Merge origin/master into token-meter-service
This commit is contained in:
Tianyi Cui
@@ -11,6 +11,7 @@ examples/*/*.jsonl
|
||||
examples/*/.sessions/
|
||||
coverage/
|
||||
.doc-typecheck-*/
|
||||
.node-next-types-*/
|
||||
.humanize/
|
||||
tmp/
|
||||
.claude/commands/
|
||||
|
||||
@@ -10,8 +10,9 @@ DeepSeek Harness SDK is a plugin-based agent harness on vendored Cordis: **every
|
||||
|
||||
```
|
||||
vendor/ Vendored Cordis source — manifest + sync procedure in vendor/README.md
|
||||
packages/ Harness packages at packages/<group>/<pkg>/, all named @deepseek-ai/dsh-<pkg>
|
||||
packages/ @deepseek-ai/dsh-<pkg> workspaces at packages/<group>/<pkg>/
|
||||
core/ product API spine: session, system-prompt, tools, agent, agent-loop
|
||||
prompt/ workspace instructions
|
||||
llm/ LLM seam + the DeepSeek adapters (hand-rolled + pi-ai design twin)
|
||||
bash/ bash executor seam + local impl + model-facing bash tools
|
||||
fs/ filesystem seam + local impl + policy gate + read/write/edit tools
|
||||
@@ -34,6 +35,7 @@ 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)
|
||||
scripts/ repo gates and generators
|
||||
website/ VitePress docs site (zh-CN); api/ pages generated from source
|
||||
```
|
||||
|
||||
Package groups: [packages/README.md](packages/README.md).
|
||||
@@ -53,12 +55,17 @@ pnpm run duplication # cross-file TypeScript clone detection
|
||||
pnpm run build # tsc emits lib/types, tsdown bundles runtime
|
||||
pnpm run hygiene # knip + publint + workspace constraints + NodeNext consumer check
|
||||
pnpm run doc-sync # all documentation gates; see the doc-sync script in package.json
|
||||
pnpm run website:build # VitePress build (doubles as the site's dead-link check)
|
||||
pnpm run demo:echo # mock-model REPL, no key needed
|
||||
pnpm run demo:repl # real REPL coding agent (needs DEEPSEEK_API_KEY)
|
||||
pnpm run demo:cordis # self-referential demo: the agent modifies its own runtime (needs key)
|
||||
pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY)
|
||||
```
|
||||
|
||||
### Host sandbox failures
|
||||
|
||||
When required `gh`, `pnpm`, build, test, or generator commands fail because the agent sandbox blocks credentials, network, IPC, file watching, or nested `sandbox-exec`, retry unchanged with the narrowest host escalation before diagnosing authentication or project failure. Require sandbox evidence; never bypass genuine test failures or the product sandbox under test.
|
||||
|
||||
### Run the CI gates locally before marking a PR ready
|
||||
|
||||
Run narrow checks during implementation and this CI-equivalent sequence before marking a PR ready. Fresh worktrees need `pnpm run build` before publint and NodeNext inspect `lib/`:
|
||||
@@ -71,6 +78,7 @@ pnpm run duplication
|
||||
pnpm run test:coverage
|
||||
pnpm run test:snapshot
|
||||
pnpm run doc-sync
|
||||
pnpm run website:build
|
||||
pnpm run verify-module-graph
|
||||
pnpm run build
|
||||
pnpm run hygiene
|
||||
|
||||
+15
-13
@@ -36,7 +36,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service
|
||||
| `ctx.tasks` | [`tasks/`](../packages/tasks/README.md) | background task registry + generic `task_*` control tools |
|
||||
| `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | script-driven multi-agent orchestration |
|
||||
| `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | durable storage for session logs |
|
||||
| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred logical-corpus and exact-event reads |
|
||||
| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred logical-corpus exact reads and relationship traces |
|
||||
|
||||
## Event
|
||||
|
||||
@@ -44,9 +44,9 @@ Events form the service extension API; see the exhaustive [events catalog](cordi
|
||||
|
||||
### Event Domains
|
||||
|
||||
- **Session events** are durable, replayable facts. Turn and step boundaries, user input, assistant output, tool calls, tool results, steering, compaction records, and tool-owned durable facts append to the session log and flow through `session/event`.
|
||||
- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, call-config shaping, result validation, and continuation policy.
|
||||
- **Capability events** belong to the seam that owns the action. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` let policy and adapters attach without importing the loop.
|
||||
- **Session events** are durable, replayable facts: boundaries, messages, tool activity, steering, compaction, and tool-owned records append to the log and flow through `session/event`.
|
||||
- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, request shaping, result validation, and continuation policy.
|
||||
- **Capability events** belong to their owning seam; `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` attach policy and adapters without importing the loop.
|
||||
|
||||
### Interception Semantics
|
||||
|
||||
@@ -54,7 +54,7 @@ Waterfall events behave like around-middleware: a listener delegates by calling
|
||||
|
||||
## Default Loop Lifecycle
|
||||
|
||||
The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins.
|
||||
The shipped loop drains work from prompt through checkpoint. Every pause is a service call or event available to plugins.
|
||||
|
||||
A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points.
|
||||
|
||||
@@ -96,23 +96,23 @@ forever:
|
||||
checkpoint persistence and notify idle/running status
|
||||
```
|
||||
|
||||
The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [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 RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)).
|
||||
|
||||
Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved.
|
||||
|
||||
### Failure Boundaries
|
||||
|
||||
The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends the current turn with an error reason and reports live diagnostics through `agent/error`; it does not kill the driver loop. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the appropriate turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and lets service disposers drain.
|
||||
The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends it with an error reason and reports `agent/error` without killing the driver. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and drains service disposers.
|
||||
|
||||
Every session event is turn-enclosed. Reloading a crashed session preserves the interrupted tail and closes it with a synthetic `interrupted` turn end. A failure after the durable turn has closed reports through `agent/error` only because no safe in-turn position remains. A turn ends with one `TurnEndReason` (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `rejected`, or `interrupted`); per-variant semantics are in [session.md § TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap).
|
||||
Every session event is turn-enclosed. Reloading preserves an interrupted tail and closes it with a synthetic `interrupted` turn end. Failures after durable turn close report only through `agent/error` because no safe in-turn position remains. Each turn has one `TurnEndReason`; [TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap) owns the variants.
|
||||
|
||||
### Agent Handles
|
||||
|
||||
`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins drive `Agent` through `send()`, `steer()`, `inject()`, `cancel()`, and `whenIdle()`. The caller fiber and factory provider structurally co-own programmatic lifecycles; the consumer handle is the only other teardown capability, and all owners await one disposer.
|
||||
`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins drive `Agent` through `send()`, `steer()`, `inject()`, `cancel()`, and `whenIdle()`. The caller fiber and factory provider structurally co-own programmatic lifecycles; the consumer handle is the only other teardown capability. All owners await one disposer.
|
||||
|
||||
### Agent Scope
|
||||
|
||||
Every live agent owns a scoped `agent.ctx`. Its registrations shadow same-named globals, receive only that agent's dispatches, and unwind with the agent; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. The [semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) defines typed resolvers that derive carrier checks from merged `Events` signatures and `scopeTarget`, eliminating the handwritten event table. See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent composition controls are documented [separately](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.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 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).
|
||||
|
||||
## State
|
||||
|
||||
@@ -126,7 +126,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session
|
||||
|
||||
### Model Content
|
||||
|
||||
Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types require coordinated adapter, UI, token-meter, and persistence changes; replay measurement types live in [token-meter.md](core-data-structures/token-meter.md).
|
||||
Messages contain typed blocks (`text`, `reasoning`, `tool-call`, `tool-result`) derived from merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types coordinate adapters, UI bridges, compaction pricing, token metering, and persistence as one repo-wide contract; replay measurement types live in [token-meter.md](core-data-structures/token-meter.md).
|
||||
|
||||
Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAssembler` as the shared chunk-to-block assembler. The loop logs raw chunks while assembling them for dispatch. `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register with `ctx.llm.registerAdapter(models, adapter)`. StreamChunk conventions live in [llm-streaming.md](core-data-structures/llm-streaming.md).
|
||||
|
||||
@@ -136,11 +136,13 @@ Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAs
|
||||
|
||||
A swappable capability usually splits into **interface / implementation / consumer**: the interface owns its `ctx` key and events, an implementation registers a backend, and a consumer exposes model behavior through tools or prompts. Bash is the reference; the [capability graph](capability-seams.md) shows every family.
|
||||
|
||||
Some seams bend the template deliberately. LLM keeps interface and consumer vocabulary together because adapters are the implementations. Filesystem adds policy gates around provider primitives. Web is one service with search and fetch provider registries, so provider swaps do not rename model tools. Skills and subagents use named provider registries; local skills scan project/user roots, and other providers can add embedded or remote catalogs without registry/tool changes. Subagents spawn fresh, fork from the parent's completed-turn prefix, or use ACP children ([subagent.md](core-data-structures/subagent.md)).
|
||||
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.
