | @@ -41,6 +41,6 @@ Groups distinguish product API from support infrastructure. New packages join an The dependency graph is generated: [docs/module-graph.md](../docs/module-graph.md) (`pnpm run gen-module-graph`, freshness-gated in CI). -The rule it must obey: **extension plugins depend on interfaces, never on the concrete loop.** `dsh-agent-loop` is swappable — UI/hook/tool plugins keep working against the `dsh-agent` vocabulary if the loop is replaced. The sanctioned exception is a **composition/bundle** package like `dsh-agent-spine-demo`, whose whole job is to assemble the concrete spine: it depends on `dsh-agent-loop` (and the other concrete spine plugins) on purpose. The rule constrains plugins that EXTEND the system, not the bundle that COMPOSES it. A swappable capability splits into interface / implementation / consumer packages (the bash trio is the template — see [capability seams](../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)). +The rule it must obey: **extension plugins depend on interfaces, never on the concrete loop.** `dsh-agent-loop` is swappable — UI/hook/tool plugins keep working against the `dsh-agent` vocabulary if the loop is replaced. The sanctioned exception is a **composition/bundle** package like `dsh-agent-spine-demo`, whose whole job is to assemble the concrete spine: it depends on `dsh-agent-loop` (and the other concrete spine plugins) on purpose. The rule constrains plugins that EXTEND the system, not the bundle that COMPOSES it. A swappable capability splits into interface / implementation / consumer packages (the bash trio is the template — see [capability seams](../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)). Package READMEs cover purpose, APIs, extension points, and [Model Experience](../docs/cookbook/adding-a-package.md#4-write-the-package-readme) unless on the model-agnostic [omission allowlist](../scripts/verify-package-readme-model-experience.ts). They also carry `## Known Limitations and Deferred Work` or use its [allowlist](../scripts/verify-package-readme-limitations.ts). diff --git a/packages/bash/README.md b/packages/bash/README.md index 20c11c5dff..2e2bb5692a 100644 --- a/packages/bash/README.md +++ b/packages/bash/README.md @@ -1,6 +1,6 @@ # bash/ — bash capability family -The canonical three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract executor interface, concrete implementations, and the model-facing tool that consumes it. All **product** packages. +The canonical three-package capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract executor interface, concrete implementations, and the model-facing tool that consumes it. All **product** packages. | Package | Role | ctx key | |---|---|---| diff --git a/packages/bash/bash-local/README.md b/packages/bash/bash-local/README.md index c63f86f797..5d99161fc0 100644 --- a/packages/bash/bash-local/README.md +++ b/packages/bash/bash-local/README.md @@ -25,7 +25,7 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; - **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` (deterministic; no rc files). All four surveyed tools spawn per call. `XXX(stateful-shell)` in `src/run.ts` records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them. - **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). After the main shell exits, inherited stdout/stderr pipes receive the same bounded drain grace so a surviving descendant cannot hold the command open indefinitely. ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools. - **Tail-keep truncation + bounded spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. A foreground `BashExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background tasks still use `maxOutputBytes`. A stream larger than `maxSpillBytes` discards its now-incomplete spill and returns only the marked truncated tail. If the final spill close reports a delayed writeback failure, the executor likewise withholds the path rather than advertising an incomplete file. -- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and all ambient `DSH_*` names, then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. A spec's ordinary `env` is merged after the scrub but rejects `DSH_*`; managed `dshEnv` rejects ordinary names and merges last, preventing stale nested-harness identity. Supplied stdin is written and closed; otherwise fd 0 is `/dev/null`. See the [stdin/env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [managed environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). +- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and all ambient `DSH_*` names, then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. A spec's ordinary `env` is merged after the scrub but rejects `DSH_*`; managed `dshEnv` rejects ordinary names and merges last, preventing stale nested-harness identity. Supplied stdin is written and closed; otherwise fd 0 is `/dev/null`. See the [stdin/env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [managed environment Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). - **Background processes** — `start()` returns a live `BashProcess` handle immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), the handle's `readOutput()` is incremental with whole-stream byte offsets, and disposal kills every running process and awaits its exit. Everything task-shaped (ids, ownership, polling, notices) lives in the generic [`ctx.tasks` runtime](../../tasks/tasks/README.md), which the tool layer registers the handle with — this executor never sees a session or a registry. ## Model Experience diff --git a/packages/bash/bash-sandbox/README.md b/packages/bash/bash-sandbox/README.md index fc6e82bcae..d08c9b4550 100644 --- a/packages/bash/bash-sandbox/README.md +++ b/packages/bash/bash-sandbox/README.md @@ -16,7 +16,7 @@ Semantics: - **Denials are result facts.** A failed run whose stderr carries the selected backend's own denial dialect — the signatures the provider stamps on every wrap (EROFS text under bwrap, EACCES under Landlock, EPERM under Seatbelt) — is reported as `BashRunResult.sandbox.denied: true` (conservative classification, read from the collected stderr tail); every CONFINED run also carries the mode it executed under (`result.sandbox.mode`) and the provider's enforcement completeness (`result.sandbox.enforcement`: `full`, or `partial` on an older Landlock ABI). - **Runner failures are sandbox failures, never command failures.** Foreground execution throws `SANDBOX_UNAVAILABLE`; a settled background process stamps `process.sandbox.runnerFailed`, which the bash producer renders through generic `task_output`. Spawn failures also pass through settlement, so confined background handles retain their mode/enforcement facts and release per-process accounting. -- **Config-time default, per-call policy.** The DEFAULT mode is fixed by this entry's config for the executor's lifetime; `resolve()` stamps it onto every spec, and an explicit request-level `sandboxMode` override — set by the tool layer only for a call whose wider mode a human granted through `ctx.approval` ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)) — makes THAT call run, classify, and report under its own mode while every neighbor keeps the default (background facts are stamped per task at settle). The capability fact `ctx.bash.sandboxMode` reports the configured default so the tool layer advertises escalation only when this executor is mounted. The model learns of the sandbox only through result facts — the static bash tool description explains the denial marker; there is no current-mode statement in the system prompt. +- **Config-time default, per-call policy.** The DEFAULT mode is fixed by this entry's config for the executor's lifetime; `resolve()` stamps it onto every spec, and an explicit request-level `sandboxMode` override — set by the tool layer only for a call whose wider mode a human granted through `ctx.approval` ([the sandbox Agent Note § Escalation](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md)) — makes THAT call run, classify, and report under its own mode while every neighbor keeps the default (background facts are stamped per task at settle). The capability fact `ctx.bash.sandboxMode` reports the configured default so the tool layer advertises escalation only when this executor is mounted. The model learns of the sandbox only through result facts — the static bash tool description explains the denial marker; there is no current-mode statement in the system prompt. - **File effects only.** Network and process visibility are deliberately not restricted — the mode vocabulary does not pretend to cover what the backend does not enforce. - Process mechanics (spawn, process-group kills, output collection/spill, background handles, credential scrub) are inherited from [`dsh-bash-local`](../bash-local/); runner selection lives in [`dsh-sandbox-local`](../../sandbox/sandbox-local/). diff --git a/packages/bash/bash/README.md b/packages/bash/bash/README.md index 9a3cbc46f1..30fa92b78f 100644 --- a/packages/bash/bash/README.md +++ b/packages/bash/bash/README.md @@ -31,7 +31,7 @@ Implementations subclass `BashExecutor` and implement the abstract methods. Disp The seam also owns the per-session mode override vocabulary: the log-only `'bash/sandbox-mode'` session event, the pure `effectiveSandboxMode(events)` fold, and the `setSandboxMode(session, mode)` write path. `run()` returns `BashRunResult`; `start()` returns `BashProcess`, whose incremental read and kill methods are adapted by `dsh-tool-bash` into a generic task registration. A sandboxing executor stamps `BashSandboxInfo` on foreground results and settled process handles. See `src/types.ts` and [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md). -`stdin` and ordinary `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload and `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` values. `dshEnv` is a separate trusted overlay restricted by type to managed keys; the exported `DSH_ENV_PREFIX` is the single source for that namespace, its `DshEnvironmentKey` template type, executor scrubbing, registry validation, derived built-in names, and model guidance. Model bash uses the current snapshot collected by `ctx.bashEnv`. Implementations remove inherited managed keys, reject those names in ordinary `env`, then merge `dshEnv`, so an omitted current fact cannot fall back to stale ambient state. The model-facing tool exposes none of these as parameters. All three remain optional on the resolved spec; absent means no input/overlay. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). +`stdin` and ordinary `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload and `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` values. `dshEnv` is a separate trusted overlay restricted by type to managed keys; the exported `DSH_ENV_PREFIX` is the single source for that namespace, its `DshEnvironmentKey` template type, executor scrubbing, registry validation, derived built-in names, and model guidance. Model bash uses the current snapshot collected by `ctx.bashEnv`. Implementations remove inherited managed keys, reject those names in ordinary `env`, then merge `dshEnv`, so an omitted current fact cannot fall back to stale ambient state. The model-facing tool exposes none of these as parameters. All three remain optional on the resolved spec; absent means no input/overlay. See [the bash-stdin-env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). ## Model Experience @@ -44,4 +44,4 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work - **No interactive-input vocabulary** — `stdin` is written once at spawn and closed; the seam has no channel to feed a running task and no PTY session concept. -- **Foreground timeouts are always executor-owned** — a caller-owned-deadline mode on the seam is explicitly deferred by [the tool-call timeout-policy RFC](../../../docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md). +- **Foreground timeouts are always executor-owned** — a caller-owned-deadline mode on the seam is explicitly deferred by [the tool-call timeout-policy Agent Note](../../../.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md). diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 6e0ddca91e..55beccacea 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -131,7 +131,7 @@ export interface BashRunResult { * short. Mutually exclusive with {@link aborted}: one fused deadline drives * both the timeout and the caller's cancellation, so a timeout and an abort * racing before process close report the single first-abort cause, not both - * (see the [timeout-library RFC](../../../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md)). + * (see the [timeout-library Agent Note](../../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md)). */ timedOut: boolean /** diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index 3eea649643..258967fad9 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -57,17 +57,17 @@ The tool owns its `presentCall`/`presentResult` render intent. A foreground call ## The tool builds its request from named args only -The `BashExecRequest` seam carries optional `stdoutMaxBytes`, `stdin`, ordinary `env`, and managed `dshEnv`, used by trusted in-process plugins and this tool's environment registry. The model-facing tool exposes none of `stdoutMaxBytes`, `stdin`, or `env`: it builds requests from named command/workdir/timeout/signal/sandbox fields plus the registry-collected `dshEnv`. Extra model keys are ignored and cannot replace managed values. Shell syntax provides equivalent command-level behavior, while the local executor scrubs ambient credentials and stale `DSH_*` values. See the [stdin/env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +The `BashExecRequest` seam carries optional `stdoutMaxBytes`, `stdin`, ordinary `env`, and managed `dshEnv`, used by trusted in-process plugins and this tool's environment registry. The model-facing tool exposes none of `stdoutMaxBytes`, `stdin`, or `env`: it builds requests from named command/workdir/timeout/signal/sandbox fields plus the registry-collected `dshEnv`. Extra model keys are ignored and cannot replace managed values. Shell syntax provides equivalent command-level behavior, while the local executor scrubs ambient credentials and stale `DSH_*` values. See the [stdin/env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). ## Permissions and escalation Commands run with the executor's full authority unless a sandboxing executor ([`dsh-bash-sandbox`](../bash-sandbox/)) confines them — the deny-only sandbox reports denials as result facts, rendered here as the denial marker; per-call allow/deny/ask policy is the `tools/pre-execute` waterfall (see docs/architecture.md). -Escalating bash calls resolve `ctx.approval` before execution. `allowed-once` applies the requested mode only to that call; rejection, cancellation, unavailability, or missing approval context executes nothing and returns a distinct error. On a real denial, the model may retry the same command once in the same turn with the narrowest sufficient mode and justification; the approval prompt itself is the consent step. Escalation is never speculative, and a disabled or rejected approval is final. The [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md) owns the rationale. +Escalating bash calls resolve `ctx.approval` before execution. `allowed-once` applies the requested mode only to that call; rejection, cancellation, unavailability, or missing approval context executes nothing and returns a distinct error. On a real denial, the model may retry the same command once in the same turn with the narrowest sufficient mode and justification; the approval prompt itself is the consent step. Escalation is never speculative, and a disabled or rejected approval is final. The [sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md) owns the rationale. ## Per-session mode switching -For sandboxing executors, each call resolves mode as one-shot escalation, then session override, then executor default. Non-sandboxing and agent-less calls carry no session override. Neither the prompt nor a switch notice announces the standing mode; denial results report the effective mode when the boundary matters. See the [`dsh-bash` fold](../bash/README.md) and [sandbox switching contract](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). +For sandboxing executors, each call resolves mode as one-shot escalation, then session override, then executor default. Non-sandboxing and agent-less calls carry no session override. Neither the prompt nor a switch notice announces the standing mode; denial results report the effective mode when the boundary matters. See the [`dsh-bash` fold](../bash/README.md) and [sandbox switching contract](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). ## Model Experience @@ -150,5 +150,5 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work - **Replay exit pills parse from result text** — output whose final line happens to be exactly `[exit code: N]` / `[killed by signal: …]` shows a wrong pill on session replay; a display-only known residual. -- **The `bash` tool opts out of `timeout-policy` budgets** — it keeps the executor-owned `BASH_TIMEOUT` path, per [the tool-call timeout-policy RFC](../../../docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md). +- **The `bash` tool opts out of `timeout-policy` budgets** — it keeps the executor-owned `BASH_TIMEOUT` path, per [the tool-call timeout-policy Agent Note](../../../.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md). - **Background processes have no executor timeout** — callers must use `task_kill`, or rely on owner/service disposal, when work no longer matters. diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index af0cdcaa1c..857e08072a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -287,7 +287,7 @@ describe('bash tool', () => { }) // Type and required-key violations are rejected by the harness - // (defineTool validates against the SchemaSpec — the arg-validation RFC) before execute. + // (defineTool validates against the SchemaSpec — the arg-validation Agent Note) before execute. it.each([ [{}, /missing required property "command"/], [{ command: 42, description: 'd' }, /"command" must be a string/], @@ -946,7 +946,7 @@ describe('the model-facing bash tool builds its request from named args only (no * model input into the post-scrub `env` merge or per-run capture budget — NOT * to defend a trust boundary * (the credential scrub in dsh-bash-local is the security control; see the - * bash-stdin-env RFC). Foreground `run()` returns a canned result; `start()` + * bash-stdin-env Agent Note). Foreground `run()` returns a canned result; `start()` * hands back an already-settled fake handle so the task registration completes. */ class RecordingBashExecutor extends BashExecutor { diff --git a/packages/code-runtime/README.md b/packages/code-runtime/README.md index 2c18ef43cf..27ef599ebe 100644 --- a/packages/code-runtime/README.md +++ b/packages/code-runtime/README.md @@ -1,6 +1,6 @@ # code-runtime/ — code-execution capability family -The code-execution capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract runtime interface for executing one model-written program against host-provided async bindings, capturing what it printed and returned. The consumer is the tool registry's [Code Mode](../core/tools/README.md) (`tools: { mode: code }` — the `run_code` tool and the generated TypeScript SDK); design in the [Code Mode RFC](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md). **Product** packages. +The code-execution capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract runtime interface for executing one model-written program against host-provided async bindings, capturing what it printed and returned. The consumer is the tool registry's [Code Mode](../core/tools/README.md) (`tools: { mode: code }` — the `run_code` tool and the generated TypeScript SDK); design in the [Code Mode Agent Note](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md). **Product** packages. | Package | Role | ctx key | |---|---|---| diff --git a/packages/code-runtime/code-runtime-worker/README.md b/packages/code-runtime/code-runtime-worker/README.md index 96d65198e2..2645e8810e 100644 --- a/packages/code-runtime/code-runtime-worker/README.md +++ b/packages/code-runtime/code-runtime-worker/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-code-runtime-worker -Worker-thread implementation of the [`@deepseek-ai/dsh-code-runtime`](../code-runtime/README.md) seam: `WorkerCodeRuntime` runs each program in ONE fresh Node `worker_threads.Worker` — TypeScript in, type-stripped host-side, bindings bridged over the message port, `{ value, logs, error? }` out. **Containment, not a security boundary**: trust posture is bash-equivalent by design (the [Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) § Trust posture), with containment bash does not have — separate isolate, empty environment, heap cap, hard termination. +Worker-thread implementation of the [`@deepseek-ai/dsh-code-runtime`](../code-runtime/README.md) seam: `WorkerCodeRuntime` runs each program in ONE fresh Node `worker_threads.Worker` — TypeScript in, type-stripped host-side, bindings bridged over the message port, `{ value, logs, error? }` out. **Containment, not a security boundary**: trust posture is bash-equivalent by design (the [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md) § Trust posture), with containment bash does not have — separate isolate, empty environment, heap cap, hard termination. ## Config diff --git a/packages/code-runtime/code-runtime/README.md b/packages/code-runtime/code-runtime/README.md index e5b1565fec..b31af71397 100644 --- a/packages/code-runtime/code-runtime/README.md +++ b/packages/code-runtime/code-runtime/README.md @@ -2,7 +2,7 @@ The **code-execution seam**: an abstract `CodeRuntime` service (`ctx.codeRuntime`) defining WHAT a code runtime does — run one model-written program against a set of host-provided async bindings and report `{ value, logs, error? }` — without saying HOW. -This package is the interface third of the capability (the bash trio is the template — see [capability seams](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): implementations subclass `CodeRuntime` and register the service; the consumer is the tool registry's Code Mode, which generates the model-facing SDK and bridges tool dispatch — both specified in the [Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md), whose first implementation is a Node worker-thread backend. The runtime knows nothing about tools or sessions: it is handed named async functions and a program string, and everything tool-shaped stays with the consumer. +This package is the interface third of the capability (the bash trio is the template — see [capability seams](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): implementations subclass `CodeRuntime` and register the service; the consumer is the tool registry's Code Mode, which generates the model-facing SDK and bridges tool dispatch — both specified in the [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md), whose first implementation is a Node worker-thread backend. The runtime knows nothing about tools or sessions: it is handed named async functions and a program string, and everything tool-shaped stays with the consumer. ## Service API (`ctx.codeRuntime`) @@ -29,5 +29,5 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work - **`run()` is one-shot** — `logs` arrive only on the resolved `CodeRunResult`; the seam exposes no streaming-log or progress surface for a live program's output. -- **A persistent REPL-style kernel is recorded future work** — the no-state-between-runs contract stands until a persistent-kernel backend brings its own logging story ([Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md)). +- **A persistent REPL-style kernel is recorded future work** — the no-state-between-runs contract stands until a persistent-kernel backend brings its own logging story ([Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)). - **Only the worker-thread backend ships** — `'process'`/`'container'` are declared well-known `isolation` values with no implementation; a hard security boundary awaits a container backend. diff --git a/packages/compact/README.md b/packages/compact/README.md index b5f5987571..890bfa3260 100644 --- a/packages/compact/README.md +++ b/packages/compact/README.md @@ -1,6 +1,6 @@ # compact/ — compaction capability family -A three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract compaction interface, a backend that summarizes, and the model-facing tool that consumes it. The interface and a first backend (`compact-basic/`) exist; the consumer tool is deferred. All **product** packages. +A three-package capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract compaction interface, a backend that summarizes, and the model-facing tool that consumes it. The interface and a first backend (`compact-basic/`) exist; the consumer tool is deferred. All **product** packages. | Package | Role | ctx key | |---|---|---| @@ -8,4 +8,4 @@ A three-package capability seam (see [capability seams](../../docs/rfc/implement | `compact-basic/` | A backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) | | `tool-compact/` (deferred) | Model-facing `/compact` tool over `ctx.compact` | (registers on `ctx.tools`) | -The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement is a reusable LLM-family service rather than a `CompactService` method; a template- or model-backed compactor can replace `compact-basic` without changing the meter or callers. +The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement is a reusable LLM-family service rather than a `CompactService` method; a template- or model-backed compactor can replace `compact-basic` without changing the meter or callers. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index 6f9f5f387d..6a67d2dfd4 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -2,7 +2,7 @@ The **basic compaction backend**: a `BasicCompactService` implementing the `@deepseek-ai/dsh-compact` seam with reusable `ctx.tokenMeter` pressure, token-budget retention, and summarization as a direct one-shot `ctx.llm.stream()` call (interceptable at `llm/stream`). -This is the implementation tier of the compaction capability — see the [interface package](../compact/README.md) for the seam and the [capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) for the design. +This is the implementation tier of the compaction capability — see the [interface package](../compact/README.md) for the seam and the [capability-seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md) for the design. ## What it owns @@ -147,4 +147,4 @@ Prefix-stable for auxiliary calls while this instruction and the summarizer rout - **Single-unit and envelope-only overflow remain outside surface compaction** — recovery cannot split one indivisible message/tool unit or shrink system/tools/prefix. - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting. - **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds. -- **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). +- **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)). diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index f0af3c6e74..c4a2dc7a5d 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -10,7 +10,7 @@ This package is the interface tier of the compaction capability, split so each c | `@deepseek-ai/dsh-compact-basic` | a backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization | | `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` | -Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). +Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md). ## Service API (`ctx.compact`) diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 7f0844c9f9..f4f666bfef 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -3,7 +3,7 @@ * compact and replace a history range with one summary node by subclassing * {@link CompactService}. This interface necessarily depends on session and LLM * vocabulary; the rationale is in the - * [compaction RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). + * [compaction Agent Note](../../../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md). * @module @deepseek-ai/dsh-compact */ diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index e831573d5a..e531430525 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -3,7 +3,7 @@ * Those declaration-merged events are log-only lock/provenance markers, not * surface events; a separate replacement `user/message` carries the summary. * Backend packages own configuration and retention policy; see - * `docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md`. + * `.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md`. * @module @deepseek-ai/dsh-compact/types */ @@ -30,7 +30,7 @@ declare module '@deepseek-ai/dsh-session' { * The model that wrote the summary — the summarize call's envelope, * reported by the backend that made the call, logged so the one-shot * request is reconstructable from log + code and "which model wrote - * this summary" has a durable answer (the reconstructability RFC). + * this summary" has a durable answer (the reconstructability Agent Note). */ model: string /** The generation cap the summarize call sent, when one applied. */ diff --git a/packages/context/README.md b/packages/context/README.md index 8a947703ec..ebfa8d2d11 100644 --- a/packages/context/README.md +++ b/packages/context/README.md @@ -7,4 +7,4 @@ Product plugins that add model-visible request context without defining a tool o | `time-context/` | Durable per-step current time and elapsed-time context | (none) | | `workspace-context/` | `AGENTS.md`/`CLAUDE.md` workspace context loader | (listens on `agent/session-prefix` + `tools/post-execute`) | -The [`workspace-context` decision record](../../docs/rfc/implemented/feature/2026-06-24-workspace-context.md) explains its per-agent/session isolation and lifecycle split. +The [`workspace-context` decision record](../../.agents/notes/implemented/feature/2026-06-24-workspace-context.md) explains its per-agent/session isolation and lifecycle split. diff --git a/packages/context/time-context/README.md b/packages/context/time-context/README.md index f29f908acb..dc79fb6d23 100644 --- a/packages/context/time-context/README.md +++ b/packages/context/time-context/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-time-context -Opt-in durable context with the current zoned time and elapsed time sampled during model-request preparation. `dsh-agent-spine-demo` and shipped examples do not mount it. Decision record: [the durable time-context RFC](../../../docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md). +Opt-in durable context with the current zoned time and elapsed time sampled during model-request preparation. `dsh-agent-spine-demo` and shipped examples do not mount it. Decision record: [the durable time-context Agent Note](../../../.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.md). ## Config diff --git a/packages/cordis/README.md b/packages/cordis/README.md index 70c7e41ce0..c7c08bbb24 100644 --- a/packages/cordis/README.md +++ b/packages/cordis/README.md @@ -1,6 +1,6 @@ # packages/cordis — the self-referential runtime toolset -Model-facing tools over the live cordis runtime the agent itself runs inside: inspect the loaded plugins and service surface, mount model-written plugins, and dispose them again. Design home: [the toolset RFC](../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). +Model-facing tools over the live cordis runtime the agent itself runs inside: inspect the loaded plugins and service surface, mount model-written plugins, and dispose them again. Design home: [the toolset Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). | Package | Role | ctx key | |---|---|---| diff --git a/packages/cordis/tool-cordis/README.md b/packages/cordis/tool-cordis/README.md index a8dc203342..7819cb8c2c 100644 --- a/packages/cordis/tool-cordis/README.md +++ b/packages/cordis/tool-cordis/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-tool-cordis -The self-referential cordis toolset: three model-facing tools over the live runtime the agent runs inside. Design home — sandbox semantics, mount lifecycle, cross-mount composition, the generated API catalog, standing decisions: [the toolset RFC](../../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). +The self-referential cordis toolset: three model-facing tools over the live runtime the agent runs inside. Design home — sandbox semantics, mount lifecycle, cross-mount composition, the generated API catalog, standing decisions: [the toolset Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). ## What it does @@ -12,7 +12,7 @@ Exact model-facing schemas: [the generated tool catalog](../../../docs/tool-cata ## Trust stance -The sandbox isolates globals but is not a security boundary. Node globals are absent or redirect to Cordis services such as `ctx.fs`, `ctx.web`, and `ctx.bash`, and writes to `globalThis` stay local, but host-realm helpers make escape possible. Mounted plugins receive a façade without framework internals, yet its allowed services affect the live runtime. Treat this toolset like bash access; see the [design and trust stance](../../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). +The sandbox isolates globals but is not a security boundary. Node globals are absent or redirect to Cordis services such as `ctx.fs`, `ctx.web`, and `ctx.bash`, and writes to `globalThis` stay local, but host-realm helpers make escape possible. Mounted plugins receive a façade without framework internals, yet its allowed services affect the live runtime. Treat this toolset like bash access; see the [design and trust stance](../../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). ## Config diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 52f8477318..c0c29331ae 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -750,7 +750,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'llm/stream', mode: 'waterfall', signature: '\'llm/stream\'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable<StreamChunk>): AsyncIterable<StreamChunk>', - jsDoc: '/**\n * Waterfall around every streaming model call (retry, replay, routing).\n * Bound to the {@link LlmService}; call `next()` to reach the resolved\n * adapter\'s stream, or yield your own chunks to short-circuit.\n * @param options - the full request. A LOOP-built request arrives\n * deep-frozen (mutation throws): its content is a pure function of the\n * session log (the reconstructability RFC), so listeners read it, never\n * rewrite it. A hand-built one-shot (compaction summarize) is the\n * caller\'s own object and stays mutable here.\n * @mode waterfall\n */', + jsDoc: '/**\n * Waterfall around every streaming model call (retry, replay, routing).\n * Bound to the {@link LlmService}; call `next()` to reach the resolved\n * adapter\'s stream, or yield your own chunks to short-circuit.\n * @param options - the full request. A LOOP-built request arrives\n * deep-frozen (mutation throws): its content is a pure function of the\n * session log (the reconstructability Agent Note), so listeners read it, never\n * rewrite it. A hand-built one-shot (compaction summarize) is the\n * caller\'s own object and stays mutable here.\n * @mode waterfall\n */', summary: 'Waterfall around every streaming model call (retry, replay, routing).', }, { diff --git a/packages/cordis/tool-cordis/src/index.ts b/packages/cordis/tool-cordis/src/index.ts index fd15d75624..4fc5bd4328 100644 --- a/packages/cordis/tool-cordis/src/index.ts +++ b/packages/cordis/tool-cordis/src/index.ts @@ -26,7 +26,7 @@ export interface Config { /** * Milliseconds the SYNCHRONOUS portion of mount code may run in the vm * before evaluation is aborted (default 5000). An async body escapes this - * bound — see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md for the trust stance. + * bound — see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md for the trust stance. */ vmTimeoutMs?: number } diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index e2c7723185..9c5c869168 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -19,7 +19,7 @@ Each agent and its session share one caller-chosen `SessionId`, assumed globally `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): - `ctx.agents.create({ sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — programmatic create under the caller-supplied shared id. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. -- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. +- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle). For a programmatic agent, the handle holder is the only consumer-facing teardown capability; AgentLoop provider unload is the independent structural teardown edge, not another handle exposed to application code. @@ -114,7 +114,7 @@ Append-only; each synthetic result follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)). +- **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)). - **Config labels are fresh by default** — omitting `sessionId` creates a fresh `${id}-session-<uuid>` on every startup; exact resume-or-create behavior requires an explicit stable `sessionId`, while `resumeSessionId` requires existing persisted history. - **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options. - **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin. diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 0012b504cd..9016c16d9b 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -1,7 +1,7 @@ /** * Drives one agent across queued durable turns. Turn failures are contained so * later work can run; the session log, not this driver, owns conversation state. - * See docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md. + * See .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md. * @module dsh-agent-loop/loop */ diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index b324c02b6c..a1d449d273 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -235,7 +235,7 @@ describe('disposed vs aborted branching', () => { }) }) -describe('structured tool error propagation (the runtime-validation RFC, part 2)', () => { +describe('structured tool error propagation (the runtime-validation Agent Note, part 2)', () => { it('forwards a tool HarnessError onto the tool/result session event', async () => { const { HarnessError } = await import('@deepseek-ai/dsh-llm') // First model turn calls the tool; second turn (after the tool result is diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 2becadcc40..ff7a6337ce 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -1,6 +1,6 @@ /** * Property-based tests for the agent loop's inbox/turn scheduling (the - * property-testing RFC). Deterministic by construction: schedules are driven + * property-testing Agent Note). Deterministic by construction: schedules are driven * through the `agent/status` settle signal (no wall-clock sleeps), so a flake * is a finding, not timing noise. * diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 9fc832fd0a..36d88feaa9 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -14,7 +14,7 @@ import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' * multi-step tool turn (plus a follow-up turn) against the live DeepSeek API must report * `cacheReadTokens > 0` on every request after the first — the adapter maps the provider's * `prompt_cache_hit_tokens`, and the per-step usage recorded on `assistant/message` events is - * the production observable for cache behavior (the reconstructability RFC's measurement + * the production observable for cache behavior (the reconstructability Agent Note's measurement * layer: prefix stability is corollary #1). Mocks establish append-extension; * this key-gated test establishes a real provider cache hit. */ diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 74192dde90..57635bbe5f 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -75,7 +75,7 @@ function throwUnknown(value: unknown): never { throw value } -describe('the session-persistence RFC: AgentLoop factory create/resume', () => { +describe('the session-persistence Agent Note: AgentLoop factory create/resume', () => { it('normalizes a non-Error resume publication failure for rollback and rethrows it', async () => { const sessionId = SessionId('unknown-resume-failure-s') const root = await persistSession(sessionId) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 372b594eb7..c2b46f210d 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -26,7 +26,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.withInitiator(agent, operation)` — run with one exact Agent and preserve the operation's exact synchronous value or Promise. - `ctx.agents.withoutInitiator(operation)` — hide an inherited initiator for unrelated process-local work. -The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. If a boundary's inherited async chain starts an owning Cordis fiber's unload, that nested boundary chain is released from the drain so the unload cannot wait on itself; its continuations observe the disposed service after teardown. The [initiator-scope decision](../../../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract. +The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. If a boundary's inherited async chain starts an owning Cordis fiber's unload, that nested boundary chain is released from the drain so the unload cannot wait on itself; its continuations observe the disposed service after teardown. The [initiator-scope decision](../../../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract. #### Factory seam (creation) @@ -34,7 +34,7 @@ Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-age - `ctx.agents.setFactory(factory: AgentFactory): () => void` — register the creation factory (the loop calls this on construction). Throws on a second factory; the slot clears on dispose. - `ctx.agents.create(options: CreateAgentOptions): Promise<AgentHandle>` — create a session and agent, await optional setup while unpublished, then publish through final `SessionStore.enter()` and `AgentRegistry.enter()` checks. Concurrent same-ID creation is unsupported: more than one operation may prepare, but only one can enter; every loser rolls its private scope/session/driver back. An optional creation-only `signal` cancels unpublished setup and is detached before the handle is returned; later cancellation uses `handle.dispose()` or `agent.cancel()`. Publication is rollback-covered and every delivered creation edge is paired during rollback. Rejects if no factory is registered. -- `ctx.agents.resume(options: ResumeAgentOptions): Promise<AgentHandle>` — load a persisted session ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), mint a fresh unpublished agent scope, await optional setup, and use the same final-entry publication sequence. Its optional `signal` is likewise creation-only. Rejects if no factory is registered or session persistence is unconfigured. +- `ctx.agents.resume(options: ResumeAgentOptions): Promise<AgentHandle>` — load a persisted session ([session persistence](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)), mint a fresh unpublished agent scope, await optional setup, and use the same final-entry publication sequence. Its optional `signal` is likewise creation-only. Rejects if no factory is registered or session persistence is unconfigured. `AgentHandle = { agent: Agent; dispose(): Promise<void> }`. The disposer is a **consumer capability** — no observer holding the bare registry entry can tear the agent down. The caller fiber and the registered factory provider are structural co-owners: caller unload enforces structured ownership, while factory unload must stop old instances because their scoped dependency surface belongs to that provider. `dispose()` from any owner reaches one memoized quiescence boundary: it stops the loop, `await`s its exit plus every outstanding idle-injection flush (not just the `disposed` status flip), unregisters the agent, removes its session from the store, and finally unwinds its scoped world. This order captures every agent-started `session/flush` before the session is detached and keeps scoped listeners alive through those checkpoints. `ctx.agents.get(id)` still returns a bare `Agent`; the ACP bridge and in-process subagent backends hold consumer handles, while config-created agents are already owned by the loop fiber. @@ -44,7 +44,7 @@ Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-age The lifecycle edges have two important local caveats. `agent/created` runs after scoped setup and after both session and agent registry entries exist. Setup is trusted composition-only code; the immediately following non-vetoing `agent/session-start` notification is the first supported startup injection point. `agent/disposed` always means the exact agent has left the registry. AgentLoop emits it after its driver is quiescent, while ordered teardown may still be detaching the session and unwinding the scope; custom agents registered directly own any stronger driver-ordering contract themselves. -Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: a retry opens a new numbered step after the failed step closes. