# Conflicts: # .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md # .agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml # .agents/notes/implemented/feature/2026-07-06-sandbox.md # .agents/notes/implemented/feature/2026-07-06-sandbox.zh.md # .agents/notes/implemented/feature/2026-07-27-tmux-location-context.i18n.yaml # .agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml # .agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml # .agents/notes/implemented/simplification/2026-07-30-private-agent-send.i18n.yaml # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/compaction.i18n.yaml # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/core.md # docs/core-data-structures/core.zh.md # docs/core-data-structures/llm-streaming.i18n.yaml # docs/core-data-structures/llm-streaming.md # docs/core-data-structures/llm-streaming.zh.md # docs/core-data-structures/session.i18n.yaml # docs/event-producer-consumer.md # docs/module-graph.md # docs/persistence-catalog.md # examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/acp-agent/tests/snapshots/bash-spill/session.jsonl # examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/cancel/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl # examples/acp-agent/tests/snapshots/error-finish/session.jsonl # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/fs-edit/session.jsonl # examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl # examples/acp-agent/tests/snapshots/fs-read/session.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl # examples/acp-agent/tests/snapshots/fs-write/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl # examples/acp-agent/tests/snapshots/multi-turn/session.jsonl # examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/pty-tools/session.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl # examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl # examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl # examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl # examples/acp-agent/tests/snapshots/skill-load/session.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/acp-agent/tests/snapshots/text-turn/session.jsonl # examples/acp-agent/tests/snapshots/todo-write/session.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl # examples/acp-agent/tests/snapshots/web-fetch/session.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.jsonl # examples/acp-agent/tests/snapshots/workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl # examples/headless-agent/tests/semantic-checkpoint-snapshots/tool-outcome-unknown/session.expected.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/provider-retry/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/pty-tools/session.jsonl # examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl # packages/client/runtime/README.i18n.yaml # packages/client/runtime/src/client/sessions/request-inspection.ts # packages/compact/compact-basic/README.i18n.yaml # packages/compact/compact-basic/README.md # packages/compact/compact-basic/README.zh.md # packages/compact/compact-basic/src/index.ts # packages/context/time-context/tests/time-context.spec.ts # packages/context/tmux-context/README.i18n.yaml # packages/context/tmux-context/tests/tmux-context.spec.ts # packages/context/workspace-context/tests/workspace-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/README.i18n.yaml # packages/core/agent-loop/README.md # packages/core/agent-loop/README.zh.md # packages/core/agent-loop/src/agent.ts # packages/core/agent/README.i18n.yaml # packages/core/agent/README.md # packages/core/agent/README.zh.md # packages/core/agent/src/types.ts # packages/core/session/README.i18n.yaml # packages/core/session/README.md # packages/core/session/README.zh.md # packages/fs/tool-str-replace-editor/tests/tools.spec.ts # packages/goal/command-goal/tests/command-goal.spec.ts # packages/goal/goal/tests/goal.spec.ts # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/tests/api-proxy-workspace.spec.ts # packages/llm/llm/README.i18n.yaml # packages/llm/llm/README.md # packages/llm/llm/README.zh.md # packages/llm/llm/src/index.ts # packages/pty/pty-local/tests/index.spec.ts # packages/pty/pty-local/tests/local.spec.ts # packages/pty/pty/tests/service.spec.ts # packages/pty/tool-bash-persistent/tests/loader-composition.spec.ts # packages/pty/tool-bash-persistent/tests/tools.spec.ts # packages/pty/tool-pty/tests/loader-composition.spec.ts # packages/pty/tool-pty/tests/tools.spec.ts # packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts # packages/skill/tool-skill/tests/tool-skill.spec.ts # packages/tasks/tasks-local/tests/tasks.spec.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/tests/tui.spec.ts # packages/ui/user-approval/src/index.ts # packages/ui/user-approval/tests/approval.spec.ts
17 KiB
DeepSeek Harness Architecture
English | 中文
DeepSeek Harness SDK uses Cordis: everything is a plugin, including the loop.
Overview
Harnesses are Cordis contexts; packages contribute services, typed events, and disposable registrations. packages/core/ groups the default flow; capabilities remain plugins.