|
||||
|
||||
### Bundles And Apps
|
||||
|
||||
`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` for terminal REPL, and `dsh-acp-demo` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
|
||||
`dsh-agent-spine-demo` bundles the default spine ([README](../packages/examples/agent-spine-demo/README.md)). `dsh-stdio-demo` adds a terminal front door; `dsh-acp-demo` adds stdout-pure ACP over JSON-RPC ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` boots external `cordis.yml`; the Python SDK supplies its default only without an explicit config channel and drives `dsh-jsonrpc` over line-delimited JSON-RPC ([Python SDK](../python/README.md)). Deployments remain thin leaves with swappable backends and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
|
||||
|
||||
### Where New Behavior Goes
|
||||
|
||||
|
||||
@@ -26,8 +26,11 @@ flowchart LR
|
||||
svc_sessionPersistence["ctx.sessionPersistence<br/>Durable session persistence seam"]
|
||||
pkg_session_persistence_jsonl["session-persistence-jsonl"]
|
||||
pkg_session_persistence_sqlite["session-persistence-sqlite"]
|
||||
pkg_tool_bash["tool-bash"]
|
||||
pkg_hooks_claude["hooks-claude"]
|
||||
pkg_hooks_codex["hooks-codex"]
|
||||
pkg_acp["acp"]
|
||||
svc_sessionQuery["ctx.sessionQuery<br/>Exact session-history reads"]
|
||||
svc_sessionQuery["ctx.sessionQuery<br/>Exact session-history reads and traces"]
|
||||
pkg_system_prompt["system-prompt"]
|
||||
svc_systemPrompt["ctx.systemPrompt<br/>System prompt assembly registry"]
|
||||
pkg_tools["tools"]
|
||||
@@ -35,7 +38,6 @@ flowchart LR
|
||||
pkg_tool_web["tool-web"]
|
||||
svc_tools["ctx.tools<br/>Tool registry and guarded execution pipeline"]
|
||||
pkg_tool_ask_user["tool-ask-user"]
|
||||
pkg_tool_bash["tool-bash"]
|
||||
pkg_tool_cordis["tool-cordis"]
|
||||
pkg_tool_skill["tool-skill"]
|
||||
pkg_tool_subagent["tool-subagent"]
|
||||
@@ -53,8 +55,7 @@ flowchart LR
|
||||
svc_bash["ctx.bash<br/>Bash executor seam"]
|
||||
pkg_bash_local["bash-local"]
|
||||
pkg_bash_sandbox["bash-sandbox"]
|
||||
pkg_hooks_claude["hooks-claude"]
|
||||
pkg_hooks_codex["hooks-codex"]
|
||||
svc_bashEnv["ctx.bashEnv<br/>Managed bash environment registry"]
|
||||
pkg_sandbox["sandbox"]
|
||||
svc_sandbox["ctx.sandbox<br/>Process-sandbox seam"]
|
||||
pkg_sandbox_local["sandbox-local"]
|
||||
@@ -86,6 +87,10 @@ flowchart LR
|
||||
pkg_web_search_perplexity["web-search-perplexity"]
|
||||
pkg_web_search_deepseek["web-search-deepseek"]
|
||||
pkg_web_fetch_local["web-fetch-local"]
|
||||
pkg_spill["spill"]
|
||||
svc_spillStore["ctx.spillStore<br/>Spill storage seam"]
|
||||
pkg_spill_local["spill-local"]
|
||||
pkg_spill_policy["spill-policy"]
|
||||
pkg_workflow["workflow"]
|
||||
svc_workflows["ctx.workflows<br/>Workflow script engine"]
|
||||
pkg_workflow_workerthread["workflow-workerthread"]
|
||||
@@ -118,6 +123,8 @@ flowchart LR
|
||||
pkg_session_query --> svc_sessionQuery
|
||||
pkg_skill --> svc_skills
|
||||
pkg_skill_local --> svc_skills
|
||||
pkg_spill --> svc_spillStore
|
||||
pkg_spill_local --> svc_spillStore
|
||||
pkg_stdio_demo --> svc_userInteraction
|
||||
pkg_subagent --> svc_subagents
|
||||
pkg_subagent_acp --> svc_subagents
|
||||
@@ -127,6 +134,7 @@ flowchart LR
|
||||
pkg_system_prompt --> svc_systemPrompt
|
||||
pkg_tasks --> svc_tasks
|
||||
pkg_token_meter --> svc_tokenMeter
|
||||
pkg_tool_bash --> svc_bashEnv
|
||||
pkg_tools --> svc_tools
|
||||
pkg_user_interaction --> svc_userInteraction
|
||||
pkg_web --> svc_web
|
||||
@@ -156,7 +164,10 @@ flowchart LR
|
||||
svc_sandbox --> pkg_bash_sandbox
|
||||
svc_sessionPersistence --> pkg_acp
|
||||
svc_sessionPersistence --> pkg_agent_loop
|
||||
svc_sessionPersistence --> pkg_hooks_claude
|
||||
svc_sessionPersistence --> pkg_hooks_codex
|
||||
svc_sessionPersistence --> pkg_session_query
|
||||
svc_sessionPersistence --> pkg_tool_bash
|
||||
svc_sessions --> pkg_agent
|
||||
svc_sessions --> pkg_agent_loop
|
||||
svc_sessions --> pkg_invariants
|
||||
@@ -164,6 +175,7 @@ flowchart LR
|
||||
svc_sessions --> pkg_session_query
|
||||
svc_sessions --> pkg_subagent_inprocess
|
||||
svc_skills --> pkg_tool_skill
|
||||
svc_spillStore --> pkg_spill_policy
|
||||
svc_subagents --> pkg_tool_subagent
|
||||
svc_systemPrompt --> pkg_agent_loop
|
||||
svc_systemPrompt --> pkg_tool_fs
|
||||
@@ -196,8 +208,8 @@ flowchart LR
|
||||
| `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. |
|
||||
| `ctx.tokenMeter` | `core` | [`token-meter`](../packages/llm/token-meter) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements. |
|
||||
| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. |
|
||||
| `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
|
||||
| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. |
|
||||
| `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
|
||||
| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads and relationship traces. |
|
||||
| `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. |
|
||||
| `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. |
|
||||
| `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. |
|
||||
@@ -205,6 +217,7 @@ flowchart LR
|
||||
| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. |
|
||||
| `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. |
|
||||
| `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. |
|
||||
| `ctx.bashEnv` | `core` | [`tool-bash`](../packages/bash/tool-bash) | - | - | - | Plugins declare effect-scoped DSH_* facts; tool-bash collects one trusted snapshot per execution and the executor rebuilds the namespace. |
|
||||
| `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. |
|
||||
| `ctx.approval` | `seam` | `approval` | [`acp`](../packages/ui/acp) | [`tools`](../packages/core/tools), [`tool-bash`](../packages/bash/tool-bash) | - | One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`. |
|
||||
| `ctx.permission` | `core` | [`permission`](../packages/ui/permission) | - | [`acp`](../packages/ui/acp) | - | User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events. |
|
||||
@@ -214,6 +227,7 @@ flowchart LR
|
||||
| `ctx.subagents` | `seam` | [`subagent`](../packages/subagent/subagent) | [`subagent-spawn`](../packages/subagent/subagent-spawn), [`subagent-fork`](../packages/subagent/subagent-fork), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-mock`](../packages/support/subagent-mock) | [`tool-subagent`](../packages/subagent/tool-subagent) | - | Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name. |
|
||||
| `ctx.tasks` | `core` | [`tasks`](../packages/tasks/tasks) | - | [`tool-bash`](../packages/bash/tool-bash), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-tasks`](../packages/tasks/tool-tasks) | - | Producers (tool-bash background commands, tool-subagent background delegations) register running work; tool-tasks is the model-facing control surface that reads, lists, and kills it. |
|
||||
| `ctx.web` | `seam` | [`web`](../packages/web/web) | [`web-search-exa`](../packages/web/web-search-exa), [`web-search-perplexity`](../packages/web/web-search-perplexity), [`web-search-deepseek`](../packages/web/web-search-deepseek), [`web-fetch-local`](../packages/web/web-fetch-local) | [`tool-web`](../packages/web/tool-web) | - | Search and fetch providers register into one ctx.web seam; tool-web owns the stable model-facing names. |
|
||||
| `ctx.spillStore` | `seam` | [`spill`](../packages/spill/spill) | [`spill-local`](../packages/spill/spill-local) | [`spill-policy`](../packages/spill/spill-policy) | - | The backend saves oversized tool text and returns a model-facing locator plus retrieval hint; spill-policy is the tools/post-execute consumer that decides when to spill. |
|
||||
| `ctx.workflows` | `seam` | [`workflow`](../packages/workflow/workflow) | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | [`tool-workflow`](../packages/workflow/tool-workflow) | - | One engine per context (bash shape, no named-provider registry); the worker-thread engine fans agent() calls out through ctx.subagents. |
|
||||
|
||||
Maintenance mode: hybrid: services are discovered from Cordis declarations; interface/implementation/consumer roles are classified in `scripts/gen-doc-graphs.ts` with a completeness guard.
|
||||
+121
-26
@@ -48,8 +48,12 @@ export interface Config {
|
||||
toolOrder?: string[]
|
||||
/** Tool-registry config — its presentation `mode` (forwarded through agent-spine-demo; see dsh-tools). */
|
||||
tools?: ToolsConfig
|
||||
/** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */
|
||||
dshHome?: string
|
||||
/** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
|
||||
persistenceRoot?: string
|
||||
/** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */
|
||||
workspaceContext: agentCore.Config['workspaceContext']
|
||||
/** Skill registry, local-provider, and model-facing consumer config forwarded to agent-spine-demo. */
|
||||
skills?: agentCore.SkillConfig
|
||||
/** Model-facing bash tool config forwarded through agent-core. */
|
||||
@@ -61,7 +65,7 @@ export interface Config {
|
||||
|
||||
Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
|
||||
|
||||
Source: [`packages/examples/acp-demo/src/index.ts:31`](../packages/examples/acp-demo/src/index.ts)
|
||||
Source: [`packages/examples/acp-demo/src/index.ts:32`](../packages/examples/acp-demo/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-agent-loop`
|
||||
|
||||
@@ -95,14 +99,14 @@ Source: [`packages/core/agent-loop/src/index.ts:322`](../packages/core/agent-loo
|
||||
* bridge, simply omits it), `persona` and `toolOrder` to the system-prompt
|
||||
* plugin (the deployment's persona section and the explicit model-facing tool
|
||||
* order), the `tools` object to the tool registry (its presentation `mode`),
|
||||
* and `toolBash`/`toolTasks` to the two model-facing tool plugins this bundle
|
||||
* owns. Producer opt-in stays producer-local: `toolBash` configures bash only;
|
||||
* future background-capable tools remain independently composed plugins.
|
||||
* Every field is optional INPUT here because each owner's schema
|
||||
* supplies the default (`[]` / `''` / absent — lexicographic / `native`); the
|
||||
* schema is the INTERSECTION of the owners' own schemas (the registry's
|
||||
* nested under its `tools` key), so validation and defaulting can never
|
||||
* drift from them.
|
||||
* `dshHome` to bash environment and local skill discovery, `skills` to the
|
||||
* skill registry/local provider/tool consumer, `workspaceContext` to the
|
||||
* workspace-context loader, and `toolBash`/`toolTasks` to the model-facing tool
|
||||
* plugins this bundle owns. Owner schemas supply defaults for optional input;
|
||||
* workspace context instead requires an explicit byte budget or `false` because
|
||||
* it changes model-visible input. Producer opt-in stays producer-local:
|
||||
* `toolBash` configures bash only; independently composed producers keep their
|
||||
* own config.
|
||||
*/
|
||||
export interface Config {
|
||||
/** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
|
||||
@@ -113,6 +117,10 @@ export interface Config {
|
||||
toolOrder?: SystemPromptConfig['toolOrder']
|
||||
/** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */
|
||||
tools?: ToolsConfig
|
||||
/** DeepSeek Harness home directory shared by shell context and local skill discovery. */
|
||||
dshHome?: string
|
||||
/** Workspace-context loader controls with an explicit byte budget; set `false` for hermetic prompts. */
|
||||
workspaceContext: workspaceContext.Config | false
|
||||
/** Skill registry, local provider, and model-facing consumer config. */
|
||||
skills?: SkillConfig
|
||||
/** Model-facing bash tool config, including this producer's background opt-in. */
|
||||
@@ -132,9 +140,9 @@ export interface SkillConfig {
|
||||
}
|
||||
```
|
||||
|
||||
Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts)
|
||||
Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts)
|
||||
|
||||
Source: [`packages/examples/agent-spine-demo/src/index.ts:55`](../packages/examples/agent-spine-demo/src/index.ts)
|
||||
Source: [`packages/examples/agent-spine-demo/src/index.ts:57`](../packages/examples/agent-spine-demo/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-bash-local`
|
||||
|
||||
@@ -253,7 +261,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/fs/fs-local/src/index.ts:35`](../packages/fs/fs-local/src/index.ts)
|
||||
Source: [`packages/fs/fs-local/src/index.ts:38`](../packages/fs/fs-local/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-hooks-claude`
|
||||
|
||||
@@ -289,7 +297,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/hooks/hooks-claude/src/index.ts:43`](../packages/hooks/hooks-claude/src/index.ts)
|
||||
Source: [`packages/hooks/hooks-claude/src/index.ts:44`](../packages/hooks/hooks-claude/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-hooks-codex`
|
||||
|
||||
@@ -314,7 +322,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/hooks/hooks-codex/src/index.ts:41`](../packages/hooks/hooks-codex/src/index.ts)
|
||||
Source: [`packages/hooks/hooks-codex/src/index.ts:42`](../packages/hooks/hooks-codex/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-jsonrpc`
|
||||
|
||||
@@ -575,7 +583,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:23`](../packages/session-persistence/session-persistence-jsonl/src/index.ts)
|
||||
Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:24`](../packages/session-persistence/session-persistence-jsonl/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-session-persistence-sqlite`
|
||||
|
||||
@@ -610,14 +618,14 @@ export interface Config {
|
||||
export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
|
||||
```
|
||||
|
||||
Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:38`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
|
||||
Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:39`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-session-query`
|
||||
|
||||
Requires: `sessions`
|
||||
|
||||
```ts config-catalog
|
||||
/** Configuration for exact session-query reads. */
|
||||
/** Configuration for exact session-query reads and traces. */
|
||||
export interface Config {
|
||||
/** Maximum accepted raw read context on either side. Defaults to 50. */
|
||||
readWindowMax?: number
|
||||
@@ -654,7 +662,41 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-local/src/index.ts)
|
||||
Source: [`packages/skill/skill-local/src/index.ts:40`](../packages/skill/skill-local/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-spill-local`
|
||||
|
||||
```ts config-catalog
|
||||
/** Plugin config (all optional — `static Config` supplies the defaults). */
|
||||
export interface Config {
|
||||
/**
|
||||
* Root directory for spill files. Omitted uses a lazily-created private
|
||||
* (0700) per-process directory under the OS temp dir — the safe default for
|
||||
* a local deployment. Set it to keep spill files under a known location.