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). +Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: a retry opens a new numbered step after the failed step closes. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). `PromptDecision.additionalContexts` is an array so every injected context keeps its own source, envelope, and metadata. A `ContinuationDecision` reason is narrower: it becomes a `steering/message`, not a `context/message`, and therefore carries only content and source. @@ -56,7 +56,7 @@ The handle every plugin programs against: - `agent.send(content, options?)` — queue a message; starts a turn when idle. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). - `agent.steer(content, options?)` — steer a running turn (inject between steps); uses the same owned acceptance boundary and behaves like `send` when idle -- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message`. `options.envelope` defaults to the canonical `<context>` framing and may be `'raw'` when the caller owns a complete familiar frame; `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)). +- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message`. `options.envelope` defaults to the canonical `<context>` framing and may be `'raw'` when the caller owns a complete familiar frame; `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)). - `agent.cancel(reason?)` — cancel ALL pending work: clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window) so a queued-but-not-started prompt never runs. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op. - `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly. - `agent.session`, `agent.status`, `agent.options`, `agent.id` @@ -103,6 +103,6 @@ Prefix-stable while an agent's scoped registrations are unchanged. Setup or relo - **Ambient identity may outlive liveness** — consumers still check `agent.status`, cancellation, and the owning capability contract before lifecycle-sensitive work. - **Inter-agent channels beyond delegation** — shared state, streaming child output, and background/poll semantics remain outside the current synchronous `ctx.subagents` seam. - **`agent/session-start` cannot gate startup** — it remains a synchronous, veto-less notification; async composition that must finish before publication belongs in the factory's `setup(agentCtx)` transaction instead. -- **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface RFC](../../../docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). +- **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface Agent Note](../../../.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). - **`HookContext` carries exactly one `MessageSource`** — contributions from several plugins merged onto one tool call collapse under one source; mixed provenance is unrepresentable. - **`SessionStartSource` reserves `'clear'`/`'compact'` with no emitter yet** — only `'startup'`/`'resume'` occur until the driving subsystems land (`TODO(compaction)`). diff --git a/packages/core/scope/README.md b/packages/core/scope/README.md index 36cc059bc4..fd6d10c84c 100644 --- a/packages/core/scope/README.md +++ b/packages/core/scope/README.md @@ -15,7 +15,7 @@ Scoped registration primitive. `createScope(ctx, key)` creates a tagged Cordis c ## Design contract -The registration context determines both visibility and ownership, preventing a registration from being visible in one scope but disposed with another. Scopes route trusted same-process plugins; they are not sandboxes or authority boundaries. See the [agent-scope RFC](../../../docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals) for rationale and security non-goals. +The registration context determines both visibility and ownership, preventing a registration from being visible in one scope but disposed with another. Scopes route trusted same-process plugins; they are not sandboxes or authority boundaries. See the [agent-scope Agent Note](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals) for rationale and security non-goals. Handing out a scoped context hands out the minting plugin's service-resolution surface (resolution walks the minting fiber's dependency chain, not the holder's) — mint it from the plugin whose dependencies the scoped registrations need to resolve. diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 07bbc4c078..a60be8da72 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -22,7 +22,7 @@ Use the split lifecycle only when teardown must be ordered with another resource - `enter(session)` performs the collision check, publishes without announcing, and returns an entry-bound idempotent detach. Concurrent same-id preparations are allowed, but only one entry succeeds; a stale detach cannot remove its replacement. - `announce(session)` emits the single creation edge and rejects repeat or reentrant announcements. Detach during that dispatch is deferred and later emits the paired disposal edge; an unannounced entry emits neither lifecycle edge. -`dsh-agent-loop` uses this split so final loop flush precedes session detach; see the [ownership RFC](../../../docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md). +`dsh-agent-loop` uses this split so final loop flush precedes session detach; see the [ownership Agent Note](../../../.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md). ### Live service events @@ -54,7 +54,7 @@ Durable values need one accepted representation, not a check followed by a secon ### Request-header reconstruction (`request-header.ts`) -`request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. `messagePrefix` remains separate from derived history. See the [reconstructable-requests RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md). +`request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. `messagePrefix` remains separate from derived history. See the [reconstructable-requests Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md). `context/message` defaults to the canonical tagged context projection. A producer may set `envelope: 'raw'` when its `content` already contains the complete model-facing frame, and may attach JSON `meta` for replayable plugin state; metadata remains durable but is excluded from `deriveMessages()`. @@ -128,6 +128,6 @@ Logging causes no invalidation, and exact reconstruction preserves request-prefi ## Known Limitations and Deferred Work - **Session branching/tree** (pi-style entry tree) — deferred unless needed beyond boundary-based `fork()`. -- **`fork()` cuts only at closed-turn boundaries of live sessions** — the boundary must be a `turn/end` event and the source must be in the store; forking a persisted-but-unloaded session is excluded from the [fork API](../../../docs/rfc/implemented/feature/2026-06-30-session-store-fork-api.md). +- **`fork()` cuts only at closed-turn boundaries of live sessions** — the boundary must be a `turn/end` event and the source must be in the store; forking a persisted-but-unloaded session is excluded from the [fork API](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md). - **`SESSION_FORMAT_VERSION` stays pinned at `0`** — pre-release, no compatibility implied: a backend rejects any other version, and no migration path exists until the first release ([policy](../../../AGENTS.md)). - **`TurnEndReasonMap` omits the ACP-named `refusal` / `max_turn_requests` variants** — producer-gated: they land when an adapter or the loop first emits them. diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index b8b76ec2ed..16732f7903 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -496,7 +496,7 @@ export class Session { * The per-node pure function {@link deriveMessages} folds over the surface; * an external reconstructor (or the dev invariant) folds the same function * over a log prefix's surface to rebuild the exact messages any request was - * built from (the reconstructability RFC). The returned message wrapper is + * built from (the reconstructability Agent Note). The returned message wrapper is * fresh; its content reuses the logged event's already deep-frozen durable * data, so changing the wrapper cannot rewrite the log and changing content * throws. diff --git a/packages/core/session/tests/properties.spec.ts b/packages/core/session/tests/properties.spec.ts index 9cb744c312..911d8ab7ab 100644 --- a/packages/core/session/tests/properties.spec.ts +++ b/packages/core/session/tests/properties.spec.ts @@ -1,5 +1,5 @@ /** - * Property-based tests for the Session event log (the property-testing RFC). + * Property-based tests for the Session event log (the property-testing Agent Note). * * Generates arbitrary event logs and asserts the derivation invariants the * agent loop and replay depend on: deriveMessages is deterministic and diff --git a/packages/core/system-prompt/README.md b/packages/core/system-prompt/README.md index 91b9eaf164..5c5c554351 100644 --- a/packages/core/system-prompt/README.md +++ b/packages/core/system-prompt/README.md @@ -7,7 +7,7 @@ System prompt assembly registry. Plugins contribute ordered sections, tool schem | Key | Default | Meaning | |---|---|---| | `persona` | `''` | The global deployment-persona default: the ONE config-authored prompt fragment, rendered as the order-0 `deployment:persona` section unless an agent-scoped contribution shadows it. A template — complete `{{…}}` groups are interpreted strictly against the registered variables (the shipped loop registers `{{model}}`/`{{cwd}}`), with no escape syntax for literal braces yet. Empty ⇒ the section is dropped at render. | -| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md). | +| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md). | ## Service: `SystemPrompt` (ctx key: `systemPrompt`) @@ -38,7 +38,7 @@ Merge-extensible: plugins can declare extra fields on `PromptAssembly` and `Asse - Tool schema providers: `ToolRegistry` registers itself as a tool provider automatically. - The [`system-prompt/assemble` waterfall](#live-events): cooperatively mutate or replace the assembly per caller. -Design rationale: [the prompt-variables RFC](../../../docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). +Design rationale: [the prompt-variables Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). ## Model Experience diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 1acb633a59..6f0959c54a 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -16,9 +16,9 @@ tools: ### Public API - `ctx.tools.register(definition: ToolDefinition): () => void` Register a trusted typed same-process definition. The layer is the calling context's scope: a plain plugin context registers globally; an agent's `agent.ctx` registers for that agent alone, shadowing a same-named global tool there. Duplicate names within one layer throw; non-native modes also reject the reserved `run_code` transport name. `timeoutMs`, when present, must be positive and finite. Disposed with the calling fiber. -- `ctx.tools.restrict(filter)` applies an agent-scoped allow/deny mask to global tools and throws from a plain context. The filter is snapshotted at registration; multiple masks intersect and scope-local tools merge afterwards. Deny masks admit later unnamed globals, while allow masks exclude later names. Unknown, local, or reserved names and empty filters reject. This is live visibility composition, not an authority boundary; see the [scope security non-goal](../../../docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals). +- `ctx.tools.restrict(filter)` applies an agent-scoped allow/deny mask to global tools and throws from a plain context. The filter is snapshotted at registration; multiple masks intersect and scope-local tools merge afterwards. Deny masks admit later unnamed globals, while allow masks exclude later names. Unknown, local, or reserved names and empty filters reject. This is live visibility composition, not an authority boundary; see the [scope security non-goal](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals). - `ctx.tools.get(name: string, scope?: ScopeKey): ToolDefinition | undefined` Resolution as one scope sees it (shadowing applied; a restricted-away global reads as absent) — presenters pass the calling agent so the card matches what executed. -- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog RFC](../../../docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md)). +- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog Agent Note](../../../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md)). - `ctx.tools.guard(guard: ToolGuard): () => void` Register a monotonic synchronous execution guard after `tools/pre-execute`: returning a reason denies the call, while `undefined` leaves it unchanged. A plain-context guard applies globally; an `agent.ctx` guard applies only to that agent. Later waterfall listeners cannot turn a guard denial back into permission. Disposed with the calling fiber. - `ctx.tools.execute(exec)` losslessly snapshots and freezes arguments, assigns an opaque token, runs the complete policy/dispatch/result pipeline, then independently snapshots the authoritative outcome before final observation. Invalid arguments use the same result path without reaching policy or the body; around wrappers may replace only `signal`. - `ctx.tools.executionMode(exec)` returns `parallel` only when the visible definition's `isConcurrencySafe(exec.arguments)` classifier returns exactly `true`; unknown, hidden, undeclared, invalid, or throwing classifications are exclusive. @@ -88,7 +88,7 @@ See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, an Optional `timeoutMs` must be positive and finite; it is policy metadata, not model-visible schema. -Optional `isConcurrencySafe(args)` receives typed, softly validated arguments. Exact `true` permits concurrent dispatch/body execution; invalid input and all other outcomes remain exclusive. Opted-in bodies do not mutate parent-owned state, and shared-state races must commute or fail closed. The [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the full safety contract. +Optional `isConcurrencySafe(args)` receives typed, softly validated arguments. Exact `true` permits concurrent dispatch/body execution; invalid input and all other outcomes remain exclusive. Opted-in bodies do not mutate parent-owned state, and shared-state races must commute or fail closed. The [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the full safety contract. ### Structured-output schema subset @@ -101,11 +101,11 @@ Tools optionally own pure `presentCall()` and `presentResult()` render intents, - Call views are `{ card: 'generic', title, kind?, rawInput?, content?, locations? }`, `{ card: 'terminal', title, description?, cwd? }`, or `{ card: 'diff', title, diffs, locations? }`. - Result views are `{ card: 'generic', title?, content? }`, `{ card: 'terminal', title?, output?, exitCode?, signal? }`, or `{ card: 'diff', title?, diffs }`. -Returning `undefined` selects generic fallback. Presenters depend only on their arguments because UIs call them during live streaming and log replay. Result presentation may read JSON-serializable `result.meta`, which persists with the result; `defineTool` soft-validates older logged arguments and falls back instead of crashing replay. `dsh-tool-bash` and `dsh-tool-fs` are the reference implementations; the [render-intent RFC](../../../docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md) owns the rationale. +Returning `undefined` selects generic fallback. Presenters depend only on their arguments because UIs call them during live streaming and log replay. Result presentation may read JSON-serializable `result.meta`, which persists with the result; `defineTool` soft-validates older logged arguments and falls back instead of crashing replay. `dsh-tool-bash` and `dsh-tool-fs` are the reference implementations; the [render-intent Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md) owns the rationale. ### Code Mode -Under `code` or `both`, the registry exposes the reserved `run_code` transport and a deterministic TypeScript SDK for the current scope; only program output re-enters model context. Each JSON-normalized binding re-enters the complete tool pipeline sequentially with logged correlation to the outer call. Denials reject that binding, ordinary side effects are not rolled back, and sub-call `additionalContexts` are deferred through the parent result to preserve call/result adjacency. Run settlement aborts and drains outstanding bindings; failures surface as `CodeRunFailedError`. See the [Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) and [code-runtime seam](../../code-runtime/README.md). Try `pnpm run demo:code-mode`. +Under `code` or `both`, the registry exposes the reserved `run_code` transport and a deterministic TypeScript SDK for the current scope; only program output re-enters model context. Each JSON-normalized binding re-enters the complete tool pipeline sequentially with logged correlation to the outer call. Denials reject that binding, ordinary side effects are not rolled back, and sub-call `additionalContexts` are deferred through the parent result to preserve call/result adjacency. Run settlement aborts and drains outstanding bindings; failures surface as `CodeRunFailedError`. See the [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md) and [code-runtime seam](../../code-runtime/README.md). Try `pnpm run demo:code-mode`. - **The SDK section** (`tools:sdk`, order 150): a lazy prompt section regenerating, at each assembly, a `declare const tools: {...}` TypeScript declaration of the calling scope's visible end capabilities (exotic names via quoted keys), plus fixed usage instructions. Deterministic — lexicographic tool order, byte-identical text for an unchanged tool set (prefix-cache-friendly). The codegen (`jsonSchemaToTs`, exported) is total: constructs outside the `defineTool` subset degrade to `unknown`, never throw. - **The dispatch bridge** (`run_code`'s execute): every binding call is JSON-normalized before dispatch (a value that does not survive — `BigInt`, circulars — rejects that one call, so the dispatched form and logged form are the same JSON value by construction), serialized through a per-run queue (even `Promise.all` executes underlying calls one at a time in submission order), given the outer execution's opaque token as `parent`, and run through the complete pre-execute → guards → execute → post-execute → result pipeline. A denial reaches the program as a binding rejection, and each sub-call is logged as a `tool/code-dispatch` session event with deterministic id `<parent>:code:<n>`; `deriveMessages()` does not surface that event. Token correlation lets commit-style observers defer an inner success until the final `run_code` result without exposing the live outer execution; ordinary tool side effects are not rolled back. Every sub-call `additionalContexts` entry is deferred through the outer `ToolRunContext` in dispatch order; the loop appends those contexts only after the parent `run_code` result, preserving adjacency and retaining each source/envelope/meta even when the program later fails. @@ -113,7 +113,7 @@ Under `code` or `both`, the registry exposes the reserved `run_code` transport a ### Parallel execution -The agent loop groups consecutive `parallel` calls into a bounded rolling pool and treats each `exclusive` call as an ordering barrier. Only dispatch/body overlaps; policy, durable results, and context retain model order. Code Mode bindings remain serial. The [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the shipped declarations and rationale. +The agent loop groups consecutive `parallel` calls into a bounded rolling pool and treats each `exclusive` call as an ordering barrier. Only dispatch/body overlaps; policy, durable results, and context retain model order. Code Mode bindings remain serial. The [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the shipped declarations and rationale. ## Model Experience @@ -177,9 +177,9 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work - **Concurrency policy is not an event seam** — `executionMode()` reads the resolved tool definition directly; plugins can only declare a classifier on definitions they own. -- **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md). +- **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md). - **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and preserves `default` as a model-visible JSON Schema annotation without applying it during validation; dynamic Cordis mounts may supply defaults even though first-party definitions do not, while raw-registered JSON-Schema tools validate their own input. - **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper. - **Code Mode is TypeScript-only and the presentation mode is service-wide** — `mode: code`/`both` rejects prompt assembly unless `ctx.codeRuntime.language === 'typescript'`; scoped restrictions/shadows still choose each agent's visible bindings, but one tool cannot be native-only while another is code-only. - **Code Mode bindings return text only** — non-text content blocks in a sub-call result collapse to `[<type> content]` placeholders. -- **`run_code` state is fresh per run** — a persistent REPL-style kernel is rejected for the MVP (cross-call state would be invisible to the log); see [the Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md). +- **`run_code` state is fresh per run** — a persistent REPL-style kernel is rejected for the MVP (cross-call state would be invisible to the log); see [the Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md). diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index 5fc045ace2..4e7ae12898 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -139,7 +139,7 @@ export interface ToolDefinition extends ToolSchema { * Opted-in executions must not mutate parent-owned state. Shared state must * tolerate concurrent dispatch; recorder races are permitted only when they * commute or fail closed. See the - * [parallel-tool-call RFC](../../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) + * [parallel-tool-call Agent Note](../../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) * for the full contract. * @param args - parsed arguments; `defineTool` validates before calling. * @returns Whether this call may join a parallel group. diff --git a/packages/core/tools/src/ts-types.ts b/packages/core/tools/src/ts-types.ts index bd8c08ed62..e5f67d0891 100644 --- a/packages/core/tools/src/ts-types.ts +++ b/packages/core/tools/src/ts-types.ts @@ -75,7 +75,7 @@ export function jsonSchemaToTs(schema: unknown, indent = 0): string { } } -/** The fixed model-facing usage contract rendered above the declarations (see the Code Mode RFC's "What the model sees"). */ +/** The fixed model-facing usage contract rendered above the declarations (see the Code Mode Agent Note's "What the model sees"). */ const SDK_INSTRUCTIONS = `## Writing code for run_code Pass \`run_code\` the body of an async TypeScript function (erasable syntax only — no \`enum\` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program: diff --git a/packages/core/tools/tests/code-mode.spec.ts b/packages/core/tools/tests/code-mode.spec.ts index bbc19d5d75..cfe317ef02 100644 --- a/packages/core/tools/tests/code-mode.spec.ts +++ b/packages/core/tools/tests/code-mode.spec.ts @@ -13,7 +13,7 @@ import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEventMap } from '@deepseek-ai/dsh-session' /** - * Code Mode unit tier (per the RFC's plan): provider contribution per mode, + * Code Mode unit tier (per the Agent Note's plan): provider contribution per mode, * misconfiguration rejections, the run_code dispatch bridge (serialization, * abort, JSON normalization, error mapping, events, quiescence), and HMR * safety — all against an in-repo fake runtime, exactly the diff --git a/packages/core/tools/tests/properties.spec.ts b/packages/core/tools/tests/properties.spec.ts index f5fce4d382..51b49fccd4 100644 --- a/packages/core/tools/tests/properties.spec.ts +++ b/packages/core/tools/tests/properties.spec.ts @@ -1,8 +1,8 @@ /** - * Property-based tests for the tool-schema DSL (the property-testing RFC), including + * Property-based tests for the tool-schema DSL (the property-testing Agent Note), including * the the property-testing ↔ runtime-validation composition composition: generated args that satisfy a SchemaSpec must * pass validateArgs, and targeted corruptions must be rejected. This closes the - * validator/InferArgs drift risk noted in the arg-validation RFC. + * validator/InferArgs drift risk noted in the arg-validation Agent Note. */ import { describe, expect, it } from 'vitest' diff --git a/packages/core/tools/tests/tools.spec.ts b/packages/core/tools/tests/tools.spec.ts index 3de73c3326..b936887bc9 100644 --- a/packages/core/tools/tests/tools.spec.ts +++ b/packages/core/tools/tests/tools.spec.ts @@ -1174,7 +1174,7 @@ describe('ToolRegistry.get', () => { }) }) -describe('validateArgs (the runtime-validation RFC, part 1)', () => { +describe('validateArgs (the runtime-validation Agent Note, part 1)', () => { it('returns [] for valid args and is total over malformed input', () => { const spec = { path: { type: 'string', required: true }, @@ -1274,7 +1274,7 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => { }) }) -describe('defineTool validation (the runtime-validation RFC, part 1)', () => { +describe('defineTool validation (the runtime-validation Agent Note, part 1)', () => { it('returns an isError result with the violations when the model sends bad args', async () => { const ctx = await setup() ctx.tools.register(defineTool({ diff --git a/packages/examples/acp-demo/README.md b/packages/examples/acp-demo/README.md index 9ef18739c8..a68fe145c3 100644 --- a/packages/examples/acp-demo/README.md +++ b/packages/examples/acp-demo/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-acp-demo -The **ACP server app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../../examples/agent-spine-demo/README.md)) with the front-door cluster an [Agent Client Protocol](../../ui/acp/README.md) server needs, and a `bin` that boots a leaf `cordis.yml` speaking ACP JSON-RPC on stdio. +The **ACP server app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md)) with the front-door cluster an [Agent Client Protocol](../../ui/acp/README.md) server needs, and a `bin` that boots a leaf `cordis.yml` speaking ACP JSON-RPC on stdio. It is the structured counterpart to [`@deepseek-ai/dsh-stdio-demo`](../stdio-demo/README.md): both consume the same spine, but this one bakes in the OPPOSITE front-door cluster. diff --git a/packages/examples/agent-spine-demo/README.md b/packages/examples/agent-spine-demo/README.md index 76efd77845..9c431d5698 100644 --- a/packages/examples/agent-spine-demo/README.md +++ b/packages/examples/agent-spine-demo/README.md @@ -34,9 +34,9 @@ The spine is everything COMMON to every front door. The swappable and front-door - **the LLM adapter** — the bundle ships the abstract `llm` service; the leaf registers a concrete adapter on `ctx.llm` (`llm-deepseek`, `llm-pi-ai`, `llm-replay`). - **the bash executor** — the bundle ships `tool-bash` (the consumer schema); the leaf provides `ctx.bash` (`bash-local` or a sandboxed impl). - **non-local skill providers** — the bundle ships the skill registry, the local filesystem provider, and the `skill` tool; deployments can add other providers such as embedded or remote catalogs as siblings. -- **presentation + per-app infra** — the terminal (`dsh-tui` / `dsh-stdio`) or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-stdio-demo`](../../examples/stdio-demo/README.md), [`dsh-acp-demo`](../../examples/acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside. +- **presentation + per-app infra** — the terminal (`dsh-tui` / `dsh-stdio`) or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-stdio-demo`](../stdio-demo/README.md), [`dsh-acp-demo`](../acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside. -This is the [interface/implementation/consumer seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door. +This is the [interface/implementation/consumer seam](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door. ## Config diff --git a/packages/examples/jsonrpc-demo/README.md b/packages/examples/jsonrpc-demo/README.md index 364b24550c..083d9a83ce 100644 --- a/packages/examples/jsonrpc-demo/README.md +++ b/packages/examples/jsonrpc-demo/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-jsonrpc-demo -Bin-only app that boots an external `cordis.yml`; its [`jsonrpc`](../../ui/jsonrpc/README.md) entry serves SDK clients over newline-delimited stdio. The config composes the spine, backends, and serving plugin. `lib/bin.js` is also the [single-executable runtime](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) entry. +Bin-only app that boots an external `cordis.yml`; its [`jsonrpc`](../../ui/jsonrpc/README.md) entry serves SDK clients over newline-delimited stdio. The config composes the spine, backends, and serving plugin. `lib/bin.js` is also the [single-executable runtime](../../../.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) entry. ## Config discovery @@ -10,7 +10,7 @@ A config without `dsh-jsonrpc` is valid and serves nothing; the bin does not des ## Exit lifecycle -stdin EOF and `SIGTERM` dispose the root to quiescence and exit 0; `SIGINT` exits 130 after the same disposal. EOF may cut off an in-flight turn as documented in the [distribution RFC](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). The `jsonrpc` plugin owns response-before-exit protocol shutdown; both paths are idempotent and safe to race. +stdin EOF and `SIGTERM` dispose the root to quiescence and exit 0; `SIGINT` exits 130 after the same disposal. EOF may cut off an in-flight turn as documented in the [distribution Agent Note](../../../.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). The `jsonrpc` plugin owns response-before-exit protocol shutdown; both paths are idempotent and safe to race. ## stdout is the protocol diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index 4eafc9e251..2d706e3008 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-stdio-demo -The **terminal chat app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../../examples/agent-spine-demo/README.md)) with JSONL persistence, human interaction, a pre-created `main` agent, and a TTY-selected pi-tui/readline front door. Its `bin` boots a leaf `cordis.yml`. +The **terminal chat app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md)) with JSONL persistence, human interaction, a pre-created `main` agent, and a TTY-selected pi-tui/readline front door. Its `bin` boots a leaf `cordis.yml`. It is the terminal counterpart to [`@deepseek-ai/dsh-acp-demo`](../acp-demo/README.md): both consume the same spine, while ACP reserves stdout for JSON-RPC and creates sessions from the client. diff --git a/packages/fs/fs-local/README.md b/packages/fs/fs-local/README.md index 60cf671a92..47d97266e8 100644 --- a/packages/fs/fs-local/README.md +++ b/packages/fs/fs-local/README.md @@ -12,7 +12,7 @@ await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) ## Behavior -- **`resolve(path, opts?)`** — a relative `path` resolves against `opts.cwd` when the caller supplies one (the model-facing tools pass the calling agent's session cwd — see [the per-session cwd RFC](../../../docs/rfc/implemented/architecture/2026-07-02-fs-per-session-cwd.md)), else `config.cwd` (default `process.cwd()`); an absolute `path` ignores both. `opts.signal` is checked before and after local resolution, while a remote sibling backend may use it to abort its round-trip. The `targetKey` is the file's `realpath`, so two input paths reaching the same file through symlinks share one identity, and writes/edits land on the link target (preserving the link). A not-yet-existing path uses the realpathed parent directory plus basename when the parent exists; only an unresolvable parent falls back to the absolute path. `displayPath` is the absolute (un-resolved) path. +- **`resolve(path, opts?)`** — a relative `path` resolves against `opts.cwd` when the caller supplies one (the model-facing tools pass the calling agent's session cwd — see [the per-session cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)), else `config.cwd` (default `process.cwd()`); an absolute `path` ignores both. `opts.signal` is checked before and after local resolution, while a remote sibling backend may use it to abort its round-trip. The `targetKey` is the file's `realpath`, so two input paths reaching the same file through symlinks share one identity, and writes/edits land on the link target (preserving the link). A not-yet-existing path uses the realpathed parent directory plus basename when the parent exists; only an unresolvable parent falls back to the absolute path. `displayPath` is the absolute (un-resolved) path. - **`stat` / `lstat`** — return target metadata or `undefined` when absent. `stat` reports `FsInfo` for an already resolved target (`version` = an opaque token derived from bigint `dev:ino:size:mtimeNs:ctimeNs`, `type` of `file`/`directory`/`other`, byte `size`); path-shaped `lstat` reports `FsPathInfo` without following the final symlink and can therefore return `symlink`. Both check cancellation before and after their asynchronous metadata probe, so an abort that lands in flight reports `FS_ABORTED` rather than stale absence. - **`readText` / `streamText`** — UTF-8 only. `readText` reads the whole file; `streamText` streams it in chunks (cross-chunk decoding) so a huge file never has to be held whole in memory. Both reject invalid UTF-8 and NUL-byte binary samples (`FS_NOT_TEXT`) and non-regular targets. The `read` tool (`@deepseek-ai/dsh-tool-fs`) decides which to call by size and owns the line windowing. - **`listDir`** — lists one directory level in stable `name.localeCompare()` order. Each entry carries the child basename, type, resolved child target (`displayPath` under the listed directory, `targetKey` as the realpath identity), and cheap stat metadata (`version`, plus `size` for regular files). It never opens or decodes file contents. Missing targets report `FS_NOT_FOUND`, file/special-file targets report `FS_NOT_DIRECTORY`, aborted calls report `FS_ABORTED`, permission failures report `FS_PERMISSION_DENIED`, and other listing or child metadata I/O failures report `FS_IO_ERROR`. Broken/disappeared children are returned as `other` without metadata, but permission/IO failures while resolving a child fail the whole listing with a structured `FsError`. @@ -31,7 +31,7 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work -- **`config.cwd` is not a sandbox** — it is a resolution default, not containment: absolute paths and `..` escape it. Enforce containment with a stricter `ctx.fs` backend or a permission plugin on the `tools/execute` waterfall ([capability-seam RFC](../../../docs/rfc/implemented/architecture/2026-06-17-filesystem-capability-seam.md#consequences)). +- **`config.cwd` is not a sandbox** — it is a resolution default, not containment: absolute paths and `..` escape it. Enforce containment with a stricter `ctx.fs` backend or a permission plugin on the `tools/execute` waterfall ([capability-seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md#consequences)). - **An overwrite reads the whole prior file into memory** — solely as the UI diff basis; bounding that pre-read above a size threshold is deferred (`TODO(overwrite-diff-bound)`). - **Version tokens are `mtimeMs:size`** — an external change that preserves both within the filesystem's timestamp granularity defeats the stale guard. - **`editText` holds the whole file (plus the edited copy) in memory** — streaming exists only on the read path. diff --git a/packages/fs/fs-local/src/index.ts b/packages/fs/fs-local/src/index.ts index bd47b53919..18433f3f7c 100644 --- a/packages/fs/fs-local/src/index.ts +++ b/packages/fs/fs-local/src/index.ts @@ -45,7 +45,7 @@ type ResolvedConfig = Required<Config> /** * The host-filesystem backend. Reads resolve relative paths from {@link Config.cwd} * (a resolution default, NOT a containment boundary — see the filesystem - * capability-seam RFC); enforce + * capability-seam Agent Note); enforce * containment with a stricter backend or a `tools/execute` permission plugin. */ export class LocalFileSystem extends FileSystem { diff --git a/packages/fs/fs-policy/README.md b/packages/fs/fs-policy/README.md index f24bd088eb..9d54491a8b 100644 --- a/packages/fs/fs-policy/README.md +++ b/packages/fs/fs-policy/README.md @@ -68,4 +68,4 @@ Append-only; newly visible content follows the reusable request prefix and does - **Observed state does not survive a session resume** — persistence of the `WeakMap` record is deferred, so a resumed session must re-read files before guarded writes/edits. - **Actors without an agent session can never satisfy the policy** — their edits throw `FS_NOT_OBSERVED` and their writes always resolve `createIfAbsent`, so a non-agent caller cannot overwrite an existing file through the gate. - **Direct `ctx.fs` reads emit no `fs/observed`** — a file read outside the `read` tool stays unobserved, and a later guarded edit rejects with `FS_NOT_OBSERVED` until the tool reads it. -- **Authorization is version freshness, not view completeness** — any windowed read authorizes a full-file overwrite of an unchanged file, deliberately weaker than a full-view rule ([seam-split RFC](../../../docs/rfc/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md)). +- **Authorization is version freshness, not view completeness** — any windowed read authorizes a full-file overwrite of an unchanged file, deliberately weaker than a full-view rule ([seam-split Agent Note](../../../.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md)). diff --git a/packages/fs/fs/README.md b/packages/fs/fs/README.md index 4ea3ec5b9f..9209c237f8 100644 --- a/packages/fs/fs/README.md +++ b/packages/fs/fs/README.md @@ -2,7 +2,7 @@ The **filesystem provider seam**: an abstract `FileSystem` service (`ctx.fs`) defining the storage primitives a backend provides — resolve a path, stat metadata, no-follow path metadata, read/stream text, list directories, write atomically, and apply a literal edit — without saying HOW. Both mutations take their version guard **optionally**, so `ctx.fs` on its own is a complete, unconstrained text-storage seam. This package also owns the `fs/*` policy event vocabulary the tool dispatches and the policy plugin listens for. -This package is the provider-seam layer of the four-layer filesystem stack, split so each concern can evolve (and be swapped) independently (see [the capability-seam RFC](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md), [the filesystem capability-seam RFC](../../../docs/rfc/implemented/architecture/2026-06-17-filesystem-capability-seam.md), [the split-the-filesystem-seam RFC](../../../docs/rfc/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md), and [the file-context event-gate RFC](../../../docs/rfc/implemented/architecture/2026-06-26-file-context-as-event-gate.md)): +This package is the provider-seam layer of the four-layer filesystem stack, split so each concern can evolve (and be swapped) independently (see [the capability-seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md), [the filesystem capability-seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md), [the split-the-filesystem-seam Agent Note](../../../.