Default Services
| ctx key | Package | Role |
|---|---|---|
| — | dsh-scope |
scoped-context registrations and shared layer storage (library) |
ctx.sessions |
dsh-session |
in-memory event-sourced sessions |
ctx.systemPrompt |
dsh-system-prompt |
ordered prompt sections, tool schemas, and variables |
ctx.tools |
dsh-tools |
tool registry and execution pipeline |
ctx.agents |
dsh-agent |
live agents, delegated creation, agent/* events, process-local initiator scope |
ctx.agentLoop |
dsh-agent-loop |
concrete Agent driver |
Capability Services
| ctx key | Package family | Role |
|---|---|---|
ctx.llm |
llm/ |
adapter registry, streaming model calls |
ctx.tokenMeter |
llm/token-meter |
replay-aware request and surface pressure |
ctx.bash |
bash/ |
foreground/background command execution |
ctx.subprocess |
subprocess/ |
managed child-process trees for bash, LSP, and ACP subagent backends |
ctx.pty |
pty/ |
owner-scoped persistent terminal sessions |
ctx.sandbox |
sandbox/ |
same-world process confinement through argv wrapping and per-call policy |
ctx.sandboxPolicy |
sandbox/ |
shared sandbox policy home |
ctx.codeRuntime |
code-runtime/ |
model-written program execution |
ctx.fs |
fs/ |
filesystem provider primitives and policy events |
ctx.lsp |
lsp/ |
semantic navigation registry |
ctx.skills |
skill/ |
skill provider registry, progressive disclosure |
ctx.web |
web/ |
search/fetch provider registries |
ctx.compact, ctx.toolResultPrune |
compact//compact-tool-result-prune |
summary compaction, optional model-free result pruning |
ctx.subagents |
subagent/ |
named delegation providers |
ctx.planMode |
plan/ |
logged plan collaboration state |
ctx.tasks |
tasks/ |
background task registry, generic task_* controls |
ctx.workflows |
workflow/ |
script-driven multi-agent orchestration |
ctx.goals |
goal/ |
persisted same-session goals |
ctx.sessionPersistence |
session-persistence/ |
durable session-log storage |
ctx.sessionQuery |
session-query/ |
live-preferred exact/filter/trace queries over SQLite FTS, workspace-authorized model tools |
ctx.sessionTitle |
session-title/ |
log-backed fallbacks, one optional asynchronous provider |
ctx.settings |
settings/ |
per-plugin user-settings namespaces layered over composition entries |
ctx.credentials |
credentials/ |
named secret references resolved per operation, never inlined in configuration |
ctx.directoryPicker |
host/directory-picker |
GUI-host directory picking (native/browse interactions) |
ctx.typert |
typert/registry |
runtime registry for generated package reflection and live Zod schemas |
ctx.invariants |
support/invariants |
package-name-selected registry of package-owned runtime checks |
Event
Events are the service extension API (catalog, producer/consumer map).
Event Domains
- Session events are durable log facts emitted through
session/event. - Agent events carry live
Agentfor inbox, step, status, request, validation, and continuation. - Capability events attach policy and adapters without a loop import.
Interception Semantics
Waterfalls are around-middleware: listeners delegate with next(); returning without it vetoes or takes over (semantics).
Default Loop Lifecycle
A session is append-only. A turn claims one queued follow-up, waits for its predecessor's checkpoint, and may share its running interval (decision); injection claims none. A step is one model request plus tools. Quotes in the sequence mark durable events.
Creation without an id mints <config-id>-session-<uuid>; sessionId resumes or creates, while resumeSessionId requires history. Resume restores lineage and delegation depth before publication; setup failure emits agent-loop/config-start-failed.