|
||||
*/
|
||||
root?: string
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/spill/spill-local/src/index.ts:22`](../packages/spill/spill-local/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-spill-policy`
|
||||
|
||||
Requires: `tools`
|
||||
|
||||
```ts config-catalog
|
||||
/** Plugin config. */
|
||||
export interface Config {
|
||||
/**
|
||||
* The model-facing context cap for a plain-text tool result, in UTF-8 bytes.
|
||||
* Omitted disables the policy entirely (no-op). When set, a result larger than
|
||||
* this is spilled and replaced with a preview derived from this same budget.
|
||||
*/
|
||||
maxInlineBytes?: number
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/spill/spill-policy/src/index.ts:45`](../packages/spill/spill-policy/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-stdio`
|
||||
|
||||
@@ -694,6 +736,8 @@ export interface Config {
|
||||
toolOrder?: string[]
|
||||
/** Tool-registry config — its presentation `mode` (forwarded through agent-spine-demo; see dsh-tools). */
|
||||
tools?: ToolsConfig
|
||||
/** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */
|
||||
dshHome?: string
|
||||
/** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
|
||||
persistenceRoot?: string
|
||||
/** stdin-chat banner printed once on start. Defaults to `'ready.'`. */
|
||||
@@ -710,12 +754,14 @@ export interface Config {
|
||||
* (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`).
|
||||
*/
|
||||
resumeSessionId?: string
|
||||
/** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */
|
||||
workspaceContext: agentCore.Config['workspaceContext']
|
||||
}
|
||||
```
|
||||
|
||||
Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
|
||||
|
||||
Source: [`packages/examples/stdio-demo/src/index.ts:36`](../packages/examples/stdio-demo/src/index.ts)
|
||||
Source: [`packages/examples/stdio-demo/src/index.ts:37`](../packages/examples/stdio-demo/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-subagent-acp`
|
||||
|
||||
@@ -850,19 +896,19 @@ Source: [`packages/core/system-prompt/src/index.ts:143`](../packages/core/system
|
||||
|
||||
## `@deepseek-ai/dsh-time-context`
|
||||
|
||||
Requires: `systemPrompt`
|
||||
Requires: `agents`
|
||||
|
||||
```ts config-catalog
|
||||
/** Request-time clock formatting and refresh policy. Invalid values fail plugin load. */
|
||||
/** Request-preparation clock formatting and append scheduling. Invalid values fail plugin load. */
|
||||
export interface Config {
|
||||
/** IANA time zone used for the rendered timestamp. Omit to resolve the Node process's system zone at plugin load. */
|
||||
timeZone?: string
|
||||
/** Maximum age of a reading within one turn, in milliseconds (default 60,000; `0` refreshes every step). */
|
||||
/** Minimum milliseconds between durable injections in one session. Omit or set to 0 to inject on every eligible pre-step attempt. */
|
||||
refreshIntervalMs?: number
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/context/time-context/src/index.ts:22`](../packages/context/time-context/src/index.ts)
|
||||
Source: [`packages/context/time-context/src/index.ts:20`](../packages/context/time-context/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-token-meter`
|
||||
|
||||
@@ -881,14 +927,16 @@ Source: [`packages/llm/token-meter/src/types.ts:10`](../packages/llm/token-meter
|
||||
Requires: `tools` · `bash` · `systemPrompt`
|
||||
|
||||
```ts config-catalog
|
||||
/** Configures whether the model may background commands. */
|
||||
/** Configuration for the bash tool and its managed child environment. */
|
||||
export interface Config {
|
||||
/** Expose `run_in_background` (default true); disabled calls are also rejected. */
|
||||
enableRunInBackground?: boolean
|
||||
/** DeepSeek Harness home directory exposed as `DSH_HOME`; defaults to `$DSH_HOME` or `~/.dsh`. */
|
||||
dshHome?: string
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/bash/tool-bash/src/index.ts:30`](../packages/bash/tool-bash/src/index.ts)
|
||||
Source: [`packages/bash/tool-bash/src/index.ts:39`](../packages/bash/tool-bash/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-cordis`
|
||||
|
||||
@@ -928,6 +976,28 @@ export interface Config {
|
||||
|
||||
Source: [`packages/fs/tool-fs/src/index.ts:22`](../packages/fs/tool-fs/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-fs-search`
|
||||
|
||||
Requires: `tools` · `systemPrompt` · `bash`
|
||||
|
||||
```ts config-catalog
|
||||
/** Plugin config (all optional — `Config` supplies the defaults). */
|
||||
export interface Config {
|
||||
/** Max paths one `glob` call retains inline; later paths go to the formatted spill file. */
|
||||
globMaxResults?: number
|
||||
/** Max flat matches one `grep` call retains inline; later matches go to the formatted spill file. */
|
||||
grepMaxMatches?: number
|
||||
/** Max bytes retained for one matched-line preview (the cut preserves UTF-8 boundaries). */
|
||||
grepMaxLineBytes?: number
|
||||
/** Max complete raw `rg` stdout bytes a search will parse; larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. */
|
||||
rawOutputMaxBytes?: number
|
||||
/** Cooperative tool-call timeout budget (ms) on both tools, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`. */
|
||||
timeoutMs?: number
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/fs/tool-fs-search/src/index.ts:59`](../packages/fs/tool-fs-search/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-skill`
|
||||
|
||||
Requires: `tools` · `skills`
|
||||
@@ -1068,7 +1138,7 @@ export interface Config {
|
||||
export type ToolPresentationMode = 'native' | 'code' | 'both'
|
||||
```
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:307`](../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:322`](../packages/core/tools/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-user-approval`
|
||||
|
||||
@@ -1240,6 +1310,26 @@ export interface Config {
|
||||
|
||||
Source: [`packages/workflow/workflow-workerthread/src/index.ts:32`](../packages/workflow/workflow-workerthread/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-workspace-context`
|
||||
|
||||
```ts config-catalog
|
||||
/** User-facing workspace instruction loader configuration. */
|
||||
export interface Config {
|
||||
/** Harness home containing the fixed user-global `AGENTS.md`; defaults to `$DSH_HOME` or `~/.dsh`. */
|
||||
dshHome?: string
|
||||
/** Directory entries that identify the project root while walking upward from the session cwd. */
|
||||
projectRootMarkers?: string[]
|
||||
/** UTF-8 byte cap for one rendered baseline or dynamic batch; non-positive or non-finite disables loading. */
|
||||
maxBytes: number
|
||||
/** Maximum UTF-8 bytes read from one instruction file; larger files are ignored. */
|
||||
maxSourceBytes?: number
|
||||
/** Ordered same-directory project candidates; the first existing regular file wins in each scope. */
|
||||
instructionFileCandidates?: string[]
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/context/workspace-context/src/config.ts:16`](../packages/context/workspace-context/src/config.ts)
|
||||
|
||||
## Loadable plugins with no config
|
||||
|
||||
These load from a `cordis.yml` entry with no `config:` block; they declare no config surface.
|
||||
@@ -1266,6 +1356,7 @@ Abstract service classes — a deployment loads a concrete implementation packag
|
||||
- `@deepseek-ai/dsh-fs` — abstract `FileSystem` ([`packages/fs/fs/src/index.ts`](../packages/fs/fs/src/index.ts))
|
||||
- `@deepseek-ai/dsh-sandbox` — abstract `SandboxProvider` ([`packages/sandbox/sandbox/src/index.ts`](../packages/sandbox/sandbox/src/index.ts))
|
||||
- `@deepseek-ai/dsh-session-persistence` — abstract `SessionPersistence` ([`packages/session-persistence/session-persistence/src/index.ts`](../packages/session-persistence/session-persistence/src/index.ts))
|
||||
- `@deepseek-ai/dsh-spill` — abstract `SpillStore` ([`packages/spill/spill/src/index.ts`](../packages/spill/spill/src/index.ts))
|
||||
- `@deepseek-ai/dsh-workflow` — abstract `WorkflowService` ([`packages/workflow/workflow/src/index.ts`](../packages/workflow/workflow/src/index.ts))
|
||||
|
||||
## Library packages (no plugin entry)
|
||||
@@ -1274,12 +1365,16 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them.
|
||||
|
||||
- `@deepseek-ai/create-sdk` ([`packages/sdk/create-sdk/src/index.ts`](../packages/sdk/create-sdk/src/index.ts))
|
||||
- `@deepseek-ai/dsh-acp-snapshot` ([`packages/support/acp-snapshot/src/index.ts`](../packages/support/acp-snapshot/src/index.ts))
|
||||
- `@deepseek-ai/dsh-agent-loop-testkit` ([`packages/support/agent-loop-testkit/src/index.ts`](../packages/support/agent-loop-testkit/src/index.ts))
|
||||
- `@deepseek-ai/dsh-app-boot` ([`packages/ui/app-boot/src/index.ts`](../packages/ui/app-boot/src/index.ts))
|
||||
- `@deepseek-ai/dsh-brand` ([`packages/util/brand/src/index.ts`](../packages/util/brand/src/index.ts))
|
||||
- `@deepseek-ai/dsh-helper` ([`packages/sdk/helper/src/index.ts`](../packages/sdk/helper/src/index.ts))
|
||||
- `@deepseek-ai/dsh-home` ([`packages/util/home/src/index.ts`](../packages/util/home/src/index.ts))
|
||||
- `@deepseek-ai/dsh-hook-protocol` ([`packages/hooks/hook-protocol/src/index.ts`](../packages/hooks/hook-protocol/src/index.ts))
|
||||
- `@deepseek-ai/dsh-jsonrpc-demo` ([`packages/examples/jsonrpc-demo/src/index.ts`](../packages/examples/jsonrpc-demo/src/index.ts))
|
||||
- `@deepseek-ai/dsh-loader-smoke` ([`packages/support/loader-smoke/src/index.ts`](../packages/support/loader-smoke/src/index.ts))
|
||||
- `@deepseek-ai/dsh-paths` ([`packages/util/paths/src/index.ts`](../packages/util/paths/src/index.ts))
|
||||
- `@deepseek-ai/dsh-retention` ([`packages/util/retention/src/index.ts`](../packages/util/retention/src/index.ts))
|
||||
- `@deepseek-ai/dsh-scope` ([`packages/core/scope/src/index.ts`](../packages/core/scope/src/index.ts))
|
||||
- `@deepseek-ai/dsh-scripts` ([`packages/sdk/scripts/src/index.ts`](../packages/sdk/scripts/src/index.ts))
|
||||
- `@deepseek-ai/dsh-subagent-inprocess` ([`packages/subagent/subagent-inprocess/src/index.ts`](../packages/subagent/subagent-inprocess/src/index.ts))
|
||||
|
||||
@@ -23,7 +23,7 @@ A fully configured agent and live session were published. Setup is composition-o
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:139`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:151`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/disposed` — emit
|
||||
|
||||
@@ -35,7 +35,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:148`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:160`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/error` — emit
|
||||
|
||||
@@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:283`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:295`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/pre-step` — serial
|
||||
|
||||
@@ -59,7 +59,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:214`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/prompt-submit` — waterfall
|
||||
|
||||
@@ -71,7 +71,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/queued` — emit
|
||||
|
||||
@@ -83,7 +83,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:167`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:179`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/request` — waterfall
|
||||
|
||||
@@ -95,7 +95,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:236`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/session-prefix` — waterfall
|
||||
|
||||
@@ -107,7 +107,7 @@ Compose request-only messages placed before derived history. The frozen result i
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:251`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/session-start` — emit
|
||||
|
||||
@@ -119,7 +119,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:180`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:192`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/status` — emit
|
||||
|
||||
@@ -131,7 +131,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:157`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:169`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/step-result` — waterfall
|
||||
|
||||
@@ -143,7 +143,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:262`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/turn-continuation` — waterfall
|
||||
|
||||
@@ -155,7 +155,7 @@ Override whether the turn continues. The default continues after tool calls or s
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:260`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:272`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
### `agent/turn-stop` — serial
|
||||
|
||||
@@ -167,7 +167,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts:270`](../../packages/core/agent/src/types.ts)
|
||||
Source: [`packages/core/agent/src/types.ts:282`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
## `approval/*`
|
||||
|
||||
@@ -195,7 +195,7 @@ Single-slot decision for the next FileSystem.editText. Calling `next()` yields a
|
||||
|
||||
Types: [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md)
|
||||
|
||||
Source: [`packages/fs/fs/src/index.ts:59`](../../packages/fs/fs/src/index.ts)
|
||||
Source: [`packages/fs/fs/src/index.ts:61`](../../packages/fs/fs/src/index.ts)
|
||||
|
||||
### `fs/observed` — emit
|
||||
|
||||
@@ -207,7 +207,7 @@ Record a successful observation. Listeners must be synchronous recorders: throws
|
||||
|
||||
Types: [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md)
|
||||
|
||||
Source: [`packages/fs/fs/src/index.ts:68`](../../packages/fs/fs/src/index.ts)
|
||||
Source: [`packages/fs/fs/src/index.ts:70`](../../packages/fs/fs/src/index.ts)
|
||||
|
||||
### `fs/write-intent` — waterfall
|
||||
|
||||
@@ -219,7 +219,7 @@ Single-slot decision for the next FileSystem.writeText. Calling `next()` yields
|
||||
|
||||
Types: [FsTarget](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md)
|
||||
|
||||
Source: [`packages/fs/fs/src/index.ts:51`](../../packages/fs/fs/src/index.ts)
|
||||
Source: [`packages/fs/fs/src/index.ts:53`](../../packages/fs/fs/src/index.ts)
|
||||
|
||||
## `llm/*`
|
||||
|
||||
@@ -469,14 +469,14 @@ Source: [`packages/workflow/workflow/src/index.ts:45`](../../packages/workflow/w
|
||||
|
||||
The framework events every plugin also sees, beyond the harness vocabulary above. This is pinned vendor source ([vendoring policy](../../vendor/README.md)); it is summarized here so the page is a complete picture of the event bus, without elevating framework internals to the harness tier's prominence.