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md), and [the file-context event-gate Agent Note](../../../.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md)): | Layer | Package | Role | |---|---|---| @@ -42,7 +42,7 @@ This package declares three events (see the generated [events catalog](../../../ ## Vocabulary -`FsTargetKey` / `FsVersion` are branded opaque ids ([the branded-ids RFC](../../../docs/rfc/implemented/architecture/2026-06-20-branded-ids.md)) — consumers must not parse `targetKey` or interpret `version`; only `displayPath` is for model/UI output. `FsWriteIntent` is the explicit GUARDED write intent (`createIfAbsent` creates a missing target and rejects an existing one with `FS_NOT_OBSERVED`; `replaceIfVersion` replaces only at the observed version, else `FS_STALE_VERSION`); omitting it from `writeText` is the third, unconditional state. `FsPathInfo` is the no-follow metadata shape that can report `symlink`, unlike target-level `FsInfo`. Failures throw `FsError` (extends `HarnessError`, [the structured error taxonomy RFC](../../../docs/rfc/implemented/architecture/2026-06-11-structured-error-taxonomy.md)) carrying a stable `FsErrorCode` (`FS_NOT_FOUND`, `FS_NOT_DIRECTORY`, `FS_NOT_TEXT`, `FS_NOT_REGULAR_FILE`, `FS_PERMISSION_DENIED`, `FS_IO_ERROR`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, `FS_ABORTED`); the tool registry surfaces `{ name, code }` on `isError` results. See `src/types.ts` for the full contracts. +`FsTargetKey` / `FsVersion` are branded opaque ids ([the branded-ids Agent Note](../../../.agents/notes/implemented/architecture/2026-06-20-branded-ids.md)) — consumers must not parse `targetKey` or interpret `version`; only `displayPath` is for model/UI output. `FsWriteIntent` is the explicit GUARDED write intent (`createIfAbsent` creates a missing target and rejects an existing one with `FS_NOT_OBSERVED`; `replaceIfVersion` replaces only at the observed version, else `FS_STALE_VERSION`); omitting it from `writeText` is the third, unconditional state. `FsPathInfo` is the no-follow metadata shape that can report `symlink`, unlike target-level `FsInfo`. Failures throw `FsError` (extends `HarnessError`, [the structured error taxonomy Agent Note](../../../.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md)) carrying a stable `FsErrorCode` (`FS_NOT_FOUND`, `FS_NOT_DIRECTORY`, `FS_NOT_TEXT`, `FS_NOT_REGULAR_FILE`, `FS_PERMISSION_DENIED`, `FS_IO_ERROR`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, `FS_ABORTED`); the tool registry surfaces `{ name, code }` on `isError` results. See `src/types.ts` for the full contracts. ## Model Experience @@ -54,7 +54,7 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work -- **Text-only by contract** — backends reject binary/non-UTF-8 content with `FS_NOT_TEXT`; binary-safe operations are a deliberate deferral of [the tool-schemas RFC](../../../docs/rfc/implemented/feature/2026-06-17-filesystem-tool-schemas.md). -- **Eight primitives only** — no delete, rename/move, copy, or watch; `listDir` is single-level, with recursion, globbing, pagination, and search out of scope per [the directory-listing RFC](../../../docs/rfc/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md). +- **Text-only by contract** — backends reject binary/non-UTF-8 content with `FS_NOT_TEXT`; binary-safe operations are a deliberate deferral of [the tool-schemas Agent Note](../../../.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md). +- **Eight primitives only** — no delete, rename/move, copy, or watch; `listDir` is single-level, with recursion, globbing, pagination, and search out of scope per [the directory-listing Agent Note](../../../.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md). - **No IO deadline** — the seam arms no timeout; cancellation is a best-effort optional `AbortSignal` per primitive (the deliberate [fs-family stance](../README.md)). - **Resolve-then-operate costs a remote backend two round-trips per tool call** — folding or caching resolution is left to such a backend. diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 16535c446d..6dd22d384f 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -22,7 +22,7 @@ All keys are optional; the defaults are the shipped read caps. | `readMaxBytes` | `51200` | Byte cap on one `read` call's selected lines; overflow ends the window with a "capped" footer. | | `readStreamMinSize` | `10485760` | Files at or above this size (or with unknown size) stream instead of loading whole into memory. | -## Tools (schemas per [the filesystem tool schemas RFC](../../../docs/rfc/implemented/feature/2026-06-17-filesystem-tool-schemas.md)) +## Tools (schemas per [the filesystem tool schemas Agent Note](../../../.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md)) | Tool | Arguments | Behavior | |---|---|---| @@ -34,7 +34,7 @@ Field names are snake_case to match Claude Code and existing harness tool schema ## The tool is the executor; policy is an event gate -The tools do **not** inject a policy service or inspect any cache. Each tool resolves the path via `ctx.fs.resolve(path, { cwd, signal })` — passing the calling agent's session cwd (`exec.agent.session.header.cwd`) so a relative path resolves against the session's workspace, matching `dsh-tool-bash`, and forwarding tool cancellation through resolution (see [the per-session cwd RFC](../../../docs/rfc/implemented/architecture/2026-07-02-fs-per-session-cwd.md)) — then: +The tools do **not** inject a policy service or inspect any cache. Each tool resolves the path via `ctx.fs.resolve(path, { cwd, signal })` — passing the calling agent's session cwd (`exec.agent.session.header.cwd`) so a relative path resolves against the session's workspace, matching `dsh-tool-bash`, and forwarding tool cancellation through resolution (see [the per-session cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)) — then: - **read** — one `ctx.fs.stat` (type + size routing + version), then `readText`/`streamText`, then builds the line window, then emits `fs/observed` with a plain `ctx.emit`. (1 stat.) - **write** — `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` for the optional guard, then `ctx.fs.writeText(target, content, intent)`, then `fs/observed`. (0 stat.) @@ -46,7 +46,7 @@ The tool passes `exec` (the tool-execution context) as the opaque `actor` on eve `fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event. -`read` opts into concurrent scheduling because its only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). +`read` opts into concurrent scheduling because its only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md). The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index 4c868654fc..30944c2254 100644 --- a/packages/guard/repeat-tool-guard/README.md +++ b/packages/guard/repeat-tool-guard/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-repeat-tool-guard -An advisory loop-breaker, not a model-facing tool: it never appears in the tool list, never vetoes or rewrites a call, and adds exactly one behavior — it watches each agent's stream of tool calls, counts runs of consecutive calls to the same tool with identical canonicalized arguments, and at configured run lengths injects an escalating advisory reminder telling the model to stop repeating itself, re-read the last result, and either change approach or conclude. The decision (retry differently, gather more evidence, or finish) stays entirely with the model: a legitimately repeated call is delayed by nothing and blocked by nothing. Decision record: [the repeat-tool-guard RFC](../../../docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md). +An advisory loop-breaker, not a model-facing tool: it never appears in the tool list, never vetoes or rewrites a call, and adds exactly one behavior — it watches each agent's stream of tool calls, counts runs of consecutive calls to the same tool with identical canonicalized arguments, and at configured run lengths injects an escalating advisory reminder telling the model to stop repeating itself, re-read the last result, and either change approach or conclude. The decision (retry differently, gather more evidence, or finish) stays entirely with the model: a legitimately repeated call is delayed by nothing and blocked by nothing. Decision record: [the repeat-tool-guard Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md). ## Config diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index 2279f53ade..dc9a047a4f 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -2,7 +2,7 @@ * Advisory per-agent repeat-call detector. It enriches post-execute decisions * with logged model context without vetoing or rewriting calls. Configuration * and chain semantics live in the package README; rationale lives in the - * repeat-tool-guard RFC. + * repeat-tool-guard Agent Note. * @module @deepseek-ai/dsh-repeat-tool-guard */ diff --git a/packages/hooks/README.md b/packages/hooks/README.md index b483964c32..0bd64e3f99 100644 --- a/packages/hooks/README.md +++ b/packages/hooks/README.md @@ -1,6 +1,6 @@ # hooks/ — hook bridges + shared protocol -The hooks subsystem lets users extend the agent at lifecycle points the way Claude Code and Codex do — by pointing a bridge plugin at an existing `hooks.json` (or settings) so those external shell hooks run faithfully. The canonical extension surface itself is the harness's typed interception seams ([the interception-seams RFC](../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)); a "native hook" is just an ordinary cordis plugin on those seams. These packages are the **bridges** that translate the external shell-hook protocol onto that same surface, plus the shared wire-protocol library they build on. +The hooks subsystem lets users extend the agent at lifecycle points the way Claude Code and Codex do — by pointing a bridge plugin at an existing `hooks.json` (or settings) so those external shell hooks run faithfully. The canonical extension surface itself is the harness's typed interception seams ([the interception-seams Agent Note](../../.agents/notes/implemented/feature/2026-06-30-interception-seams.md)); a "native hook" is just an ordinary cordis plugin on those seams. These packages are the **bridges** that translate the external shell-hook protocol onto that same surface, plus the shared wire-protocol library they build on. | Package | Role | Shape | |---|---|---| diff --git a/packages/hooks/hook-protocol/README.md b/packages/hooks/hook-protocol/README.md index b36059bd4f..cae3f5e6b6 100644 --- a/packages/hooks/hook-protocol/README.md +++ b/packages/hooks/hook-protocol/README.md @@ -27,7 +27,7 @@ Why a shared lib at all: Codex deliberately reimplements a *subset* of the Claud Declaration-merged into `SessionEventMap` (log-only, like `compact/*` — NOT a `SurfaceEventType`, no `surfaceOp`): `hook/invoked` (a hook command ran) and `hook/result` (its outcome, paired by `handlerId`, with `appendHookResult` owning the decision rule). Payloads and per-event JSDoc are in the generated [persistence log event catalog](../../../docs/persistence-catalog.md); `stderrSummary` is truncated to the record's `stderrSummaryMaxChars` (the bridge's config, reference default `DEFAULT_STDERR_SUMMARY_MAX_CHARS` = 500; omitted when empty). -Like every event they must sit inside an open turn. The mid-turn points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn by construction; `SessionStart` gets no `hook/*` record (its injected `context/message` is the durable evidence) — see the hooks RFC. +Like every event they must sit inside an open turn. The mid-turn points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn by construction; `SessionStart` gets no `hook/*` record (its injected `context/message` is the durable evidence) — see the hooks Agent Note. ## Model Experience @@ -39,5 +39,5 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work -- **`HookOutput.updatedInput` is parsed but not honored** — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)); a bridge logs + warns when a hook sets it. See `src/types.ts` for the full contracts. +- **`HookOutput.updatedInput` is parsed but not honored** — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)); a bridge logs + warns when a hook sets it. See `src/types.ts` for the full contracts. - **An invalid matcher regex matches nothing, silently** — `matchesMatcher` never throws; surfacing the error needs a diagnostic-returning variant or parse-time validation (`TODO(matcher-diagnostics)`). diff --git a/packages/hooks/hook-protocol/src/types.ts b/packages/hooks/hook-protocol/src/types.ts index 7458419a01..e14473b3e1 100644 --- a/packages/hooks/hook-protocol/src/types.ts +++ b/packages/hooks/hook-protocol/src/types.ts @@ -43,7 +43,7 @@ declare module '@deepseek-ai/dsh-session' { /** * The bridge that ran a hook — the CC bridge stamps `'claude'`, the Codex * bridge `'codex'`. A native plugin on the interception seams is not a bridge - * and writes no `hook/*` provenance (see the interception-seams RFC). + * and writes no `hook/*` provenance (see the interception-seams Agent Note). */ export type HookDialect = 'claude' | 'codex' @@ -130,7 +130,7 @@ export interface HookOutput { systemMessage?: string /** * A tool-input rewrite a hook requested (CC `updatedInput`). PARSED but NOT - * honored — input rewrite is deferred (see the interception-seams RFC); a + * honored — input rewrite is deferred (see the interception-seams Agent Note); a * bridge logs + warns when this is present. */ updatedInput?: Record<string, unknown> diff --git a/packages/hooks/hooks-claude/README.md b/packages/hooks/hooks-claude/README.md index 96c0362023..b492b2939d 100644 --- a/packages/hooks/hooks-claude/README.md +++ b/packages/hooks/hooks-claude/README.md @@ -2,7 +2,7 @@ A cordis plugin that runs the supported command-hook subset of a user's existing **Claude Code** hook config (a `hooks.json`, or a settings file's `hooks` key) on the harness's canonical interception seams. It is the **CC dialect** half of the hooks subsystem: it owns the bridge's CC-shaped per-event stdin payloads, CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the mapping from a hook's neutral outcome onto the harness's typed Decisions. The dialect-agnostic primitives (matcher, exit-code/stdout codec, `ctx.bash` execution, most-restrictive merge, the `hook/*` events) come from [`@deepseek-ai/dsh-hook-protocol`](../hook-protocol/README.md). -A native cordis plugin could do everything this bridge does — more powerfully, with typed returns and no serialization boundary. **The bridge exists only as a compatibility path for the mapped CC command-hook subset**; anything bespoke should be a native plugin on the same seams (see [the interception-seams RFC](../../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)). +A native cordis plugin could do everything this bridge does — more powerfully, with typed returns and no serialization boundary. **The bridge exists only as a compatibility path for the mapped CC command-hook subset**; anything bespoke should be a native plugin on the same seams (see [the interception-seams Agent Note](../../../.agents/notes/implemented/feature/2026-06-30-interception-seams.md)). ## Config @@ -44,7 +44,7 @@ The hooks **themselves** run in the agent's session workspace: for the agent-sco The three emit points run detached — no seam awaits a `SessionStart`/`SubagentStart`/`SubagentStop` hook. Each run chain is tracked, and disposing the bridge aborts still-running hook processes, then drains the continuations before the dispose resolves (`createDetachedRuns` in `dsh-hook-protocol`). -The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the RFC's "run serially, not concurrently" note). +The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the Agent Note's "run serially, not concurrently" note). Every agent-scoped stdin payload carries `session_id` and string-shaped `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `''`. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn. @@ -87,7 +87,7 @@ A blocked prompt sends no request and invalidates nothing. Denial, feedback, and - **Unsupported hook events (23 of Claude Code's current 30):** `Setup`, `InstructionsLoaded`, `UserPromptExpansion`, `MessageDisplay`, `PermissionRequest`, `PostToolUseFailure`, `PostToolBatch`, `PermissionDenied`, `Notification`, `TaskCreated`, `TaskCompleted`, `StopFailure`, `TeammateIdle`, `ConfigChange`, `CwdChanged`, `FileChanged`, `WorktreeCreate`, `WorktreeRemove`, `PreCompact`, `PostCompact`, `SessionEnd`, `Elicitation`, and `ElicitationResult`. Config for these events is parsed but never dispatched. The comparison baseline is Claude Code's [official hook-event reference](https://code.claude.com/docs/en/hooks#hook-events). - **`SessionStart` is partial:** JSON `additionalContext` is consumed, but plain stdout context, `initialUserMessage`, `sessionTitle`, `watchPaths`, `reloadSkills`, and `CLAUDE_ENV_FILE` are unsupported. The hook runs detached, so context can miss the first request (`TODO(session-start-gating)`), and the payload omits current optional fields such as `model`, `agent_type`, and `session_title`. - **`UserPromptSubmit` is partial:** blocking and JSON `additionalContext` work, but plain stdout context, `sessionTitle`, and `suppressOriginalPrompt` are unsupported. Unless overridden, the bridge also uses its 600-second default instead of Claude Code's event-specific 30-second command timeout. -- **`PreToolUse` is partial:** `deny` and `ask` decisions work; `allow` does not pre-approve, `defer` is unsupported, `additionalContext` is ignored, and `updatedInput` is logged + warned but not honored ([the pre-tool-input-rewrite RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)). +- **`PreToolUse` is partial:** `deny` and `ask` decisions work; `allow` does not pre-approve, `defer` is unsupported, `additionalContext` is ignored, and `updatedInput` is logged + warned but not honored ([the pre-tool-input-rewrite Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)). - **`PostToolUse` is partial:** blocking feedback and JSON `additionalContext` work, but `updatedToolOutput` and `updatedMCPToolOutput` are unsupported and `tool_response` is flattened to text. - **`SubagentStart` and `SubagentStop` are partial:** both report a constant `agent_type` of `general-purpose` and use the child session id where Claude Code reports the parent session. Start context is best-effort and can only reach a live in-process child, while stop is observe-only and cannot block the subagent or feed it context. Start omits `transcript_path`; stop also omits `agent_transcript_path`, `last_assistant_message`, `background_tasks`, and `session_crons` and always reports `stop_hook_active: false`. - **`Stop` is partial:** blocking forces another model turn, but `stop_hook_active` is always `false`, `last_assistant_message`, `background_tasks`, and `session_crons` are omitted, and the consecutive-block cap is not implemented (`TODO(stop-loop-guard)`). An unconditionally blocking hook therefore force-continues every step unless it self-limits. diff --git a/packages/hooks/hooks-claude/src/index.ts b/packages/hooks/hooks-claude/src/index.ts index 121e5cf75a..03ac21fea6 100644 --- a/packages/hooks/hooks-claude/src/index.ts +++ b/packages/hooks/hooks-claude/src/index.ts @@ -5,7 +5,7 @@ * mapping; shared execution and parsing live in `dsh-hook-protocol`. * `updatedInput` is logged and warned but not honored. Bespoke behavior should * use typed native plugins on the same seams; see the - * [hook-bridges RFC](../../../../docs/rfc/implemented/feature/2026-06-30-hook-bridges.md). + * [hook-bridges Agent Note](../../../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md). * @module @deepseek-ai/dsh-hooks-claude */ diff --git a/packages/hooks/hooks-codex/README.md b/packages/hooks/hooks-codex/README.md index 0e69362c36..0c8c4c16ba 100644 --- a/packages/hooks/hooks-codex/README.md +++ b/packages/hooks/hooks-codex/README.md @@ -10,7 +10,7 @@ This bridge implements a deliberate subset of Codex's current hook protocol: - **No Codex plugin env injection and no config-time placeholder substitution** (the command still receives the executor's environment and runs through its shell). - **No pre-tool approval or rewrite path** — a hook can block, but the bridge does not pre-approve or replace tool input. -A native cordis plugin could do everything this bridge does, more powerfully; the bridge exists only as a compatibility path for the mapped Codex subset (see [the interception-seams RFC](../../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)). +A native cordis plugin could do everything this bridge does, more powerfully; the bridge exists only as a compatibility path for the mapped Codex subset (see [the interception-seams Agent Note](../../../.agents/notes/implemented/feature/2026-06-30-interception-seams.md)). ## Config diff --git a/packages/hooks/hooks-codex/src/index.ts b/packages/hooks/hooks-codex/src/index.ts index 8fa89a469d..75c33e2d92 100644 --- a/packages/hooks/hooks-codex/src/index.ts +++ b/packages/hooks/hooks-codex/src/index.ts @@ -5,7 +5,7 @@ * or command substitution, and no pre-tool approval or rewrite path; only * blocking decisions are honored. Shared execution and parsing live in * `dsh-hook-protocol`; see the - * [hook-bridges RFC](../../../../docs/rfc/implemented/feature/2026-06-30-hook-bridges.md). + * [hook-bridges Agent Note](../../../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md). * @module @deepseek-ai/dsh-hooks-codex */ diff --git a/packages/llm/README.md b/packages/llm/README.md index 4a5e6769e2..ac08ffafc2 100644 --- a/packages/llm/README.md +++ b/packages/llm/README.md @@ -9,4 +9,4 @@ The LLM seam and its provider adapters. The interface package (`llm`) owns the a | `llm-deepseek/` | DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on `ctx.llm`) | | `llm-pi-ai/` | Multi-provider adapter via `@earendil-works/pi-ai` | (registers on `ctx.llm`) | -The interface lives at `llm/llm/`; adapters and the reusable token meter are flat siblings under the group. Requests route by `provider`, while `model` is passed through to the selected adapter. A new provider adapter joins here and registers one or more provider routes on `ctx.llm` without touching the interface. See [twin LLM adapters](../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the contract-validation origin of the two shipping implementations and the [replay token meter RFC](../../docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md) for measurement ownership. +The interface lives at `llm/llm/`; adapters and the reusable token meter are flat siblings under the group. Requests route by `provider`, while `model` is passed through to the selected adapter. A new provider adapter joins here and registers one or more provider routes on `ctx.llm` without touching the interface. See [twin LLM adapters](../../.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the contract-validation origin of the two shipping implementations and the [replay token meter Agent Note](../../.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md) for measurement ownership. diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 24a8879aa3..f9142dbc52 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -40,7 +40,7 @@ Streaming is a raw chunk protocol (`block-start`, `text-delta`, `reasoning-delta ### App attribution (`attribution.ts`) -Every product adapter sends application identity on provider HTTP requests. `attributionHeaders(identity?)` builds the standard `User-Agent`, defaulting to public `APP_IDENTITY`; white-label deployments may replace but not suppress it. Adapters verify the wire header directly or through their library hook. See [the attribution RFC](../../../docs/rfc/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md). +Every product adapter sends application identity on provider HTTP requests. `attributionHeaders(identity?)` builds the standard `User-Agent`, defaulting to public `APP_IDENTITY`; white-label deployments may replace but not suppress it. Adapters verify the wire header directly or through their library hook. See [the attribution Agent Note](../../../.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md). ### Classes @@ -52,7 +52,7 @@ Every product adapter sends application identity on provider HTTP requests. `att ### Real adapters -Two adapters implement `LlmAdapter` on different internals: [`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) uses hand-rolled fetch/SSE for the `deepseek` route, while [`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) dynamically resolves configured provider/model pairs through `@earendil-works/pi-ai`. Both follow the `StreamChunk` conventions in `types.ts`: usage precedes finish, tool arguments remain raw strings, and errors take one of two sanctioned paths. See [the twin LLM adapters](../../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the design rationale. +Two adapters implement `LlmAdapter` on different internals: [`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) uses hand-rolled fetch/SSE for the `deepseek` route, while [`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) dynamically resolves configured provider/model pairs through `@earendil-works/pi-ai`. Both follow the `StreamChunk` conventions in `types.ts`: usage precedes finish, tool arguments remain raw strings, and errors take one of two sanctioned paths. See [the twin LLM adapters](../../../.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the design rationale. ## Model Experience @@ -65,8 +65,8 @@ Pass-through; the registry preserves the assembled request prefix, while the sel ## Known Limitations and Deferred Work - **No default retry/caching/rate-limit policy ships in this service** — `llm/stream` remains the call-wrapper seam; the agent loop separately offers proven model-request failures to `agent/request-error`, whose default preserves the original failure. -- **`GenerateOptions` sampling is `temperature`/`maxTokens`/`stop` only** — no `tool_choice`, `top_p`, or penalty fields; the vocabulary grows when a producer lands ([dropped inert knobs](../../../docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md)). -- **Producer-gated variants stay out until produced** — `prefill`, per-tool `strict`, block `cache` hints, and the `agent` message-source variant were pruned as producerless ([RFC](../../../docs/rfc/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)). +- **`GenerateOptions` sampling is `temperature`/`maxTokens`/`stop` only** — no `tool_choice`, `top_p`, or penalty fields; the vocabulary grows when a producer lands ([dropped inert knobs](../../../.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md)). +- **Producer-gated variants stay out until produced** — `prefill`, per-tool `strict`, block `cache` hints, and the `agent` message-source variant were pruned as producerless ([Agent Note](../../../.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)). - **`BlockAssembler` handles core block kinds only** — a plugin-added block type whose stream is never closed by `block-end` makes `blocks()` throw. - **`APP_IDENTITY.url` names a repository that does not exist yet** — `FIXME`: creating the public `deepseek-ai/deepseek-harness-sdk` repo gates the first release. - **`GenerateOptions.sessionId` is a locally-declared brand** — importing dsh-session's `SessionId` would cycle; a future ids-owning package would dissolve the workaround. diff --git a/packages/llm/llm/src/attribution.ts b/packages/llm/llm/src/attribution.ts index 8f0f156aa1..cdaea4b96b 100644 --- a/packages/llm/llm/src/attribution.ts +++ b/packages/llm/llm/src/attribution.ts @@ -1,7 +1,7 @@ /** * Centralize the non-secret product identity every provider request sends as `User-Agent`, keeping * adapters from drifting. See - * `docs/rfc/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md`. + * `.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md`. * * App-attribution vocabulary for provider requests. * @module @deepseek-ai/dsh-llm/attribution diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index ac31738a61..f276aa9f92 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -35,7 +35,7 @@ declare module 'cordis' { * adapter's stream, or yield your own chunks to short-circuit. * @param options - the full request. A LOOP-built request arrives * deep-frozen (mutation throws): its content is a pure function of the - * session log (the reconstructability RFC), so listeners read it, never + * session log (the reconstructability Agent Note), so listeners read it, never * rewrite it. A hand-built one-shot (compaction summarize) is the * caller's own object and stays mutable here. * @mode waterfall diff --git a/packages/llm/llm/tests/properties.spec.ts b/packages/llm/llm/tests/properties.spec.ts index 3bb2a76c38..0d65b545d1 100644 --- a/packages/llm/llm/tests/properties.spec.ts +++ b/packages/llm/llm/tests/properties.spec.ts @@ -1,5 +1,5 @@ /** - * Property-based tests for the BlockAssembler (the property-testing RFC). + * Property-based tests for the BlockAssembler (the property-testing Agent Note). * * The assembler is protocol-shaped: arbitrary interleavings of block-start, * deltas, block-end, usage, and finish — valid and malformed (duplicate diff --git a/packages/mcp/mcp-client/src/tools.ts b/packages/mcp/mcp-client/src/tools.ts index ae01fc0f84..7b9217e814 100644 --- a/packages/mcp/mcp-client/src/tools.ts +++ b/packages/mcp/mcp-client/src/tools.ts @@ -3,7 +3,7 @@ * under deterministic server-qualified public names, and handles re-sync when * the server's tool list changes. * - * Naming contract (see the mcp-client RFC "Naming invariants"): every MCP tool + * Naming contract (see the mcp-client Agent Note "Naming invariants"): every MCP tool * has the stable identity `(serverName, rawName)`; the model-facing public name * is `mcp__<serverName>__<rawName>`, normalized to the DeepSeek function-name * constraints. The raw name is only ever sent on the wire (`tools/call`); the diff --git a/packages/sandbox/README.md b/packages/sandbox/README.md index cb2c7b5747..93287f299f 100644 --- a/packages/sandbox/README.md +++ b/packages/sandbox/README.md @@ -1,12 +1,12 @@ # sandbox/ — process-sandbox capability family -The confinement half of the [capability-seam split](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md): an abstract provider interface and platform backends. Consumers hand `ctx.sandbox` the exact argv they are about to spawn and spawn the returned (wrapped) argv instead; policy (`SandboxPolicy`: mode + workspace root) rides each call, so different consumers confine under different policies at the same instant. All **product** packages. +The confinement half of the [capability-seam split](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md): an abstract provider interface and platform backends. Consumers hand `ctx.sandbox` the exact argv they are about to spawn and spawn the returned (wrapped) argv instead; policy (`SandboxPolicy`: mode + workspace root) rides each call, so different consumers confine under different policies at the same instant. All **product** packages. | Package | Role | ctx key | |---|---|---| | `sandbox/` | Abstract process-sandbox seam (the `SandboxProvider` contract + the mode/enforcement/policy vocabulary) | `ctx.sandbox` | | `sandbox-local/` | Local backends by platform chain: Linux `bwrap` else the `landlock-run` launcher (the npm-distributed [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) family, built and released from its own repository), darwin `sandbox-exec`/Seatbelt — multi-candidate chains functionally probed, sole candidates selected directly, verdict cached, fail-closed | (registers `ctx.sandbox`) | -The seam confines SAME-WORLD subprocesses only (shared filesystem and kernel). Containers, microVMs, and remote executors are NOT backends here — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups; the boundary is recorded in [the sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). +The seam confines SAME-WORLD subprocesses only (shared filesystem and kernel). Containers, microVMs, and remote executors are NOT backends here — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups; the boundary is recorded in [the sandbox Agent Note](../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). -Consumers today: [`bash/bash-sandbox`](../bash/bash-sandbox/) (wraps `['bash', '-c', command]`; see [the acp-agent example's default composition](../../examples/acp-agent/) for the composed leaf). In-process tools (fs/web) cannot be confined by an OS wrapper — their sandbox semantics are policy at their own seams (the sandbox RFC's cross-family phase). +Consumers today: [`bash/bash-sandbox`](../bash/bash-sandbox/) (wraps `['bash', '-c', command]`; see [the acp-agent example's default composition](../../examples/acp-agent/) for the composed leaf). In-process tools (fs/web) cannot be confined by an OS wrapper — their sandbox semantics are policy at their own seams (the sandbox Agent Note's cross-family phase). diff --git a/packages/sandbox/sandbox-local/README.md b/packages/sandbox/sandbox-local/README.md index 7df7cc2e31..ed85802cf7 100644 --- a/packages/sandbox/sandbox-local/README.md +++ b/packages/sandbox/sandbox-local/README.md @@ -4,9 +4,9 @@ Local implementation of the [`dsh-sandbox`](../sandbox/) seam. It selects and ca The package root exports the default and named `LocalSandboxProvider` plugin, `Config`, and its public test-injection seam; platform profile builders stay internal. -Unsupported platforms and unusable runners fail closed with `SANDBOX_UNAVAILABLE`; execution never silently falls through unconfined. Each wrap carries runner-failure signatures so consumers can distinguish a broken sandbox from a command failure. The [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md) owns selection rationale and profile differences. +Unsupported platforms and unusable runners fail closed with `SANDBOX_UNAVAILABLE`; execution never silently falls through unconfined. Each wrap carries runner-failure signatures so consumers can distinguish a broken sandbox from a command failure. The [sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md) owns selection rationale and profile differences. -Policy is per call; the provider stores only the mechanism and cached runner verdict. Each wrap reports enforcement completeness plus backend-specific denial and runner-failure signatures. `runnerCommand` is an operator assertion of a bwrap-shaped runner and skips probes, but missing or unexecutable commands still fail closed at execution. Because its mechanism is unknown, it carries both Linux denial dialects. `probeTimeoutMs` bounds functional probes. The [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md) owns selection and failure semantics. +Policy is per call; the provider stores only the mechanism and cached runner verdict. Each wrap reports enforcement completeness plus backend-specific denial and runner-failure signatures. `runnerCommand` is an operator assertion of a bwrap-shaped runner and skips probes, but missing or unexecutable commands still fail closed at execution. Because its mechanism is unknown, it carries both Linux denial dialects. `probeTimeoutMs` bounds functional probes. The [sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md) owns selection and failure semantics. The Seatbelt profile is allow-default with `(deny file-write*)` plus write allow-lists, so exactly the mode's promised file effects are governed: `read-only` grants the `/dev/null` literal alone; `workspace-write` adds the workspace root, `/tmp`, and the per-user darwin temp dir (`os.tmpdir()` — the platform's real temp area for mkstemp-family tools), every root canonicalized because Seatbelt matches resolved paths (`/tmp` IS `/private/tmp`). Apple marks the `sandbox-exec` CLI deprecated but ships it on every macOS; the functional probe is what fails closed if that ever changes. diff --git a/packages/sandbox/sandbox/README.md b/packages/sandbox/sandbox/README.md index 087786c802..fccb08c18f 100644 --- a/packages/sandbox/sandbox/README.md +++ b/packages/sandbox/sandbox/README.md @@ -1,12 +1,12 @@ # @deepseek-ai/dsh-sandbox -Abstract process-sandbox seam. Owns the `ctx.sandbox` service contract ([`SandboxProvider`](src/index.ts)) and the confinement vocabulary the harness shares: `SandboxMode` (`read-only` / `workspace-write` / `danger-full-access`, file effects only), `SandboxEnforcement` (`full` / `partial`, per kernel ABI), `SandboxPolicy` (per-CALL policy — mode + workspace root), and the fail-closed `SANDBOX_UNAVAILABLE` error. Interface package of the [capability-seam split](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md): depends only on cordis (+ the harness error base), never on a backend. +Abstract process-sandbox seam. Owns the `ctx.sandbox` service contract ([`SandboxProvider`](src/index.ts)) and the confinement vocabulary the harness shares: `SandboxMode` (`read-only` / `workspace-write` / `danger-full-access`, file effects only), `SandboxEnforcement` (`full` / `partial`, per kernel ABI), `SandboxPolicy` (per-CALL policy — mode + workspace root), and the fail-closed `SANDBOX_UNAVAILABLE` error. Interface package of the [capability-seam split](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md): depends only on cordis (+ the harness error base), never on a backend. The contract in one line: `ctx.sandbox.confine(argv, policy)` returns the argv to spawn INSTEAD of your own — wrapped so the process (and everything it spawns) runs confined — plus two facts about the selected backend: the enforcement completeness it achieves and its denial dialect (`denialSignatures`, the stderr substrings its kernel prints on a denied file effect — what stderr-inferring consumers match instead of a cross-backend union); when no backend is usable it throws rather than passing the argv through unconfined. Policy rides the call, not the provider: two consumers may confine under different policies at the same instant (bash under `read-only` while a confined child agent keeps its state directory writable), and an approved escalated retry is just a new call with a wider policy. -**Same-world confinement only.** A backend shares the host's filesystem and kernel (`bwrap`, Landlock, Seatbelt); `workspaceRoot` names a real host path. Containers, microVMs, and remote executors are NOT backends of this seam — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups. The boundary and its rationale: [the sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). +**Same-world confinement only.** A backend shares the host's filesystem and kernel (`bwrap`, Landlock, Seatbelt); `workspaceRoot` names a real host path. Containers, microVMs, and remote executors are NOT backends of this seam — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups. The boundary and its rationale: [the sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). Implementations: [`@deepseek-ai/dsh-sandbox-local`](../sandbox-local/) (Linux: `bwrap`, else the per-platform Landlock launcher; macOS: `sandbox-exec`/Seatbelt). Consumers: [`@deepseek-ai/dsh-bash-sandbox`](../../bash/bash-sandbox/) (wraps `['bash', '-c', command]`). diff --git a/packages/sdk/README.md b/packages/sdk/README.md index 953d52ea76..9bd32b4017 100644 --- a/packages/sdk/README.md +++ b/packages/sdk/README.md @@ -2,7 +2,7 @@ Developer tooling for creating, editing, building, and running DeepSeek Harness projects. -The [feature RFC](../../docs/rfc/proposed/feature/2026-07-14-sdk-developer-projects.md) owns the developer workflow; the [architecture RFC](../../docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md) owns the package and project-editing boundaries. +The [feature Agent Note](../../.agents/notes/proposed/feature/2026-07-14-sdk-developer-projects.md) owns the developer workflow; the [architecture Agent Note](../../.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md) owns the package and project-editing boundaries. | Package | Role | |---|---| diff --git a/packages/sdk/helper/README.md b/packages/sdk/helper/README.md index 31ee34f59e..45ad545458 100644 --- a/packages/sdk/helper/README.md +++ b/packages/sdk/helper/README.md @@ -1,6 +1,6 @@ # `@deepseek-ai/dsh-helper` -Shared project domain and infrastructure for `create-sdk` and `dsh-sdk config`. `SdkProject` is a read-only snapshot; `ProjectEditSession` is the only mutation and commit boundary. The [SDK architecture RFC](../../../docs/rfc/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md) owns the rationale. +Shared project domain and infrastructure for `create-sdk` and `dsh-sdk config`. `SdkProject` is a read-only snapshot; `ProjectEditSession` is the only mutation and commit boundary. The [SDK architecture Agent Note](../../../.agents/notes/proposed/architecture/2026-07-15-sdk-project-editing-architecture.md) owns the rationale. The package owns the builtin typed-spec catalog, provider/app behavior entities, structured project file objects, helper-owned project templates, the shared typed `TextTemplate` renderer, package-manager strategies, local-plugin blueprints, typed questions, and the clack prompt adapter. It never boots a Cordis application. diff --git a/packages/session-persistence/README.md b/packages/session-persistence/README.md index 603e525ee0..6435a4bea7 100644 --- a/packages/session-persistence/README.md +++ b/packages/session-persistence/README.md @@ -8,4 +8,4 @@ The durable session-persistence seam and its storage backends. The interface pac | `session-persistence-jsonl/` | JSONL-sidecar persistence backend | (registers `ctx.sessionPersistence`) | | `session-persistence-sqlite/` | SQLite persistence backend | (registers `ctx.sessionPersistence`) | -The interface lives at `session-persistence/session-persistence/`; backends are flat siblings. A new storage backend joins here and registers on `ctx.sessionPersistence`. See [session persistence](../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md). +The interface lives at `session-persistence/session-persistence/`; backends are flat siblings. A new storage backend joins here and registers on `ctx.sessionPersistence`. See [session persistence](../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md). diff --git a/packages/session-persistence/session-persistence-jsonl/README.md b/packages/session-persistence/session-persistence-jsonl/README.md index ed7a056c69..cf733b85d4 100644 --- a/packages/session-persistence/session-persistence-jsonl/README.md +++ b/packages/session-persistence/session-persistence-jsonl/README.md @@ -25,7 +25,7 @@ The JSONL durable session-persistence backend — a concrete `SessionPersistence - **Lazy materialization.