Turn Flow
choose declarative identity and fresh/resume path
-> prepare private session + agent.ctx -> await unpublished setup
-> enter session + agent -> session/created -> agent/created
-> enable driving -> agent/session-start(source) -> start driver
forever:
wait for waking inbox work
claim next-step input plus one next-turn message
-> emit agent/inbox/claimed({ message, turn }) for each claimed message
-> emit agent/status(running) if starting an interval
-> agent/pre-step(messages, { turn, step, signal })
reject or listener failure -> the claimed batch stays removed; stop the driver
enter:
'turn/start'
step loop:
'step/start'
append the returned batch as separate 'user/message' events
assemble ordered prompt and tool schemas -> snapshot derived messages
agent/request (config only) -> prepare adapter defaults/provenance + context capacity under turn signal -> log request/header (+ request/context on route change) -> llm/stream (frozen, registration-bound)
'assistant/chunk'
'assistant/message'
schedule tool calls by ctx.tools.executionMode:
exclusive -> barrier
parallel -> rolling pool, <= maxParallelToolCalls; reclassify at start
start -> 'tool/call' -> tools/pre-execute -> concurrent tools/execute
model-order result -> ordered tools/post-execute -> 'tool/result'
'step/end'
tools owe another request or next-step inbox is nonempty
-> claim -> agent/pre-step -> append entered batch -> continue
otherwise agent/turn-stopping -> re-check the next-step inbox
'turn/end'
start the next waking queued message, or emit agent/status(idle)
idle inject:
queue non-waking next-step context
leave it pending until followup or steer wakes the driver
Each step assembles ordered prompt sections, tool schemas, and variables; unknown references fail the turn. dsh-system-prompt owns identity and persona; the loop supplies provider, model, and cwd (prompt ownership).
inject() queues non-waking next-step context; an idle driver leaves it pending until followup() or steer() wakes the driver. Post-tool additionalContexts use the same inbox. agent/pre-step receives the exclusive claimed batch and upcoming turn, step, and signal. Reject opens no step; enter supplies the complete batch appended after step/start. Empty tool continuations still traverse the waterfall, whose final value settles all rewrites.
Pruning precedes summaries; overflow retries require durable progress. agent/request-error may authorize a same-step retry of the frozen prompt; cancellation wins. Adapter retryPolicy bounds normal mode, while always mode retries after specialized recovery (compaction, retry foundation, provider policy).
Failure Boundaries
Adapter selection, dispatch, and iteration failures become terminal error or aborted finish chunks. agent/request-error receives request coordinates, normalized LlmFailure, available retry policy, and signal; middleware and consumer errors remain outside recovery. Failed chunks commit neither messages nor tool calls.
Other failures use agent/error; cancellation and disposal beat recovery. Before request-header commit, the turn signal cancels capability preparation; undispatched tools get synthetic tool/call/ABORTED_BEFORE_DISPATCH pairs. Effective cancel(cause) reports its cause before clearing and aborting; idle calls emit nothing. Durability distinguishes aborted cancellation from disposed teardown, which awaits quiescence (decision).
Turn and step events are turn-enclosed; the loop appends user/message events only from entered batches inside a turn. Standalone compact/* { turn: null } events consume no turn, and their lock-time markers may interleave with inbox splices. Reload synthesizes interrupted turn ends; session/end-seed distinguishes stale compaction orphans from live locks. After close, only agent/error reports failures. Each turn has one TurnEndReason.
Agent Handles
ctx.agents owns agents and returns AgentHandle { agent, dispose() }. Plugins use send() or its followup(), steer(), and inject() presets. cancel() and whenIdle() control lifecycle, while awaited disposal owns teardown. A follow-up MessageId follows durable inbox insertion, claiming, and discard notifications, not prompt output or turn ending; only an owner of a whole activity interval may summarize it as a run result (decision).
Agent Scope
Each agent owns scoped agent.ctx; shared storage overlays its tool, prompt, and command entries on globals while preserving domain views (decision). Scoped listeners filter dispatch; contributions unwind with awaited cleanup. CreateAgentOptions.setup(agentCtx) composes before publication. Typed resolvers derive carrier checks from merged Events and scopeTarget (semantic gates). Details: agent scope, subagent composition. AgentLoop runs under ctx.agents.withInitiator(); private orchestration derives agent.session, but turn, step, signal, cwd, and authority stay explicit (decision).
State
Session Log
The session log is authoritative. deriveMessages() projects model history; raw assistant/chunk events preserve replay and UI fidelity. Fork, resume, transcript rendering, telemetry, and persistence derive from this stream.