|
||||
|
||||
- `internal/plugin` — A plugin fiber was created. ([`vendor/cordis/src/events.ts:197`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/status` — A fiber changed lifecycle state. ([`vendor/cordis/src/events.ts:198`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/service` — Interception hook for a service binding (no core producer). ([`vendor/cordis/src/events.ts:199`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/update` — Waterfall: a fiber config update is being applied. ([`vendor/cordis/src/events.ts:200`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/get` — Waterfall: a service is being read from the store. ([`vendor/cordis/src/events.ts:201`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/set` — Waterfall: a service is being written to the store. ([`vendor/cordis/src/events.ts:202`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/listener` — A listener was registered. ([`vendor/cordis/src/events.ts:203`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/dispatch` — An event is being dispatched to listeners. ([`vendor/cordis/src/events.ts:204`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/plugin` — A plugin fiber was created. ([`vendor/cordis/src/events.ts:328`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/status` — A fiber changed lifecycle state. ([`vendor/cordis/src/events.ts:330`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/service` — Interception hook for a service binding (no core producer). ([`vendor/cordis/src/events.ts:332`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/update` — Waterfall: a fiber config update is being applied. ([`vendor/cordis/src/events.ts:334`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/get` — Waterfall: a service is being read from the store. ([`vendor/cordis/src/events.ts:336`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/set` — Waterfall: a service is being written to the store. ([`vendor/cordis/src/events.ts:338`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/listener` — A listener was registered. ([`vendor/cordis/src/events.ts:340`](../../vendor/cordis/src/events.ts))
|
||||
- `internal/dispatch` — An event is being dispatched to listeners. ([`vendor/cordis/src/events.ts:342`](../../vendor/cordis/src/events.ts))
|
||||
- `hmr/change` — A watched source file changed on disk. ([`vendor/hmr/src/index.ts:20`](../../vendor/hmr/src/index.ts))
|
||||
- `hmr/reload` — Plugins are being reloaded after a change. ([`vendor/hmr/src/index.ts:21`](../../vendor/hmr/src/index.ts))
|
||||
- `exit` — The process is exiting on a signal. ([`vendor/loader/src/index.ts:23`](../../vendor/loader/src/index.ts))
|
||||
|
||||
@@ -71,7 +71,21 @@ abstract start(spec: BashExecSpec): BashProcess
|
||||
|
||||
Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md)
|
||||
|
||||
Source: [`packages/bash/bash/src/index.ts:46`](../../packages/bash/bash/src/index.ts)
|
||||
Source: [`packages/bash/bash/src/index.ts:49`](../../packages/bash/bash/src/index.ts)
|
||||
|
||||
## `ctx.bashEnv` — `BashEnvRegistry`
|
||||
|
||||
Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. The namespace is rebuilt for every model bash call: ambient `DSH_*` values are discarded by the executor, then the registry's current snapshot is injected. Built-in shell facts remain owned by the registry itself while plugins can register additional, enumerable facts with effect-scoped disposal.
|
||||
|
||||
```ts cordis-catalog
|
||||
register(contributor: BashEnvContributor): () => void
|
||||
collect(execution: ToolExecution): DshEnvironment
|
||||
list(): BashEnvVariableInfo[]
|
||||
```
|
||||
|
||||
Types: [ToolExecution](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/bash/tool-bash/src/index.ts:102`](../../packages/bash/tool-bash/src/index.ts)
|
||||
|
||||
## `ctx.codeRuntime` — `CodeRuntime` (abstract seam)
|
||||
|
||||
@@ -103,8 +117,9 @@ Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/comp
|
||||
Abstract filesystem provider. Targets must preserve identity across aliases; reads expose regular UTF-8 text or typed errors, listings are stable and content-free, and mutations are atomic. Optional guards add stale protection without changing the unguarded provider contract.
|
||||
|
||||
```ts cordis-catalog
|
||||
abstract resolve(path: string, opts?: { cwd?: string }): Promise<FsTarget>
|
||||
abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget>
|
||||
abstract stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined>
|
||||
abstract lstat(path: string, opts?: { cwd?: string }, signal?: AbortSignal): Promise<FsPathInfo | undefined>
|
||||
abstract readText(target: FsTarget, signal?: AbortSignal): Promise<string>
|
||||
abstract streamText(target: FsTarget, signal?: AbortSignal): Promise<AsyncIterable<string>>
|
||||
abstract listDir(target: FsTarget, signal?: AbortSignal): Promise<FsDirEntry[]>
|
||||
@@ -114,7 +129,7 @@ abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: F
|
||||
|
||||
Types: [FsEditOutcome](../core-data-structures/filesystem.md) · [FsEditRequest](../core-data-structures/filesystem.md) · [FsInfo](../core-data-structures/filesystem.md) · [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md) · [FsWriteOutcome](../core-data-structures/filesystem.md)
|
||||
|
||||
Source: [`packages/fs/fs/src/index.ts:78`](../../packages/fs/fs/src/index.ts)
|
||||
Source: [`packages/fs/fs/src/index.ts:80`](../../packages/fs/fs/src/index.ts)
|
||||
|
||||
## `ctx.llm` — `LlmService`
|
||||
|
||||
@@ -162,6 +177,7 @@ Source: [`packages/sandbox/sandbox/src/index.ts:111`](../../packages/sandbox/san
|
||||
Durable append-only session storage. Implementations preserve contiguous, losslessly JSON-serializable events; append resolves only after durability, and load balances a complete interrupted tail without rewriting committed events.
|
||||
|
||||
```ts cordis-catalog
|
||||
abstract locate(meta: SessionHeader): SessionLocation | undefined
|
||||
abstract create(meta: SessionHeader): Promise<void>
|
||||
abstract append(id: SessionId, events: readonly SessionEvent[]): Promise<void>
|
||||
abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>
|
||||
@@ -170,19 +186,21 @@ abstract list(): Promise<SessionHeader[]>
|
||||
|
||||
Types: [SessionEvent](../core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/session-persistence/session-persistence/src/index.ts:30`](../../packages/session-persistence/session-persistence/src/index.ts)
|
||||
Source: [`packages/session-persistence/session-persistence/src/index.ts:42`](../../packages/session-persistence/session-persistence/src/index.ts)
|
||||
|
||||
## `ctx.sessionQuery` — `SessionQueryService`
|
||||
|
||||
Live-preferred logical-corpus and exact-event read service.
|
||||
Live-preferred logical-corpus exact-read and relationship-tracing service.
|
||||
|
||||
```ts cordis-catalog
|
||||
listSessions(): Promise<SessionRecord[]>
|
||||
async listEvents(sessionId: SessionId): Promise<SessionEventRecord[]>
|
||||
async traceSession(sessionId: SessionId): Promise<SessionLineageTrace>
|
||||
async traceEvent(request: SessionEventTraceRequest): Promise<SessionEventTrace>
|
||||
async readEvent(request: SessionEventReadRequest): Promise<SessionEventWindow>
|
||||
```
|
||||
|
||||
Source: [`packages/session-query/session-query/src/index.ts:35`](../../packages/session-query/session-query/src/index.ts)
|
||||
Source: [`packages/session-query/session-query/src/index.ts:38`](../../packages/session-query/session-query/src/index.ts)
|
||||
|
||||
## `ctx.sessions` — `SessionStore`
|
||||
|
||||
@@ -201,7 +219,7 @@ list(): Session[]
|
||||
fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session
|
||||
```
|
||||
|
||||
Source: [`packages/core/session/src/index.ts:563`](../../packages/core/session/src/index.ts)
|
||||
Source: [`packages/core/session/src/index.ts:539`](../../packages/core/session/src/index.ts)
|
||||
|
||||
## `ctx.skills` — `SkillService`
|
||||
|
||||
@@ -216,6 +234,22 @@ async get(name: string, options: SkillLookupOptions = {}): Promise<SkillDefiniti
|
||||
|
||||
Source: [`packages/skill/skill/src/index.ts:141`](../../packages/skill/skill/src/index.ts)
|
||||
|
||||
## `ctx.spillStore` — `SpillStore` (abstract seam)
|
||||
|
||||
Abstract spill storage service. Subclass, implement saveText, and load the subclass as a plugin — it registers as `ctx.spillStore` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior).
|
||||
|
||||
Semantics every implementation must honor:
|
||||
|
||||
- saveText persists the FULL `content` verbatim and returns an opaque locator, exact byte length, and model-facing retrieval guidance.
|
||||
- Storage is scoped by the request's SaveTextSpill.owner session; the backend chooses a private (not world-readable) location and a collision-free name derived from — never equal to — the caller's `suggestedName`.
|
||||
- `saveText` REJECTS on a real storage failure (permissions, ENOSPC, backend unavailable); the caller decides how to degrade (the spill policy treats a rejection as best-effort and keeps the inline result).
|
||||
|
||||
```ts cordis-catalog
|
||||
abstract saveText(input: SaveTextSpill): Promise<SpillRef>
|
||||
```
|
||||
|
||||
Source: [`packages/spill/spill/src/index.ts:45`](../../packages/spill/spill/src/index.ts)
|
||||
|
||||
## `ctx.subagents` — `SubagentService`
|
||||
|
||||
Named provider registry and capability-checked start surface.
|
||||
@@ -289,7 +323,7 @@ async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>
|
||||
|
||||
Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:363`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:378`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
## `ctx.userInteraction` — `UserInteractionService`
|
||||
|
||||
@@ -338,12 +372,12 @@ Source: [`packages/workflow/workflow/src/index.ts:159`](../../packages/workflow/
|
||||
|
||||
The framework `ctx` surface every plugin also sees, beyond the harness services above. This is pinned vendor source ([vendoring policy](../../vendor/README.md)); it is summarized here so the page is a complete picture of what `ctx` offers, without elevating framework internals to the harness tier's prominence.