** `create(meta)` writes nothing; on the first `append`, the backend writes and `fsync`s a temporary file, publishes it without overwrite via a hard link, then `fsync`s the directory when the host supports it. A created-but-never-appended session leaves nothing on disk and is absent from `list`. - **Append-only.** Committed events (at or below a flushed `turn/end`) are never rewritten. Subsequent appends are line appends at EOF + `fsync`. -- **Crash recovery — preserve valid tail work.** `load` keeps the contiguous valid prefix of an interrupted final turn. It truncates from the first unparsable or sequence-gapped uncommitted record, then appends the synthetic tool, step, and turn closers required by the shared [persistence contract](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md); the same defect at or before the last committed `turn/end` rejects. +- **Crash recovery — preserve valid tail work.** `load` keeps the contiguous valid prefix of an interrupted final turn. It truncates from the first unparsable or sequence-gapped uncommitted record, then appends the synthetic tool, step, and turn closers required by the shared [persistence contract](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md); the same defect at or before the last committed `turn/end` rejects. - **Contiguous-seq.** `append` rejects a batch whose first `seq` does not continue the stored log, and rejects non-JSON-serializable `event.data` naming the offending event type. ## Write path diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index 5eb0338f99..8099aaf9cc 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-session-persistence-sqlite -A SQLite durable session-persistence backend — a second `SessionPersistence` implementation ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), built to validate that the abstract seam and the shared `runPersistenceContract` suite are genuinely backend-agnostic. It satisfies the SAME contract as `dsh-session-persistence-jsonl` (append-only, contiguous-seq, lazy materialization, interrupted-turn close on load), expressed over `node:sqlite` rows instead of file bytes. +A SQLite durable session-persistence backend — a second `SessionPersistence` implementation ([session persistence](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)), built to validate that the abstract seam and the shared `runPersistenceContract` suite are genuinely backend-agnostic. It satisfies the SAME contract as `dsh-session-persistence-jsonl` (append-only, contiguous-seq, lazy materialization, interrupted-turn close on load), expressed over `node:sqlite` rows instead of file bytes. `locate(meta)` returns `undefined`: all sessions share one database, so there is no honest independent per-session transcript path. @@ -8,7 +8,7 @@ A SQLite durable session-persistence backend — a second `SessionPersistence` i ## Storage model -Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, type, time, data, source_event_seqs, surface_op)` — `data` is the event payload as JSON text, so the row shape is the event verbatim (including `assistant/chunk`, keeping `seq` contiguous). The two `TEXT` columns `source_event_seqs` and `surface_op` are nullable; they store the event's optional surface-metadata fields (see [session surface](../../../docs/rfc/implemented/architecture/2026-06-18-session-surface.md)). Out-of-log metadata (`SessionHeader`) lives in a `sessions` row. A `sessions` row is written only by the first `append` — its existence is the lazy-materialization signal (`list` reports exactly the sessions that have a row), so no separate column is needed. +Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, type, time, data, source_event_seqs, surface_op)` — `data` is the event payload as JSON text, so the row shape is the event verbatim (including `assistant/chunk`, keeping `seq` contiguous). The two `TEXT` columns `source_event_seqs` and `surface_op` are nullable; they store the event's optional surface-metadata fields (see [session surface](../../../.agents/notes/implemented/architecture/2026-06-18-session-surface.md)). Out-of-log metadata (`SessionHeader`) lives in a `sessions` row. A `sessions` row is written only by the first `append` — its existence is the lazy-materialization signal (`list` reports exactly the sessions that have a row), so no separate column is needed. The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. @@ -18,7 +18,7 @@ On filesystems with POSIX modes, the backend requests mode `0700` for missing di - **Append = a transaction.** `append` runs `BEGIN`/`COMMIT` around the batch: it materializes the `sessions` row (if still lazy) and INSERTs every event, asserting the contiguous-seq contract first (the first event's `seq` must equal the stored next-seq). A mid-batch failure (a UNIQUE violation on a duplicated seq) rolls back entirely, so the stored log and the in-memory cursor stay consistent. (`load()` already balanced the stored log, so `append` never has to repair a crash tail.) - **Lazy materialization.** `create()` records intent in memory only — no row is written until the first `append`. A created-but-never-appended session has no `sessions` row, so it is absent from `list()` (which reports exactly the sessions that have a row). -- **Interrupted-turn close on load.** `load()` implements the shared [crash-recovery contract](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md): preserve the valid interrupted turn, append its synthetic closing events in one transaction, and remove only a torn tail row. Committed parse errors or sequence gaps make the session unloadable. Because recovery mutates stored rows, the next append starts from a balanced log and accurate cursor. +- **Interrupted-turn close on load.** `load()` implements the shared [crash-recovery contract](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md): preserve the valid interrupted turn, append its synthetic closing events in one transaction, and remove only a torn tail row. Committed parse errors or sequence gaps make the session unloadable. Because recovery mutates stored rows, the next append starts from a balanced log and accurate cursor. ## Configuration (schemastery) diff --git a/packages/session-persistence/session-persistence/README.md b/packages/session-persistence/session-persistence/README.md index a8c478d941..ca04cd1ab8 100644 --- a/packages/session-persistence/session-persistence/README.md +++ b/packages/session-persistence/session-persistence/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-session-persistence -The abstract durable session-persistence seam (`ctx.sessionPersistence`). Defines WHAT a persistence backend does — durably store, reload, and list sessions — without saying HOW. Mirrors the `dsh-bash` capability-seam template ([capability seams](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract service here, a concrete implementation in a sibling package, consumers that inject the interface. +The abstract durable session-persistence seam (`ctx.sessionPersistence`). Defines WHAT a persistence backend does — durably store, reload, and list sessions — without saying HOW. Mirrors the `dsh-bash` capability-seam template ([capability seams](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract service here, a concrete implementation in a sibling package, consumers that inject the interface. The persisted unit IS the existing `SessionEvent` (event-sourced model — the log is the single source of truth), so there is no parallel "persisted message" type. Metadata that is NOT replayable conversation state (format version, cwd, lineage, seed boundary) travels separately as `SessionHeader`, owned by `dsh-session` and re-exported here. @@ -23,7 +23,7 @@ The persisted unit IS the existing `SessionEvent` (event-sourced model — the l ## The write coordinator -`PersistenceCoordinator` owns per-id state, write-behind buffers and serialization, the `session/event` → `session/flush` drain, lazy materialization, crash-tail repair, session adoption, and quiescent disposal. A first-party backend composes one, implements the small `PersistenceBackend` storage hook interface, and delegates its four public service methods. JSONL and SQLite therefore share lifecycle correctness while retaining different storage primitives; see the [coordinator RFC](../../../docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md). +`PersistenceCoordinator` owns per-id state, write-behind buffers and serialization, the `session/event` → `session/flush` drain, lazy materialization, crash-tail repair, session adoption, and quiescent disposal. A first-party backend composes one, implements the small `PersistenceBackend` storage hook interface, and delegates its four public service methods. JSONL and SQLite therefore share lifecycle correctness while retaining different storage primitives; see the [coordinator Agent Note](../../../.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md). When a live session emits `session/disposed`, the coordinator waits for its initialization, serializes a final buffer drain, then releases every map entry owned by that exact `Session` object. A failed final drain keeps the pending buffer for backend teardown to retry. Backend teardown stops event admission first, awaits all in-flight session retirements and remaining per-id operations, drains any retained buffers, and only then closes the storage handle. @@ -41,7 +41,7 @@ The `PersistenceBackend<TornMarker>` hooks (the only seam between the coordinato | `list()` | List all stored metadata. | | `close?()` | Optional lifecycle teardown (e.g. close a db handle), awaited after the dispose drain. | -The `tornMarker` is fully OPAQUE: the coordinator only tests `!== undefined` and round-trips it to `commitRepair`, never inspecting its value (the JSONL backend uses the byte offset to truncate to, the SQLite backend the seq to delete from). The public `SessionPersistence` service shape is unchanged, so a third-party backend MAY still implement the abstract service directly without the coordinator. See [the write-coordinator RFC](../../../docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md). +The `tornMarker` is fully OPAQUE: the coordinator only tests `!== undefined` and round-trips it to `commitRepair`, never inspecting its value (the JSONL backend uses the byte offset to truncate to, the SQLite backend the seq to delete from). The public `SessionPersistence` service shape is unchanged, so a third-party backend MAY still implement the abstract service directly without the coordinator. See [the write-coordinator Agent Note](../../../.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md). ## Testing backends diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index 1a5ed99949..76fc5eff80 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -33,4 +33,4 @@ None; this package neither assembles nor sends a provider request. ## Known Limitations and Deferred Work - **No caller authorization** — this is trusted context-wide infrastructure; a future model tool or UI must constrain which sessions its caller may inspect. -- **No search or extraction** — filters, extraction registry, search-provider protocol, index synchronization, and a model-facing tool are absent. The [tracing decision](../../../docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md) owns relationship semantics; content-bearing full-text-search results and their chainable filters belong beside their first implementation in the proposed [SQLite package](../../../docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md). +- **No search or extraction** — filters, extraction registry, search-provider protocol, index synchronization, and a model-facing tool are absent. The [tracing decision](../../../.agents/notes/implemented/feature/2026-07-13-session-query-tracing.md) owns relationship semantics; content-bearing full-text-search results and their chainable filters belong beside their first implementation in the proposed [SQLite package](../../../.agents/notes/proposed/feature/2026-07-10-sqlite-session-query-provider.md). diff --git a/packages/skill/tool-skill/README.md b/packages/skill/tool-skill/README.md index 4d46ad0b75..89a6e843ab 100644 --- a/packages/skill/tool-skill/README.md +++ b/packages/skill/tool-skill/README.md @@ -8,7 +8,7 @@ Requires `ctx.tools` and `ctx.skills` (`inject: ['tools', 'skills']`). The plugin contributes one user-role `<system-reminder>` catalog through `agent/session-prefix`. It resolves skills for the calling session's cwd, forwards the prefix abort signal to discovery, and lists only sorted `name` and `description` entries; skill bodies, paths, sources, providers, and `whenToUse` hints remain outside the catalog. The catalog is omitted when no model-invocable skills are available, and also when that agent's tool view restricts away the shipped `skill` tool or resolves a same-name scoped shadow instead. This exact-definition check keeps prompt guidance, the model-visible schema, and executable dispatch aligned. -`catalogDescriptionMaxLength` controls normalized, XML-escaped catalog descriptions. Its default is `500` and values must be integers of at least `3`, which reserves room for a truncation ellipsis. The [session-prefix RFC](../../../docs/rfc/implemented/feature/2026-07-07-session-prefix.md) defines the request-only, header-logged lifecycle of this message. +`catalogDescriptionMaxLength` controls normalized, XML-escaped catalog descriptions. Its default is `500` and values must be integers of at least `3`, which reserves room for a truncation ellipsis. The [session-prefix Agent Note](../../../.agents/notes/implemented/feature/2026-07-07-session-prefix.md) defines the request-only, header-logged lifecycle of this message. ## Tool: `skill` diff --git a/packages/spill/README.md b/packages/spill/README.md index 7d54c91eb5..c7b59adf74 100644 --- a/packages/spill/README.md +++ b/packages/spill/README.md @@ -10,4 +10,4 @@ The tool-output spill capability seam: an abstract storage interface, a local fi The interface lives at `spill/spill/`. The split mirrors bash/fs: the seam owns storage only, `spill-local` owns the filesystem mechanics, and `spill-policy` owns WHEN to spill and the model-facing notice. Preview mechanics stay in [`util/retention`](../util/README.md) — the policy composes the two without either owning the other's job. -See the [tool output spill RFC](../../docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md) for the design rationale, including why final-result spill is separate from tool-owned early spill (bash streams, subagent rollouts) and why creation belongs to the runtime spill seam rather than the model-facing `write` tool. +See the [tool output spill Agent Note](../../.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md) for the design rationale, including why final-result spill is separate from tool-owned early spill (bash streams, subagent rollouts) and why creation belongs to the runtime spill seam rather than the model-facing `write` tool. diff --git a/packages/spill/spill-local/README.md b/packages/spill/spill-local/README.md index 07199c5caa..cef794b548 100644 --- a/packages/spill/spill-local/README.md +++ b/packages/spill/spill-local/README.md @@ -16,7 +16,7 @@ Files land at `<root>/session-<hash>/​<random>-<safeName>`: |---|---|---| | `root` | private 0700 temp dir | Root directory for spill files. Set to keep them under a known location. | -`saveText` rejects on a real storage failure (permissions, ENOSPC); the spill policy treats a rejection as best-effort and keeps the inline result. See the seam README for the vocabulary and the [tool output spill RFC](../../../docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md) for the design. +`saveText` rejects on a real storage failure (permissions, ENOSPC); the spill policy treats a rejection as best-effort and keeps the inline result. See the seam README for the vocabulary and the [tool output spill Agent Note](../../../.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md) for the design. ## Model Experience diff --git a/packages/spill/spill-policy/README.md b/packages/spill/spill-policy/README.md index 64625c61ef..936f254d6a 100644 --- a/packages/spill/spill-policy/README.md +++ b/packages/spill/spill-policy/README.md @@ -30,7 +30,7 @@ This plugin registers **no service** and owns no storage or preview mechanics: p ## Scope -The policy sees only the FINAL formatted tool result — not a tool's internal resource. If a provider already truncated (e.g. `web-fetch-local.maxBodyChars`), the spill artifact holds the full formatted result the tool returned, not the full original source. Provider/resource caps stay mandatory and separate. Tool-owned early spill (bash streams, subagent rollouts) is future work — see the [tool output spill RFC](../../../docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md). +The policy sees only the FINAL formatted tool result — not a tool's internal resource. If a provider already truncated (e.g. `web-fetch-local.maxBodyChars`), the spill artifact holds the full formatted result the tool returned, not the full original source. Provider/resource caps stay mandatory and separate. Tool-owned early spill (bash streams, subagent rollouts) is future work — see the [tool output spill Agent Note](../../../.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md). ## Model Experience diff --git a/packages/spill/spill/README.md b/packages/spill/spill/README.md index c6a26cfddc..8e64e72608 100644 --- a/packages/spill/spill/README.md +++ b/packages/spill/spill/README.md @@ -24,7 +24,7 @@ Storage is grouped by the request's `owner` session as a save-time namespace; th `SaveTextSpill` (owner, source, suggestedName, content) is the request; `SpillRef` (locator, bytes, retrievalHint) is the result. `SpillLocator` is [branded](../../util/brand) and rendered to the model as an opaque string — a local path for `dsh-spill-local`, but a future backend may return a URI, key, or command token without changing policy/tool consumers. `SpillOwner.sessionId` is the save-time storage namespace: forked sessions inherit existing locators from the seeded log without copying or re-owning them, and new spills after the fork use the child session id. `SpillSource` (toolName, callId, label) is descriptive provenance for backend naming and inspection, not access control. See `src/types.ts` for the full contracts. -See the [tool output spill RFC](../../../docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md) for the design rationale, including why creation belongs to the runtime spill seam rather than the model-facing `write` tool. +See the [tool output spill Agent Note](../../../.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md) for the design rationale, including why creation belongs to the runtime spill seam rather than the model-facing `write` tool. ## Model Experience diff --git a/packages/subagent/README.md b/packages/subagent/README.md index 9935233e85..ccc6ab9cba 100644 --- a/packages/subagent/README.md +++ b/packages/subagent/README.md @@ -1,6 +1,6 @@ # subagent/ — subagent capability family -The subagent seam: an agent delegating work to a child agent. Like the [bash](../bash/README.md) and [llm](../llm/README.md) families this is a capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)) — but with one defining difference: **multiple provider implementations coexist in one context**, registered by name, rather than the single-implementation bash shape. The registry mirrors the LLM adapter registry. +The subagent seam: an agent delegating work to a child agent. Like the [bash](../bash/README.md) and [llm](../llm/README.md) families this is a capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)) — but with one defining difference: **multiple provider implementations coexist in one context**, registered by name, rather than the single-implementation bash shape. The registry mirrors the LLM adapter registry. | Package | Role | ctx key | |---|---|---| @@ -14,4 +14,4 @@ The subagent seam: an agent delegating work to a child agent. Like the [bash](.. The interface lives at `subagent/subagent/`. The in-process `subagent-spawn` / `subagent-fork` backends share the `subagent-inprocess` driver (a library with no provider of its own — both depend on it, neither on the other), and the out-of-process `subagent-acp` backend builds on the `subagent-subprocess` library (the credential env scrub, the dispose ladder, isolated config dirs). Tests replace only the child boundary with package-local fixtures. -The proposal and design rationale: [docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md](../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md). +The proposal and design rationale: [.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md). diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index 0ce06fca2e..7ac583575b 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -91,7 +91,7 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **A fresh process per run** — persistent-process pooling is a future optimization ([the seam RFC](../../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md)). +- **A fresh process per run** — persistent-process pooling is a future optimization ([the seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)). - **No optional start-time capabilities** — this provider cannot apply the local harness's `outputSchema`, depth cap, tool filter, or persona inside the remote process, so it advertises none and the service rejects requests that require them. - **Only `agent_message_chunk` text is collected** — the child's tool-call activity, thought chunks, and plan updates are not surfaced to the parent. - **Permission prompts are auto-answered** (`permission: allow | reject`) — no human is surfaced a child's `session/request_permission` in this cut. diff --git a/packages/subagent/subagent-subprocess/README.md b/packages/subagent/subagent-subprocess/README.md index 5ca9720f00..dd1784672e 100644 --- a/packages/subagent/subagent-subprocess/README.md +++ b/packages/subagent/subagent-subprocess/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-subagent-subprocess -Shared machinery for **out-of-process subagent backends** — providers that spawn an external agent as a child process, such as the [ACP backend](../subagent-acp/README.md). A pure library (no provider, no registration, no Config): what every spawn-a-CLI-child backend needs to keep the parent deployment's credentials out of the child, tear the child down to quiescence, and isolate it from the host user's on-disk CLI state. Design rationale: [the Claude Code / Codex subagent backends RFC](../../../docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md). +Shared machinery for **out-of-process subagent backends** — providers that spawn an external agent as a child process, such as the [ACP backend](../subagent-acp/README.md). A pure library (no provider, no registration, no Config): what every spawn-a-CLI-child backend needs to keep the parent deployment's credentials out of the child, tear the child down to quiescence, and isolate it from the host user's on-disk CLI state. Design rationale: [the Claude Code / Codex subagent backends Agent Note](../../../.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md). Every tunable is a **parameter**: the dispose ladder takes its grace periods per call, the config-dir helper takes an optional pinned path. Defaults live in each consuming plugin's Config (defaulted, validated fields changeable from `cordis.yml`), never in this library. diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index c810a1f6ce..5097ad914a 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -60,7 +60,7 @@ Provider additions and removals also emit `subagent/provider-added` and `subagen ## Collection model -The model-facing tool collects synchronously by default: it awaits the child result and disposes the run before returning. Background delegation does not change this seam; the consumer registers startup and the eventual run with the generic `ctx.tasks` runtime, then collection and cancellation use the shared task tools. See the [background subagent tasks RFC](../../../docs/rfc/implemented/feature/2026-07-08-background-subagent-tasks.md), the [capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md), and `src/types.ts` for the complete contracts. +The model-facing tool collects synchronously by default: it awaits the child result and disposes the run before returning. Background delegation does not change this seam; the consumer registers startup and the eventual run with the generic `ctx.tasks` runtime, then collection and cancellation use the shared task tools. See the [background subagent tasks Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md), the [capability-seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md), and `src/types.ts` for the complete contracts. ## Model Experience diff --git a/packages/subagent/tool-subagent/README.md b/packages/subagent/tool-subagent/README.md index 8d382b6ce4..6355208a4d 100644 --- a/packages/subagent/tool-subagent/README.md +++ b/packages/subagent/tool-subagent/README.md @@ -8,9 +8,9 @@ Each plugin instance binds one `provider` to one `toolName`; the model receives A foreground call passes the execution signal through startup and execution, awaits `run.result`, and always awaits `run.dispose()` before returning. Only `completed` returns final text; abort, refusal, token limit, and other failures become errored tool results without partial output. -With `run_in_background: true`, the tool registers the parent-owned task before starting the provider. A task-owned signal covers pending startup and the child after the starting call returns. `task_kill` and owner disposal abort it. Settlement awaits startup rollback or child disposal, then maps completed final text, abort to `killed`, and other failures to `failed`. The task has no incremental read; generic task tools own later status, collection, cancellation, and notices. See the [background subagent RFC](../../../docs/rfc/implemented/feature/2026-07-08-background-subagent-tasks.md). +With `run_in_background: true`, the tool registers the parent-owned task before starting the provider. A task-owned signal covers pending startup and the child after the starting call returns. `task_kill` and owner disposal abort it. Settlement awaits startup rollback or child disposal, then maps completed final text, abort to `killed`, and other failures to `failed`. The task has no incremental read; generic task tools own later status, collection, cancellation, and notices. See the [background subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md). -`toolFilter` changes the child's global tool layer but is not a parent-derived authority ceiling. See the [agent-scope security non-goal](../../../docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals). +`toolFilter` changes the child's global tool layer but is not a parent-derived authority ceiling. See the [agent-scope security non-goal](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals). ## Config @@ -26,7 +26,7 @@ With `run_in_background: true`, the tool registers the parent-owned task before ## Concurrency -Foreground and background calls are exclusive. Children may share the parent's workspace or external resources, and a unary classifier cannot prove that sibling delegations have disjoint effects. See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). +Foreground and background calls are exclusive. Children may share the parent's workspace or external resources, and a unary classifier cannot prove that sibling delegations have disjoint effects. See the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md). ## Model Experience diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 2f55ebdfaa..231ba0d6e8 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -6,7 +6,7 @@ Four layers, importable separately: - **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit, inherited stdio closure, and ACP parser exhaustion before resolving or propagating a child error, so captures are complete and callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the expected-output and purity checks, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). Startup failures preserve captured agent stderr in the rejected diagnostic. -- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header Agent Note](../../../.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.expected.md` plus `tool-schemas.expected.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session.<n>.jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. A consuming `*.snapshot.ts` is the scenario table plus one factory call: @@ -38,7 +38,7 @@ defineAcpSnapshotSuite({ A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode and filesystem scenarios are templates. Each pinning directory stores the normalized full prompt sequence in generated `system-prompt.expected.md` and the corresponding full tool-schema sequence in generated `tool-schemas.expected.json`; `session.jsonl` stores `"system":"{{system}}","tools":"{{tools}}"` while retaining config, reason, and any model-visible prefix. A pin with legitimate mid-run header changes declares `expectedHeaderChanges`, which fixes the length of both sidecar sequences. -The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config RFC](../../../docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log expected outputs, and each pin's prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md). +The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config Agent Note](../../../.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log expected outputs, and each pin's prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md). Constraints: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run (the launcher, harness, and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript). diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 81e02da6a3..50d7763609 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -11,7 +11,7 @@ * shutdown flush. The pure normalizers in ./normalize.ts turn the captured * stdout frames and the session-log events into stable, snapshot-able text. * - * See docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md. + * See .agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md. * * @module @deepseek-ai/dsh-acp-snapshot/harness */ diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index bda9524bbe..139caf8584 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -40,13 +40,13 @@ Agent status (per agent): Model requests (on `llm/stream`): -- **a loop-built request is exactly what the log reconstructs** — a frozen request with a live `sessionId` (the loop-built marker; hand-built one-shots like compaction's summarize are unfrozen and skipped) must carry frozen `messages` deep-equal to the derivation over the log prefix strictly before the in-flight step's `step/start` (rebuilt through a FRESH `Session`, so the live cache cannot vouch for itself — and boundary-correct: content logged after `step/start` legitimately belongs to the next request), and every non-content field must equal the latest logged `request/header` (see [the reconstructability RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). Registered with `prepend: true` so a short-circuiting `llm/stream` listener (the replay adapter) cannot silence it; prepend orders it against append-registered listeners only — correctness rests on the seq-bounded rebuild, never listener timing. +- **a loop-built request is exactly what the log reconstructs** — a frozen request with a live `sessionId` (the loop-built marker; hand-built one-shots like compaction's summarize are unfrozen and skipped) must carry frozen `messages` deep-equal to the derivation over the log prefix strictly before the in-flight step's `step/start` (rebuilt through a FRESH `Session`, so the live cache cannot vouch for itself — and boundary-correct: content logged after `step/start` legitimately belongs to the next request), and every non-content field must equal the latest logged `request/header` (see [the reconstructability Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)). Registered with `prepend: true` so a short-circuiting `llm/stream` listener (the replay adapter) cannot silence it; prepend orders it against append-registered listeners only — correctness rests on the seq-bounded rebuild, never listener timing. On any violation it throws `InvariantError` (`code: 'INVARIANT'`). ## Why runtime assertions remain useful -Session enforces the per-record storage boundary at runtime, where a cast cannot bypass it. Pervasive `DeepReadonly<SessionEvent>` types would add noise across consumers without expressing relationships such as turn/step nesting, subject-correct scoped dispatch, or equality between a request and its log reconstruction. This plugin checks those relationships wherever it is mounted while `dsh-session` keeps history immutable in every composition. See [source-owned session immutability and dev-mode invariants](../../../docs/rfc/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md). +Session enforces the per-record storage boundary at runtime, where a cast cannot bypass it. Pervasive `DeepReadonly<SessionEvent>` types would add noise across consumers without expressing relationships such as turn/step nesting, subject-correct scoped dispatch, or equality between a request and its log reconstruction. This plugin checks those relationships wherever it is mounted while `dsh-session` keeps history immutable in every composition. See [source-owned session immutability and dev-mode invariants](../../../.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md). ## Seeded sessions diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index cdb06edbac..deabeeea17 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -86,7 +86,7 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr // Boundary/step-scoped events have explicit cases; every OTHER event type — // including plugin-added (merge-extensible) SessionEventMap keys — is caught - // by the `default` and must be turn-enclosed (the turn-enclosure RFC). No assertNever: an + // by the `default` and must be turn-enclosed (the turn-enclosure Agent Note). No assertNever: an // unknown variant is valid, not a compile error. switch (event.type) { case 'turn/start': { @@ -162,7 +162,7 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr pendingCalls = { kind: 'delete', callId: event.data.callId } break } - // Turn-enclosure (the turn-enclosure RFC): EVERY session event not handled by a boundary + // Turn-enclosure (the turn-enclosure Agent Note): EVERY session event not handled by a boundary // case above must sit inside an open turn. The durable session log uses the // turn as its commit/replay boundary (the JSONL backend treats anything // after the last turn/end as a crash tail), so a bare event between turns is @@ -330,7 +330,7 @@ export function apply(ctx: Context): void { } }, { global: true }) - // Request-reconstruction cross-check (the reconstructability RFC): a + // Request-reconstruction cross-check (the reconstructability Agent Note): a // loop-built request — frozen envelope + live sessionId is the marker; a // hand-built one-shot (compaction summarize) is unfrozen and skipped — must // be EXACTLY what the session log reconstructs: diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index de0046c00e..c6fe68d6d2 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -149,7 +149,7 @@ describe('session-log invariants', () => { it('rejects a message event appended outside any open turn (turn-enclosure)', async () => { const { ctx } = await setup() const session = ctx.sessions.create() - // No turn open: every message-bearing event must be turn-enclosed (the turn-enclosure RFC). + // No turn open: every message-bearing event must be turn-enclosed (the turn-enclosure Agent Note). expect(() => session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' })) .toThrow(/outside any open turn/) expect(() => session.append('context/message', { content: [{ type: 'text', text: 'ctx' }], source: { kind: 'user' } }, { surfaceOp: 'append' })) @@ -160,7 +160,7 @@ describe('session-log invariants', () => { const { ctx } = await setup() const session = ctx.sessions.create() // steering/message is turn-scoped: outside a turn it would land past the - // commit boundary and be dropped on resume (the turn-enclosure RFC). + // commit boundary and be dropped on resume (the turn-enclosure Agent Note). expect(() => session.append('steering/message', { turn: 1, content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, { surfaceOp: 'append' })) .toThrow(/outside any open turn/) // A PLUGIN-added (merge-extensible) event type is caught by the default too. diff --git a/packages/tasks/README.md b/packages/tasks/README.md index 12e8f41a59..71c68ea250 100644 --- a/packages/tasks/README.md +++ b/packages/tasks/README.md @@ -1,6 +1,6 @@ # tasks/ — background task capability family -The shared home for background-task ids, owner isolation, reads, cancellation, waiting, and completion notices. Bash, subagents, and future long-running tools use one model-facing protocol. See the [background-task runtime RFC](../../docs/rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md). +The shared home for background-task ids, owner isolation, reads, cancellation, waiting, and completion notices. Bash, subagents, and future long-running tools use one model-facing protocol. See the [background-task runtime Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md). | Package | ctx key | Role | |---|---|---| diff --git a/packages/tasks/tasks/README.md b/packages/tasks/tasks/README.md index afe458c711..37d342e0fe 100644 --- a/packages/tasks/tasks/README.md +++ b/packages/tasks/tasks/README.md @@ -20,7 +20,7 @@ Tasks belong to their owner and backend, not the producer tool fiber, so produce Service disposal closes listeners, cancels all live tasks, awaits their records, and detaches effects from surviving owner scopes. If teardown cancellation throws, the service force-fails the record and warns that work may be orphaned instead of deadlocking. A cancellation that returns but never settles `done` remains indistinguishable from a slow stop and can stall teardown. -See the [task type catalog](../../../docs/core-data-structures/tasks.md) and [runtime RFC](../../../docs/rfc/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md). +See the [task type catalog](../../../docs/core-data-structures/tasks.md) and [runtime Agent Note](../../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md). ## Model Experience diff --git a/packages/timeout/README.md b/packages/timeout/README.md index 36f52abaf3..321f21373c 100644 --- a/packages/timeout/README.md +++ b/packages/timeout/README.md @@ -6,4 +6,4 @@ The tool-call timeout policy plugin. A single **product** package: it is a deplo |---|---|---| | `timeout-policy/` | A `tools/execute` wrapper: for each configured tool it arms a per-call deadline on `exec.signal` and returns a structured `TOOL_TIMEOUT` result when that deadline wins | (registers a `tools/execute` listener; injects nothing) | -Timeout is split across three layers: [`dsh-timeout`](../util/timeout) owns the pure timing/classification primitive (`deadline`/`timeoutOf`), each capability owns termination (bash kills its process group, the fetch provider tears down its socket), and this package owns the *model-facing tool-call budget as deployment policy* — no model-facing timeout argument, no global default. It is the middleware the [timeout-library RFC](../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md) foresaw. `bash` and hook command execution keep their own `BASH_TIMEOUT` backend timeout and do not route through this policy. +Timeout is split across three layers: [`dsh-timeout`](../util/timeout) owns the pure timing/classification primitive (`deadline`/`timeoutOf`), each capability owns termination (bash kills its process group, the fetch provider tears down its socket), and this package owns the *model-facing tool-call budget as deployment policy* — no model-facing timeout argument, no global default. It is the middleware the [timeout-library Agent Note](../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md) foresaw. `bash` and hook command execution keep their own `BASH_TIMEOUT` backend timeout and do not route through this policy. diff --git a/packages/timeout/timeout-policy/README.md b/packages/timeout/timeout-policy/README.md index bb73090ef7..60b590a7f8 100644 --- a/packages/timeout/timeout-policy/README.md +++ b/packages/timeout/timeout-policy/README.md @@ -1,6 +1,6 @@ # dsh-timeout-policy -Tool-call timeout enforcer: a single `tools/execute` around-dispatch listener that arms a per-call cooperative deadline on `exec.signal` for a tool declaring `timeoutMs` on its `ToolDefinition` and returns a structured `TOOL_TIMEOUT` result when that deadline wins. The budget is read from the tool's own declaration (`ToolDefinition.timeoutMs`, set by the owning tool plugin), so this plugin is **zero-config**. It is the reference `tools/execute` wrapper and the enforcement home for model-facing tool-call budgets (the timeout-library RFC's foreseen middleware). +Tool-call timeout enforcer: a single `tools/execute` around-dispatch listener that arms a per-call cooperative deadline on `exec.signal` for a tool declaring `timeoutMs` on its `ToolDefinition` and returns a structured `TOOL_TIMEOUT` result when that deadline wins. The budget is read from the tool's own declaration (`ToolDefinition.timeoutMs`, set by the owning tool plugin), so this plugin is **zero-config**. It is the reference `tools/execute` wrapper and the enforcement home for model-facing tool-call budgets (the timeout-library Agent Note's foreseen middleware). ## Plugin (namespace: `timeout-policy`) diff --git a/packages/todo/tool-todo/README.md b/packages/todo/tool-todo/README.md index 45220706eb..6323d86247 100644 --- a/packages/todo/tool-todo/README.md +++ b/packages/todo/tool-todo/README.md @@ -10,7 +10,7 @@ Registers one tool, `todo_write(todos: [{ content, status }])`, on `ctx.tools`. ## Single owner -The list belongs to the ONE agent session that called the tool. There is no subagent/shared/swarm scope: a non-agent caller (no `exec.agent`) has nowhere to write the list and is rejected. This is a deliberate scope limit — see the RFC. +The list belongs to the ONE agent session that called the tool. There is no subagent/shared/swarm scope: a non-agent caller (no `exec.agent`) has nowhere to write the list and is rejected. This is a deliberate scope limit — see the Agent Note. ## Validation diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 8642e33d6b..44748add2a 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -2,7 +2,7 @@ Agent Client Protocol bridge over JSON-RPC stdio. Editors can create or resume agents, stream their events, answer questions and approvals, and render tool calls. One connection supports multiple isolated sessions; Zed is the primary compatibility target. -It is a **client-driver / UI plugin**, the structured analogue of the terminal `dsh-tui`/`dsh-stdio` channels — NOT a loop change and NOT a [capability seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`. +It is a **client-driver / UI plugin**, the structured analogue of the terminal `dsh-tui`/`dsh-stdio` channels — NOT a loop change and NOT a [capability seam](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`. ## Service / plugin @@ -37,13 +37,13 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -One id-keyed record map plus exact agent-object checks route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). +One id-keyed record map plus exact agent-object checks route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session Agent Note](../../../.