Model-visible ⟺ logged: messages entering at step/start plus the folded request/header reconstruct every request. The header marks adapter defaults so later proposals discard them and re-resolve the route without losing explicit settings. request/context separately records registration-bound provider, model, and capacity metadata when the route changes; it does not participate in request reconstruction or header equality. dsh-agent-loop/invariant asserts reconstructability through ctx.invariants (reconstructability).
Durability is a plugin concern. Backends eagerly drain synchronous session/event notifications. session/flush precedes requests and top-level tool dispatch, and follows turn/end before another turn or idle. SessionPersistence stores events and header metadata; JSONL defaults to checksummed Zstandard and SQLite shares the contract (decision).
Between turns, owners append log-only events through Session, flushing only for durability. session/title needs eager persistence and lifecycle drains; manual compaction flushes its bracket before the operation completes. Title work never delays responses; latest wins with provenance. Title records are inherited fork boundaries (decision).
Model Content
Messages use typed blocks from merge-extensible ContentBlockMap; the pattern also types MessageSource, FinishReason, TurnTrigger, and TurnEndReason. New blocks coordinate adapters, UI, compaction, token metering, and persistence; replay measurements live in token-meter.md.
Streaming uses raw chunks and BlockAssembler. Each LlmAdapter.stream() is one provider attempt; adapters report normalized failure facts, and a handling agent/request-error plugin returns a retry action. The loop logs chunks, successful provenance, and replay state. Remote adapters use per-read idle watchdogs. Replay crosses routes only through a shared adapter instance (contract).
Extension And Composition
Capability Pattern
A swappable capability usually has interface / implementation / consumer layers: service/events, backend, and model-facing tools/prompts. Bash is the reference; the capability graph maps each family.
Exceptions combine LLM interface/consumer, filesystem policy, web registries, and named skill/subagent providers. Subagents spawn fresh, fork a completed-turn prefix, or use ACP children (subagent.md).
dsh-workspace-context prepends its baseline to the next-step inbox on first agent/pre-step, replacing a pending predecessor, and adds ctx.fs changes after tools. Because claim precedes pre-step, the baseline may miss the current request (decision). dsh-paths owns shared paths.
Bundles And Apps
dsh-agent-spine-demo bundles a spine and optional goals. App packages own TUI, CLI, ACP automation, and JSON-RPC front doors (README, acp/, ui/). dsh-jsonrpc-agent boots external cordis.yml; the Python SDK defaults when config is absent (Python SDK). Thin deployments use swappable backends and optional tools (examples/, runnable wirings, graph atlas).
Where New Behavior Goes
New behavior attaches to a documented extension point; a loop change updates this map.
| Goal | Mechanism |
|---|---|
| Add a model provider | register its adapter on ctx.llm |
| Add a model-facing capability | register on ctx.tools; schemas join prompt assembly |
| Add shell execution | implement and register a ctx.bash backend; the local backend spawns through ctx.subprocess |
| Add persistent terminal execution | register a ctx.pty backend plus dsh-tool-pty |
| Add a human command | register on ctx.commands; adapters discover and dispatch without a model turn |
| Add background work | register on ctx.tasks; generic task_* tools collect or stop it |
| Add filesystem access or policy | implement a ctx.fs provider or listen to fs/* policy events |
| Confine spawned processes | use a ctx.sandbox backend; consumers wrap argv before spawning |
| Intercept a request, tool, or turn | use its agent/* or tools/* event; agent/turn-stopping is the stop boundary |
| Add model-facing context | call agent.inject() to queue sourced context for the next admitted request |
| Add UI or editor integration | drive ctx.agents, render from session/event; terminal-only overlays use ctx.tui |
| Add durable session state | extend SessionEventMap; render and replay from the log |
| Add asynchronous session-title generation | register the sole ctx.sessionTitle provider |
| Manage a same-session objective | use ctx.goals; continue through Agent and agent/* |
| Fork a live session | call ctx.sessions.fork(source, boundary?, childSessionId?) |
| Scope a registration to one agent | use its agent.ctx (see Agent Scope) |
The extension cookbook has plugin skeletons and the feature-to-seam map; guides cover packages, tools, LLM adapters, and vendored packages.