|
||||
|
||||
- `ctx.on / ctx.once` — Register an event listener (disposable). ([`vendor/cordis/src/events.ts:29`](../../vendor/cordis/src/events.ts))
|
||||
- `ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall` — Dispatch an event (sync / awaited / first-bail / veto-chain). ([`vendor/cordis/src/events.ts:29`](../../vendor/cordis/src/events.ts))
|
||||
- `ctx.plugin / ctx.inject` — Load a plugin / declare required services. ([`vendor/cordis/src/registry.ts:144`](../../vendor/cordis/src/registry.ts))
|
||||
- `ctx.on / ctx.once` — Register an event listener (disposable). ([`vendor/cordis/src/events.ts:34`](../../vendor/cordis/src/events.ts))
|
||||
- `ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall` — Dispatch an event (sync / awaited / first-bail / veto-chain). ([`vendor/cordis/src/events.ts:34`](../../vendor/cordis/src/events.ts))
|
||||
- `ctx.plugin / ctx.inject` — Load a plugin / declare required services. ([`vendor/cordis/src/registry.ts:164`](../../vendor/cordis/src/registry.ts))
|
||||
- `ctx.effect` — Register a disposable side effect tied to the fiber. ([`vendor/cordis/src/fiber.ts:9`](../../vendor/cordis/src/fiber.ts))
|
||||
- `ctx.get / ctx.set / ctx.provide / ctx.accessor / ctx.mixin` — Low-level service-store access and binding. ([`vendor/cordis/src/reflect.ts:7`](../../vendor/cordis/src/reflect.ts))
|
||||
- `ctx.extend / ctx.isolate / ctx.intercept` — Derive a child context (scoped services / isolation / interception). ([`vendor/cordis/src/context.ts:35`](../../vendor/cordis/src/context.ts))
|
||||
- `ctx.extend / ctx.isolate / ctx.intercept` — Derive a child context (scoped services / isolation / interception). ([`vendor/cordis/src/context.ts:42`](../../vendor/cordis/src/context.ts))
|
||||
- `ctx.root / ctx.scope / ctx.fiber / ctx.registry / ctx.reflect / ctx.events / ctx.logger` — Ambient handles onto the running context graph. ([`vendor/cordis/src/context.ts:16`](../../vendor/cordis/src/context.ts))
|
||||
- `ctx.timer (+ interval / timeout / throttle / debounce / setTimeout / setInterval)` — Disposable timer helpers. The `timer` key is provided at runtime; the six helpers are mixed onto ctx directly (declared via Pick). ([`vendor/timer/src/index.ts:4`](../../vendor/timer/src/index.ts))
|
||||
- `ctx.loader` — The config Loader that booted the app (present under the loader). ([`vendor/loader/src/index.ts:30`](../../vendor/loader/src/index.ts))
|
||||
|
||||
@@ -4,9 +4,21 @@ The bash execution seam is split across interface ([dsh-bash](../../packages/bas
|
||||
|
||||
Source: [`packages/bash/bash/src/types.ts`](../../packages/bash/bash/src/types.ts)
|
||||
|
||||
## Managed shell environment namespace
|
||||
|
||||
`DSH_*` variables are Harness-owned child-process facts. The model-facing bash tool collects them through `ctx.bashEnv` and passes them through `BashExecRequest.dshEnv`; executors remove inherited `DSH_*` names before merging the current snapshot.
|
||||
|
||||
```ts type-equiv
|
||||
type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}`
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
type DshEnvironment = Readonly<Record<DshEnvironmentKey, string>>
|
||||
```
|
||||
|
||||
## Request vs. spec: the `resolve()` split
|
||||
|
||||
The seam separates the **model-/plugin-facing request** (optional `workdir`/`timeoutMs`, filled from config) from the **fully-resolved spec** the executor acts on (those fields required). The tool layer calls `ctx.bash.resolve(request)` between them — this is the repo's "explicit > implicit at package seams" rule made concrete: the reader of a `BashExecSpec` never wonders where the working directory came from.
|
||||
The seam separates the **model-/plugin-facing request** (optional `workdir`/`timeoutMs`/`stdoutMaxBytes`, filled from config or request policy) from the **fully-resolved spec** the executor acts on (those fields required). The tool layer calls `ctx.bash.resolve(request)` between them — this is the repo's "explicit > implicit at package seams" rule made concrete: the reader of a `BashExecSpec` never wonders where the working directory or output budget came from.
|
||||
|
||||
```ts type-equiv
|
||||
interface BashExecRequest {
|
||||
@@ -15,6 +27,13 @@ interface BashExecRequest {
|
||||
workdir?: string | undefined
|
||||
/** Timeout override in milliseconds (implementations cap it). */
|
||||
timeoutMs?: number | undefined
|
||||
/**
|
||||
* Foreground stdout capture budget in bytes. Absent uses the executor's
|
||||
* default output cap. Trusted in-process consumers use this when they must
|
||||
* parse complete stdout up to their own bounded limit; the model-facing bash
|
||||
* tool does not expose it as a parameter.
|
||||
*/
|
||||
stdoutMaxBytes?: number | undefined
|
||||
/** Abort signal — implementations kill the command when it fires. */
|
||||
signal?: AbortSignal | undefined
|
||||
/**
|
||||
@@ -26,15 +45,20 @@ interface BashExecRequest {
|
||||
*/
|
||||
stdin?: string | undefined
|
||||
/**
|
||||
* Extra environment entries for the command, merged AFTER the
|
||||
* implementation's credential scrub (so an explicit entry here is honored even
|
||||
* when its name matches the scrub pattern — the caller named a value it holds,
|
||||
* not the harness's ambient secret). Set by in-process plugins (the hooks
|
||||
* bridges set `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing
|
||||
* bash tool does not expose it as a parameter (a model that needs an env var
|
||||
* uses shell syntax like `FOO=bar cmd`).
|
||||
* Ordinary environment entries for the command, merged after the credential
|
||||
* scrub. `DSH_*` is reserved for {@link dshEnv} and implementations reject it
|
||||
* here. Set by in-process plugins (the hooks bridges set
|
||||
* `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing bash tool
|
||||
* does not expose it as a parameter.
|
||||
*/
|
||||
env?: Record<string, string> | undefined
|
||||
/**
|
||||
* Harness-owned `DSH_*` variables for this execution. Executors discard
|
||||
* ambient `DSH_*` entries before merging this snapshot, so an unavailable
|
||||
* current fact cannot inherit a stale value from the harness process, and
|
||||
* reject non-`DSH_*` names supplied through this managed channel.
|
||||
*/
|
||||
dshEnv?: DshEnvironment | undefined
|
||||
/**
|
||||
* Explicit per-call sandbox-policy input, overriding the executor's
|
||||
* configured default mode for THIS call. Never a silent default: a
|
||||
@@ -57,6 +81,11 @@ interface BashExecSpec {
|
||||
command: string
|
||||
workdir: string
|
||||
timeoutMs: number
|
||||
/**
|
||||
* Resolved foreground stdout capture budget in bytes. `run()` uses it for
|
||||
* stdout; background tasks and stderr keep the executor's own output cap.
|
||||
*/
|
||||
stdoutMaxBytes: number
|
||||
/** Abort signal — implementations kill the command when it fires. */
|
||||
signal?: AbortSignal | undefined
|
||||
/**
|
||||
@@ -73,6 +102,8 @@ interface BashExecSpec {
|
||||
* config default, absent means "no extra env".
|
||||
*/
|
||||
env?: Record<string, string> | undefined
|
||||
/** Managed `DSH_*` snapshot; implementations reject ordinary names. */
|
||||
dshEnv?: DshEnvironment | undefined
|
||||
/**
|
||||
* The sandbox mode this call executes under, required-but-nullable so every
|
||||
* resolved spec states its policy. A sandboxing executor's `resolve()` stamps
|
||||
@@ -88,6 +119,8 @@ 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).
|
||||
|
||||
`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.
|
||||
|
||||
## Foreground runs: `BashRunResult`
|
||||
|
||||
The outcome of one completed (or killed) foreground run. Orthogonal outcomes are reported **independently** — a process can both time out AND exit 0 because it trapped the signal — so `timedOut`, `aborted`, `signal`, and `exitCode` are each their own field; a caller never reads a cut-short run as a clean success.
|
||||
|
||||
@@ -20,7 +20,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
|
||||
| [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context |
|
||||
| [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant |
|
||||
| [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
|
||||
| [session-query.md](session-query.md) | logical session/event records and bounded exact-event reads |
|
||||
| [session-query.md](session-query.md) | logical records, bounded exact-event reads, and relationship traces |
|
||||
| [system-prompt.md](system-prompt.md) | per-assembly context, tool-provider results, prompt sections, and cooperative assembly |
|
||||
| [tools.md](tools.md) | `ToolDefinition` full fields, the schema DSL, `ToolExecution`/`ToolResult`, tool-presentation UI types, and the guarded execution pipeline |
|
||||
| [user-interaction.md](user-interaction.md) | the UI-backed human question/answer seam: `AskUserQuestionRequest`, answer/options vocabulary, provider API, error taxonomy |
|
||||
@@ -33,6 +33,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
|
||||
| [compaction.md](compaction.md) | the compaction seam: the `compact/*` session events, `CompactionResult`, the `CompactService` interface |
|
||||
| [subagent.md](subagent.md) | the subagent seam: the named-provider registry, `SubagentStartRequest`/`Result`/`Run`, the start-time-vs-runtime capability split |
|
||||
| [web.md](web.md) | the web access seam: `WebSearchRequest`/`Result`, `WebFetchRequest`/`Result`, `WebFetchBody`, provider availability, `WebError` |
|
||||
| [spill.md](spill.md) | the spill storage seam: `SaveTextSpill`, `SpillOwner`/`SpillSource`, `SpillRef`, the branded `SpillLocator` |
|
||||
| [workflow.md](workflow.md) | the workflow seam: `WorkflowStartRequest`, `WorkflowMeta`, `WorkflowRun`/`Result`, the `workflow/*` event payloads, `WorkflowError` fatality |
|
||||
|
||||
> Type definitions on this page are pasted **verbatim** from source and drift-checked by `pnpm run verify-type-equiv` (see [development.md](../development.md#documenting-types-verbatim-ts-type-equiv)). Inline JSDoc is omitted for readability; follow the source link for the full contracts.
|
||||
@@ -247,6 +248,15 @@ The fifteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`,
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
`InjectOptions` extends ordinary message attribution with context-only framing and durable model-hidden JSON metadata:
|
||||
|
||||
```ts type-equiv
|
||||
interface InjectOptions extends SendOptions {
|
||||
envelope?: ContextEnvelope
|
||||
meta?: JsonValue
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
interface Agent {
|
||||
readonly id: AgentId
|
||||
@@ -283,8 +293,10 @@ interface Agent {
|
||||
/**
|
||||
* Inject in-session context (file-change notices, skill content, cron
|
||||
* notifications, …): appends a `context/message` session event the next model
|
||||
* request sees at its chronological position, rendered as tagged synthetic
|
||||
* context rather than a user prompt. Does not run the model.
|
||||
* request sees at its chronological position, rendered as synthetic context
|
||||
* rather than a user prompt. The default uses the canonical context tag;
|
||||
* `options.envelope: 'raw'` preserves caller-owned framing. Does not run the
|
||||
* model.
|
||||
*
|
||||
* Turn-enclosure (the turn-enclosure RFC): an inject while a turn is open joins that turn;
|
||||
* an inject while idle wraps its `context/message` in a one-shot `injection`
|
||||
@@ -294,11 +306,11 @@ interface Agent {
|
||||
* (inject is synchronous): a failing flush is reported via `agent/error`
|
||||
* (step `0`) and the logger, never thrown into the caller.
|
||||
*
|
||||
* Live-adapter review has validated the tagged-envelope rendering against
|
||||
* current DeepSeek behavior; provider-specific mismatches belong in that
|
||||
* adapter, not in the canonical session vocabulary.
|
||||
* Live-adapter review has validated the canonical tagged-envelope rendering
|
||||
* against current DeepSeek behavior; provider-specific mismatches belong in
|
||||
* that adapter, not in the canonical session vocabulary.
|
||||
*/
|
||||
inject(content: ContentBlock[], options?: SendOptions): void
|
||||
inject(content: ContentBlock[], options?: InjectOptions): void
|
||||
|
||||
/**
|
||||
* Cancel ALL pending work for the agent. `cancel()`:
|
||||
@@ -354,7 +366,7 @@ The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, che
|
||||
|
||||
## Interception decisions
|
||||
|
||||
Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. They share one envelope for model-facing context, `HookContext`, which is `inject()`ed as a `context/message` and so carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt).
|
||||
Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. Prompt and post-tool decisions share one model-facing context shape, `HookContext`, which is `inject()`ed as a `context/message` and therefore carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt). Its optional `envelope` selects the canonical context tag or caller-owned raw framing, while JSON `meta` persists plugin state without exposing it to the model. Both decisions carry `additionalContexts[]` so every entry preserves its own provenance, framing, and metadata. Continuation reasons are steering messages instead and deliberately use the narrower content/source shape.