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md). ## Session config options The bridge advertises a `model`-category select in `session/new` and `session/load` when the session has a complete target whose provider is registered. Values encode the complete provider/model pair, are grouped by provider when more than one group is available, and come from `ctx.llm.listProviders()` / `listModels()`. The configured or last-requested model is added when absent because catalogs are advisory and private adapters may accept unlisted ids. A selection changes only that ACP session. Agent-scoped prompt assembly snapshots the selected pair for one step, supplies matching `{{provider}}` / `{{model}}` variables, and the `agent/request` waterfall applies the same pair; a concurrent selection therefore takes effect on the next step instead of splitting prompt text from routing. The resulting request header is the durable record restored by `session/load`; a selection never used by a request remains in-memory only. -When `ctx.permission` is composed, the bridge also advertises a `permission` select. Options come from the deployment's preset table; the current value comes from the session fold, with switch-away-only `custom` for unmatched knobs. `session/set_config_option` accepts advertised presets and writes both sandbox-mode and approval-policy events through `PermissionService.set()`. Open-turn switches append immediately; idle switches overlay responses and anchor at the next `agent/prompt-submit`, before request assembly. A crash before anchoring restores the durable fold. See the [model-catalog RFC](../../../docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md), [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), [`dsh-permission`](../permission/README.md), and [protocol matrix](acp-feature-support.md#6-session-modes--config-options--models). +When `ctx.permission` is composed, the bridge also advertises a `permission` select. Options come from the deployment's preset table; the current value comes from the session fold, with switch-away-only `custom` for unmatched knobs. `session/set_config_option` accepts advertised presets and writes both sandbox-mode and approval-policy events through `PermissionService.set()`. Open-turn switches append immediately; idle switches overlay responses and anchor at the next `agent/prompt-submit`, before request assembly. A crash before anchoring restores the durable fold. See the [model-catalog Agent Note](../../../.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md), [sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md), [`dsh-permission`](../permission/README.md), and [protocol matrix](acp-feature-support.md#6-session-modes--config-options--models). The shared [`ctx.tasks` runtime](../../tasks/tasks/) fences access to predictable task ids by the owning session; ACP sessions therefore cannot read or stop one another's background work. @@ -57,7 +57,7 @@ Tools return provider-neutral `generic`, `terminal`, or `diff` render intents fr ## Terminal card (capability-gated) -When the client advertises `_meta.terminal_output`, terminal intents map to Zed's terminal info, output, and exit metadata. The bridge resolves relative cwd against the session, places the description before the terminal block, and omits result content because ACP updates replace call content. Other clients receive a generic card and bridge-derived fenced console fallback. Session creation snapshots the capability so call and result agree. The command still executes through the harness, not ACP terminal creation. See the [terminal-rendering RFC](../../../docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) and [render-intent RFC](../../../docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md). +When the client advertises `_meta.terminal_output`, terminal intents map to Zed's terminal info, output, and exit metadata. The bridge resolves relative cwd against the session, places the description before the terminal block, and omits result content because ACP updates replace call content. Other clients receive a generic card and bridge-derived fenced console fallback. Session creation snapshots the capability so call and result agree. The command still executes through the harness, not ACP terminal creation. See the [terminal-rendering Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) and [render-intent Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md). ## Settle-exactly-once @@ -73,7 +73,7 @@ Disposal and client disconnect share one memoized teardown. It cancels pending p ## stdout is the protocol -The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loads **no stdout logger** (the console logger writes to stdout and would corrupt the frames). The guarantee is config-only — see `examples/acp-agent` (no console logger) and [ACP support risks](../../../docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md#risks). A stderr exporter is fine for logging. +The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loads **no stdout logger** (the console logger writes to stdout and would corrupt the frames). The guarantee is config-only — see `examples/acp-agent` (no console logger) and [ACP support risks](../../../.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md#risks). A stderr exporter is fine for logging. ## Running @@ -166,5 +166,5 @@ Loading does not rewrite the stored log, but the next request is reconstructed u - **`additionalDirectories`** — rejected. A session operates in its single `cwd` (see Per-session cwd); widening the tool/filesystem scope to extra roots is a separate sandbox concern, not yet implemented. - **Prompt content is `text` + `resource_link` only** — image, audio, and embedded-resource blocks are rejected, as is a non-empty `mcpServers` list at `session/new`. -- **Terminal cards render completed output** — live incremental streaming and command classification are named follow-ups of [the terminal-rendering RFC](../../../docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md). +- **Terminal cards render completed output** — live incremental streaming and command classification are named follow-ups of [the terminal-rendering Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md). - **Permission answers are one-shot only** — the bridge offers `allow_once` / `reject_once`; durable `allow_always` grants and their storage/revocation policy remain deferred to the approval seam. diff --git a/packages/ui/acp/acp-feature-support.md b/packages/ui/acp/acp-feature-support.md index 34e3caae8a..0b108cae67 100644 --- a/packages/ui/acp/acp-feature-support.md +++ b/packages/ui/acp/acp-feature-support.md @@ -86,13 +86,13 @@ These are capabilities the bridge would *drive* on the editor. The harness runs | `plan` | S | ❌ | ✅ | ✅ | No agent plan emitted. Both adapters emit real plan entries (Codex's `CodexEventHandler.updatePlan` maps `turn/plan/updated` → `{ sessionUpdate: 'plan', entries }`). | | `available_commands_update` | S | ❌ | ✅ | ✅ | No slash commands advertised. | | `current_mode_update` | S | ❌ | ✅ | ✅ | No session modes. | -| `config_option_update` | S | ❌ | ✅ | ✅ | Config options exist (advertised in `session/new`/`session/load`, switched via `session/set_config_option`), but the bridge never pushes agent-initiated changes — an operator default drift is narrated to the MODEL, not echoed to the editor. Future work in the [sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). | +| `config_option_update` | S | ❌ | ✅ | ✅ | Config options exist (advertised in `session/new`/`session/load`, switched via `session/set_config_option`), but the bridge never pushes agent-initiated changes — an operator default drift is narrated to the MODEL, not echoed to the editor. Future work in the [sandbox Agent Note § Per-session mode switching](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). | | `usage_update` | S | ❌ | ✅ | ✅ | Token/cost reporting not surfaced (the harness records token usage internally on `assistant/message`). | | `session_info_update` | S | ❌ | ⚠️ | ⚠️ | Session title/metadata not pushed. | ## 5. Tool-call rendering -Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult` on the `dsh-tools` definition), not special-cased in the bridge — see the [terminal-and-tool-rendering RFC](../../../docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md). +Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult` on the `dsh-tools` definition), not special-cased in the bridge — see the [terminal-and-tool-rendering Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md). | Feature | Stable | Bridge | Claude | Codex | Notes | |---|---|---|---|---|---| @@ -111,7 +111,7 @@ Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult ## 6. Session modes / config options / models -Config options ✅: the bridge advertises a `model` select from the advisory LLM provider/model catalog, preserving each provider/model pair in an opaque value and grouping multiple providers. A selected pair is isolated to one session, snapshotted with the prompt for each step, applied through `agent/request`, and restored from the logged request header on load. When `ctx.permission` is composed, the bridge also advertises one `permission` select whose values come from the deployment preset table and whose current value derives from the session log; idle permission switches anchor at the next `agent/prompt-submit` inside its open turn. Session modes stay deliberately unmodeled because config options replace them in ACP v2. See the [model-catalog RFC](../../../docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) and [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). +Config options ✅: the bridge advertises a `model` select from the advisory LLM provider/model catalog, preserving each provider/model pair in an opaque value and grouping multiple providers. A selected pair is isolated to one session, snapshotted with the prompt for each step, applied through `agent/request`, and restored from the logged request header on load. When `ctx.permission` is composed, the bridge also advertises one `permission` select whose values come from the deployment preset table and whose current value derives from the session log; idle permission switches anchor at the next `agent/prompt-submit` inside its open turn. Session modes stay deliberately unmodeled because config options replace them in ACP v2. See the [model-catalog Agent Note](../../../.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) and [sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). ## 7. Content blocks @@ -130,7 +130,7 @@ The bridge rejects unsupported prompt blocks rather than silently dropping them | Feature | Stable | Bridge | Notes | |---|---|---|---| | `StopReason` mapping | S | ✅ | `turnEndToStopReason` is total over harness turn-end reasons → `end_turn`/`max_tokens`/`cancelled`. | -| Multi-session (N per connection) | S | ✅ | Strict per-session demux; concurrent streams never interleave. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). | +| Multi-session (N per connection) | S | ✅ | Strict per-session demux; concurrent streams never interleave. See the [multi-session Agent Note](../../../.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md). | | Disconnect / disposal teardown | S | ✅ | Quiesces every live session on client disconnect or Cordis disposal. | | `_meta` extensibility | S | ⚠️ | Consumed (Zed terminal cap) and emitted (terminal `_meta`); no other custom extensions. | | Background-task ownership isolation | — | ✅ | Generic `task_output`/`task_kill` reject tasks whose branded owner `SessionId` belongs to another session. | @@ -156,4 +156,4 @@ Unstable/draft ACP features that **neither** reference adapter ships are not tra - Stable spec: `schema/v1/schema.json` (schema `1.14.0`) and `docs/protocol/v1/*.mdx` in the [agent-client-protocol](https://github.com/agentclientprotocol/agent-client-protocol) repo. - Reference adapters: [`claude-agent-acp`](https://github.com/zed-industries/claude-code-acp) and [`codex-acp`](https://github.com/zed-industries/codex-acp). -- Bridge: [`README.md`](README.md), [`src/index.ts`](src/index.ts), and the ACP RFCs under [`docs/rfc/`](../../../docs/rfc/README.md). +- Bridge: [`README.md`](README.md), [`src/index.ts`](src/index.ts), and the ACP Agent Notes under [`.agents/notes/`](../../../.agents/notes/README.md). diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index e20cd40f10..fe6b2630c7 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -537,7 +537,7 @@ export function apply(ctx: Context, config: AcpConfig): void { // the fail-closed `unavailable` default) takes the question. A rejected // `requestPermission` (client gone, bridge torn down) propagates and the // ApprovalService contains it as `unavailable`. Options are one-shot only: - // allow_always is a grant-storage design the approval RFC defers, so the + // allow_always is a grant-storage design the approval Agent Note defers, so the // prompt never offers a durable grant the harness could not honor. ctx.on('approval/request', (req, next) => { const rec = ownedRecord(req.agent) @@ -627,7 +627,7 @@ export function apply(ctx: Context, config: AcpConfig): void { const protocolVersion = params.protocolVersion === PROTOCOL_VERSION ? params.protocolVersion : PROTOCOL_VERSION // Remember the Zed terminal-output `_meta` capability: when set, bash and // other shell tools render as a terminal card (see streamSessionEventUpdate - // + the terminal-rendering RFC). `_meta` is `{[k]: unknown} | null`, so + // + the terminal-rendering Agent Note). `_meta` is `{[k]: unknown} | null`, so // narrow defensively to a strict boolean true. terminalOutputCap = params.clientCapabilities?._meta?.['terminal_output'] === true return Promise.resolve({ diff --git a/packages/ui/jsonrpc/src/index.ts b/packages/ui/jsonrpc/src/index.ts index 099ef6008f..3da953400f 100644 --- a/packages/ui/jsonrpc/src/index.ts +++ b/packages/ui/jsonrpc/src/index.ts @@ -1,6 +1,6 @@ /** * SDK-facing JSON-RPC plugin over stdio. An external `cordis.yml` decides - * whether to load it; see the single-executable RFC and package README. + * whether to load it; see the single-executable Agent Note and package README. * Stdout is reserved for protocol frames, so the tree must not load a stdout logger. * This plugin answers `shutdown`, disposes its own fiber, and exits 0; the app bin * owns EOF and signal exits. Keep named plugin exports with no default export so diff --git a/packages/ui/permission/README.md b/packages/ui/permission/README.md index e5ee51b69d..f7c135f5e3 100644 --- a/packages/ui/permission/README.md +++ b/packages/ui/permission/README.md @@ -4,7 +4,7 @@ User-facing permission presets through `ctx.permission` ([`PermissionService`](s `set(session, name)` records a changed selection in a log-only `permission/preset` event, then calls each knob's setter only when its effective value changes. The selection event precedes the knob events and preserves user intent when presets share a bundle; a net-zero selection appends nothing. `current(events)` prefers a still-matching recorded selection, then the first matching table entry, and otherwise returns `custom`. Clients may display `custom` as the current value, but cannot select it. -The service requires a confining `ctx.bash` executor and `ctx.approval`. A table entry named `custom` throws at load; composition defaults outside the table instead make a zero-event session derive `custom`. See the [acp-agent composition](../../../examples/acp-agent/) and [sandbox switching design](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). +The service requires a confining `ctx.bash` executor and `ctx.approval`. A table entry named `custom` throws at load; composition defaults outside the table instead make a zero-event session derive `custom`. See the [acp-agent composition](../../../examples/acp-agent/) and [sandbox switching design](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). ## Model Experience diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md index 5da32cbc8d..6d2c7858e4 100644 --- a/packages/ui/tui/README.md +++ b/packages/ui/tui/README.md @@ -2,7 +2,7 @@ The interactive terminal front door for DeepSeek Harness agents, built on [`@earendil-works/pi-tui`](https://www.npmjs.com/package/@earendil-works/pi-tui). It requires stdin and stdout TTYs; scripts and Loader pipes should compose [`@deepseek-ai/dsh-stdio`](../stdio/README.md) instead. -The implemented [TUI feature RFC](../../../docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md) owns the front-door decision; the [terminal-state snapshot RFC](../../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns its verification strategy. +The implemented [TUI feature Agent Note](../../../.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md) owns the front-door decision; the [terminal-state snapshot Agent Note](../../../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns its verification strategy. This package owns interactive terminal presentation and input only. It injects `agents`, `tools`, and `userInteraction`, then drives an agent created or resumed by app or developer code. Agent lifecycle, persistence, and the model-facing [`ask_user_question`](../tool-ask-user/README.md) tool remain separate composition entries. diff --git a/packages/ui/user-approval/README.md b/packages/ui/user-approval/README.md index 94a30ee28e..77b368fac3 100644 --- a/packages/ui/user-approval/README.md +++ b/packages/ui/user-approval/README.md @@ -8,7 +8,7 @@ Answerers are `approval/request` waterfall listeners. Return an outcome to answe `ApprovalPolicy` is `'ask'` or `'never'`. The effective value is the last `approval/policy` event, falling back to config; `setApprovalPolicy()` is the write path. `'never'` rejects before interactive dispatch and is the only policy stated in the prompt. Switches produce at most one coalesced notice, attributed to the user when the override follows the last `request/header` and to operator/config otherwise. -The tools pipeline routes `ask` decisions through this seam and fails closed when it is absent; the sandboxed bash tool also uses it for escalated retries. The ACP bridge is the shipped human answerer for calls it owns. Audit events remain log-only, so the model sees only the asking consumer's result. See the [approval-seam RFC](../../../docs/rfc/implemented/feature/2026-07-06-approval-seam.md) and [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). +The tools pipeline routes `ask` decisions through this seam and fails closed when it is absent; the sandboxed bash tool also uses it for escalated retries. The ACP bridge is the shipped human answerer for calls it owns. Audit events remain log-only, so the model sees only the asking consumer's result. See the [approval-seam Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-approval-seam.md) and [sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). ## Model Experience diff --git a/packages/util/README.md b/packages/util/README.md index 4b4f23ddf7..954026c99c 100644 --- a/packages/util/README.md +++ b/packages/util/README.md @@ -14,6 +14,6 @@ Zero-dependency primitives shared across the other groups. A package lands here `dsh-home` gives every package the same configurable Harness home without assigning that cross-cutting fact to bash, skills, or a composition bundle. It resolves an explicit value before `$DSH_HOME`, falls back to `~/.dsh`, and returns an absolute path without caching, creating, or mutating anything. -`dsh-timeout` follows the same shape for the timeout family: `dsh-bash` and `dsh-web-fetch-local` each fuse a caller's cancellation with a deadline and later classify "timed out" vs "cancelled" by depending on `dsh-timeout` alone. It deliberately owns only the timing/classification half — the *termination* (SIGKILL a process group, tear down a fetch socket) stays in each capability, because no shared layer can own every capability's kill (see [the timeout-library RFC](../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md)). +`dsh-timeout` follows the same shape for the timeout family: `dsh-bash` and `dsh-web-fetch-local` each fuse a caller's cancellation with a deadline and later classify "timed out" vs "cancelled" by depending on `dsh-timeout` alone. It deliberately owns only the timing/classification half — the *termination* (SIGKILL a process group, tear down a fetch socket) stays in each capability, because no shared layer can own every capability's kill (see [the timeout-library Agent Note](../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md)). -`dsh-retention` is the same split for bounded tool output: a tool (`glob`/`grep`/`bash`/`web_fetch`/`web_search`) feeds items or text into a retainer and gets back what it kept and exactly what it omitted — while grouping, exit codes, provider errors, and recovery prose stay tool-owned. It deliberately owns only the retention mechanic; `truncated` is a budget fact, never an "incomplete inspection" state (see [the retention-library RFC](../../docs/rfc/implemented/architecture/2026-07-06-tool-result-retention-library.md)). +`dsh-retention` is the same split for bounded tool output: a tool (`glob`/`grep`/`bash`/`web_fetch`/`web_search`) feeds items or text into a retainer and gets back what it kept and exactly what it omitted — while grouping, exit codes, provider errors, and recovery prose stay tool-owned. It deliberately owns only the retention mechanic; `truncated` is a budget fact, never an "incomplete inspection" state (see [the retention-library Agent Note](../../.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md)). diff --git a/packages/util/retention/README.md b/packages/util/retention/README.md index 21f8e240ba..e3bc6affc2 100644 --- a/packages/util/retention/README.md +++ b/packages/util/retention/README.md @@ -2,7 +2,7 @@ A dependency-light **retention** library: bounded model-facing output for tools that must cap how much context they return. A caller feeds items or text chunks into a bounded object, then gets the retained content plus exact omission metadata. -The library owns **only** the mechanical question *"what did we keep, and what did we omit?"*. Tool-specific code keeps its business semantics: file grouping, line numbering, exit codes, provider error states, per-line preview truncation, spill files, and the model-facing prose. This is the boundary the [RFC](../../../docs/rfc/implemented/architecture/2026-07-06-tool-result-retention-library.md) draws. +The library owns **only** the mechanical question *"what did we keep, and what did we omit?"*. Tool-specific code keeps its business semantics: file grouping, line numbering, exit codes, provider error states, per-line preview truncation, spill files, and the model-facing prose. This is the boundary the [Agent Note](../../../.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md) draws. It is a **library, not a service or plugin**: no `ctx`, registers nothing, emits no events. The only state is per-retainer (one accumulation), never cross-call. Tool packages import it directly. diff --git a/packages/util/timeout/README.md b/packages/util/timeout/README.md index a14f385b2a..b5923a3a73 100644 --- a/packages/util/timeout/README.md +++ b/packages/util/timeout/README.md @@ -2,7 +2,7 @@ The **timing-and-classification** half of a timeout — a zero-dependency library of pure functions (no runtime harness deps) shared by every capability that clamps a caller's timeout hint, arms a deadline, and later has to tell "timed out" apart from "cancelled". -It owns **no termination**. The signal it hands out only *notifies*; actually stopping the work stays in each capability, because that mechanism differs — bash SIGKILLs an OS process group, web tears down a `fetch` socket — and no shared layer can own all of them. This is the boundary the [RFC](../../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md) draws: share the timing/classification, keep the hard kill local. +It owns **no termination**. The signal it hands out only *notifies*; actually stopping the work stays in each capability, because that mechanism differs — bash SIGKILLs an OS process group, web tears down a `fetch` socket — and no shared layer can own all of them. This is the boundary the [Agent Note](../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md) draws: share the timing/classification, keep the hard kill local. It is a **library, not a service or plugin**: no `ctx`, registers nothing, holds no state, emits no events. A "timeout service" would have to understand how to stop every capability's work — exactly the knowledge a microkernel keeps out of shared layers. diff --git a/packages/web/README.md b/packages/web/README.md index c2d34e615f..b465925c79 100644 --- a/packages/web/README.md +++ b/packages/web/README.md @@ -13,4 +13,4 @@ The web access capability seam: an abstract web interface, search/fetch provider The interface lives at `web/web/`. Unlike bash/fs, the seam spans **two capabilities** (search and fetch) with potentially multiple providers each: `ctx.web` is one web-access middle layer with one provider-selection policy, one abort/error vocabulary, and one product-facing "how this harness reaches the web" config surface. Providers register **capabilities**, not tools; `tool-web` is the only owner of model-facing names, schemas, prompt guidance, and presentation. A search provider swap does not change how the model asks for a query, and a fetch implementation swap does not change how the model asks for a URL. -See the [web capability seam RFC](../../docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md) for the design rationale, including why search and fetch are deliberately one seam and why `web_fetch`'s SSRF protection is deferred. +See the [web capability seam Agent Note](../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md) for the design rationale, including why search and fetch are deliberately one seam and why `web_fetch`'s SSRF protection is deferred. diff --git a/packages/web/tool-web/README.md b/packages/web/tool-web/README.md index 399235467e..8cdb9ea737 100644 --- a/packages/web/tool-web/README.md +++ b/packages/web/tool-web/README.md @@ -123,5 +123,5 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work - **`htmlToMarkdown` is a minimal regex converter, not an HTML parser** — it strips script/style/noscript, keeps headings/bullets/links, and decodes about a dozen named entities; tables, images, and nested formatting are lost. -- **The model-facing surface is minimal by design, with promotions deferred** — `max_results` stays a config bound (not a model argument), and `web_fetch` takes only `url` (no `format`/`prompt`/LLM-summarization mode); both are named later steps in [the seam RFC](../../../docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md). +- **The model-facing surface is minimal by design, with promotions deferred** — `max_results` stays a config bound (not a model argument), and `web_fetch` takes only `url` (no `format`/`prompt`/LLM-summarization mode); both are named later steps in [the seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md). - **No web-specific permission policy** — both tools execute without requesting `ctx.approval`; a deployment that needs confirmation must add a `tools/pre-execute` policy, and the package does not define persistent URL/domain grants. diff --git a/packages/web/tool-web/tests/spill.spec.ts b/packages/web/tool-web/tests/spill.spec.ts index 58599d2c54..a2b1f9889d 100644 --- a/packages/web/tool-web/tests/spill.spec.ts +++ b/packages/web/tool-web/tests/spill.spec.ts @@ -1,7 +1,7 @@ /** * Showcase integration: the real `web_fetch` tool + the real spill stack * (`dsh-spill-local` backend + `dsh-spill-policy`), exercised through - * `ctx.tools.execute()`. Proves the RFC's default local-backend path — a large + * `ctx.tools.execute()`. Proves the Agent Note's default local-backend path — a large * formatted fetch result is automatically retained and spilled with NO * tool-specific spill code, and the model-facing text changes ONLY by the * deliberate spill notice (the full formatted result lands in the spill file). @@ -48,7 +48,7 @@ beforeEach(async () => { await ctx.plugin(ToolRegistry) await ctx.plugin(WebService, { fetchProvider: WebFetchLocal.LOCAL_FETCH_PROVIDER_ID }) // Provider cap generous so the tool returns a large formatted result; the - // policy cap is what triggers the spill (the RFC's separation of concerns). + // policy cap is what triggers the spill (the Agent Note's separation of concerns). await ctx.plugin(WebFetchLocal, { maxBodyChars: 500_000 }) await ctx.plugin(LocalSpillStore, { root: spillRoot }) await ctx.plugin(SpillPolicy, { maxInlineBytes: MAX_INLINE_BYTES }) diff --git a/packages/web/web-fetch-local/README.md b/packages/web/web-fetch-local/README.md index 94c23e9c66..160d1c6abd 100644 --- a/packages/web/web-fetch-local/README.md +++ b/packages/web/web-fetch-local/README.md @@ -44,6 +44,6 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work -- **SSRF / private-network protection is deferred** — no blocking of private, loopback, link-local, multicast, or otherwise non-public destinations, no DNS-resolve-then-validate, no per-hop re-validation (see [the web capability seam RFC](../../../docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md)). Until it lands, this provider is an SSRF primitive and **must not be enabled** in a deployment that can reach sensitive internal network targets. +- **SSRF / private-network protection is deferred** — no blocking of private, loopback, link-local, multicast, or otherwise non-public destinations, no DNS-resolve-then-validate, no per-hop re-validation (see [the web capability seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md)). Until it lands, this provider is an SSRF primitive and **must not be enabled** in a deployment that can reach sensitive internal network targets. - **Only textual content decodes** — html/xhtml and `text/*`-plus-JSON/XML families; a missing `Content-Type` or any binary type throws `WEB_UNSUPPORTED_CONTENT_TYPE`, and text-extractable PDF decoding is named deferred work. - **Charset comes only from the `Content-Type` header** (UTF-8 default) — an HTML `<meta charset>` declaration is ignored, and a declared-but-unrecognized charset label throws rather than falling back. diff --git a/packages/web/web-fetch-local/src/policy.ts b/packages/web/web-fetch-local/src/policy.ts index f37697765a..fda9937e47 100644 --- a/packages/web/web-fetch-local/src/policy.ts +++ b/packages/web/web-fetch-local/src/policy.ts @@ -15,7 +15,7 @@ export type FetchableKind = 'html' | 'text' * Validate a request URL against the basic transport hygiene the provider * enforces before any network access: http(s) only, no embedded credentials, * bounded length. Returns the parsed `URL`. Throws {@link WebError} otherwise. - * (SSRF / private-network blocking is deferred — see the package RFC.) + * (SSRF / private-network blocking is deferred — see the package Agent Note.) * * @param input - the raw URL string from the fetch request. * @param maxUrlLength - inclusive upper bound on `input`'s length. diff --git a/packages/web/web-search-exa/README.md b/packages/web/web-search-exa/README.md index 47a420e3ca..a4f1fa648e 100644 --- a/packages/web/web-search-exa/README.md +++ b/packages/web/web-search-exa/README.md @@ -36,5 +36,5 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work - **A result with no non-blank highlight is dropped entirely** — no portable snippet to map, so fewer sources than the requested count can return. -- **Only `searchType`/`numResults`/`highlightsPerResult` are exposed** — Exa's other controls (livecrawl, category, domain/date filters, full-text contents) wait on provider-neutral seam fields ([seam RFC](../../../docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md)). +- **Only `searchType`/`numResults`/`highlightsPerResult` are exposed** — Exa's other controls (livecrawl, category, domain/date filters, full-text contents) wait on provider-neutral seam fields ([seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md)). - **Abort classification is error-shape-based** — only a `DOMException` named `AbortError` maps to `WEB_ABORTED`; an abort carrying a custom reason (e.g. `dsh-timeout`'s `TimeoutReason`) surfaces as `WEB_PROVIDER_ERROR`. diff --git a/packages/web/web-search-perplexity/README.md b/packages/web/web-search-perplexity/README.md index 909930424b..d8f9191621 100644 --- a/packages/web/web-search-perplexity/README.md +++ b/packages/web/web-search-perplexity/README.md @@ -59,5 +59,5 @@ Append-only; newly visible content follows the reusable request prefix and does - **Citation-fallback sources are URL-only** — when Perplexity omits structured `search_results[]`, sources carry no `title`/`snippet`/`publishedAt`, so the tool renders bare hostname labels. - **Over-returned sources still cost tokens and latency** — with no result-count control on the wire, `maxResults` is enforced only post-hoc by seam truncation. -- **Only `model`/`maxTokens`/`searchRecency` are exposed** — Perplexity's other search controls (domain filters, `web_search_options` context size, images) wait on provider-neutral seam fields ([seam RFC](../../../docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md)). +- **Only `model`/`maxTokens`/`searchRecency` are exposed** — Perplexity's other search controls (domain filters, `web_search_options` context size, images) wait on provider-neutral seam fields ([seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md)). - **Abort classification is error-shape-based** — only a `DOMException` named `AbortError` maps to `WEB_ABORTED`; an abort carrying a custom reason (e.g. `dsh-timeout`'s `TimeoutReason`) surfaces as `WEB_PROVIDER_ERROR`. diff --git a/packages/web/web/README.md b/packages/web/web/README.md index 29e6092ff8..507dd1772e 100644 --- a/packages/web/web/README.md +++ b/packages/web/web/README.md @@ -53,7 +53,7 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work -- **No observation surface** — no provider-change event and no capability-status query; availability is observed only by executing `search()`/`fetch()` and routing the thrown `WebError` codes, and the no-provider failure is the generic `WEB_PROVIDER_UNAVAILABLE` with no per-provider reason enumeration ([RFC](../../../docs/rfc/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md)). -- **`WebSearchRequest` carries only `query` + `maxResults`** — provider-neutral controls (recency, domain filters, regional hints, search depth) are deferred until Exa and Perplexity can both honor them honestly ([seam RFC](../../../docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md)). +- **No observation surface** — no provider-change event and no capability-status query; availability is observed only by executing `search()`/`fetch()` and routing the thrown `WebError` codes, and the no-provider failure is the generic `WEB_PROVIDER_UNAVAILABLE` with no per-provider reason enumeration ([Agent Note](../../../.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md)). +- **`WebSearchRequest` carries only `query` + `maxResults`** — provider-neutral controls (recency, domain filters, regional hints, search depth) are deferred until Exa and Perplexity can both honor them honestly ([seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md)). - **`WebFetchBody` has no `pdf` arm** — text-extractable PDF support is named deferred work; the closed union makes adding it a compile-enforced change across the three web packages. - **Provider-backed page extraction is out of scope of `fetch()`** — a Firecrawl/Tavily-style `web_extract` capability is deferred rather than widening the fetch seam. diff --git a/packages/workflow/README.md b/packages/workflow/README.md index 98fa3cfe04..c89e05c6a7 100644 --- a/packages/workflow/README.md +++ b/packages/workflow/README.md @@ -1,6 +1,6 @@ # workflow/ — dynamic-workflow capability family -The workflow seam: a model-written JavaScript orchestration script that fans out subagents at scale (phases, structured per-agent results, concurrency caps), modeled on Claude Code's dynamic workflows. A capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)) in the bash shape: ONE engine implementation per context registers as `ctx.workflows`; the model-facing tool consumes it. +The workflow seam: a model-written JavaScript orchestration script that fans out subagents at scale (phases, structured per-agent results, concurrency caps), modeled on Claude Code's dynamic workflows. A capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)) in the bash shape: ONE engine implementation per context registers as `ctx.workflows`; the model-facing tool consumes it. | Package | Role | ctx key | |---|---|---| @@ -10,4 +10,4 @@ The workflow seam: a model-written JavaScript orchestration script that fans out The interface lives at `workflow/workflow/`. The engine's `agent()` hook rides the [subagent seam](../subagent/README.md) (any registered provider; the shipped examples use `spawn`), and `agent({ schema })` rides the structured-output support the in-process backends implement. The worker thread isolates the SCRIPT — the host never blocks on it, and a cancelled run's post-grace termination is real — but it is NOT a security boundary; an isolated-vm/separate-process engine (actual sandboxing) swaps in behind the same interface if that ever matters. -The proposal, decisions, and deferred work: [docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md](../../docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md). +The proposal, decisions, and deferred work: [.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md](../../.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md). diff --git a/packages/workflow/tool-workflow/README.md b/packages/workflow/tool-workflow/README.md index dc86a38b9d..016f885914 100644 --- a/packages/workflow/tool-workflow/README.md +++ b/packages/workflow/tool-workflow/README.md @@ -12,7 +12,7 @@ Collection is SYNCHRONOUS this cut (like [`dsh-tool-subagent`](../../subagent/to ## Render intent -Decided up front (per the [render-intent RFC](../../../docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md)): a `generic` card titled `workflow: <meta.name>`, read directly from `args.meta.name` (presentation is a pure function of args and does not ask the engine to parse); the script text rides as `rawInput`. The result keeps the generic card. +Decided up front (per the [render-intent Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md)): a `generic` card titled `workflow: <meta.name>`, read directly from `args.meta.name` (presentation is a pure function of args and does not ask the engine to parse); the script text rides as `rawInput`. The result keeps the generic card. ## Config diff --git a/packages/workflow/workflow-workerthread/src/realm.ts b/packages/workflow/workflow-workerthread/src/realm.ts index b16e2f6860..cdcc86f8a0 100644 --- a/packages/workflow/workflow-workerthread/src/realm.ts +++ b/packages/workflow/workflow-workerthread/src/realm.ts @@ -4,7 +4,7 @@ * lossy JSON shapes but trusts model-written workflow scripts: getters and proxy traps may * run, and the vm is not a security boundary. The worker provides host-loop isolation and * forced termination, not hostile-value containment. See - * docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md for the isolation rationale. + * .agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md for the isolation rationale. * @module @deepseek-ai/dsh-workflow-workerthread/realm */ diff --git a/packages/workflow/workflow/README.md b/packages/workflow/workflow/README.md index 9f2b557811..331ae36e8d 100644 --- a/packages/workflow/workflow/README.md +++ b/packages/workflow/workflow/README.md @@ -54,4 +54,4 @@ No direct invalidation; the named consumer owns any request-prefix changes. - **No token-budget vocabulary** — engines cap concurrency, items, and children, but neither the request nor result accounts for model tokens across children. - **Runs are holder-owned, not service-tracked** — unloading the engine does not discover independent live handles; every consumer must dispose the run it started. -See the [dynamic-workflows RFC](../../../docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md) for the deferred workflow surface. +See the [dynamic-workflows Agent Note](../../../.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md) for the deferred workflow surface. diff --git a/pnpm-workspace.yaml b/pnpm-workspace.yaml index 8f93814899..26bfaeeb0b 100644 --- a/pnpm-workspace.yaml +++ b/pnpm-workspace.yaml @@ -7,7 +7,7 @@ packages: # plain-node (`:lib`) boot of any leaf (examples/<leaf>/cordis.yml) resolves its # plugins through real package `exports`→lib by walking up to examples/node_modules. # Members for DEPENDENCY RESOLUTION only — NOT build targets: tsdown's explicit - # globs (vendor/*, packages/*/*) exclude them. See the example-execute-over-tsx RFC. + # globs (vendor/*, packages/*/*) exclude them. See the example-execute-over-tsx Agent Note. - examples # Deploy root of the single-exe build: a pure dependency manifest whose # closure is what the exe bundles and what the Python runtime distributes. diff --git a/python/README.i18n.yaml b/python/README.i18n.yaml index 1470a34443..5df1ca291d 100644 --- a/python/README.i18n.yaml +++ b/python/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 30bca971f1bfc6f694302c8f7eb8ce80843ed9b2 -README.zh.md: d2eea59d148b6de1bdf36b2f2e9c96fc1c933be7 +README.md: d2b6a1cfe9897026d567b2def301799069c350fb +README.zh.md: 2ffccef922d52923f7c6e373a01ed8b19d9a55c1 diff --git a/python/README.md b/python/README.md index 30bca971f1..d2b6a1cfe9 100644 --- a/python/README.md +++ b/python/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Python packages for driving DeepSeek Harness as a subprocess: a client SDK that spawns the `dsh-jsonrpc-agent` binary and talks newline-delimited JSON-RPC over stdio. The runtime carrier is the single-file executable produced by this repo; design, build, and acceptance details live in [docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). +Python packages for driving DeepSeek Harness as a subprocess: a client SDK that spawns the `dsh-jsonrpc-agent` binary and talks newline-delimited JSON-RPC over stdio. The runtime carrier is the single-file executable produced by this repo; design, build, and acceptance details live in [.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). ## Packages diff --git a/python/README.zh.md b/python/README.zh.md index d2eea59d14..2ffccef922 100644 --- a/python/README.zh.md +++ b/python/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -以子进程方式驱动 DeepSeek Harness 的 Python 包：客户端 SDK spawn `dsh-jsonrpc-agent` 二进制，并通过 stdio 上按行分隔的 JSON-RPC 与之通信。运行时载体是本仓库产出的单文件可执行文件；设计、构建与验收细节见 [docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)。 +以子进程方式驱动 DeepSeek Harness 的 Python 包：客户端 SDK spawn `dsh-jsonrpc-agent` 二进制，并通过 stdio 上按行分隔的 JSON-RPC 与之通信。运行时载体是本仓库产出的单文件可执行文件；设计、构建与验收细节见 [.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)。 ## 包 diff --git a/scripts/rfc-index.ts b/scripts/agent-note-index.ts similarity index 61% rename from scripts/rfc-index.ts rename to scripts/agent-note-index.ts index a8d7868bce..e5006eab80 100644 --- a/scripts/rfc-index.ts +++ b/scripts/agent-note-index.ts @@ -1,8 +1,8 @@ /** - * Shared source of truth for the RFC index: the tree walker (structure rules) and the README - * table renderer. `gen-rfc-index.ts` writes the generated regions; - * `verify-rfc-classification.ts` checks structure and asserts the committed regions are fresh. - * Lifecycle and class sets are closed under `docs/rfc/README.md`; rows derive + * Shared source of truth for the Agent Note index: the tree walker (structure rules) and the README + * table renderer. `gen-agent-note-index.ts` writes the generated regions; + * `verify-agent-note-classification.ts` checks structure and asserts the committed regions are fresh. + * Lifecycle and class sets are closed under `.agents/notes/README.md`; rows derive * from path, H1, and filename date and sort deterministically. Import is pure. */ @@ -10,59 +10,59 @@ import { readFileSync, readdirSync } from 'node:fs' import { resolve, sep } from 'node:path' import { globSync } from 'node:fs' -export const rfcRoot = resolve(import.meta.dirname, '../docs/rfc') +export const agentNoteRoot = resolve(import.meta.dirname, '../.agents/notes') -/** The closed set of RFC lifecycles (top-level folders under docs/rfc/). */ +/** The closed set of Agent Note lifecycles (top-level folders under .agents/notes/). */ const LIFECYCLES = ['proposed', 'implemented', 'rejected'] as const /** - * The closed set of RFC classes (nested folder under each lifecycle). Adding a + * The closed set of Agent Note classes (nested folder under each lifecycle). Adding a * class is a deliberate act: extend this list AND the README's Classification * section. The gate rejects any folder not listed here. */ const CLASSES = ['feature', 'bug-fix', 'simplification', 'architecture', 'process', 'testing'] as const -/** Non-RFC Markdown allowed to sit directly at a lifecycle root. */ +/** Non-Agent Note Markdown allowed to sit directly at a lifecycle root. */ const ROOT_ALLOWLIST = new Set(['AGENTS.md', 'CLAUDE.md']) /** Title-case a class/lifecycle folder name for a README heading. */ const heading = (s: string): string => s.charAt(0).toUpperCase() + s.slice(1) -/** One RFC file, as discovered by the walker. */ -export interface Rfc { +/** One Agent Note file, as discovered by the walker. */ +export interface AgentNote { lifecycle: string cls: string base: string - /** Path relative to docs/rfc — the README link target. */ + /** Path relative to .agents/notes — the README link target. */ rel: string - /** H1 text with any `RFC: ` prefix stripped — the README row title. */ + /** H1 text with any `Agent Note: ` prefix stripped — the README row title. */ title: string /** `yyyy-mm-dd` from the filename — the "First proposed" column. */ date: string } /** - * Walk the RFC tree, enforcing the structure rules. Returns every valid RFC + * Walk the Agent Note tree, enforcing the structure rules. Returns every valid Agent Note * plus one error string per violation (unknown lifecycle or class folder, bad * depth, bad filename, missing/malformed H1). Callers treat a non-empty error * list as fatal — the index is only generated from a structurally valid tree. */ -export function walkRfcTree(): { rfcs: Rfc[]; errors: string[] } { - const rfcs: Rfc[] = [] +export function walkAgentNoteTree(): { notes: AgentNote[]; errors: string[] } { + const notes: AgentNote[] = [] const errors: string[] = [] - // The lifecycle set is closed too: any directory under docs/rfc/ that is not - // a known lifecycle would otherwise hold RFCs invisible to the walk below. - for (const entry of readdirSync(rfcRoot, { withFileTypes: true })) { + // The lifecycle set is closed too: any directory under .agents/notes/ that is not + // a known lifecycle would otherwise hold Agent Notes invisible to the walk below. + for (const entry of readdirSync(agentNoteRoot, { withFileTypes: true })) { if (entry.isDirectory() && !(LIFECYCLES as readonly string[]).includes(entry.name)) { errors.push(`structure: ${entry.name}/ — unknown lifecycle folder (allowed: ${LIFECYCLES.join(', ')})`) } } for (const lifecycle of LIFECYCLES) { - for (const match of globSync(`${lifecycle}/**/*.md`, { cwd: rfcRoot }).map(path => path.split(sep).join('/')).sort()) { + for (const match of globSync(`${lifecycle}/**/*.md`, { cwd: agentNoteRoot }).map(path => path.split(sep).join('/')).sort()) { const segs = match.split('/') // Allowlisted file directly at the lifecycle root (e.g. implemented/AGENTS.md). if (segs.length === 2 && ROOT_ALLOWLIST.has(segs[1] ?? '')) continue - // A Chinese counterpart (foo.zh.md, docs/i18n/README.md) is the SAME RFC, + // A Chinese counterpart (foo.zh.md, docs/i18n/README.md) is the SAME Agent Note, // indexed via its English filename; the pairing gate owns its consistency. if (match.endsWith('.zh.md')) continue const cls = segs[1] @@ -79,16 +79,16 @@ export function walkRfcTree(): { rfcs: Rfc[]; errors: string[] } { errors.push(`structure: ${match} — filename must be yyyy-mm-dd-topic.md`) continue } - const firstLine = readFileSync(resolve(rfcRoot, match), 'utf8').split('\n', 1)[0] ?? '' - const h1 = /^#\s+(?:RFC:\s+)?(.+?)\s*$/.exec(firstLine) + const firstLine = readFileSync(resolve(agentNoteRoot, match), 'utf8').split('\n', 1)[0] ?? '' + const h1 = /^#\s+(?:Agent Note:\s+)?(.+?)\s*$/.exec(firstLine) if (!h1?.[1]) { - errors.push(`title: ${match} — first line must be an H1 (\`# RFC: <title>\` or \`# <title>\`), got: ${JSON.stringify(firstLine)}`) + errors.push(`title: ${match} — first line must be an H1 (\`# Agent Note: <title>\` or \`# <title>\`), got: ${JSON.stringify(firstLine)}`) continue } - rfcs.push({ lifecycle, cls, base, rel: match, title: h1[1], date: base.slice(0, 10) }) + notes.push({ lifecycle, cls, base, rel: match, title: h1[1], date: base.slice(0, 10) }) } } - return { rfcs, errors } + return { notes, errors } } /** @@ -96,10 +96,10 @@ export function walkRfcTree(): { rfcs: Rfc[]; errors: string[] } { * `| Title | First proposed |` table for every non-empty class, in CLASSES * order, rows sorted by date then filename. */ -function renderLifecycle(rfcs: Rfc[], lifecycle: string): string { +function renderLifecycle(notes: AgentNote[], lifecycle: string): string { const sections: string[] = [] for (const cls of CLASSES) { - const rows = rfcs + const rows = notes .filter(r => r.lifecycle === lifecycle && r.cls === cls) .sort((a, b) => a.date.localeCompare(b.date) || a.base.localeCompare(b.base)) if (rows.length === 0) continue @@ -110,18 +110,18 @@ function renderLifecycle(rfcs: Rfc[], lifecycle: string): string { } /** - * Render the complete `docs/rfc/INDEX.md` content: a generated-file banner + * Render the complete `.agents/notes/INDEX.md` content: a generated-file banner * followed by one `## {Lifecycle}` section per lifecycle in canonical order. * The whole file is generated state — there is no curated region to preserve. */ -export function renderIndex(rfcs: Rfc[]): string { +export function renderIndex(notes: AgentNote[]): string { const parts = [ - '# RFC index', + '# Agent Note index', '', - 'Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; `verify-rfc-classification` fails when this file is stale. The curated front door — layout, classification, when to write one, and the in-file format — is [README.md](README.md).', + 'Generated by `pnpm run gen-agent-note-index` from the Agent Note tree — never edit by hand; `verify-agent-note-classification` fails when this file is stale. The curated front door — layout, classification, when to write one, and the in-file format — is [README.md](README.md).', ] for (const lifecycle of LIFECYCLES) { - parts.push('', `## ${heading(lifecycle)}`, '', renderLifecycle(rfcs, lifecycle)) + parts.push('', `## ${heading(lifecycle)}`, '', renderLifecycle(notes, lifecycle)) } return `${parts.join('\n')}\n` } diff --git a/scripts/build-exe-for-python-sdk.ts b/scripts/build-exe-for-python-sdk.ts index ebca6cebd7..b72f73671e 100644 --- a/scripts/build-exe-for-python-sdk.ts +++ b/scripts/build-exe-for-python-sdk.ts @@ -1,7 +1,7 @@ /** * Build the SDK runtime executables and Python node carrier. The fixed * `@yao-pkg/pkg --sea` route, deploy flags, and artifact layout are owned by - * docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md. + * .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md. * The staged closure is symlink-free, and whole-tree assets cover Cordis's * runtime imports that pkg cannot discover statically. */ @@ -69,7 +69,7 @@ class Target { readonly nodeRange: string, /** * pkg platform tag. Windows is a documented non-goal - * (docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). + * (.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). */ readonly platform: Platform, /** pkg CPU tag. */ @@ -190,7 +190,7 @@ class BuildCli { ' --dry-run print every command and config patch without executing.', ' --help print this help.', '', - `Build route: ${PKG_SPEC} --sea; see docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md.`, + `Build route: ${PKG_SPEC} --sea; see .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md.`, `Stages the node carrier in ${PYTHON_RUNTIME_DIR}/${PYTHON_NODE_SUBDIR} and writes executables to ${OUT_DIR}/.`, ].join('\n') } diff --git a/scripts/doc-typecheck.ts b/scripts/doc-typecheck.ts index 34af82b48b..9149653e6d 100644 --- a/scripts/doc-typecheck.ts +++ b/scripts/doc-typecheck.ts @@ -192,7 +192,7 @@ function remapBlockPaths(output: string, blocks: Block[]): string { }) } -const markdownGlobs = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', 'website/zh-CN/**/*.md'] +const markdownGlobs = ['README.md', '.agents/notes/**/*.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', 'website/zh-CN/**/*.md'] const files: string[] = [] for (const pattern of markdownGlobs) { diff --git a/scripts/gen-agent-note-index.ts b/scripts/gen-agent-note-index.ts new file mode 100644 index 0000000000..df54300a19 --- /dev/null +++ b/scripts/gen-agent-note-index.ts @@ -0,0 +1,36 @@ +/** + * Regenerate `.agents/notes/INDEX.md` — the fully generated Agent Note index — from the + * Agent Note tree (see [agent-note-index.ts](./agent-note-index.ts) for the layout contract and + * rendering rules). The whole file is generated state; the curated prose lives + * in `.agents/notes/README.md`. Freshness is asserted by + * `verify-agent-note-classification.ts` (a `doc-sync` member), so a stale committed + * index fails CI. + * + * Run: `pnpm run gen-agent-note-index`. + */ + +import { readFileSync, writeFileSync } from 'node:fs' +import { resolve } from 'node:path' +import { agentNoteRoot, renderIndex, walkAgentNoteTree } from './agent-note-index.ts' + +const { notes, errors } = walkAgentNoteTree() +if (errors.length > 0) { + console.error('gen-agent-note-index: refusing to generate from a structurally invalid tree:') + for (const e of errors) console.error(` ${e}`) + process.exit(1) +} + +const indexPath = resolve(agentNoteRoot, 'INDEX.md') +const next = renderIndex(notes) +let current: string | undefined +try { + current = readFileSync(indexPath, 'utf8') +} catch { + // Missing INDEX.md is the fresh-generation case, not an error: fall through and write it. +} +if (next === current) { + console.log(`gen-agent-note-index: .agents/notes/INDEX.md is up to date (${notes.length} Agent Notes).`) +} else { + writeFileSync(indexPath, next) + console.log(`gen-agent-note-index: .agents/notes/INDEX.md regenerated (${notes.length} Agent Notes).`) +} diff --git a/scripts/gen-config-catalog.ts b/scripts/gen-config-catalog.ts index a0f3909a36..b4c20d596a 100644 --- a/scripts/gen-config-catalog.ts +++ b/scripts/gen-config-catalog.ts @@ -837,7 +837,7 @@ export function render(entries: CatalogEntry[]): string { '', '## Seam packages (not directly loadable)', '', - 'Abstract service classes — a deployment loads a concrete implementation package instead ([capability seams](rfc/implemented/architecture/2026-06-13-capability-seams.md)).', + 'Abstract service classes — a deployment loads a concrete implementation package instead ([capability seams](../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)).', '', ...entries.filter(e => e.kind === 'seam').map(e => renderTerse(e, ` — abstract \`${e.className ?? ''}\``)), '', diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 4e3f049ac9..bef2fea1e2 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -1046,7 +1046,7 @@ function renderIndex(docs: GraphDoc[]): string { ...generatedHeader('Documentation Graph Index'), 'These diagrams are the relationship layer above the generated catalogs. Use them to navigate package topology, capability seams, event flow, model-facing tools, app composition, and runtime lifecycle paths. Exact signatures and type shapes still live in the generated [events](cordis-catalog/events.md) / [services](cordis-catalog/services.md) catalogs, [tool-catalog.md](tool-catalog.md), and [core-data-structures/](core-data-structures/core.md).', '', - 'The process decision behind this index is recorded in [the documentation graph RFC](rfc/implemented/process/2026-07-03-documentation-graph-atlas.md).', + 'The process decision behind this index is recorded in [the documentation graph Agent Note](../.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md).', '', '| Graph | Mode |', '| --- | --- |', diff --git a/scripts/gen-persistence-catalog.ts b/scripts/gen-persistence-catalog.ts index 8762b8529e..167fd3c7f1 100644 --- a/scripts/gen-persistence-catalog.ts +++ b/scripts/gen-persistence-catalog.ts @@ -349,7 +349,7 @@ export function render(events: AnnotatedLogEventEntry[], envelopeTypes: EventEnv '', 'Every event type that can appear in a session\'s durable event log: the complete persisted `SessionEvent` envelope and each member of the merge-extensible `SessionEventMap` — the owning vocabulary in `@deepseek-ai/dsh-session` plus every plugin declaration merge in this repo — with source JSDoc, full payload declaration, surface badge, and declaration site. It complements [session.md](core-data-structures/session.md) (surface ordering and the `deriveMessages()` projection), [persistence.md](core-data-structures/persistence.md) (how the log is made durable), and the [cordis events catalog](cordis-catalog/events.md) (the live bus wiring — a log event is NOT a cordis event; it reaches listeners via the single `session/event` emit).', '', - 'This file is GENERATED from source (`scripts/gen-persistence-catalog.ts`) and verified fresh by `pnpm run verify-persistence-catalog` (part of `doc-sync`) — do not edit it by hand. Declaration blocks retain the source declaration and nested property JSDoc, removing only the indentation imposed by a containing interface/module, and use a `ts persistence-catalog` fence (skipped by doc-typecheck because declarations reference types from their owning modules). Type names in a payload link to the page that documents them. See [the persistence-log-catalog RFC](rfc/implemented/process/2026-07-04-persistence-log-catalog.md).', + 'This file is GENERATED from source (`scripts/gen-persistence-catalog.ts`) and verified fresh by `pnpm run verify-persistence-catalog` (part of `doc-sync`) — do not edit it by hand. Declaration blocks retain the source declaration and nested property JSDoc, removing only the indentation imposed by a containing interface/module, and use a `ts persistence-catalog` fence (skipped by doc-typecheck because declarations reference types from their owning modules). Type names in a payload link to the page that documents them. See [the persistence-log-catalog Agent Note](../.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md).', '', 'The envelope declarations below compose each event\'s `type`, monotonic `seq`, epoch-ms `time`, `data`, and the conditional `surfaceOp`/`sourceEventSeqs` fields. **surface** marks a `SurfaceEventType` member: it produces an LLM message and declares how it joins the surface list. **log-only** marks everything else: a durable, replayable record with no derived-history contribution. Every payload is JSON-serializable (enforced at `Session.append`), and the whole format is pinned at `SESSION_FORMAT_VERSION = 0` — pre-release, no compatibility implied ([the version stance](core-data-structures/persistence.md)). Scope: the packages in this repo; a downstream plugin can merge further event types, which are outside this catalog by construction.', '', diff --git a/scripts/gen-rfc-index.ts b/scripts/gen-rfc-index.ts deleted file mode 100644 index 37ad96d73a..0000000000 --- a/scripts/gen-rfc-index.ts +++ /dev/null @@ -1,36 +0,0 @@ -/** - * Regenerate `docs/rfc/INDEX.md` — the fully generated RFC index — from the - * RFC tree (see [rfc-index.ts](./rfc-index.ts) for the layout contract and - * rendering rules). The whole file is generated state; the curated prose lives - * in `docs/rfc/README.md`. Freshness is asserted by - * `verify-rfc-classification.ts` (a `doc-sync` member), so a stale committed - * index fails CI. - * - * Run: `pnpm run gen-rfc-index`. - */ - -import { readFileSync, writeFileSync } from 'node:fs' -import { resolve } from 'node:path' -import { renderIndex, rfcRoot, walkRfcTree } from './rfc-index.ts' - -const { rfcs, errors } = walkRfcTree() -if (errors.length > 0) { - console.error('gen-rfc-index: refusing to generate from a structurally invalid tree:') - for (const e of errors) console.error(` ${e}`) - process.exit(1) -} - -const indexPath = resolve(rfcRoot, 'INDEX.md') -const next = renderIndex(rfcs) -let current: string | undefined -try { - current = readFileSync(indexPath, 'utf8') -} catch { - // Missing INDEX.md is the fresh-generation case, not an error: fall through and write it. -} -if (next === current) { - console.log(`gen-rfc-index: docs/rfc/INDEX.md is up to date (${rfcs.length} RFCs).`) -} else { - writeFileSync(indexPath, next) - console.log(`gen-rfc-index: docs/rfc/INDEX.md regenerated (${rfcs.length} RFCs).`) -} diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 8606d30895..ab9e0bb86f 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -3,7 +3,7 @@ * plugin. Runtime registration is the source of truth for computed schemas; * the manifest is checked against every on-disk `tool-*` package. `--check` * verifies the committed artifact. Rationale and ownership live in - * `docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md`. + * `.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md`. */ import { globSync, readFileSync, writeFileSync } from 'node:fs' @@ -119,7 +119,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ toolsConfig: { mode: 'code' }, async mount() {}, note: - 'Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the registry\'s only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result.', + 'Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode Agent Note). Under `code` it is the registry\'s only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result.', }, { pkg: '@deepseek-ai/dsh-tool-bash', @@ -144,7 +144,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolCordis) }, note: - 'Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes.', + 'Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes.', }, { pkg: '@deepseek-ai/dsh-tool-fs', @@ -367,7 +367,7 @@ export function render(catalog: ToolCatalog): string { '', 'Every model-facing tool a shipped plugin contributes to `ctx.tools`: the `name`, `description`, and JSON-Schema `parameters` the model receives via the system-prompt assembly. It complements the cordis [events](cordis-catalog/events.md) & [services](cordis-catalog/services.md) catalogs (the wiring a plugin listens to and calls) and [core-data-structures/](core-data-structures/core.md) (the types those signatures move) — this page is the *tools* the agent is offered.', '', - 'This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator\'s boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md).', + 'This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator\'s boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog Agent Note](../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md).', '', 'Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`\'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog\'s packages-only scope.', '', diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index f46de4475a..0262c1099c 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -344,8 +344,8 @@ function docSyncLeafGates(options: { pnpmScript('package-paths', 'verify-package-paths', { label: 'package paths' }), pnpmScript('package-readme-model-experience', 'verify-package-readme-model-experience', { label: 'package README model experience' }), pnpmScript('mermaid', 'verify-mermaid'), - pnpmScript('rfc-classification', 'verify-rfc-classification', { label: 'rfc classification' }), - pnpmScript('rfc-format', 'verify-rfc-format', { label: 'rfc format' }), + pnpmScript('agent-note-classification', 'verify-agent-note-classification', { label: 'agent note classification' }), + pnpmScript('agent-note-format', 'verify-agent-note-format', { label: 'agent note format' }), pnpmScript('type-equivalence', 'verify-type-equiv', { label: 'type equivalence' }), pnpmScript('translation-prompt', 'verify-translation-prompt', { label: 'translation prompt' }), pnpmScript('translation-pairing', 'verify-translation-pairing', { label: 'translation pairing' }), diff --git a/scripts/translation-pairing.manifest.json b/scripts/translation-pairing.manifest.json index 35a957e57d..7f6202a8f4 100644 --- a/scripts/translation-pairing.manifest.json +++ b/scripts/translation-pairing.manifest.json @@ -11,13 +11,15 @@ "docs/development.md", "docs/i18n/README.md", "docs/i18n/translation-rules.md", - "docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md", - "docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md", + ".agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md", + ".agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md", "python/README.md", "python/sdk-runtime/README.md", "python/sdk/README.md" ], "excluded": [ + ".agents/notes/AGENTS.md", + ".agents/notes/implemented/AGENTS.md", "docs/AGENTS.md", "docs/config-catalog.md", "docs/cordis-catalog/", diff --git a/scripts/translation-pairing.spec.ts b/scripts/translation-pairing.spec.ts index 39051969fc..2bdc4f4e15 100644 --- a/scripts/translation-pairing.spec.ts +++ b/scripts/translation-pairing.spec.ts @@ -50,13 +50,13 @@ describe('date-based pairing frontier', () => { const cutoff = '2026-07-14' it('enforces the cutoff day and every later day, but not the preceding day', () => { - expect(requiresPairByDate('docs/rfc/2026-07-13-before.md', cutoff)).toBe(false) - expect(requiresPairByDate('docs/rfc/2026-07-14-at-cutoff.md', cutoff)).toBe(true) - expect(requiresPairByDate('docs/rfc/2026-07-15-after.md', cutoff)).toBe(true) + expect(requiresPairByDate('.agents/notes/2026-07-13-before.md', cutoff)).toBe(false) + expect(requiresPairByDate('.agents/notes/2026-07-14-at-cutoff.md', cutoff)).toBe(true) + expect(requiresPairByDate('.agents/notes/2026-07-15-after.md', cutoff)).toBe(true) }) it('matches only a date at the start of the basename', () => { - expect(datedDocumentDate('docs/rfc/2026-07-14-proposal.md')).toBe('2026-07-14') + expect(datedDocumentDate('.agents/notes/2026-07-14-proposal.md')).toBe('2026-07-14') expect(datedDocumentDate('docs/release-notes-2026-07-14-alpha.md')).toBeUndefined() expect(requiresPairByDate('docs/release-notes-2026-07-14-alpha.md', cutoff)).toBe(false) }) diff --git a/scripts/verify-agent-note-classification.ts b/scripts/verify-agent-note-classification.ts new file mode 100644 index 0000000000..81cc79c5f5 --- /dev/null +++ b/scripts/verify-agent-note-classification.ts @@ -0,0 +1,46 @@ +/** + * Enforce Agent Note lifecycle/class paths, dated filenames, and titles; verify the + * generated index and reject index rows in the curated README. Structural rules + * and rendering are shared with `agent-note-index.ts`; the closed classification + * contract lives in `.agents/notes/README.md`. + */ + +import { existsSync, readFileSync } from 'node:fs' +import { resolve } from 'node:path' +import { agentNoteRoot, INDEX_ROW, renderIndex, walkAgentNoteTree } from './agent-note-index.ts' + +const { notes, errors } = walkAgentNoteTree() + +// Keep the former homes unavailable so new notes cannot silently escape this tree. +for (const legacyRoot of ['docs/rfc', 'docs/rfcs']) { + if (existsSync(resolve(import.meta.dirname, '..', legacyRoot))) { + errors.push(`legacy-path: ${legacyRoot}/ is forbidden — put Agent Notes under .agents/notes/`) + } +} + +if (errors.length === 0) { + let index: string | undefined + try { + index = readFileSync(resolve(agentNoteRoot, 'INDEX.md'), 'utf8') + } catch { + // A missing INDEX.md is reported below as staleness, exactly like a drifted one. + } + if (renderIndex(notes) !== index) { + errors.push('index: .agents/notes/INDEX.md is stale or missing — run `pnpm run gen-agent-note-index` and commit the result') + } + const readme = readFileSync(resolve(agentNoteRoot, 'README.md'), 'utf8') + for (const line of readme.split('\n')) { + if (INDEX_ROW.test(line)) { + errors.push(`readme: index-shaped row in the curated README (the list lives in INDEX.md): ${JSON.stringify(line.slice(0, 80))}`) + } + } +} + +if (errors.length === 0) { + console.log(`verify-agent-note-classification: ${notes.length} Agent Note(s) checked, structure and index consistent.`) + process.exit(0) +} + +console.error('verify-agent-note-classification: violations found:') +for (const e of errors) console.error(` ${e}`) +process.exit(1) diff --git a/scripts/verify-rfc-format.ts b/scripts/verify-agent-note-format.ts similarity index 60% rename from scripts/verify-rfc-format.ts rename to scripts/verify-agent-note-format.ts index 341f184abb..b38c6225bd 100644 --- a/scripts/verify-rfc-format.ts +++ b/scripts/verify-agent-note-format.ts @@ -1,22 +1,22 @@ /** - * Enforce RFC headers, lifecycle-specific sections, alternatives, and retired + * Enforce Agent Note headers, lifecycle-specific sections, alternatives, and retired * marker rules. Classification and filenames belong to the sibling tree gate; * translation structure belongs to the pairing gate. Exact format and - * grandfathering rules live in `docs/rfc/README.md`. + * grandfathering rules live in `.agents/notes/README.md`. */ import { readFileSync } from 'node:fs' import { resolve } from 'node:path' -import { rfcRoot, walkRfcTree } from './rfc-index.ts' +import { agentNoteRoot, walkAgentNoteTree } from './agent-note-index.ts' /** The date the format contract landed; the grandfather comment is valid only before it. */ const FORMAT_ADOPTED = '2026-07-05' -/** The exact comment a pre-format RFC carries in place of `## Alternatives considered`. */ -const GRANDFATHER = '<!-- rfc-format: alternatives-not-recorded (pre-format RFC) -->' +/** The exact comment a pre-format Agent Note carries in place of `## Alternatives considered`. */ +const GRANDFATHER = '<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) -->' /** The retired debt marker that flagged pre-format bodies; banned so it cannot creep back. */ -const LEGACY_MARKER = 'XXX: legacy ADR/RFC body format' +const LEGACY_MARKERS = ['XXX: legacy ADR/RFC body format', 'XXX: legacy ADR/Agent Note body format'] /** Status-line grammar per lifecycle folder. */ const STATUS: Record<string, RegExp> = { @@ -35,13 +35,13 @@ const REQUIRED: Record<string, string[]> = { /** Headings banned in `implemented/` — proposal-era spec-speak per the slop checklist. */ const BANNED_IMPLEMENTED = /^## (?:Proposal\b|Plan\b|Migration plan\b|Acceptance criteria\b)/i -const { rfcs, errors } = walkRfcTree() +const { notes, errors } = walkAgentNoteTree() -for (const rfc of rfcs) { +for (const note of notes) { const fail = (msg: string): void => { - errors.push(`format: ${rfc.rel} — ${msg}`) + errors.push(`format: ${note.rel} — ${msg}`) } - const lines = readFileSync(resolve(rfcRoot, rfc.rel), 'utf8').split('\n') + const lines = readFileSync(resolve(agentNoteRoot, note.rel), 'utf8').split('\n') // Format tokens inside fenced examples are not document structure. let inFence = false const prose = lines.filter((l) => { @@ -52,11 +52,11 @@ for (const rfc of rfcs) { return !inFence }) - if (!/^# RFC: \S/.test(lines[0] ?? '')) fail('line 1 must be `# RFC: <title>`') + if (!/^# Agent Note: \S/.test(lines[0] ?? '')) fail('line 1 must be `# Agent Note: <title>`') if (lines[1] !== '') fail('line 2 must be blank') - const status = STATUS[rfc.lifecycle] + const status = STATUS[note.lifecycle] if (status !== undefined && !status.test(lines[2] ?? '')) { - fail(`line 3 must match the ${rfc.lifecycle} status grammar (${String(status)})`) + fail(`line 3 must match the ${note.lifecycle} status grammar (${String(status)})`) } if (lines[3] !== '') fail('line 4 must be blank') const statusLines = prose.filter(l => l.startsWith('Status:') && l !== lines[2]) @@ -66,29 +66,29 @@ for (const rfc of rfcs) { const h2s = prose.filter(l => l.startsWith('## ')).map(l => l.trimEnd()) if (h2s[0] !== '## Problem') fail(`the first section must be \`## Problem\` (got ${JSON.stringify(h2s[0] ?? '<none>')})`) - for (const required of REQUIRED[rfc.lifecycle] ?? []) { + for (const required of REQUIRED[note.lifecycle] ?? []) { if (!h2s.includes(required)) fail(`missing the required \`${required}\` section`) } - if (rfc.lifecycle === 'implemented') { + if (note.lifecycle === 'implemented') { for (const h2 of h2s.filter(h => BANNED_IMPLEMENTED.test(h))) { - fail(`\`${h2}\` is a proposal-era heading; an implemented RFC states what is (fold it into Decision/Consequences/Testing)`) + fail(`\`${h2}\` is a proposal-era heading; an implemented Agent Note states what is (fold it into Decision/Consequences/Testing)`) } } const hasSection = h2s.includes('## Alternatives considered') const hasGrandfather = prose.includes(GRANDFATHER) if (hasSection && hasGrandfather) fail('carries both `## Alternatives considered` and the grandfather comment — drop the comment') - if (!hasSection && !hasGrandfather) fail('missing `## Alternatives considered` (a pre-format RFC whose alternatives are not reconstructible carries the grandfather comment instead — see docs/rfc/README.md § The file format)') - if (hasGrandfather && rfc.date >= FORMAT_ADOPTED) fail(`the grandfather comment is only valid for RFCs dated before ${FORMAT_ADOPTED}`) + if (!hasSection && !hasGrandfather) fail('missing `## Alternatives considered` (a pre-format Agent Note whose alternatives are not reconstructible carries the grandfather comment instead — see .agents/notes/README.md § The file format)') + if (hasGrandfather && note.date >= FORMAT_ADOPTED) fail(`the grandfather comment is only valid for Agent Notes dated before ${FORMAT_ADOPTED}`) - if (prose.some(l => l.includes(LEGACY_MARKER))) fail('carries the retired legacy-format debt marker') + if (prose.some(line => LEGACY_MARKERS.some(marker => line.includes(marker)))) fail('carries the retired legacy-format debt marker') } if (errors.length === 0) { - console.log(`verify-rfc-format: ${rfcs.length} RFC(s) checked, all conform to docs/rfc/README.md § The file format.`) + console.log(`verify-agent-note-format: ${notes.length} Agent Note(s) checked, all conform to .agents/notes/README.md § The file format.`) process.exit(0) } -console.error('verify-rfc-format: violations found:') +console.error('verify-agent-note-format: violations found:') for (const e of errors) console.error(` ${e}`) process.exit(1) diff --git a/scripts/verify-doc-refs.ts b/scripts/verify-doc-refs.ts index e1885f7b6e..8e181a1d85 100644 --- a/scripts/verify-doc-refs.ts +++ b/scripts/verify-doc-refs.ts @@ -1,7 +1,8 @@ /** - * Verify root-relative `docs/*.md` tokens in repo-authored TypeScript. The - * textual scan requires the extension, checks matching string literals too, - * and excludes built declarations and vendored source. + * Verify root-relative documentation paths in repo-authored TypeScript. The + * textual scan covers `docs/*.md` and `.agents/notes/*.md`, requires the + * extension, checks matching string literals too, and excludes built + * declarations and vendored source. */ import { existsSync } from 'node:fs' @@ -18,9 +19,9 @@ const isExcluded = (p: string): boolean => p.includes('/lib/') || p.endsWith('.d.ts') || p.startsWith('vendor/') /** Root-relative Markdown path token, excluding trailing prose. */ -const DOC_REF = /\bdocs\/[A-Za-z0-9._/-]+\.md/g +const DOC_REF = /(?:\bdocs|\.agents\/notes)\/[A-Za-z0-9._/-]+\.md/g -/** Find every broken `docs/….md` reference in one TypeScript file. */ +/** Find every broken root-relative documentation reference in one TypeScript file. */ function findViolations(absPath: string): Violation[] { return findReferenceViolations(root, absPath, DOC_REF, ref => ref, ref => !existsSync(resolve(root, ref))) } @@ -30,11 +31,11 @@ const all = files.flatMap(file => findViolations(file.abs)) const checked = files.length if (all.length === 0) { - console.log(`verify-doc-refs: ${checked} file(s) checked, all docs/*.md references resolve.`) + console.log(`verify-doc-refs: ${checked} file(s) checked, all documentation references resolve.`) process.exit(0) } -console.error('verify-doc-refs: broken docs/*.md references found in source comments (target does not exist):') +console.error('verify-doc-refs: broken documentation references found in source comments (target does not exist):') for (const v of all) { console.error(` ${v.file}:${v.line} ${v.ref}`) } diff --git a/scripts/verify-md-links.ts b/scripts/verify-md-links.ts index f0d61feb6a..23da09db5f 100644 --- a/scripts/verify-md-links.ts +++ b/scripts/verify-md-links.ts @@ -17,6 +17,7 @@ const root = resolve(import.meta.dirname, '..') const PATTERNS = [ 'README.md', 'README.zh.md', + '.agents/notes/**/*.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', diff --git a/scripts/verify-md-wrap.ts b/scripts/verify-md-wrap.ts index f9679e5537..0e8dba9371 100644 --- a/scripts/verify-md-wrap.ts +++ b/scripts/verify-md-wrap.ts @@ -17,6 +17,7 @@ const root = resolve(import.meta.dirname, '..') const PATTERNS = [ 'README.md', 'README.zh.md', + '.agents/notes/**/*.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', diff --git a/scripts/verify-mermaid.ts b/scripts/verify-mermaid.ts index c487c2fd5c..d44ca9bcdf 100644 --- a/scripts/verify-mermaid.ts +++ b/scripts/verify-mermaid.ts @@ -17,6 +17,7 @@ const root = resolve(import.meta.dirname, '..') const PATTERNS = [ 'README.md', 'README.zh.md', + '.agents/notes/**/*.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', diff --git a/scripts/verify-package-paths.ts b/scripts/verify-package-paths.ts index bf03da4247..0cc0f63536 100644 --- a/scripts/verify-package-paths.ts +++ b/scripts/verify-package-paths.ts @@ -14,6 +14,7 @@ const root = resolve(import.meta.dirname, '..') /** Markdown + repo-authored TypeScript that may cite package paths. */ const PATTERNS = [ 'README.md', + '.agents/notes/**/*.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', diff --git a/scripts/verify-package-readme-limitations.ts b/scripts/verify-package-readme-limitations.ts index 042db1787c..22ac66a278 100644 --- a/scripts/verify-package-readme-limitations.ts +++ b/scripts/verify-package-readme-limitations.ts @@ -2,7 +2,7 @@ * Doc-sync gate for the canonical package-README limitations section. It scans * package manifests, rejects missing or variant sections, and requires one * top-level bullet; audited packages in {@link NO_LIMITATIONS} must omit it. - * See the [limitations RFC](../docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md). + * See the [limitations Agent Note](../.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md). */ import { existsSync, globSync, readFileSync } from 'node:fs' diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 93f30621c5..b62cd5999e 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -2,7 +2,7 @@ * Doc-sync gate for package README Model Experience sections. It validates * audited package classifications, model/token/KV-cache fields, package-owned * text blocks, generated-catalog links, and final-section order. See the - * [Model Experience RFC](../docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md). + * [Model Experience Agent Note](../.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md). */ import { existsSync, globSync, readFileSync } from 'node:fs' diff --git a/scripts/verify-rfc-classification.ts b/scripts/verify-rfc-classification.ts deleted file mode 100644 index 0511efd2e7..0000000000 --- a/scripts/verify-rfc-classification.ts +++ /dev/null @@ -1,39 +0,0 @@ -/** - * Enforce RFC lifecycle/class paths, dated filenames, and titles; verify the - * generated index and reject index rows in the curated README. Structural rules - * and rendering are shared with `rfc-index.ts`; the closed classification - * contract lives in `docs/rfc/README.md`. - */ - -import { readFileSync } from 'node:fs' -import { resolve } from 'node:path' -import { INDEX_ROW, renderIndex, rfcRoot, walkRfcTree } from './rfc-index.ts' - -const { rfcs, errors } = walkRfcTree() - -if (errors.length === 0) { - let index: string | undefined - try { - index = readFileSync(resolve(rfcRoot, 'INDEX.md'), 'utf8') - } catch { - // A missing INDEX.md is reported below as staleness, exactly like a drifted one. - } - if (renderIndex(rfcs) !== index) { - errors.push('index: docs/rfc/INDEX.md is stale or missing — run `pnpm run gen-rfc-index` and commit the result') - } - const readme = readFileSync(resolve(rfcRoot, 'README.md'), 'utf8') - for (const line of readme.split('\n')) { - if (INDEX_ROW.test(line)) { - errors.push(`readme: index-shaped row in the curated README (the list lives in INDEX.md): ${JSON.stringify(line.slice(0, 80))}`) - } - } -} - -if (errors.length === 0) { - console.log(`verify-rfc-classification: ${rfcs.length} RFC(s) checked, structure and index consistent.`) - process.exit(0) -} - -console.error('verify-rfc-classification: violations found:') -for (const e of errors) console.error(` ${e}`) -process.exit(1) diff --git a/scripts/verify-translation-pairing.ts b/scripts/verify-translation-pairing.ts index ced55d5be1..860e193b4f 100644 --- a/scripts/verify-translation-pairing.ts +++ b/scripts/verify-translation-pairing.ts @@ -24,8 +24,18 @@ const root = resolve(import.meta.dirname, '..') const listMode = process.argv.includes('--list') const writeMode = process.argv.includes('--write') -/** Scope of the bilingual contract: the root README, the docs tree, and the Python SDK tree. */ -const SCOPE_PATTERNS = ['README.md', 'README.zh.md', 'README.i18n.yaml', 'docs/**/*.md', 'docs/**/*.i18n.yaml', 'python/**/*.md', 'python/**/*.i18n.yaml'] +/** Scope of the bilingual contract: root docs, Agent Notes, the docs tree, and the Python SDK tree. */ +const SCOPE_PATTERNS = [ + 'README.md', + 'README.zh.md', + 'README.i18n.yaml', + '.agents/notes/**/*.md', + '.agents/notes/**/*.i18n.yaml', + 'docs/**/*.md', + 'docs/**/*.i18n.yaml', + 'python/**/*.md', + 'python/**/*.i18n.yaml', +] const manifest = parseTranslationPairingManifest(readFileSync(join(root, 'scripts/translation-pairing.manifest.json'), 'utf8')) @@ -121,8 +131,8 @@ for (const req of manifest.required) { } } -// 2. Date-named documents (RFCs) dated on/after the requiredSince cutoff merge -// bilingual: a new RFC lands with its pair or not at all. Deterministic from +// 2. Date-named documents (Agent Notes) dated on/after the requiredSince cutoff merge +// bilingual: a new Agent Note lands with its pair or not at all. Deterministic from // the filename alone — no git history, so it holds on shallow CI checkouts. for (const source of sources) { if (isExcluded(source)) continue diff --git a/scripts/verify-type-equiv.ts b/scripts/verify-type-equiv.ts index d703536f17..f886aac567 100644 --- a/scripts/verify-type-equiv.ts +++ b/scripts/verify-type-equiv.ts @@ -14,7 +14,7 @@ import ts from 'typescript' const root = resolve(import.meta.dirname, '..') /** Scan doc-typecheck's full Markdown scope so unmanifested blocks also fail. */ -const MARKDOWN_GLOBS = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', 'website/zh-CN/**/*.md'] +const MARKDOWN_GLOBS = ['README.md', '.agents/notes/**/*.