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
@@ -362,23 +374,25 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types
|
||||
interface HookContext {
|
||||
content: ContentBlock[]
|
||||
source: MessageSource
|
||||
envelope?: ContextEnvelope
|
||||
meta?: JsonValue
|
||||
}
|
||||
```
|
||||
|
||||
`agent/prompt-submit` returns a `PromptDecision` (allow a drained queued message — optionally rewriting its `content` or attaching `additionalContext` — or block it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`):
|
||||
`agent/prompt-submit` returns a `PromptDecision` (allow a drained queued message — optionally rewriting its `content` or attaching `additionalContexts` — or block it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`):
|
||||
|
||||
```ts type-equiv
|
||||
type PromptDecision =
|
||||
| { kind: 'allow'; content?: ContentBlock[]; additionalContext?: HookContext }
|
||||
| { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
|
||||
| { kind: 'block'; reason: string }
|
||||
```
|
||||
|
||||
`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn — the typed `/goal` pattern):
|
||||
`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn and therefore carries no context envelope or metadata — the typed `/goal` pattern):
|
||||
|
||||
```ts type-equiv
|
||||
type ContinuationDecision =
|
||||
| { action: 'stop' }
|
||||
| { action: 'continue'; reason?: HookContext }
|
||||
| { action: 'continue'; reason?: { content: ContentBlock[]; source: MessageSource } }
|
||||
```
|
||||
|
||||
`agent/turn-stop` returns the stop-only `ContinuationStop` subset or `undefined`. The loop calls this serial checkpoint after folding the ordinary decision, its reason, and pending steering; a stop is terminal and discards pending steering.
|
||||
|
||||
@@ -37,6 +37,16 @@ interface FsInfo {
|
||||
}
|
||||
```
|
||||
|
||||
`lstat` is the path-level no-follow metadata primitive. It takes a path instead of an `FsTarget` because `resolve` intentionally follows symlinks to produce stable identity; consumers that need trust-boundary checks can call `lstat` first and reject `symlink` before resolving.
|
||||
|
||||
```ts type-equiv
|
||||
interface FsPathInfo {
|
||||
version: FsVersion
|
||||
type: 'file' | 'directory' | 'symlink' | 'other'
|
||||
size?: number
|
||||
}
|
||||
```
|
||||
|
||||
`listDir` returns direct child entries in stable name order. Each entry carries the child basename, type, resolved target, and cheap metadata when the backend can report it. It must not read file contents, so `size` is only for regular files and `version` is metadata-derived. Broken or disappeared children may be returned as `other` without metadata; permission or backend I/O failures while listing or resolving child metadata fail the whole listing with `FS_PERMISSION_DENIED` or `FS_IO_ERROR`.
|
||||
|
||||
```ts type-equiv
|
||||
@@ -144,4 +154,4 @@ type FsErrorCode =
|
||||
|
||||
## The service and the plugin
|
||||
|
||||
`FileSystem` (`ctx.fs`, abstract) owns the provider primitives: `resolve`, `stat`, `readText`, `streamText`, `listDir`, `writeText`, and `editText`. `dsh-fs-policy` registers **no service** — it is a plugin that adds policy through the `fs/*` event gate: it decides the write/edit intent waterfalls (supplying `createIfAbsent`/`replaceIfVersion`/`{ version }` or throwing `FS_NOT_OBSERVED`) and records on `fs/observed`. The executor is `dsh-tool-fs`: it reads/writes/edits through `ctx.fs`, dispatches the waterfalls, and emits the recording event. The generated wiring catalog shows the exact `ctx.fs` signatures on [services.md](../cordis-catalog/services.md#ctxfs--filesystem-abstract-seam).
|
||||
`FileSystem` (`ctx.fs`, abstract) owns the provider primitives: `resolve`, `stat`, `lstat`, `readText`, `streamText`, `listDir`, `writeText`, and `editText`. `dsh-fs-policy` registers **no service** — it is a plugin that adds policy through the `fs/*` event gate: it decides the write/edit intent waterfalls (supplying `createIfAbsent`/`replaceIfVersion`/`{ version }` or throwing `FS_NOT_OBSERVED`) and records on `fs/observed`. The executor is `dsh-tool-fs`: it reads/writes/edits through `ctx.fs`, dispatches the waterfalls, and emits the recording event. The generated wiring catalog shows the exact `ctx.fs` signatures on [services.md](../cordis-catalog/services.md#ctxfs--filesystem-abstract-seam).
|
||||
@@ -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 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](../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 flush checkpoint
|
||||
|
||||
@@ -12,6 +12,19 @@ The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06
|
||||
|
||||
A backend that reloads a log crashed mid-turn finds an open `turn/start` with no `turn/end`. It does **not** truncate — a single turn can be huge in a long-horizon task (many steps, large tool output), and those events were durably appended before the crash. Instead it closes the orphaned turn with a synthetic `turn/end { reason: { kind: 'interrupted' } }`, keeping the log balanced and the turn-enclosure invariant intact. `interrupted` is the one `TurnEndReason` no loop emits (see [session.md](session.md#why-a-turn-ended-turnendreasonmap)).
|
||||
|
||||
## `SessionLocation` — optional per-session artifact target
|
||||
|
||||
`SessionPersistence.locate(meta)` synchronously resolves a backend-owned independent artifact without reading, creating, or flushing it. JSONL returns its absolute target path; SQLite returns `undefined` because sessions share one database. A returned path can therefore name a file that does not yet exist or lacks the current unflushed turn; it is a location hint, not authorization or a freshness guarantee.
|
||||
|
||||
```ts type-equiv
|
||||
interface SessionLocation {
|
||||
/** Backend-specific artifact kind, for example `jsonl`. */
|
||||
readonly kind: string
|
||||
/** Absolute path to this session's backend-owned artifact. */
|
||||
readonly path: string
|
||||
}
|
||||
```
|
||||
|
||||
## `SessionHeader` — metadata beside the log
|
||||
|
||||
Per-session metadata travels **separately** from the event log: format version, cwd, lineage, and the seed boundary are storage concerns, not conversation events, so they stay out of `SessionEventMap` and never reach `deriveMessages()`. The header is attached to a `Session` via `session.header`.
|
||||
@@ -80,7 +93,7 @@ Replay/fork is therefore `ctx.sessions.create(id, { seed: seedEvents })`; resumi
|
||||
|
||||
## The backends
|
||||
|
||||
Both implement the same abstract `SessionPersistence` (create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic:
|
||||
Both implement the same abstract `SessionPersistence` (locate/create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic:
|
||||
|
||||
- **[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.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Session Query
|
||||
|
||||
Exact reads over the live-preferred logical session corpus. The [package contract](../../packages/session-query/session-query) owns source precedence, dynamic optional persistence, cloning, surface classification, bounded windows, and typed failures. Full-text search is a separate proposed SQLite phase.
|
||||
Exact reads and relationship traces over the live-preferred logical session corpus. The [package contract](../../packages/session-query/session-query) owns source precedence, dynamic optional persistence, cloning, surface classification, bounded windows, tracing validation, and typed failures. Full-text search is a separate proposed SQLite package.
|
||||
|
||||
Source: [`packages/session-query/session-query/src/types.ts`](../../packages/session-query/session-query/src/types.ts)
|
||||
|
||||
@@ -30,6 +30,34 @@ export interface SessionEventRecord {
|
||||
}
|
||||
```
|
||||
|
||||
## Session lineage
|
||||
|
||||
`SessionLineageTrace` carries known parents in immediate-to-outward order and a forest of recursively nested direct descendants. The completeness discriminant makes a known root and a missing parent mutually exclusive.
|
||||
|
||||
```ts type-equiv
|
||||
export interface SessionLineageNode {
|
||||
session: SessionRecord
|
||||
descendants: SessionLineageNode[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
export type SessionLineageTrace = {
|
||||
target: SessionRecord
|
||||
ancestors: SessionRecord[]
|
||||
descendants: SessionLineageNode[]
|
||||
} & (
|
||||
| {
|
||||
complete: true
|
||||
root: SessionRecord
|
||||
}
|
||||
| {
|
||||
complete: false
|
||||
unresolvedParentId: SessionId
|
||||
}
|
||||
)
|
||||
```
|
||||
|
||||
## Bounded event reads
|
||||
|
||||
The request addresses one raw seq and optional neighboring counts. The result carries a `SessionHeader` rather than availability flags so a known live target can remain independent of persistence health.
|
||||
@@ -53,6 +81,28 @@ export interface SessionEventWindow {
|
||||
}
|
||||
```
|
||||
|
||||
## Event relationships
|
||||
|
||||
Event traces distinguish positional surface replacement from logged provenance. Every seq list contains direct links except `replacementChain`, which follows immediate replacers from the target to the final positional replacement.
|
||||
|
||||
```ts type-equiv
|
||||
export interface SessionEventTraceRequest {
|
||||
sessionId: SessionId
|
||||
seq: number
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
export interface SessionEventTrace {
|
||||
target: SessionEventRecord
|
||||
replacedBy?: number
|
||||
replacementChain: number[]
|
||||
replacedEventSeqs: number[]
|
||||
sourceEventSeqs: number[]
|
||||
derivedEventSeqs: number[]
|
||||
}
|
||||
```
|
||||
|
||||
## Errors
|
||||
|
||||
The closed code union distinguishes request validation, missing targets, malformed surface logs, optional-backend failure, and contradictory source metadata.
|
||||
@@ -61,6 +111,7 @@ The closed code union distinguishes request validation, missing targets, malform
|
||||
export type SessionQueryErrorCode =
|
||||
| 'SESSION_QUERY_EVENT_NOT_FOUND'
|
||||
| 'SESSION_QUERY_INVALID_CONFIG'
|
||||
| 'SESSION_QUERY_INVALID_LINEAGE'
|
||||
| 'SESSION_QUERY_INVALID_SURFACE'
|
||||
| 'SESSION_QUERY_INVALID_WINDOW'
|
||||
| 'SESSION_QUERY_PERSISTENCE_FAILED'
|
||||
|
||||
@@ -4,6 +4,14 @@ The in-memory, event-sourced model of [dsh-session](../../packages/core/session)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts)
|
||||
|
||||
## Context framing
|
||||
|
||||
`ContextEnvelope` selects the standard tagged projection or preserves a producer-owned complete frame. The latter changes framing only; the event remains a user-role `context/message` in chronological history.
|
||||
|
||||
```ts type-equiv
|
||||
type ContextEnvelope = 'context' | 'raw'
|
||||
```
|
||||
|
||||
## `SessionEventMap` — the event vocabulary
|
||||
|
||||
The append-only event types. Merge-extensible: a plugin declares extra event types via declaration merging — e.g. the [compaction seam](compaction.md) adds `compact/start` / `compact/summary` / `compact/end`, and `@deepseek-ai/dsh-hook-protocol` adds log-only `hook/invoked` / `hook/result` provenance for a hook bridge. Like `compact/*`, these are NOT `SurfaceEventType`s (no `surfaceOp`). The generated [persistence log event catalog](../persistence-catalog.md) enumerates every member — core and merged — with its payload, surface badge, and declaration site.