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', 'website/zh-CN/**/*.md'] /** One manifest entry: a source-equivalence block and its source symbol. */ interface ManifestEntry { diff --git a/vitest.config.ts b/vitest.config.ts index c0946e2e10..4f4baa06ba 100644 --- a/vitest.config.ts +++ b/vitest.config.ts @@ -19,8 +19,8 @@ export default defineConfig({ exclude: ['packages/*/*/src/types.ts', 'packages/*/*/src/bin.ts', 'packages/*/*/src/worker.ts'], // 100% or it doesn't merge (docs/testing.md: excessive tests are welcome). // Per-file so a well-covered big file can't subsidize a bare one. - // Every v8 ignore comment must carry a reason — see the quality-gates RFC - // (docs/rfc/implemented/process/2026-06-11-quality-gates.md). + // Every v8 ignore comment must carry a reason — see the quality-gates Agent Note + // (.agents/notes/implemented/process/2026-06-11-quality-gates.md). thresholds: { perFile: true, statements: 100, diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index c3afe6b3aa..9cad9215fb 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -532,7 +532,7 @@ Single-slot decision for the next FileSystem.writeText. Calling `next()` yields * adapter's stream, or yield your own chunks to short-circuit. * @param options - the full request. A LOOP-built request arrives * deep-frozen (mutation throws): its content is a pure function of the - * session log (the reconstructability RFC), so listeners read it, never + * session log (the reconstructability Agent Note), so listeners read it, never * rewrite it. A hand-built one-shot (compaction summarize) is the * caller's own object and stays mutable here. * @mode waterfall @@ -542,7 +542,7 @@ Single-slot decision for the next FileSystem.writeText. Calling `next()` yields Waterfall around every streaming model call (retry, replay, routing). Bound to the LlmService; call `next()` to reach the resolved adapter's stream, or yield your own chunks to short-circuit. -- `options` — the full request. A LOOP-built request arrives deep-frozen (mutation throws): its content is a pure function of the session log (the reconstructability RFC), so listeners read it, never rewrite it. A hand-built one-shot (compaction summarize) is the caller's own object and stays mutable here. +- `options` — the full request. A LOOP-built request arrives deep-frozen (mutation throws): its content is a pure function of the session log (the reconstructability Agent Note), so listeners read it, never rewrite it. A hand-built one-shot (compaction summarize) is the caller's own object and stays mutable here. [Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L43) diff --git a/website/zh-CN/api/index.md b/website/zh-CN/api/index.md index 4357fcbfe3..f39fce8ca0 100644 --- a/website/zh-CN/api/index.md +++ b/website/zh-CN/api/index.md @@ -6,38 +6,38 @@ Cordis 微内核提供的基础能力，所有插件开发都建立在这些 API 之上： -- [Context](./cordis/context) — 上下文对象，所有服务和方法的入口 -- [Events](./cordis/events) — 事件系统 API（on / emit / bail / serial / waterfall） -- [Fiber](./cordis/fiber) — 插件生命周期（状态机、effect、dispose） -- [Registry](./cordis/registry) — 插件注册（plugin / inject） -- [Service](./cordis/service) — 服务基类 +- [Context](cordis/context) — 上下文对象，所有服务和方法的入口 +- [Events](cordis/events) — 事件系统 API（on / emit / bail / serial / waterfall） +- [Fiber](cordis/fiber) — 插件生命周期（状态机、effect、dispose） +- [Registry](cordis/registry) — 插件注册（plugin / inject） +- [Service](cordis/service) — 服务基类 ## Harness API 每个 `ctx.*` 服务一页，按服务名索引： -- [ctx.agentLoop](./harness/agent-loop) — ReAct 循环的创建与恢复 -- [ctx.agents](./harness/agents) — Agent 注册表与工厂 -- [ctx.approval](./harness/approval) — 用户审批 -- [ctx.bash](./harness/bash) — Bash 执行接口（抽象缝） -- [ctx.codeRuntime](./harness/code-runtime) — 代码执行接口（抽象缝） -- [ctx.compact](./harness/compact) — 上下文压缩接口（抽象缝） -- [ctx.fs](./harness/fs) — 文件系统接口（抽象缝） -- [ctx.llm](./harness/llm) — LLM 服务与适配器注册 -- [ctx.permission](./harness/permission) — 权限策略 -- [ctx.sandbox](./harness/sandbox) — 沙箱执行接口（抽象缝） -- [ctx.sessionPersistence](./harness/session-persistence) — 会话持久化接口（抽象缝） -- [ctx.sessionQuery](./harness/session-query) — 会话检索 -- [ctx.sessions](./harness/sessions) — 会话存储 -- [ctx.skills](./harness/skills) — 技能加载 -- [ctx.subagents](./harness/subagents) — 子代理委派 -- [ctx.systemPrompt](./harness/system-prompt) — 系统提示词组装 -- [ctx.tasks](./harness/tasks) — 后台任务 -- [ctx.tools](./harness/tools) — Tool 注册表 -- [ctx.userInteraction](./harness/user-interaction) — 用户交互接口 -- [ctx.web](./harness/web) — Web 搜索与抓取 -- [ctx.workflows](./harness/workflows) — 动态工作流引擎（抽象缝） +- [ctx.agentLoop](harness/agent-loop) — ReAct 循环的创建与恢复 +- [ctx.agents](harness/agents) — Agent 注册表与工厂 +- [ctx.approval](harness/approval) — 用户审批 +- [ctx.bash](harness/bash) — Bash 执行接口（抽象缝） +- [ctx.codeRuntime](harness/code-runtime) — 代码执行接口（抽象缝） +- [ctx.compact](harness/compact) — 上下文压缩接口（抽象缝） +- [ctx.fs](harness/fs) — 文件系统接口（抽象缝） +- [ctx.llm](harness/llm) — LLM 服务与适配器注册 +- [ctx.permission](harness/permission) — 权限策略 +- [ctx.sandbox](harness/sandbox) — 沙箱执行接口（抽象缝） +- [ctx.sessionPersistence](harness/session-persistence) — 会话持久化接口（抽象缝） +- [ctx.sessionQuery](harness/session-query) — 会话检索 +- [ctx.sessions](harness/sessions) — 会话存储 +- [ctx.skills](harness/skills) — 技能加载 +- [ctx.subagents](harness/subagents) — 子代理委派 +- [ctx.systemPrompt](harness/system-prompt) — 系统提示词组装 +- [ctx.tasks](harness/tasks) — 后台任务 +- [ctx.tools](harness/tools) — Tool 注册表 +- [ctx.userInteraction](harness/user-interaction) — 用户交互接口 +- [ctx.web](harness/web) — Web 搜索与抓取 +- [ctx.workflows](harness/workflows) — 动态工作流引擎（抽象缝） -事件总表：[Harness events](./harness/events) — 全部事件按作用域分组，含触发模式与载荷签名。 +事件总表：[Harness events](harness/events) — 全部事件按作用域分组，含触发模式与载荷签名。 想学"怎么写一个 tool / 插件"？教程在[开发指南](../develop/basic/)；本节只做精确的接口参考。 diff --git a/website/zh-CN/design/effects-coeffects.md b/website/zh-CN/design/effects-coeffects.md index 01c181315f..c6c0a71b29 100644 --- a/website/zh-CN/design/effects-coeffects.md +++ b/website/zh-CN/design/effects-coeffects.md @@ -52,8 +52,8 @@ Cordis 选择了不同的路径——在运行时层面解决可组合性问题 这由两个互补机制实现： -- **[可逆作用](./revertible-effects)** — 将副作用形式化为可逆的群操作 -- **[响应式余作用](./reactive-coeffects)** — 将依赖建模为具有生命周期的服务 +- **[可逆作用](revertible-effects)** — 将副作用形式化为可逆的群操作 +- **[响应式余作用](reactive-coeffects)** — 将依赖建模为具有生命周期的服务 ## 在 Agent 开发中的意义 diff --git a/website/zh-CN/design/index.md b/website/zh-CN/design/index.md index de6ebcf7aa..ea9ec2b6cd 100644 --- a/website/zh-CN/design/index.md +++ b/website/zh-CN/design/index.md @@ -16,11 +16,11 @@ Harness 追求三种可组合性的统一： ## 目录 -- [可组合性与插件系统](./composability) — 组合的本质，以及传统插件系统为什么不可靠 -- [作用与余作用](./effects-coeffects) — Cordis 效果系统的理论模型 -- [可逆作用](./revertible-effects) — 时间可组合性的形式化定义与证明 -- [响应式余作用](./reactive-coeffects) — 空间可组合性的服务语义 -- [上下文模型](./context-model) — Context 如何将作用与余作用统一 +- [可组合性与插件系统](composability) — 组合的本质，以及传统插件系统为什么不可靠 +- [作用与余作用](effects-coeffects) — Cordis 效果系统的理论模型 +- [可逆作用](revertible-effects) — 时间可组合性的形式化定义与证明 +- [响应式余作用](reactive-coeffects) — 空间可组合性的服务语义 +- [上下文模型](context-model) — Context 如何将作用与余作用统一 ## 设计如何映射到 Harness diff --git a/website/zh-CN/develop/basic/index.md b/website/zh-CN/develop/basic/index.md index 6b482f1401..81862c4d36 100644 --- a/website/zh-CN/develop/basic/index.md +++ b/website/zh-CN/develop/basic/index.md @@ -159,5 +159,5 @@ export function apply(ctx: Context) { ## 下一步 -- [开发一个 Tool](./tool) — 详细了解 tool 定义 DSL -- [插件配置](./config) — 让插件接受用户配置 +- [开发一个 Tool](tool) — 详细了解 tool 定义 DSL +- [插件配置](config) — 让插件接受用户配置 diff --git a/website/zh-CN/develop/basic/tool.md b/website/zh-CN/develop/basic/tool.md index d9e6f10b80..96f4d7ba24 100644 --- a/website/zh-CN/develop/basic/tool.md +++ b/website/zh-CN/develop/basic/tool.md @@ -238,5 +238,5 @@ export function apply(ctx: Context) { ## 下一步 -- [插件配置](./config) — 让你的 tool 可配置 +- [插件配置](config) — 让你的 tool 可配置 - [能力三件套](../practice/) — 了解 seam/impl/consumer 模式 diff --git a/website/zh-CN/develop/framework/index.md b/website/zh-CN/develop/framework/index.md index d9c6def99a..c23b4aa221 100644 --- a/website/zh-CN/develop/framework/index.md +++ b/website/zh-CN/develop/framework/index.md @@ -153,5 +153,5 @@ effect cleaned up ## 下一步 -- [服务与依赖](./service) — 让你的插件对外提供能力 -- [事件系统](./events) — 插件间通信的核心机制 +- [服务与依赖](service) — 让你的插件对外提供能力 +- [事件系统](events) — 插件间通信的核心机制 diff --git a/website/zh-CN/develop/framework/service.md b/website/zh-CN/develop/framework/service.md index b935c905df..7b31a1c23b 100644 --- a/website/zh-CN/develop/framework/service.md +++ b/website/zh-CN/develop/framework/service.md @@ -177,5 +177,5 @@ export function apply(ctx: Context) { ## 下一步 -- [事件系统](./events) — 插件间松耦合通信 +- [事件系统](events) — 插件间松耦合通信 - [能力三件套](../practice/) — 服务在 seam 模式中的应用 diff --git a/website/zh-CN/develop/practice/index.md b/website/zh-CN/develop/practice/index.md index 2a077aa22e..24ad0ffa52 100644 --- a/website/zh-CN/develop/practice/index.md +++ b/website/zh-CN/develop/practice/index.md @@ -153,4 +153,4 @@ export function apply(ctx: Context) { ## 下一步 -- [LLM 适配器](./llm-adapter) — 实现一个 LLM 后端（最常见的 seam 扩展） +- [LLM 适配器](llm-adapter) — 实现一个 LLM 后端（最常见的 seam 扩展） diff --git a/website/zh-CN/guide/index.md b/website/zh-CN/guide/index.md index 02b8fe0465..f0d77a3735 100644 --- a/website/zh-CN/guide/index.md +++ b/website/zh-CN/guide/index.md @@ -28,7 +28,7 @@ Harness 将一个 AI Agent（智能体） 所需要的所有能力——LLM 调 2. 填写 API key 3. 运行 -不需要写任何代码。详见 [快速开始](./quickstart)。 +不需要写任何代码。详见 [快速开始](quickstart)。 ### 插件开发者 diff --git a/website/zh-CN/guide/quickstart.md b/website/zh-CN/guide/quickstart.md index 27725fc6b9..13e25694de 100644 --- a/website/zh-CN/guide/quickstart.md +++ b/website/zh-CN/guide/quickstart.md @@ -94,5 +94,5 @@ echo-agent 和 repl-agent 用的是同一个应用框架(`@deepseek-ai/dsh-stdio ## 下一步 -- [配置文件](./config) — 了解 `cordis.yml` 的完整语法 +- [配置文件](config) — 了解 `cordis.yml` 的完整语法 - [开发插件](../develop/basic/) — 编写你自己的 tool 或后端 From 642b1c29d3a2155bb101194d8c0d0bb31f6f0977 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 23:03:08 +0800 Subject: [PATCH 2/3] feat(examples): configure max-token success via env --- examples/jsonrpc-agent/README.md | 1 + examples/jsonrpc-agent/cordis.yml | 2 +- .../jsonrpc-agent/tests/keyless-smoke.e2e.ts | 52 ++++++++++++++++++- 3 files changed, 52 insertions(+), 3 deletions(-) diff --git a/examples/jsonrpc-agent/README.md b/examples/jsonrpc-agent/README.md index cfbf6787b1..83c6e98fa5 100644 --- a/examples/jsonrpc-agent/README.md +++ b/examples/jsonrpc-agent/README.md @@ -18,6 +18,7 @@ The surrounding runtime also loads JSONL session persistence and automatic conte | `DEEPSEEK_API_KEY` | Credential passed to the OpenAI-compatible host endpoint | | `DEEPSEEK_BASE_URL` | Host endpoint used by `dsh-llm-deepseek` | | `DSH_CWD` | Agent workspace for bash and filesystem tools | +| `DSH_MAX_TOKENS_AS_SUCCESS` | `true` (default) accepts token-limited results; `false` reports them as errors | | `DSH_SESSION_ROOT` | JSONL trajectory directory | | `DSH_SYSTEM_PROMPT` | Deployment-provided coding persona | diff --git a/examples/jsonrpc-agent/cordis.yml b/examples/jsonrpc-agent/cordis.yml index de19b3da94..00ef48f4ed 100644 --- a/examples/jsonrpc-agent/cordis.yml +++ b/examples/jsonrpc-agent/cordis.yml @@ -4,7 +4,7 @@ - id: jsonrpc name: '@deepseek-ai/dsh-jsonrpc' config: - maxTokensAsSuccess: true + maxTokensAsSuccess: !!js "process.env.DSH_MAX_TOKENS_AS_SUCCESS === undefined ? true : JSON.parse(process.env.DSH_MAX_TOKENS_AS_SUCCESS)" - id: llm-deepseek name: '@deepseek-ai/dsh-llm-deepseek' diff --git a/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts b/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts index 41afb03574..c99b2c3c50 100644 --- a/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts +++ b/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts @@ -43,7 +43,11 @@ function waitForLine( } describe('jsonrpc-agent keyless smoke', () => { - it('boots the real Cordis tree and serves initialize/shutdown over clean stdout', async () => { + it.each([ + { label: 'accepts max-token results by default', envValue: undefined, expectedStatus: 'ok' }, + { label: 'accepts max-token results when enabled through env', envValue: 'true', expectedStatus: 'ok' }, + { label: 'reports max-token results as errors when disabled through env', envValue: 'false', expectedStatus: 'error' }, + ])('$label', async ({ envValue, expectedStatus }) => { const root = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-agent-smoke-')) const modelRequests: Record<string, unknown>[] = [] const modelServer = createServer((request, response) => { @@ -55,7 +59,7 @@ describe('jsonrpc-agent keyless smoke', () => { response.writeHead(200, { 'content-type': 'text/event-stream' }) response.write('data: {"choices":[{"delta":{"role":"assistant","content":null}}]}\n\n') response.write('data: {"choices":[{"delta":{"content":"done"}}]}\n\n') - response.write('data: {"choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}\n\n') + response.write('data: {"choices":[{"delta":{},"finish_reason":"length"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}\n\n') response.end('data: [DONE]\n\n') }) }) @@ -76,6 +80,7 @@ describe('jsonrpc-agent keyless smoke', () => { DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`, DSH_CWD: root, DSH_SESSION_ROOT: join(root, '.sessions'), + ...(envValue === undefined ? {} : { DSH_MAX_TOKENS_AS_SUCCESS: envValue }), }, stdio: ['pipe', 'pipe', 'pipe'], }) @@ -112,6 +117,16 @@ describe('jsonrpc-agent keyless smoke', () => { method: 'session/prompt', params: { sessionId: 'main', contentBlocks: [{ type: 'text', text: 'inspect tools' }] }, })}\n`) + const finished = await waitForLine(lines, value => value.method === 'session.finished', () => stderr) + expect(finished).toMatchObject({ + jsonrpc: '2.0', + method: 'session.finished', + params: { + sessionId: 'main', + status: expectedStatus, + reason: { kind: 'max-tokens' }, + }, + }) const prompt = await waitForLine(lines, value => value.id === 2, () => stderr) expect(prompt).toMatchObject({ jsonrpc: '2.0', id: 2, result: { accepted: true } }) const tools = modelRequests[0]?.tools as { function?: { name?: string } }[] @@ -143,4 +158,37 @@ describe('jsonrpc-agent keyless smoke', () => { await rm(root, { recursive: true, force: true }) } }, 40_000) + + it('rejects an invalid max-token success env value', async () => { + const child = spawn(process.execPath, [ + '--expose-internals', + '--import', + 'tsx', + binScript, + configPath, + ], { + cwd: repoRoot, + env: { + ...process.env, + DEEPSEEK_API_KEY: 'keyless-smoke-no-call', + DSH_MAX_TOKENS_AS_SUCCESS: 'sometimes', + }, + stdio: ['ignore', 'pipe', 'pipe'], + }) + let stdout = '' + let stderr = '' + child.stdout.setEncoding('utf8') + child.stdout.on('data', (chunk: string) => { stdout += chunk }) + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => { stderr += chunk }) + + const exitCode = await new Promise<number | null>((resolve, reject) => { + child.once('error', reject) + child.once('exit', resolve) + }) + + expect(exitCode, stderr).toBe(1) + expect(stdout).toBe('') + expect(stderr).toContain('plugin(s) failed to load: @deepseek-ai/dsh-jsonrpc') + }, 10_000) }) From 4779d04af8143fbd5e1a98a1cf7d4413374abf6d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 23:15:23 +0800 Subject: [PATCH 3/3] Remove generated Agent Note index --- .agents/notes/INDEX.md | 248 ------------------ .agents/notes/README.md | 6 +- .../2026-06-20-agent-note-classification.md | 12 +- ...-07-04-generate-agent-note-index-tables.md | 32 --- .../2026-07-05-uniform-agent-note-format.md | 4 +- ...emove-generated-agent-note-index.i18n.yaml | 6 + ...07-19-remove-generated-agent-note-index.md | 33 +++ ...19-remove-generated-agent-note-index.zh.md | 33 +++ ...-07-04-generate-agent-note-index-tables.md | 36 +++ .agents/skills/dsh-code-review/SKILL.md | 2 +- .../skills/dsh-find-simplifications/SKILL.md | 4 +- docs/development.i18n.yaml | 4 +- docs/development.md | 1 - docs/development.zh.md | 1 - package.json | 1 - scripts/agent-note-index.ts | 130 --------- scripts/agent-note-tree.ts | 78 ++++++ scripts/gen-agent-note-index.ts | 36 --- scripts/verify-agent-note-classification.ts | 31 +-- scripts/verify-agent-note-format.ts | 2 +- 20 files changed, 210 insertions(+), 490 deletions(-) delete mode 100644 .agents/notes/INDEX.md delete mode 100644 .agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md create mode 100644 .agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.i18n.yaml create mode 100644 .agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.md create mode 100644 .agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.zh.md create mode 100644 .agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md delete mode 100644 scripts/agent-note-index.ts create mode 100644 scripts/agent-note-tree.ts delete mode 100644 scripts/gen-agent-note-index.ts diff --git a/.agents/notes/INDEX.md b/.agents/notes/INDEX.md deleted file mode 100644 index fe92f57aef..0000000000 --- a/.agents/notes/INDEX.md +++ /dev/null @@ -1,248 +0,0 @@ -# Agent Note index - -Generated by `pnpm run gen-agent-note-index` from the Agent Note tree — never edit by hand; `verify-agent-note-classification` fails when this file is stale. The curated front door — layout, classification, when to write one, and the in-file format — is [README.md](README.md). - -## Proposed - -### Feature - -| Title | First proposed | -|---|---| -| [Pre-tool input rewrite — a consistent design](proposed/feature/2026-06-30-pre-tool-input-rewrite.md) | 2026-06-30 | -| [Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall](proposed/feature/2026-07-06-recallable-compaction.md) | 2026-07-06 | -| [Claude Code and Codex subagent backends (out-of-process delegation to external coding agents)](proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md) | 2026-07-07 | -| [Interactive side sessions and merge-back](proposed/feature/2026-07-08-interactive-side-sessions.md) | 2026-07-08 | -| [SQLite FTS5 session search](proposed/feature/2026-07-10-sqlite-session-query-provider.md) | 2026-07-10 | -| [Stream workflow progress through tool calls](proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md) | 2026-07-13 | -| [Developer-owned SDK projects](proposed/feature/2026-07-14-sdk-developer-projects.md) | 2026-07-14 | -| [SDK follow-up capabilities](proposed/feature/2026-07-17-sdk-follow-up-capabilities.md) | 2026-07-17 | - -### Simplification - -| Title | First proposed | -|---|---| -| [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | -| [Make JSON-RPC completion and transport directional](proposed/simplification/2026-07-19-make-jsonrpc-directional.md) | 2026-07-19 | - -### Architecture - -| Title | First proposed | -|---|---| -| [Runtime schemas for the event vocabulary (Zod vs the merge-extensible-map pattern)](proposed/architecture/2026-06-16-typed-event-schemas.md) | 2026-06-16 | -| [SDK project editing architecture](proposed/architecture/2026-07-15-sdk-project-editing-architecture.md) | 2026-07-15 | - -### Process - -| Title | First proposed | -|---|---| -| [API extractor reports](proposed/process/2026-06-11-api-extractor-reports.md) | 2026-06-11 | -| [Architectural conformance — dependency rules and the adapter kit](proposed/process/2026-06-11-architectural-conformance.md) | 2026-06-11 | -| [Supply chain checks and vendor drift verification](proposed/process/2026-06-11-supply-chain-and-vendor-drift.md) | 2026-06-11 | -| [Discover package inventories instead of maintaining static lists](proposed/process/2026-06-20-discover-package-inventory.md) | 2026-06-20 | -| [Periodic human-review maintenance for dsh-code-review](proposed/process/2026-07-13-human-review-skill-maintenance.md) | 2026-07-13 | - -### Testing - -| Title | First proposed | -|---|---| -| [Deterministic tests, the replay invariant fixture, and race stress](proposed/testing/2026-06-11-deterministic-and-stress-testing.md) | 2026-06-11 | -| [Mutation testing as the coverage counterweight](proposed/testing/2026-06-11-mutation-testing.md) | 2026-06-11 | - -## Implemented - -### Feature - -| Title | First proposed | -|---|---| -| [Agent Client Protocol (ACP) support — drive the coding agent from external editors](implemented/feature/2026-06-14-acp-agent-client-protocol.md) | 2026-06-14 | -| [Multiplex concurrent ACP sessions over one connection](implemented/feature/2026-06-14-acp-multi-session.md) | 2026-06-14 | -| [Code Mode — the model writes TypeScript against the tool registry](implemented/feature/2026-06-15-code-mode.md) | 2026-06-15 | -| [Filesystem tool schemas — model-facing read/write/edit shapes](implemented/feature/2026-06-17-filesystem-tool-schemas.md) | 2026-06-17 | -| [Rich ACP bash rendering — the terminal card via the `_meta` convention](implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) | 2026-06-18 | -| [Compaction as a capability seam (abstract contract + basic backend)](implemented/feature/2026-06-18-compaction-capability-seam.md) | 2026-06-18 | -| [Subagent capability seam](implemented/feature/2026-06-21-subagent-capability-seam.md) | 2026-06-21 | -| [ACP subagent backend (out-of-process delegation)](implemented/feature/2026-06-22-acp-subagent-backend.md) | 2026-06-22 | -| [Workspace context instruction files](implemented/feature/2026-06-24-workspace-context.md) | 2026-06-24 | -| [Ask-user question capability](implemented/feature/2026-06-25-ask-user-question.md) | 2026-06-25 | -| [The `todo_write` tool — model task list as event-sourced session state](implemented/feature/2026-06-29-todo-write-tool.md) | 2026-06-29 | -| [dsh-hooks-claude + dsh-hooks-codex — the Claude Code / Codex hook bridges](implemented/feature/2026-06-30-hook-bridges.md) | 2026-06-30 | -| [dsh-hook-protocol — the shared Claude Code / Codex hook wire-protocol core](implemented/feature/2026-06-30-hook-protocol-lib.md) | 2026-06-30 | -| [Interception seams — the typed-Decision surface a hook programs against](implemented/feature/2026-06-30-interception-seams.md) | 2026-06-30 | -| [SessionStore fork API](implemented/feature/2026-06-30-session-store-fork-api.md) | 2026-06-30 | -| [Subagent lifecycle enrichment — lastAssistantMessage (observe-only)](implemented/feature/2026-06-30-subagent-observe-enrich.md) | 2026-06-30 | -| [Dynamic workflows — a script-driven multi-agent orchestration seam](implemented/feature/2026-07-05-dynamic-workflows.md) | 2026-07-05 | -| [Skill system — progressive disclosure instructions for agents](implemented/feature/2026-07-05-skill-system.md) | 2026-07-05 | -| [The approval seam — one-shot permission decisions over a waterfall of answerers](implemented/feature/2026-07-06-approval-seam.md) | 2026-07-06 | -| [Explicit model-facing tool order](implemented/feature/2026-07-06-explicit-tool-order.md) | 2026-07-06 | -| [The subprocess sandbox — confinement seam, native runners, escalation, and per-session modes](implemented/feature/2026-07-06-sandbox.md) | 2026-07-06 | -| [MCP client plugin — connect to external MCP servers and bridge their tools](implemented/feature/2026-07-07-mcp-client-plugin.md) | 2026-07-07 | -| [The session prefix — request-only messages in front of the derived history](implemented/feature/2026-07-07-session-prefix.md) | 2026-07-07 | -| [Background subagent tasks](implemented/feature/2026-07-08-background-subagent-tasks.md) | 2026-07-08 | -| [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 | -| [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 | -| [Bash-backed grep and glob discovery tools](implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md) | 2026-07-09 | -| [Expose agent session identity and JSONL location to tools and hooks](implemented/feature/2026-07-10-agent-session-identity-and-log-location.md) | 2026-07-10 | -| [Parallel tool-call execution by per-call safety](implemented/feature/2026-07-10-parallel-tool-call-execution.md) | 2026-07-10 | -| [Exact session query service](implemented/feature/2026-07-10-session-query-service.md) | 2026-07-10 | -| [Configure subagent persona, tool visibility, and depth](implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) | 2026-07-12 | -| [Session query relationship tracing](implemented/feature/2026-07-13-session-query-tracing.md) | 2026-07-13 | -| [Optional time-context plugin](implemented/feature/2026-07-14-time-context-plugin.md) | 2026-07-14 | -| [Durable per-step time context](implemented/feature/2026-07-16-durable-per-step-time-context.md) | 2026-07-16 | -| [Dedicated full-screen TUI front door](implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md) | 2026-07-17 | - -### Simplification - -| Title | First proposed | -|---|---| -| [Drop the mutable session summary](implemented/simplification/2026-06-19-drop-mutable-session-summary.md) | 2026-06-19 | -| [Fold trace-only session facts into load-bearing events](implemented/simplification/2026-06-20-collapse-trace-only-session-events.md) | 2026-06-20 | -| [Drop the unconsumed `llm/adapter-change` event](implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md) | 2026-06-20 | -| [Drop unconsumed assembled LLM convenience surfaces](implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md) | 2026-06-20 | -| [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | -| [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | -| [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | -| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | -| [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | -| [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | -| [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | -| [Drop `GenerateOptions.prefill` and `ToolSchema.strict` — request knobs with no working end-to-end path](implemented/simplification/2026-07-04-drop-inert-request-knobs.md) | 2026-07-04 | -| [Drop the unconsumed web observation surface — the `providers-change` event and the status methods](implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) | 2026-07-04 | -| [Fold the stdio UI helper into the stdio app](implemented/simplification/2026-07-04-fold-stdio-ui-helper.md) | 2026-07-04 | -| [Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger)](implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md) | 2026-07-04 | -| [Prune write-only fields and a dead routing knob from the fs seam](implemented/simplification/2026-07-04-prune-write-only-fs-surface.md) | 2026-07-04 | -| [Remove the `agent/steering` mirror emit](implemented/simplification/2026-07-04-remove-agent-steering-mirror.md) | 2026-07-04 | -| [Share the app bins' boot glue instead of maintaining twin copies](implemented/simplification/2026-07-04-share-app-bin-boot-glue.md) | 2026-07-04 | -| [Tighten the hook-protocol contract — dialect, discarded fields, double defaults, and lib-owned `hook/result` semantics](implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md) | 2026-07-04 | -| [Trim unreachable ACP bridge surface — the branding knobs and the kind-sniffing fallback](implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md) | 2026-07-04 | -| [Drop unconsumed skill provider events](implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | -| [Prune unused web seam fields](implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | -| [Simplify session-log representation](implemented/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 | -| [Retire the standalone subagent mock package](implemented/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | -| [Use one surface manager per session](implemented/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | - -### Architecture - -| Title | First proposed | -|---|---| -| [Provider-neutral content-block vocabulary owned by dsh-llm](implemented/architecture/2026-06-11-content-block-vocabulary.md) | 2026-06-11 | -| [Custom typed tool-schema DSL instead of schemastery](implemented/architecture/2026-06-11-custom-schema-dsl.md) | 2026-06-11 | -| [Source-owned session immutability and dev-mode invariants](implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md) | 2026-06-11 | -| [Event-sourced sessions with derived message history](implemented/architecture/2026-06-11-event-sourced-sessions.md) | 2026-06-11 | -| [Microkernel — extension via Cordis event taxonomy, one concrete loop](implemented/architecture/2026-06-11-microkernel-event-taxonomy.md) | 2026-06-11 | -| [Runtime arg validation at the model boundary](implemented/architecture/2026-06-11-runtime-arg-validation.md) | 2026-06-11 | -| [Structured error taxonomy](implemented/architecture/2026-06-11-structured-error-taxonomy.md) | 2026-06-11 | -| [Tool schemas are part of the system-prompt assembly](implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md) | 2026-06-11 | -| [Capability seams — interface / implementation / consumer split](implemented/architecture/2026-06-13-capability-seams.md) | 2026-06-13 | -| [Two LLM adapters as a design-verification twin](implemented/architecture/2026-06-13-twin-llm-adapters.md) | 2026-06-13 | -| [Session persistence as an abstract service over the existing `SessionEvent`](implemented/architecture/2026-06-14-session-persistence.md) | 2026-06-14 | -| [Every session event is enclosed in a turn](implemented/architecture/2026-06-15-turn-enclosure-invariant.md) | 2026-06-15 | -| [Filesystem capability seam — ctx.fs, local backend, and model-facing filesystem tools](implemented/architecture/2026-06-17-filesystem-capability-seam.md) | 2026-06-17 | -| [Agent lifecycle and ownership seams](implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md) | 2026-06-18 | -| [Session surface — an ordered projection over the event log](implemented/architecture/2026-06-18-session-surface.md) | 2026-06-18 | -| [Shared persistence write coordinator](implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md) | 2026-06-18 | -| [Branded IDs everywhere they belong](implemented/architecture/2026-06-20-branded-ids.md) | 2026-06-20 | -| [Extract example apps into packages](implemented/architecture/2026-06-20-extract-example-app-packages.md) | 2026-06-20 | -| [The background task runtime (`ctx.tasks`) and generic task control tools](implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md) | 2026-06-20 | -| [Reorganize packages into a modular hierarchy](implemented/architecture/2026-06-20-package-hierarchy.md) | 2026-06-20 | -| [Mandatory `User-Agent` attribution for provider requests](implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md) | 2026-06-21 | -| [Web capability seam - stable tools over multiple providers](implemented/architecture/2026-06-24-web-capability-seam.md) | 2026-06-24 | -| [Make `dsh-fs-policy` an event-gate plugin, not a method interface](implemented/architecture/2026-06-26-file-context-as-event-gate.md) | 2026-06-26 | -| [stdin + extra env on the bash seam](implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) | 2026-06-30 | -| [Event-domain semantics — session is the fact log, agent is the live surface](implemented/architecture/2026-06-30-event-domain-semantics.md) | 2026-06-30 | -| [Resolve filesystem paths against the caller's session cwd](implemented/architecture/2026-07-02-fs-per-session-cwd.md) | 2026-07-02 | -| [Result-time applied-hunk diffs for file mutations](implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md) | 2026-07-02 | -| [Tagged render-intent union for tool-call presentation](implemented/architecture/2026-07-02-tool-render-intent-union.md) | 2026-07-02 | -| [Add direct directory listing to the filesystem seam](implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md) | 2026-07-03 | -| [Prompt variables and tool-guidance ownership](implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md) | 2026-07-05 | -| [Every LLM request is reconstructable from the session log](implemented/architecture/2026-07-05-reconstructable-requests.md) | 2026-07-05 | -| [Subagent provider-lifecycle events — `subagent/provider-added` / `subagent/provider-removed`](implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md) | 2026-07-05 | -| [A shared timeout/deadline primitive, with hard-kill left to each capability](implemented/architecture/2026-07-06-timeout-deadline-library.md) | 2026-07-06 | -| [Tool result retention library](implemented/architecture/2026-07-06-tool-result-retention-library.md) | 2026-07-06 | -| [Tool-call timeout policy as a plugin](implemented/architecture/2026-07-07-tool-call-timeout-policy.md) | 2026-07-07 | -| [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 | -| [Tool output spill policy](implemented/architecture/2026-07-08-tool-output-spill-files.md) | 2026-07-08 | -| [After-call compaction pressure and context-overflow recovery](implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) | 2026-07-10 | -| [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | -| [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | -| [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 | -| [Initiating Agent scope over AsyncLocalStorage](implemented/architecture/2026-07-15-agent-initiator-scope.md) | 2026-07-15 | -| [Advisory LLM catalogs and per-session ACP model selection](implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) | 2026-07-15 | -| [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 | - -### Process - -| Title | First proposed | -|---|---| -| [Doc-sync enforcement](implemented/process/2026-06-11-doc-sync-enforcement.md) | 2026-06-11 | -| [Mechanical quality gates over prose guidelines](implemented/process/2026-06-11-quality-gates.md) | 2026-06-11 | -| [tsdown for JS bundling instead of dumble](implemented/process/2026-06-11-tsdown-over-dumble.md) | 2026-06-11 | -| [Vendor Cordis as source, not npm dependencies](implemented/process/2026-06-11-vendor-cordis-as-source.md) | 2026-06-11 | -| [pnpm as the package manager instead of Yarn 4](implemented/process/2026-06-16-pnpm-over-yarn.md) | 2026-06-16 | -| [TSC-first build and one tsconfig](implemented/process/2026-06-17-ts-build-config.md) | 2026-06-17 | -| [Markdown cross-link validity linting](implemented/process/2026-06-18-markdown-cross-link-lint.md) | 2026-06-18 | -| [Classify Agent Notes by kind via path-encoded subdirectories](implemented/process/2026-06-20-agent-note-classification.md) | 2026-06-20 | -| [Core-data-structures catalog and the `ts type-equiv` drift gate](implemented/process/2026-06-20-core-data-structures-catalog.md) | 2026-06-20 | -| [Generated cordis events + services catalog](implemented/process/2026-06-20-generated-cordis-catalog.md) | 2026-06-20 | -| [Bilingual documentation via paired sibling files and a pairing gate](implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md) | 2026-07-02 | -| [Generated tool-schema catalog (boot-and-harvest)](implemented/process/2026-07-02-tool-schema-catalog.md) | 2026-07-02 | -| [Documentation graph index for maintainers and SDK users](implemented/process/2026-07-03-documentation-graph-atlas.md) | 2026-07-03 | -| [JSDoc completeness gate for the cordis surface](implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md) | 2026-07-04 | -| [Documentation tiers, budgets, and the ceiling gate](implemented/process/2026-07-04-doc-tiers-and-budgets.md) | 2026-07-04 | -| [Generate the Agent Note index tables](implemented/process/2026-07-04-generate-agent-note-index-tables.md) | 2026-07-04 | -| [Generated persistence log event catalog](implemented/process/2026-07-04-persistence-log-catalog.md) | 2026-07-04 | -| [One gated in-file format for Agent Notes](implemented/process/2026-07-05-uniform-agent-note-format.md) | 2026-07-05 | -| [Export-surface JSDoc gate](implemented/process/2026-07-06-export-surface-jsdoc-gate.md) | 2026-07-06 | -| [Generated plugin config catalog](implemented/process/2026-07-06-generated-config-catalog.md) | 2026-07-06 | -| [Raise the Node LTS engine floor to 22.19](implemented/process/2026-07-06-node-engine-floor.md) | 2026-07-06 | -| [Parallel GitHub CI gates](implemented/process/2026-07-06-parallel-github-ci-gates.md) | 2026-07-06 | -| [Parallel pre-push gates](implemented/process/2026-07-06-parallel-pre-push-gates.md) | 2026-07-06 | -| [A gated Known-Limitations section in every package README](implemented/process/2026-07-10-readme-known-limitations-gate.md) | 2026-07-10 | -| [Package Model Experience contract](implemented/process/2026-07-12-package-model-experience-contract.md) | 2026-07-12 | -| [TypeScript Program-backed semantic gates](implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) | 2026-07-14 | -| [Run CI examples from built lib](implemented/process/2026-07-17-run-ci-examples-from-built-lib.md) | 2026-07-17 | - -### Testing - -| Title | First proposed | -|---|---| -| [Property-based testing for protocol-shaped code](implemented/testing/2026-06-11-property-based-testing.md) | 2026-06-11 | -| [ACP snapshot tests — record-once / replay-deterministic](implemented/testing/2026-06-19-acp-snapshot-tests.md) | 2026-06-19 | -| [Real-API e2e in CI against the external DeepSeek API](implemented/testing/2026-06-19-real-api-e2e-ci.md) | 2026-06-19 | -| [Use `session.jsonl` as the only snapshot session-log artifact](implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md) | 2026-06-20 | -| [Persist the seed boundary so fork-child replay routes correctly](implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md) | 2026-06-22 | -| [Record fork and mixed spawn+fork snapshot scenarios](implemented/testing/2026-06-22-fork-snapshot-scenarios.md) | 2026-06-22 | -| [Per-session snapshot replay for nested agents](implemented/testing/2026-06-22-subagent-snapshot-replay.md) | 2026-06-22 | -| [Hook snapshot matrix — end-to-end expected outputs for both bridges](implemented/testing/2026-07-04-hook-snapshot-matrix.md) | 2026-07-04 | -| [Single-source the acp-agent replay config](implemented/testing/2026-07-04-single-source-acp-replay-config.md) | 2026-07-04 | -| [Pin request-header content in one snapshot scenario](implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md) | 2026-07-06 | -| [Extract the ACP snapshot suite into a support package](implemented/testing/2026-07-08-shared-acp-snapshot-package.md) | 2026-07-08 | -| [Snapshot semantic terminal state for the TUI](implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) | 2026-07-18 | - -## Rejected - -### Simplification - -| Title | First proposed | -|---|---| -| [Persist assembled assistant messages, not stream chunks](rejected/simplification/2026-06-20-assembled-assistant-messages-only.md) | 2026-06-20 | -| [Drop ACP session/load until resume has a product shape](rejected/simplification/2026-06-20-drop-acp-session-load.md) | 2026-06-20 | -| [Drop ACP terminal `_meta` rendering](rejected/simplification/2026-06-20-drop-acp-terminal-meta.md) | 2026-06-20 | -| [Drop bash full-output spill files](rejected/simplification/2026-06-20-drop-bash-output-spill-files.md) | 2026-06-20 | -| [Drop durable step boundary events](rejected/simplification/2026-06-20-drop-durable-step-boundaries.md) | 2026-06-20 | -| [Drop unused session lineage metadata](rejected/simplification/2026-06-20-drop-unused-session-lineage.md) | 2026-06-20 | -| [Fold the persistence interface into dsh-session](rejected/simplification/2026-06-20-fold-session-persistence-interface.md) | 2026-06-20 | -| [Collapse tool-owned UI presentation](rejected/simplification/2026-06-20-generic-tool-rendering.md) | 2026-06-20 | -| [Retire mid-turn steering](rejected/simplification/2026-06-20-retire-mid-turn-steering.md) | 2026-06-20 | -| [Return the ACP bridge to one live session per connection](rejected/simplification/2026-06-20-single-session-acp-bridge.md) | 2026-06-20 | -| [Truncate interrupted final turns on load](rejected/simplification/2026-06-20-truncate-interrupted-turns.md) | 2026-06-20 | -| [Prune the unimplemented subagent seam vocabulary](rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md) | 2026-07-04 | -| [Collapse workflows to the exercised foreground core](rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md) | 2026-07-12 | -| [Prune unused skill registry surface](rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md) | 2026-07-12 | -| [Fold the single compaction backend into its service package](rejected/simplification/2026-07-19-fold-compaction-package-split.md) | 2026-07-19 | - -### Architecture - -| Title | First proposed | -|---|---| -| [Deep-readonly public surfaces](rejected/architecture/2026-06-11-immutable-public-surfaces.md) | 2026-06-11 | -| [Make the shared example base providerless](rejected/architecture/2026-06-20-providerless-example-base.md) | 2026-06-20 | diff --git a/.agents/notes/README.md b/.agents/notes/README.md index 16cbf07037..79aa2fb8d4 100644 --- a/.agents/notes/README.md +++ b/.agents/notes/README.md @@ -1,6 +1,6 @@ # Agent Notes -One kind of design doc lives here. An **Agent Note** records a decision or proposal that shapes this codebase — the *why* and *what we gave up*, the parts code and docs can't carry. The full list is the generated [INDEX.md](INDEX.md); this file is the contract — where Agent Notes live, when to write one, and [the in-file format](#the-file-format). +One kind of design doc lives here. An **Agent Note** records a decision or proposal that shapes this codebase — the *why* and *what we gave up*, the parts code and docs can't carry. This file is the front door and contract: where Agent Notes live, when to write one, and [the in-file format](#the-file-format). ## Layout and naming @@ -14,9 +14,11 @@ Every Agent Note has two axes, both encoded in its **path** — `{lifecycle}/{cl The date in the filename is when the topic was **first proposed** (per git history). Cross-references between Agent Notes use relative markdown links (`[topic](../../implemented/architecture/2026-…-….md)`) — never bare prose or numbers — so they are mechanically checkable and survive moves between folders. +The tree is the inventory: browse its lifecycle/class folders or search the repository. Do not add a centralized `INDEX.md`; the [no-index Agent Note](implemented/process/2026-07-19-remove-generated-agent-note-index.md) owns the rationale. + ## Classification -Each Agent Note belongs to one path-encoded class from the closed set in `scripts/agent-note-index.ts`; the classification gate rejects other folders. [INDEX.md](INDEX.md) is generated from paths, titles, and filename dates, and its freshness is gated. Adding a class requires updating the canonical set and this section. See the [classification](implemented/process/2026-06-20-agent-note-classification.md) and [index-generation](implemented/process/2026-07-04-generate-agent-note-index-tables.md) Agent Notes. +Each Agent Note belongs to one path-encoded class from the closed set in `scripts/agent-note-tree.ts`; the classification gate rejects other folders. Adding a class requires updating the canonical set and this section. See the [classification Agent Note](implemented/process/2026-06-20-agent-note-classification.md). | Class | What it covers | |---|---| diff --git a/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md index 4984ac36c2..42c4523e0c 100644 --- a/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md +++ b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md @@ -4,7 +4,7 @@ Status: implemented ## Problem -`.agents/notes/` grouped Agent Notes by **lifecycle** only — `proposed/` / `implemented/` / `rejected/`. Nothing recorded what *kind* of decision each Agent Note was. The index was one flat list per lifecycle, with no way to scan "show me every simplification" or "every testing-strategy decision." A wave of simplification Agent Notes landing on the same day made the gap concrete: a reader skimming `proposed/` could not tell a new capability from a removal from a tooling-policy change without opening each file. +A lifecycle-only Agent Note tree — `proposed/` / `implemented/` / `rejected/` — does not record what *kind* of decision each file contains. A reader browsing one lifecycle cannot distinguish a new capability from a removal or a tooling-policy change without opening each file. The repo's standing bias is [mechanical quality gates over prose guidelines](2026-06-11-quality-gates.md): a convention that isn't machine-checked rots. So a classification scheme here had to be enforceable, not an honor-system header. @@ -29,18 +29,18 @@ The `architecture` / `process` line: **architecture** is about the source we shi Both are `doc-sync` members, in the `verify-md-wrap` style (tsx ESM, verify-don't-generate, exit non-zero on the first violation): -- **`scripts/verify-agent-note-classification.ts`** — the closed set and index freshness. It asserts every file under a lifecycle folder lives in a class folder from the canonical set (a loose `.md` at a lifecycle root, or an unknown class folder, fails), and that the generated [INDEX.md](../../INDEX.md) byte-matches a fresh render from the tree (see [generate the Agent Note index tables](2026-07-04-generate-agent-note-index-tables.md)). The canonical class set lives as a `const` in `scripts/agent-note-index.ts` — the machine source of truth shared with the generator — and [the README](../../README.md) documents it in prose; the class *descriptions* stay hand-written, the index is generated. -- **`scripts/verify-doc-refs.ts`** — source comments that cite docs. Agent Note paths are referenced not only from Markdown but from TypeScript doc comments (root-relative prose like `.