|
||||
@@ -30,9 +38,16 @@ interface SessionEventMap {
|
||||
/**
|
||||
* In-session context injection (file-change notices, subdir AGENTS.md,
|
||||
* skill content, cron notifications, …). Rendered into the derived history
|
||||
* as tagged synthetic context — NOT a user prompt.
|
||||
* as synthetic context — NOT a user prompt. `envelope: 'raw'` lets a caller
|
||||
* supply its own complete framing; `meta` is persisted JSON hidden from the
|
||||
* model.
|
||||
*/
|
||||
'context/message': { content: ContentBlock[]; source: MessageSource }
|
||||
'context/message': {
|
||||
content: ContentBlock[]
|
||||
source: MessageSource
|
||||
envelope?: ContextEnvelope
|
||||
meta?: JsonValue
|
||||
}
|
||||
/** Raw stream chunk — token-level replay fidelity. */
|
||||
'assistant/chunk': { turn: number; step: number; chunk: StreamChunk }
|
||||
/**
|
||||
@@ -229,7 +244,8 @@ export interface SurfaceFoldResult {
|
||||
- `user/message` → a user message.
|
||||
- `assistant/message` → an assistant message. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its `usage`, but a content-less assistant turn must not enter the provider transcript.
|
||||
- `tool/result` → a user message carrying a `tool-result` block.
|
||||
- `context/message`, `steering/message` → user-role messages wrapped in a tagged envelope (`<context source="…">…</context>`) at their chronological position — the "system-reminder" pattern; the model distinguishes them from real prompts by the envelope.
|
||||
- `context/message` → a user-role message at its chronological position. The default `envelope` is `context`, which wraps content as `<context source="…">…</context>`; `envelope: 'raw'` uses caller-owned framing verbatim. Optional JSON `meta` remains in the event log and is never rendered.
|
||||
- `steering/message` → a user-role message wrapped in `<steering source="…">…</steering>` at its chronological position.
|
||||
|
||||
Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`.
|
||||
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
# 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.
|
||||
|
||||
Source: [`packages/spill/spill/src/types.ts`](../../packages/spill/spill/src/types.ts)
|
||||
|
||||
## The save request
|
||||
|
||||
`saveText` is the whole seam: persist `content` verbatim, return an opaque locator, a backend-supplied retrieval hint, and the exact byte count. The request carries the save-time storage namespace (`owner`), WHERE it came from (`source`, descriptive provenance for naming and inspection — not access control), and a `suggestedName` the backend may use as a naming hint (it is not a path).
|
||||
|
||||
```ts type-equiv
|
||||
interface SaveTextSpill {
|
||||
owner: SpillOwner
|
||||
source: SpillSource
|
||||
suggestedName: string
|
||||
content: string
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
interface SpillOwner {
|
||||
sessionId: SessionId
|
||||
}
|
||||
```
|
||||
|
||||
`SpillOwner.sessionId` is the save-time storage namespace. Forked sessions inherit existing spill locators from the seeded log; those artifacts are not copied or re-owned, and spills produced after the fork use the child session id. A retention-period cleanup may expire old locators with other old session artifacts; the spill seam does not define a per-session cleanup policy.
|
||||
|
||||
```ts type-equiv
|
||||
interface SpillSource {
|
||||
toolName: string
|
||||
callId: CallId
|
||||
label: string
|
||||
}
|
||||
```
|
||||
|
||||
## The result
|
||||
|
||||
```ts type-equiv
|
||||
interface SpillRef {
|
||||
locator: SpillLocator
|
||||
bytes: number
|
||||
retrievalHint: string
|
||||
}
|
||||
```
|
||||
|
||||
`SpillLocator` is a [branded](core.md#branded-ids) model-facing handle returned by the backend. The local backend renders it as a filesystem path; a remote or database backend can render a URI, key, or command token. Consumers treat it as opaque and render it with `retrievalHint` instead of assuming `read` is always the right retrieval mechanism.
|
||||
|
||||
```ts type-equiv
|
||||
type SpillLocator = Branded<'SpillLocator'>
|
||||
```
|
||||
|
||||
## The service
|
||||
|
||||
`SpillStore` (`ctx.spillStore`, defined in [`packages/spill/spill/src/index.ts`](../../packages/spill/spill/src/index.ts)) is a one-method abstract service: `saveText(input) → Promise<SpillRef>`. It persists the FULL `content` and REJECTS on a real storage failure (permissions, ENOSPC, backend unavailable). The seam owns storage only: no retention policy, no tool-result replacement, no retrieval/search API.
|
||||
|
||||
The local backend ([dsh-spill-local](../../packages/spill/spill-local)) writes under `<root>/session-<hash>/<random>-<safeName>` — a configured or lazily-created private (0700) root, a `sha256(sessionId)` session subdir, and an exclusive owner-only (`open(path, 'wx', 0o600)`) write so a planted symlink cannot redirect it. Its `locator` is the local path and its `retrievalHint` tells the model to use `read` or `grep` on that path. The policy consumer ([dsh-spill-policy](../../packages/spill/spill-policy)) replaces an over-`maxInlineBytes` plain-text final result with a retention-library head/tail preview plus the spill reference, best-effort: a save failure keeps the original inline result rather than turning a successful call into an `isError`.
|
||||
@@ -10,7 +10,7 @@ A `ToolSchema` (the model-facing fields) plus the `execute` function and optiona
|
||||
|
||||
```ts type-equiv
|
||||
interface ToolDefinition extends ToolSchema {
|
||||
execute(args: unknown, exec: ToolExecution): Promise<ToolExecuteReturn>
|
||||
execute(args: unknown, exec: ToolRunContext): Promise<ToolExecuteReturn>
|
||||
/**
|
||||
* Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
|
||||
* Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it
|
||||
@@ -120,6 +120,19 @@ interface ToolExecutionInput {
|
||||
}
|
||||
```
|
||||
|
||||
A tool body receives the runtime extension. `deferContext()` is the composite-tool channel: it records nested-dispatch context without injecting inside the still-open outer call.
|
||||
|
||||
```ts type-equiv
|
||||
interface ToolRunContext extends ToolExecution {
|
||||
/**
|
||||
* Defer one nested-dispatch context until this tool's final result reaches
|
||||
* the agent loop. Contexts retain their individual source, envelope, and
|
||||
* metadata and are emitted in call order.
|
||||
*/
|
||||
deferContext(context: HookContext): void
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
interface ToolExecution extends ToolExecutionInput {
|
||||
/** Registry-assigned identity shared with nested calls only as their opaque `parent` token. */
|
||||
@@ -146,16 +159,14 @@ interface ToolExecutionResult {
|
||||
*/
|
||||
error?: ToolErrorInfo
|
||||
/**
|
||||
* Extra model-facing context a `tools/post-execute` listener attached for the
|
||||
* NEXT request (Claude Code's PostToolUse `additionalContext`). It is NOT part
|
||||
* of this call's `content` — `content`/`feedback` shape the tool RESULT, but
|
||||
* `additionalContext` is a SEPARATE `context/message`. A step can carry
|
||||
* multiple tool calls, so the loop BUFFERS every call's `additionalContext`
|
||||
* and appends them only AFTER all `tool/result`s for the step, keeping
|
||||
* tool-call/result adjacency intact. Carried on the result purely to ferry it
|
||||
* from `execute()` up to the loop's per-step buffer.
|
||||
* Extra model-facing contexts deferred by a composite tool or attached by
|
||||
* `tools/post-execute` listeners for the NEXT request. They are NOT part of
|
||||
* this call's `content`: the loop buffers every context and appends them only
|
||||
* AFTER all `tool/result`s for the step, preserving tool-call/result
|
||||
* adjacency. The array preserves each context's source, envelope, metadata,
|
||||
* and production order instead of flattening mixed plugin provenance.
|
||||
*/
|
||||
additionalContext?: HookContext
|
||||
additionalContexts?: HookContext[]
|
||||
/**
|
||||
* The tool-private presentation payload from a successful `execute` (the object
|
||||
* return form). Threaded onto the `tool/result` session event and back into
|
||||
@@ -181,8 +192,8 @@ type PreToolDecision =
|
||||
|
||||
```ts type-equiv
|
||||
type PostToolDecision =
|
||||
| { kind: 'accept'; content?: ContentBlock[]; additionalContext?: HookContext }
|
||||
| { kind: 'block'; feedback: ContentBlock[]; additionalContext?: HookContext }
|
||||
| { kind: 'accept'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
|
||||
| { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: HookContext[] }
|
||||
```
|
||||
|
||||
Call `next()` for the default or return a decision to short-circuit. Pre-policy may deny or ask; only `allowed-once` proceeds, while a non-grant, missing approval channel or service, or agent-less request becomes a denial. Guards may still impose a final denial. Arguments cannot be rewritten because history, audit, UI, and execution must agree.