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md`). `verify-md-links` never saw those, so the reorg could have silently orphaned them. This gate scans repo-authored `.ts` under `packages/**` and `examples/**` (excluding built `lib/` and `vendor/`) for `docs/….md` tokens, resolves each root-relative, and asserts it exists. It requires the `.md` extension so extensionless prose (`docs/postmortem/0001`, `docs/architecture.md § Extending The Harness`) is left alone. +- **`scripts/verify-agent-note-classification.ts`** — the closed lifecycle and class sets. It asserts every file under a lifecycle folder lives in a class folder from the canonical set (a loose `.md` at a lifecycle root, or an unknown class folder, fails) and rejects a centralized `INDEX.md`. The canonical sets live in `scripts/agent-note-tree.ts`, and [the README](../../README.md) documents each class in prose. +- **`scripts/verify-doc-refs.ts`** — source comments that cite docs. Agent Note paths are referenced not only from Markdown but from TypeScript doc comments (root-relative prose like `.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md`). `verify-md-links` does not see those, so a reorganization could silently orphan them. This gate scans repo-authored `.ts` under `packages/**` and `examples/**` (excluding built `lib/` and `vendor/`) for `docs/….md` and `.agents/notes/….md` tokens, resolves each root-relative path, and asserts it exists. It requires the `.md` extension so extensionless prose is left alone. ## Alternatives considered - **A `Classification:` prose line** in each file (next to `Status:`), parsed by the gate. Workable, but it duplicates into the file a fact the path can already carry, and a line can disagree with its folder. Path-encoding makes the label and its storage the same thing — there is nothing to keep in sync. - **A `refactor` class.** It overlaps `simplification` almost entirely; the only discriminator anyone reached for was "does observable behavior change?", which `simplification` already encodes (it does not). One class, not two. -- **Auto-generating the index** from the filesystem. Rejected here to keep the index hand-written; superseded by [generate the Agent Note index tables](2026-07-04-generate-agent-note-index-tables.md) once stacked proposal waves made the hand-written tables the repo's most conflict-prone docs region — the list is now the fully generated [INDEX.md](../../INDEX.md) while the README prose stays curated. +- **A generated or hand-maintained corpus index.** Rejected because the lifecycle/class tree is authoritative, while a centralized inventory creates a merge hotspot without providing discovery that tree navigation or repository search cannot provide. The separate [index proposal](../../rejected/process/2026-07-04-generate-agent-note-index-tables.md) records the discarded generated shape. ## Consequences -- Every Agent Note now sits under a class folder, and the index groups by class within each lifecycle. A reader scans one heading to see all simplifications, or all testing decisions. +- Every Agent Note sits under a class folder. A reader can browse one folder to see all simplifications or all testing decisions within a lifecycle. - Two more fast tsx scripts in the `doc-sync` chain; no new dependency (the mdast/GFM stack was already present for `verify-md-wrap`/`verify-md-links`). -- Adding a class is a deliberate act: amend the `const` in `scripts/agent-note-index.ts` and the [Classification section](../../README.md#classification), not just `mkdir` a folder. The gate rejects an unknown folder, so an ad-hoc class can't slip in. +- Adding a class is a deliberate act: amend the `const` in `scripts/agent-note-tree.ts` and the [Classification section](../../README.md#classification), not just `mkdir` a folder. The gate rejects an unknown folder, so an ad-hoc class can't slip in. - Source-comment doc references are now gated too — a moved or renamed doc that a `.ts` comment cites fails the pre-push hook, closing a drift class `verify-md-links` structurally could not see. diff --git a/.agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md b/.agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md deleted file mode 100644 index b0f292d4a0..0000000000 --- a/.agents/notes/implemented/process/2026-07-04-generate-agent-note-index-tables.md +++ /dev/null @@ -1,32 +0,0 @@ -# Agent Note: Generate the Agent Note index tables - -Status: implemented - -## Problem - -The Agent Note index's per-lifecycle/per-class tables list facts that are fully derivable: an Agent Note's path encodes lifecycle and class, its filename encodes the first-proposed date, and its H1 carries the title. A hand-maintained copy of those facts is also the repo's highest-contention docs hotspot: every proposal wave appends rows to the same few lines, so concurrent Agent Note branches conflict precisely there while agreeing everywhere else, and each conflict is resolved by hand-merging rows whose content the filesystem already knows. [The classification Agent Note](2026-06-20-agent-note-classification.md) originally kept the index hand-written for curation's sake — but the curated part of the README is the prose, and the prose never conflicts; only the mechanical tables do. - -## Decision - -Keep the curated prose; generate the list. The tables live in [`.agents/notes/INDEX.md`](../../INDEX.md), a **fully generated file** — the curated prose stays in README.md, which carries no index rows at all. [`scripts/agent-note-index.ts`](../../../../scripts/agent-note-index.ts) is the shared source of truth — the tree walker (owning the closed lifecycle/class sets and the structure rules, including a parseable-H1 requirement) and the renderer (rows from H1 title with any `Agent Note: ` prefix stripped, plus the filename date, sorted by date then filename, grouped as `### {Class}` sections in canonical class order). Two thin consumers share it: - -- [`scripts/gen-agent-note-index.ts`](../../../../scripts/gen-agent-note-index.ts) (`pnpm run gen-agent-note-index`) rewrites INDEX.md in full from the tree. -- [`scripts/verify-agent-note-classification.ts`](../../../../scripts/verify-agent-note-classification.ts) (a `doc-sync` member) checks structure, asserts the committed INDEX.md byte-matches a fresh render — the `gen-cordis-catalog`/`verify-cordis-catalog` pattern — and rejects an index-shaped row in the curated README. Freshness subsumes the index-completeness check: a generated-from-disk table is definitionally complete and correctly headed. - -Adding, moving, or deleting an Agent Note means editing only the Agent Note file and running the generator; the classification Agent Note's rejected-alternatives record carries the supersession cross-link. - -## Alternatives considered - -### Why not marker-delimited regions inside README.md? - -The first landed shape: the generator spliced the tables into README.md between `gen-agent-note-index` marker comments, under each `## {Lifecycle}` heading. Superseded by the whole-file INDEX.md once the README also absorbed the in-file format contract ([the uniform-format Agent Note](2026-07-05-uniform-agent-note-format.md)): a front-door README hosting hundreds of generated rows dwarfed its curated prose, and splice mechanics (marker pairs, heading checks, outside-region row detection) exist only to protect curated text that a dedicated generated file simply doesn't contain. - -### Why not the verifier-only model? - -It catches mistakes but still makes every proposal edit a shared hotspot in a hand-maintained table, and a failed verifier is strictly more annoying than a generator for a purely mechanical row: the author has already named and placed the file; the index copy adds no information. This is the same hand-list-versus-derivation judgment the [package-inventory proposal](../../proposed/process/2026-06-20-discover-package-inventory.md) applies to tsconfig references and knip stanzas — applied to the one list that demonstrably conflicts. - -## Consequences - -- The generated file is explicit: its banner names the generator, there is no curated region to protect inside it, and the generator refuses to run on a structurally invalid tree. -- A malformed or missing H1 is a hard error in both the generator and the gate — the H1 is now load-bearing as the index title source. -- Concurrent Agent Note branches resolve index conflicts by rerunning the generator, never by hand-merging rows. diff --git a/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md index 40c2dd6ec2..1a6aa40477 100644 --- a/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md +++ b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md @@ -18,10 +18,10 @@ The whole corpus was normalized in the same change that defined the format — t - **Header-only normalization** (H1 and Status, bodies untouched) — rejected: the debt markers flagged the *body* genre split, and leaving `Context`/`Decision` beside `Problem`/`Proposal` indefinitely resolves nothing. - **No Status line** (the folder already is the status; the three newest pre-format Agent Notes (and the zh counterpart of one) omitted the line) — rejected in favor of keeping a self-describing file: the drift risk that motivated dropping it is neutralized by gating the line against the folder instead. - **Dated status** (`Status: implemented (accepted YYYY-MM-DD)`) — rejected: the acceptance date is narrated history the writing rules keep out of docs; the filename carries first-proposed, git carries the rest, and the gate could check a date's format but never its truth. -- **A bare `# <title>` H1** — rejected: the `Agent Note: ` prefix is the corpus-majority form and self-describes the genre when a file is read outside its tree; the index generator strips it, so index rows are identical either way. +- **A bare `# <title>` H1** — rejected: the `Agent Note: ` prefix self-describes the genre when a file is read outside its tree, and the format gate prevents it from drifting. - **`## What we give up` as the implemented closer** (the README's own phrase for what an Agent Note records) — rejected: it names only costs, and an honest consequences section records what the trade-off bought as well. - **Convention without a gate** (write the contract down, enforce by review) — rejected: the slop checklist already outlawed spec-speak in `implemented/` by convention, and nineteen files show what convention alone achieves here. -- **A standalone `FORMAT.md` contract file** — the first landed home; folded into README.md once the generated index moved out to [INDEX.md](../../INDEX.md): with the tables gone the README regained the room, and one front door carrying layout, classification, and format beats splitting the contract across two files. +- **A standalone `FORMAT.md` contract file** — rejected because one front door carrying layout, classification, and format is easier to discover and maintain than two contract files. ## Consequences diff --git a/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.i18n.yaml b/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.i18n.yaml new file mode 100644 index 0000000000..2b1dc53f6b --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-remove-generated-agent-note-index.md: 27c1591b29a1ca64370de6ffadfb9c524a804ced +2026-07-19-remove-generated-agent-note-index.zh.md: 868955bc10900f784bd88066042abe24454e27b5 diff --git a/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.md b/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.md new file mode 100644 index 0000000000..27c1591b29 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.md @@ -0,0 +1,33 @@ +# Agent Note: Keep Agent Notes discoverable without a generated index + +Status: implemented + +English | [中文](2026-07-19-remove-generated-agent-note-index.zh.md) + +## Problem + +A committed Agent Note index duplicates facts already encoded by each file's lifecycle/class path, filename date, and H1. Every branch that adds, moves, or renames an otherwise unrelated Agent Note rewrites the same generated file, making that artifact a predictable merge hotspot. + +The centralized chronological list adds little discovery value beyond browsing the lifecycle/class tree or searching the repository, while its generator, renderer, command, and freshness check remain maintenance surface. + +## Decision + +The lifecycle/class filesystem tree is the Agent Note inventory. [README.md](../../README.md) remains the curated front door and contract, while ordinary tree navigation and repository search provide discovery. + +`scripts/agent-note-tree.ts` owns the closed lifecycle/class sets and structural walker. `verify-agent-note-classification` validates that tree and rejects the legacy homes and a root `INDEX.md`; it does not render or freshness-check a centralized list. + +This decision supersedes the rejected [generated-index proposal](../../rejected/process/2026-07-04-generate-agent-note-index-tables.md). + +## Alternatives considered + +**Keep the committed generated index and resolve conflicts by regenerating it.** Regeneration makes conflict resolution mechanical but does not prevent unrelated branches from modifying the same artifact or reduce the review noise it creates. + +**Offer an uncommitted on-demand index command.** It avoids committed conflicts but preserves a renderer and command for a discovery path already served by tree navigation and repository search. + +**Restore a hand-maintained index.** It has the same shared-file contention and adds completeness/order mistakes that generation avoided. + +## Consequences + +- Adding, moving, or renaming an Agent Note no longer changes a corpus-wide generated file. +- The classification gate performs less work and the documentation gate topology gains no process or stage. +- Readers give up a single chronological page and use the lifecycle/class tree or repository search instead. diff --git a/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.zh.md b/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.zh.md new file mode 100644 index 0000000000..868955bc10 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-19-remove-generated-agent-note-index.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 无需生成索引即可发现 Agent Note + +Status: implemented + +[English](2026-07-19-remove-generated-agent-note-index.md) | 中文 + +## 问题 + +提交到仓库的 Agent Note 索引，会重复记录每个文件的生命周期／类别路径、文件名日期和 H1 已经编码的事实。任何分支只要添加、移动或重命名彼此无关的 Agent Note，都会重写同一个生成文件，因此该产物会成为可预见的合并冲突热点。 + +与浏览生命周期／类别目录树或搜索仓库相比，这份集中式时间顺序清单提供的发现价值有限；但其生成器、渲染器、命令和新鲜度检查仍然构成维护负担。 + +## 决策 + +生命周期／类别文件系统目录树就是 Agent Note 清单。[README.md](../../README.md) 继续作为人工维护的入口和契约，普通的目录树浏览与仓库搜索负责内容发现。 + +`scripts/agent-note-tree.ts` 持有封闭的生命周期／类别集合与结构遍历器。`verify-agent-note-classification` 校验该目录树，并拒绝旧目录和根目录中的 `INDEX.md`，但不会渲染集中式清单或检查其新鲜度。 + +本决策取代已拒绝的[生成索引提案](../../rejected/process/2026-07-04-generate-agent-note-index-tables.md)。 + +## 备选方案 + +**保留提交到仓库的生成索引，并通过重新生成解决冲突。** 重新生成能让冲突解决过程机械化，但无法阻止无关分支修改同一产物，也不会减少由此产生的评审噪音。 + +**提供不提交到仓库的按需索引命令。** 这可以避免已提交文件的冲突，但仍需维护渲染器和命令，而目录树浏览与仓库搜索已经覆盖该发现路径。 + +**恢复人工维护的索引。** 它具有相同的共享文件争用问题，还会重新引入生成机制已经避免的完整性和排序错误。 + +## 影响 + +- 添加、移动或重命名 Agent Note 时，不再改动覆盖整个语料库的生成文件。 +- 分类门禁执行的工作更少，文档门禁拓扑也不会增加进程或阶段。 +- 读者不再获得单一的时间顺序页面，改用生命周期／类别目录树或仓库搜索。 diff --git a/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md new file mode 100644 index 0000000000..90c942411d --- /dev/null +++ b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md @@ -0,0 +1,36 @@ +# Agent Note: Generate the Agent Note index tables + +Status: rejected — a centralized generated list is merge-prone and adds little discovery value + +## Problem + +Per-lifecycle/per-class tables would list facts that are fully derivable: an Agent Note's path encodes lifecycle and class, its filename encodes the first-proposed date, and its H1 carries the title. A hand-maintained copy of those facts would also be a high-contention docs hotspot because concurrent Agent Note branches append rows to the same few lines. [The classification Agent Note](../../implemented/process/2026-06-20-agent-note-classification.md) makes the tree itself authoritative. + +## Proposal + +Keep the curated prose and generate the list as a fully generated `.agents/notes/INDEX.md`. A shared `scripts/agent-note-index.ts` module would own both the tree walker and the renderer. Two thin consumers would share it: + +- `scripts/gen-agent-note-index.ts` (`pnpm run gen-agent-note-index`) would rewrite INDEX.md in full from the tree. +- `scripts/verify-agent-note-classification.ts` would check structure and assert that the committed INDEX.md byte-matches a fresh render. + +Adding, moving, or deleting an Agent Note would mean editing the Agent Note file and running the generator. + +## Alternatives considered + +### Why not marker-delimited regions inside README.md? + +Marker-delimited tables inside README.md would mix generated and curated text, requiring splice mechanics and protection for the surrounding contract. A dedicated generated file would at least keep those concerns separate. + +### Why not the verifier-only model? + +It catches mistakes but still makes every proposal edit a shared hotspot in a hand-maintained table. The author has already named and placed the file, so the index copy adds no information. This is the same hand-list-versus-derivation judgment the [package-inventory proposal](../../proposed/process/2026-06-20-discover-package-inventory.md) applies to tsconfig references and knip stanzas. + +## Consequences + +- The generated file would be explicit and contain no curated region. +- A malformed or missing H1 would be a hard error because the H1 supplies each row title. +- Concurrent branches would still modify the same committed artifact, even if conflicts could be resolved by rerunning the generator. + +## Related + +The implemented [no-index decision](../../implemented/process/2026-07-19-remove-generated-agent-note-index.md) keeps the tree and repository search as the discovery mechanisms. diff --git a/.agents/skills/dsh-code-review/SKILL.md b/.agents/skills/dsh-code-review/SKILL.md index c980ad444c..814132d481 100644 --- a/.agents/skills/dsh-code-review/SKILL.md +++ b/.agents/skills/dsh-code-review/SKILL.md @@ -14,7 +14,7 @@ description: Use when reviewing a pull request in the deepseek-harness repo — - [docs/AGENTS.md](../../../docs/AGENTS.md): documentation placement and prose discipline. - [dsh-prose-standard](../dsh-prose-standard/SKILL.md): required coverage and editorial judgment for comments, docs, prompts, and visible strings. - [docs/testing.md](../../../docs/testing.md) and the [quality-gates Agent Note](../../notes/implemented/process/2026-06-11-quality-gates.md): required test tiers and gates. -- [Agent Note index](../../notes/README.md): design rationale. Treat disagreement with an Agent Note as a design discussion, not an automatic veto. +- [Agent Notes](../../notes/README.md): design rationale. Treat disagreement with an Agent Note as a design discussion, not an automatic veto. - For bilingual changes, read [translation-rules.md](../../../docs/i18n/translation-rules.md), [terminology.md](../../../docs/i18n/terminology.md), and [dsh-translate-docs](../dsh-translate-docs/SKILL.md). ## Blocking requirements diff --git a/.agents/skills/dsh-find-simplifications/SKILL.md b/.agents/skills/dsh-find-simplifications/SKILL.md index ae1f3b60d1..2ce80f3f74 100644 --- a/.agents/skills/dsh-find-simplifications/SKILL.md +++ b/.agents/skills/dsh-find-simplifications/SKILL.md @@ -11,7 +11,7 @@ This skill helps turn a broad "find things to simplify" request into evidence-ba - Read `AGENTS.md`, especially the pre-release stance and the conventions (including the tests-are-not-golden-truth and Agent Notes-are-not-golden-truth doctrines), plus [docs/defensive-patterns.md](../../../docs/defensive-patterns.md) and [docs/testing.md](../../../docs/testing.md). - Skim [docs/architecture.md](../../../docs/architecture.md) before judging anything under `packages/`; simplifications that fight the service map or event taxonomy need extra evidence. -- Use the Agent Note index ([.agents/notes/README.md](../../notes/README.md)) to understand intentional architecture. The most relevant implemented examples are [drop mutable session summary](../../notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md), [shared persistence write coordinator](../../notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md), [capability seams](../../notes/implemented/architecture/2026-06-13-capability-seams.md), and the twin adapter / dual persistence backend Agent Notes. +- Use the Agent Note tree and its [contract](../../notes/README.md) to understand intentional architecture. The most relevant implemented examples are [drop mutable session summary](../../notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md), [shared persistence write coordinator](../../notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md), [capability seams](../../notes/implemented/architecture/2026-06-13-capability-seams.md), and the twin adapter / dual persistence backend Agent Notes. - Treat dual LLM adapters and dual persistence backends as intentional by default. Do not propose deleting either twin/backend as "low effort" unless the user explicitly overrides that constraint. Removing an unused method or hook inside a protected seam can still be valid if it does not collapse the protected design. ## What Counts As A Strong Candidate @@ -68,7 +68,7 @@ Reject or downgrade a candidate when: ## Write The Agent Note -Create one file per durable proposal under `.agents/notes/<lifecycle>/<class>/yyyy-mm-dd-topic.md`, following the lifecycle/classification contract in `.agents/notes/README.md`. Regenerate `.agents/notes/INDEX.md`; never add a manual Agent Note table to the README. Keep prose paragraphs on one physical line and use relative Markdown links. +Create one file per durable proposal under `.agents/notes/<lifecycle>/<class>/yyyy-mm-dd-topic.md`, following the lifecycle/classification contract in `.agents/notes/README.md`. Keep prose paragraphs on one physical line and use relative Markdown links. Prefer this shape, adjusting when the idea needs it: diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index 8036d11e0b..2ca3f14fbc 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: 31d9f76b6f32b1d26e7b61cdbc2a09aa3504fd6a -development.zh.md: 57d9ca376ed85c212cfd075e1b056882f6449e05 +development.md: 94eb4f03329b574862a1ac1de2f8c1d4db4f4a0a +development.zh.md: b533aff43a66ff7cfc5dc61e5b9b224a01c51f12 diff --git a/docs/development.md b/docs/development.md index 31d9f76b6f..94eb4f0332 100644 --- a/docs/development.md +++ b/docs/development.md @@ -86,7 +86,6 @@ pnpm run verify-cordis-catalog # fail if either cordis catalog is stale pnpm run verify-export-jsdoc # fail if a module-level package export lacks complete JSDoc pnpm run gen-doc-graphs # regenerate generated relationship docs from source and curated graph definitions pnpm run verify-doc-graphs # fail if generated relationship docs are stale -pnpm run gen-agent-note-index # regenerate .agents/notes/INDEX.md from the Agent Note tree pnpm run verify-md-wrap # fail on hard-wrapped prose paragraphs in docs/README markdown pnpm run verify-mermaid # fail if a ```mermaid diagram has invalid Mermaid syntax pnpm run verify-type-equiv # fail if a ```ts type-equiv doc block drifts from its source type diff --git a/docs/development.zh.md b/docs/development.zh.md index 57d9ca376e..b533aff43a 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -86,7 +86,6 @@ pnpm run verify-cordis-catalog # fail if either cordis catalog is stale pnpm run verify-export-jsdoc # fail if a module-level package export lacks complete JSDoc pnpm run gen-doc-graphs # regenerate generated relationship docs from source and curated graph definitions pnpm run verify-doc-graphs # fail if generated relationship docs are stale -pnpm run gen-agent-note-index # regenerate .agents/notes/INDEX.md from the Agent Note tree pnpm run verify-md-wrap # fail on hard-wrapped prose paragraphs in docs/README markdown pnpm run verify-mermaid # fail if a ```mermaid diagram has invalid Mermaid syntax pnpm run verify-type-equiv # fail if a ```ts type-equiv doc block drifts from its source type diff --git a/package.json b/package.json index 42988ca5ad..ad4704bf98 100644 --- a/package.json +++ b/package.json @@ -53,7 +53,6 @@ "verify-runtime-closure": "tsx scripts/verify-runtime-closure.ts", "verify-cordis-config": "tsx scripts/verify-cordis-config.ts", "gen-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts", - "gen-agent-note-index": "tsx scripts/gen-agent-note-index.ts", "verify-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts --check", "gen-cordis-api": "tsx scripts/gen-cordis-api.ts", "verify-cordis-api": "tsx scripts/gen-cordis-api.ts --check", diff --git a/scripts/agent-note-index.ts b/scripts/agent-note-index.ts deleted file mode 100644 index e5006eab80..0000000000 --- a/scripts/agent-note-index.ts +++ /dev/null @@ -1,130 +0,0 @@ -/** - * Shared source of truth for the Agent Note index: the tree walker (structure rules) and the README - * table renderer. `gen-agent-note-index.ts` writes the generated regions; - * `verify-agent-note-classification.ts` checks structure and asserts the committed regions are fresh. - * Lifecycle and class sets are closed under `.agents/notes/README.md`; rows derive - * from path, H1, and filename date and sort deterministically. Import is pure. - */ - -import { readFileSync, readdirSync } from 'node:fs' -import { resolve, sep } from 'node:path' -import { globSync } from 'node:fs' - -export const agentNoteRoot = resolve(import.meta.dirname, '../.agents/notes') - -/** The closed set of Agent Note lifecycles (top-level folders under .agents/notes/). */ -const LIFECYCLES = ['proposed', 'implemented', 'rejected'] as const - -/** - * The closed set of Agent Note classes (nested folder under each lifecycle). Adding a - * class is a deliberate act: extend this list AND the README's Classification - * section. The gate rejects any folder not listed here. - */ -const CLASSES = ['feature', 'bug-fix', 'simplification', 'architecture', 'process', 'testing'] as const - -/** Non-Agent Note Markdown allowed to sit directly at a lifecycle root. */ -const ROOT_ALLOWLIST = new Set(['AGENTS.md', 'CLAUDE.md']) - -/** Title-case a class/lifecycle folder name for a README heading. */ -const heading = (s: string): string => s.charAt(0).toUpperCase() + s.slice(1) - -/** One Agent Note file, as discovered by the walker. */ -export interface AgentNote { - lifecycle: string - cls: string - base: string - /** Path relative to .agents/notes — the README link target. */ - rel: string - /** H1 text with any `Agent Note: ` prefix stripped — the README row title. */ - title: string - /** `yyyy-mm-dd` from the filename — the "First proposed" column. */ - date: string -} - -/** - * Walk the Agent Note tree, enforcing the structure rules. Returns every valid Agent Note - * plus one error string per violation (unknown lifecycle or class folder, bad - * depth, bad filename, missing/malformed H1). Callers treat a non-empty error - * list as fatal — the index is only generated from a structurally valid tree. - */ -export function walkAgentNoteTree(): { notes: AgentNote[]; errors: string[] } { - const notes: AgentNote[] = [] - const errors: string[] = [] - // The lifecycle set is closed too: any directory under .agents/notes/ that is not - // a known lifecycle would otherwise hold Agent Notes invisible to the walk below. - for (const entry of readdirSync(agentNoteRoot, { withFileTypes: true })) { - if (entry.isDirectory() && !(LIFECYCLES as readonly string[]).includes(entry.name)) { - errors.push(`structure: ${entry.name}/ — unknown lifecycle folder (allowed: ${LIFECYCLES.join(', ')})`) - } - } - for (const lifecycle of LIFECYCLES) { - for (const match of globSync(`${lifecycle}/**/*.md`, { cwd: agentNoteRoot }).map(path => path.split(sep).join('/')).sort()) { - const segs = match.split('/') - // Allowlisted file directly at the lifecycle root (e.g. implemented/AGENTS.md). - if (segs.length === 2 && ROOT_ALLOWLIST.has(segs[1] ?? '')) continue - // A Chinese counterpart (foo.zh.md, docs/i18n/README.md) is the SAME Agent Note, - // indexed via its English filename; the pairing gate owns its consistency. - if (match.endsWith('.zh.md')) continue - const cls = segs[1] - const base = segs[2] - if (segs.length !== 3 || cls === undefined || base === undefined) { - errors.push(`structure: ${match} — expected {lifecycle}/{class}/file.md (got depth ${segs.length})`) - continue - } - if (!(CLASSES as readonly string[]).includes(cls)) { - errors.push(`structure: ${match} — unknown class folder "${cls}" (allowed: ${CLASSES.join(', ')})`) - continue - } - if (!/^\d{4}-\d{2}-\d{2}-.+\.md$/.test(base)) { - errors.push(`structure: ${match} — filename must be yyyy-mm-dd-topic.md`) - continue - } - const firstLine = readFileSync(resolve(agentNoteRoot, match), 'utf8').split('\n', 1)[0] ?? '' - const h1 = /^#\s+(?:Agent Note:\s+)?(.+?)\s*$/.exec(firstLine) - if (!h1?.[1]) { - errors.push(`title: ${match} — first line must be an H1 (\`# Agent Note: <title>\` or \`# <title>\`), got: ${JSON.stringify(firstLine)}`) - continue - } - notes.push({ lifecycle, cls, base, rel: match, title: h1[1], date: base.slice(0, 10) }) - } - } - return { notes, errors } -} - -/** - * Render one lifecycle's section body: a `### {Class}` heading plus a - * `| Title | First proposed |` table for every non-empty class, in CLASSES - * order, rows sorted by date then filename. - */ -function renderLifecycle(notes: AgentNote[], lifecycle: string): string { - const sections: string[] = [] - for (const cls of CLASSES) { - const rows = notes - .filter(r => r.lifecycle === lifecycle && r.cls === cls) - .sort((a, b) => a.date.localeCompare(b.date) || a.base.localeCompare(b.base)) - if (rows.length === 0) continue - const table = rows.map(r => `| [${r.title}](${r.rel}) | ${r.date} |`).join('\n') - sections.push(`### ${heading(cls)}\n\n| Title | First proposed |\n|---|---|\n${table}`) - } - return sections.join('\n\n') -} - -/** - * Render the complete `.agents/notes/INDEX.md` content: a generated-file banner - * followed by one `## {Lifecycle}` section per lifecycle in canonical order. - * The whole file is generated state — there is no curated region to preserve. - */ -export function renderIndex(notes: AgentNote[]): string { - const parts = [ - '# Agent Note index', - '', - 'Generated by `pnpm run gen-agent-note-index` from the Agent Note tree — never edit by hand; `verify-agent-note-classification` fails when this file is stale. The curated front door — layout, classification, when to write one, and the in-file format — is [README.md](README.md).', - ] - for (const lifecycle of LIFECYCLES) { - parts.push('', `## ${heading(lifecycle)}`, '', renderLifecycle(notes, lifecycle)) - } - return `${parts.join('\n')}\n` -} - -/** Matches an index-shaped table row (a `| [title](lifecycle/…) |` line) — generated state that must not appear in curated prose. */ -export const INDEX_ROW = /^\|\s*\[[^\]]+\]\((?:proposed|implemented|rejected)\// diff --git a/scripts/agent-note-tree.ts b/scripts/agent-note-tree.ts new file mode 100644 index 0000000000..1dff5aab22 --- /dev/null +++ b/scripts/agent-note-tree.ts @@ -0,0 +1,78 @@ +/** + * Shared structural source of truth for the Agent Note tree. Lifecycle and class + * sets are closed under `.agents/notes/README.md`; importing this module is pure. + */ + +import { globSync, readdirSync } from 'node:fs' +import { resolve, sep } from 'node:path' + +export const agentNoteRoot = resolve(import.meta.dirname, '../.agents/notes') + +/** The closed set of Agent Note lifecycles (top-level folders under .agents/notes/). */ +const LIFECYCLES = ['proposed', 'implemented', 'rejected'] as const + +/** + * The closed set of Agent Note classes (nested folder under each lifecycle). Adding a + * class is a deliberate act: extend this list AND the README's Classification + * section. The gate rejects any folder not listed here. + */ +const CLASSES = ['feature', 'bug-fix', 'simplification', 'architecture', 'process', 'testing'] as const + +/** Non-Agent Note Markdown allowed to sit directly at a lifecycle root. */ +const ROOT_ALLOWLIST = new Set(['AGENTS.md', 'CLAUDE.md']) + +/** One Agent Note file, as discovered by the walker. */ +export interface AgentNote { + lifecycle: string + /** Path relative to .agents/notes. */ + rel: string + /** `yyyy-mm-dd` from the filename. */ + date: string +} + +/** + * Walk the Agent Note tree, enforcing the structure rules. Returns every valid Agent Note + * plus one error string per violation (unknown lifecycle or class folder, bad + * depth, or bad filename). Callers treat a non-empty error list as fatal. + */ +export function walkAgentNoteTree(): { notes: AgentNote[]; errors: string[] } { + const notes: AgentNote[] = [] + const errors: string[] = [] + // The lifecycle set is closed too: any directory under .agents/notes/ that is not + // a known lifecycle would otherwise hold Agent Notes invisible to the walk below. + for (const entry of readdirSync(agentNoteRoot, { withFileTypes: true })) { + if (entry.name === 'INDEX.md') { + errors.push('structure: INDEX.md — centralized Agent Note indexes are forbidden; browse the lifecycle/class tree or search the repository') + continue + } + if (entry.isDirectory() && !(LIFECYCLES as readonly string[]).includes(entry.name)) { + errors.push(`structure: ${entry.name}/ — unknown lifecycle folder (allowed: ${LIFECYCLES.join(', ')})`) + } + } + for (const lifecycle of LIFECYCLES) { + for (const match of globSync(`${lifecycle}/**/*.md`, { cwd: agentNoteRoot }).map(path => path.split(sep).join('/')).sort()) { + const segs = match.split('/') + // Allowlisted file directly at the lifecycle root (e.g. implemented/AGENTS.md). + if (segs.length === 2 && ROOT_ALLOWLIST.has(segs[1] ?? '')) continue + // A Chinese counterpart (foo.zh.md, docs/i18n/README.md) is the SAME Agent Note, + // indexed via its English filename; the pairing gate owns its consistency. + if (match.endsWith('.zh.md')) continue + const cls = segs[1] + const base = segs[2] + if (segs.length !== 3 || cls === undefined || base === undefined) { + errors.push(`structure: ${match} — expected {lifecycle}/{class}/file.md (got depth ${segs.length})`) + continue + } + if (!(CLASSES as readonly string[]).includes(cls)) { + errors.push(`structure: ${match} — unknown class folder "${cls}" (allowed: ${CLASSES.join(', ')})`) + continue + } + if (!/^\d{4}-\d{2}-\d{2}-.+\.md$/.test(base)) { + errors.push(`structure: ${match} — filename must be yyyy-mm-dd-topic.md`) + continue + } + notes.push({ lifecycle, rel: match, date: base.slice(0, 10) }) + } + } + return { notes, errors } +} diff --git a/scripts/gen-agent-note-index.ts b/scripts/gen-agent-note-index.ts deleted file mode 100644 index df54300a19..0000000000 --- a/scripts/gen-agent-note-index.ts +++ /dev/null @@ -1,36 +0,0 @@ -/** - * Regenerate `.agents/notes/INDEX.md` — the fully generated Agent Note index — from the - * Agent Note tree (see [agent-note-index.ts](./agent-note-index.ts) for the layout contract and - * rendering rules). The whole file is generated state; the curated prose lives - * in `.agents/notes/README.md`. Freshness is asserted by - * `verify-agent-note-classification.ts` (a `doc-sync` member), so a stale committed - * index fails CI. - * - * Run: `pnpm run gen-agent-note-index`. - */ - -import { readFileSync, writeFileSync } from 'node:fs' -import { resolve } from 'node:path' -import { agentNoteRoot, renderIndex, walkAgentNoteTree } from './agent-note-index.ts' - -const { notes, errors } = walkAgentNoteTree() -if (errors.length > 0) { - console.error('gen-agent-note-index: refusing to generate from a structurally invalid tree:') - for (const e of errors) console.error(` ${e}`) - process.exit(1) -} - -const indexPath = resolve(agentNoteRoot, 'INDEX.md') -const next = renderIndex(notes) -let current: string | undefined -try { - current = readFileSync(indexPath, 'utf8') -} catch { - // Missing INDEX.md is the fresh-generation case, not an error: fall through and write it. -} -if (next === current) { - console.log(`gen-agent-note-index: .agents/notes/INDEX.md is up to date (${notes.length} Agent Notes).`) -} else { - writeFileSync(indexPath, next) - console.log(`gen-agent-note-index: .agents/notes/INDEX.md regenerated (${notes.length} Agent Notes).`) -} diff --git a/scripts/verify-agent-note-classification.ts b/scripts/verify-agent-note-classification.ts index 81cc79c5f5..776e155f4f 100644 --- a/scripts/verify-agent-note-classification.ts +++ b/scripts/verify-agent-note-classification.ts @@ -1,13 +1,12 @@ /** - * Enforce Agent Note lifecycle/class paths, dated filenames, and titles; verify the - * generated index and reject index rows in the curated README. Structural rules - * and rendering are shared with `agent-note-index.ts`; the closed classification - * contract lives in `.agents/notes/README.md`. + * Enforce Agent Note lifecycle/class paths and dated filenames. Structural rules + * are shared with `agent-note-tree.ts`; the closed classification contract lives + * in `.agents/notes/README.md`. */ -import { existsSync, readFileSync } from 'node:fs' +import { existsSync } from 'node:fs' import { resolve } from 'node:path' -import { agentNoteRoot, INDEX_ROW, renderIndex, walkAgentNoteTree } from './agent-note-index.ts' +import { walkAgentNoteTree } from './agent-note-tree.ts' const { notes, errors } = walkAgentNoteTree() @@ -19,25 +18,7 @@ for (const legacyRoot of ['docs/rfc', 'docs/rfcs']) { } if (errors.length === 0) { - let index: string | undefined - try { - index = readFileSync(resolve(agentNoteRoot, 'INDEX.md'), 'utf8') - } catch { - // A missing INDEX.md is reported below as staleness, exactly like a drifted one. - } - if (renderIndex(notes) !== index) { - errors.push('index: .agents/notes/INDEX.md is stale or missing — run `pnpm run gen-agent-note-index` and commit the result') - } - const readme = readFileSync(resolve(agentNoteRoot, 'README.md'), 'utf8') - for (const line of readme.split('\n')) { - if (INDEX_ROW.test(line)) { - errors.push(`readme: index-shaped row in the curated README (the list lives in INDEX.md): ${JSON.stringify(line.slice(0, 80))}`) - } - } -} - -if (errors.length === 0) { - console.log(`verify-agent-note-classification: ${notes.length} Agent Note(s) checked, structure and index consistent.`) + console.log(`verify-agent-note-classification: ${notes.length} Agent Note(s) checked, structure consistent.`) process.exit(0) } diff --git a/scripts/verify-agent-note-format.ts b/scripts/verify-agent-note-format.ts index b38c6225bd..39018588e6 100644 --- a/scripts/verify-agent-note-format.ts +++ b/scripts/verify-agent-note-format.ts @@ -7,7 +7,7 @@ import { readFileSync } from 'node:fs' import { resolve } from 'node:path' -import { agentNoteRoot, walkAgentNoteTree } from './agent-note-index.ts' +import { agentNoteRoot, walkAgentNoteTree } from './agent-note-tree.ts' /** The date the format contract landed; the grandfather comment is valid only before it. */ const FORMAT_ADOPTED = '2026-07-05'