|
||||
|
||||
@@ -7,27 +7,27 @@ This matrix shows which packages dispatch each harness-owned event and which pac
|
||||
|
||||
| Event | Mode | Declared in | Dispatchers | Listeners |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) |
|
||||
| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) |
|
||||
| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
|
||||
| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) |
|
||||
| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
|
||||
| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
|
||||
| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
|
||||
| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) |
|
||||
| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) |
|
||||
| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
|
||||
| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
|
||||
| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:151`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) |
|
||||
| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:160`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) |
|
||||
| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:295`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
|
||||
| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:214`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) |
|
||||
| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
|
||||
| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:179`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
|
||||
| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:236`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
|
||||
| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:251`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:192`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:169`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) |
|
||||
| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:262`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
|
||||
| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:272`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:282`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
|
||||
| `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) |
|
||||
| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
|
||||
| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) |
|
||||
| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:51`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
|
||||
| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:61`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
|
||||
| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) |
|
||||
| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:53`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
|
||||
| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) |
|
||||
| `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) |
|
||||
| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - |
|
||||
| `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter) |
|
||||
| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
|
||||
| `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
|
||||
| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:108`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) |
|
||||
| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
|
||||
@@ -37,9 +37,9 @@ This matrix shows which packages dispatch each harness-owned event and which pac
|
||||
| `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
|
||||
| `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
|
||||
| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:89`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) |
|
||||
| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:98`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
|
||||
| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:98`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`spill-policy`](../packages/spill/spill-policy), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:80`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:106`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
|
||||
| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:106`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `workflow/agent-end` | `emit` | [`packages/workflow/workflow/src/index.ts:81`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
|
||||
| `workflow/agent-start` | `emit` | [`packages/workflow/workflow/src/index.ts:70`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
|
||||
| `workflow/end` | `emit` | [`packages/workflow/workflow/src/index.ts:91`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
|
||||
|
||||
+64
-9
@@ -9,6 +9,9 @@ Inter-package dependencies among the `@deepseek-ai/dsh-*` harness packages, deri
|
||||
flowchart TD
|
||||
subgraph group_util["packages/util"]
|
||||
pkg_brand["brand"]
|
||||
pkg_home["home"]
|
||||
pkg_paths["paths"]
|
||||
pkg_retention["retention"]
|
||||
pkg_timeout["timeout"]
|
||||
end
|
||||
subgraph group_llm["packages/llm"]
|
||||
@@ -36,6 +39,7 @@ flowchart TD
|
||||
pkg_fs_local["fs-local"]
|
||||
pkg_fs_policy["fs-policy"]
|
||||
pkg_tool_fs["tool-fs"]
|
||||
pkg_tool_fs_search["tool-fs-search"]
|
||||
end
|
||||
subgraph group_skill["packages/skill"]
|
||||
pkg_skill["skill"]
|
||||
@@ -63,6 +67,11 @@ flowchart TD
|
||||
pkg_web_search_exa["web-search-exa"]
|
||||
pkg_web_search_perplexity["web-search-perplexity"]
|
||||
end
|
||||
subgraph group_spill["packages/spill"]
|
||||
pkg_spill["spill"]
|
||||
pkg_spill_local["spill-local"]
|
||||
pkg_spill_policy["spill-policy"]
|
||||
end
|
||||
subgraph group_timeout["packages/timeout"]
|
||||
pkg_timeout_policy["timeout-policy"]
|
||||
end
|
||||
@@ -87,6 +96,7 @@ flowchart TD
|
||||
end
|
||||
subgraph group_support["packages/support"]
|
||||
pkg_acp_snapshot["acp-snapshot"]
|
||||
pkg_agent_loop_testkit["agent-loop-testkit"]
|
||||
pkg_invariants["invariants"]
|
||||
pkg_llm_replay["llm-replay"]
|
||||
pkg_loader_smoke["loader-smoke"]
|
||||
@@ -108,6 +118,7 @@ flowchart TD
|
||||
end
|
||||
subgraph group_context["packages/context"]
|
||||
pkg_time_context["time-context"]
|
||||
pkg_workspace_context["workspace-context"]
|
||||
end
|
||||
subgraph group_examples["packages/examples"]
|
||||
pkg_acp_demo["acp-demo"]
|
||||
@@ -165,6 +176,7 @@ flowchart TD
|
||||
pkg_fs_local --> pkg_fs
|
||||
pkg_fs_policy --> pkg_fs
|
||||
pkg_skill_local --> pkg_fs
|
||||
pkg_skill_local --> pkg_home
|
||||
pkg_skill_local --> pkg_skill
|
||||
pkg_compact --> pkg_llm
|
||||
pkg_compact --> pkg_session
|
||||
@@ -173,6 +185,9 @@ flowchart TD
|
||||
pkg_web_search_deepseek --> pkg_web
|
||||
pkg_web_search_exa --> pkg_web
|
||||
pkg_web_search_perplexity --> pkg_web
|
||||
pkg_spill --> pkg_brand
|
||||
pkg_spill --> pkg_llm
|
||||
pkg_spill --> pkg_session
|
||||
pkg_session_persistence --> pkg_session
|
||||
pkg_llm_replay --> pkg_llm
|
||||
pkg_llm_replay --> pkg_session
|
||||
@@ -185,6 +200,7 @@ flowchart TD
|
||||
pkg_compact_basic --> pkg_llm
|
||||
pkg_compact_basic --> pkg_session
|
||||
pkg_compact_basic --> pkg_token_meter
|
||||
pkg_spill_local --> pkg_spill
|
||||
pkg_hook_protocol --> pkg_bash
|
||||
pkg_hook_protocol --> pkg_session
|
||||
pkg_session_persistence_jsonl --> pkg_session
|
||||
@@ -207,7 +223,6 @@ flowchart TD
|
||||
pkg_user_interaction --> pkg_agent
|
||||
pkg_user_interaction --> pkg_llm
|
||||
pkg_time_context --> pkg_agent
|
||||
pkg_time_context --> pkg_system_prompt
|
||||
pkg_tasks --> pkg_agent
|
||||
pkg_tasks --> pkg_brand
|
||||
pkg_tasks --> pkg_session
|
||||
@@ -242,8 +257,10 @@ flowchart TD
|
||||
pkg_agent_loop --> pkg_tools
|
||||
pkg_tool_bash --> pkg_agent
|
||||
pkg_tool_bash --> pkg_bash
|
||||
pkg_tool_bash --> pkg_home
|
||||
pkg_tool_bash --> pkg_llm
|
||||
pkg_tool_bash --> pkg_sandbox
|
||||
pkg_tool_bash --> pkg_session_persistence
|
||||
pkg_tool_bash --> pkg_system_prompt
|
||||
pkg_tool_bash --> pkg_tasks
|
||||
pkg_tool_bash --> pkg_tools
|
||||
@@ -253,6 +270,13 @@ flowchart TD
|
||||
pkg_tool_fs --> pkg_session
|
||||
pkg_tool_fs --> pkg_system_prompt
|
||||
pkg_tool_fs --> pkg_tools
|
||||
pkg_tool_fs_search --> pkg_bash
|
||||
pkg_tool_fs_search --> pkg_llm
|
||||
pkg_tool_fs_search --> pkg_retention
|
||||
pkg_tool_fs_search --> pkg_session
|
||||
pkg_tool_fs_search --> pkg_spill
|
||||
pkg_tool_fs_search --> pkg_system_prompt
|
||||
pkg_tool_fs_search --> pkg_tools
|
||||
pkg_tool_skill --> pkg_agent
|
||||
pkg_tool_skill --> pkg_llm
|
||||
pkg_tool_skill --> pkg_skill
|
||||
@@ -265,6 +289,11 @@ flowchart TD
|
||||
pkg_tool_web --> pkg_system_prompt
|
||||
pkg_tool_web --> pkg_tools
|
||||
pkg_tool_web --> pkg_web
|
||||
pkg_spill_policy --> pkg_llm
|
||||
pkg_spill_policy --> pkg_retention
|
||||
pkg_spill_policy --> pkg_session
|
||||
pkg_spill_policy --> pkg_spill
|
||||
pkg_spill_policy --> pkg_tools
|
||||
pkg_timeout_policy --> pkg_llm
|
||||
pkg_timeout_policy --> pkg_timeout
|
||||
pkg_timeout_policy --> pkg_tools
|
||||
@@ -277,7 +306,13 @@ flowchart TD
|
||||
pkg_hooks_codex --> pkg_hook_protocol
|
||||
pkg_hooks_codex --> pkg_llm
|
||||
pkg_hooks_codex --> pkg_session
|
||||
pkg_hooks_codex --> pkg_session_persistence
|
||||
pkg_hooks_codex --> pkg_tools
|
||||
pkg_agent_loop_testkit --> pkg_agent
|
||||
pkg_agent_loop_testkit --> pkg_llm
|
||||
pkg_agent_loop_testkit --> pkg_session
|
||||
pkg_agent_loop_testkit --> pkg_system_prompt
|
||||
pkg_agent_loop_testkit --> pkg_tools
|
||||
pkg_acp --> pkg_agent
|
||||
pkg_acp --> pkg_bash
|
||||
pkg_acp --> pkg_llm
|
||||
@@ -291,6 +326,12 @@ flowchart TD
|
||||
pkg_tool_ask_user --> pkg_agent
|
||||
pkg_tool_ask_user --> pkg_tools
|
||||
pkg_tool_ask_user --> pkg_user_interaction
|
||||
pkg_workspace_context --> pkg_agent
|
||||
pkg_workspace_context --> pkg_fs
|
||||
pkg_workspace_context --> pkg_llm
|
||||
pkg_workspace_context --> pkg_paths
|
||||
pkg_workspace_context --> pkg_session
|
||||
pkg_workspace_context --> pkg_tools
|
||||
pkg_repeat_tool_guard --> pkg_agent
|
||||
pkg_repeat_tool_guard --> pkg_tools
|
||||
pkg_mcp_client --> pkg_llm
|
||||
@@ -323,6 +364,7 @@ flowchart TD
|
||||
pkg_hooks_claude --> pkg_hook_protocol
|
||||
pkg_hooks_claude --> pkg_llm
|
||||
pkg_hooks_claude --> pkg_session
|
||||
pkg_hooks_claude --> pkg_session_persistence
|
||||
pkg_hooks_claude --> pkg_subagent
|
||||
pkg_hooks_claude --> pkg_tools
|
||||
pkg_subagent_mock --> pkg_agent
|
||||
@@ -335,6 +377,7 @@ flowchart TD
|
||||
pkg_jsonrpc --> pkg_subagent
|
||||
pkg_agent_spine_demo --> pkg_agent
|
||||
pkg_agent_spine_demo --> pkg_agent_loop
|
||||
pkg_agent_spine_demo --> pkg_home
|
||||
pkg_agent_spine_demo --> pkg_invariants
|
||||
pkg_agent_spine_demo --> pkg_llm
|
||||
pkg_agent_spine_demo --> pkg_session
|
||||
@@ -346,6 +389,7 @@ flowchart TD
|
||||
pkg_agent_spine_demo --> pkg_tool_skill
|
||||
pkg_agent_spine_demo --> pkg_tool_tasks
|
||||
pkg_agent_spine_demo --> pkg_tools
|
||||
pkg_agent_spine_demo --> pkg_workspace_context
|
||||
pkg_workflow_workerthread --> pkg_agent
|
||||
pkg_workflow_workerthread --> pkg_brand
|
||||
pkg_workflow_workerthread --> pkg_llm
|
||||
@@ -365,6 +409,7 @@ flowchart TD
|
||||
pkg_acp_demo --> pkg_session_persistence_jsonl
|
||||
pkg_acp_demo --> pkg_tools
|
||||
pkg_acp_demo --> pkg_user_interaction
|
||||
pkg_acp_demo --> pkg_workspace_context
|
||||
pkg_stdio_demo --> pkg_agent
|
||||
pkg_stdio_demo --> pkg_agent_spine_demo
|
||||
pkg_stdio_demo --> pkg_app_boot
|
||||
@@ -375,11 +420,15 @@ flowchart TD
|
||||
pkg_stdio_demo --> pkg_tool_ask_user
|
||||
pkg_stdio_demo --> pkg_tools
|
||||
pkg_stdio_demo --> pkg_user_interaction
|
||||
pkg_stdio_demo --> pkg_workspace_context
|
||||
```
|
||||
|
||||
| Package | Group | Depends on |
|
||||
| --- | --- | --- |
|
||||
| [`brand`](../packages/util/brand) | `util` | — |
|
||||
| [`home`](../packages/util/home) | `util` | — |
|
||||
| [`paths`](../packages/util/paths) | `util` | — |
|
||||
| [`retention`](../packages/util/retention) | `util` | — |
|
||||
| [`timeout`](../packages/util/timeout) | `util` | — |
|
||||
| [`scope`](../packages/core/scope) | `core` | — |
|
||||
| [`skill`](../packages/skill/skill) | `skill` | — |
|
||||
@@ -405,17 +454,19 @@ flowchart TD
|
||||
| [`bash`](../packages/bash/bash) | `bash` | [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) |
|
||||
| [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) |
|
||||
| [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) |
|
||||
| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) |
|
||||
| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`home`](../packages/util/home), [`skill`](../packages/skill/skill) |
|
||||
| [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
|
||||
| [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) |
|
||||
| [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) |
|
||||
| [`web-search-exa`](../packages/web/web-search-exa) | `web` | [`web`](../packages/web/web) |
|
||||
| [`web-search-perplexity`](../packages/web/web-search-perplexity) | `web` | [`web`](../packages/web/web) |
|
||||
| [`spill`](../packages/spill/spill) | `spill` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
|
||||
| [`session-persistence`](../packages/session-persistence/session-persistence) | `session-persistence` | [`session`](../packages/core/session) |
|
||||
| [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
|
||||
| [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) |
|
||||
| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) |
|
||||
| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) |
|
||||
| [`spill-local`](../packages/spill/spill-local) | `spill` | [`spill`](../packages/spill/spill) |
|
||||
| [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) |
|
||||
| [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
|
||||
| [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
|
||||
@@ -423,7 +474,7 @@ flowchart TD
|
||||
| [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) |
|
||||
| [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
|
||||
| [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) |
|
||||
| [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) |
|
||||
| [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent) |
|
||||
| [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) |
|
||||
| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) |
|
||||
| [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) |
|
||||
@@ -431,17 +482,21 @@ flowchart TD
|
||||
| [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) |
|
||||
| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) |
|
||||
| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
|
||||
| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`home`](../packages/util/home), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
|
||||
| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) |
|
||||
| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |
|
||||
| [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) |
|
||||
| [`spill-policy`](../packages/spill/spill-policy) | `spill` | [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`tools`](../packages/core/tools) |
|
||||
| [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
|
||||
| [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
|
||||
| [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |
|
||||
| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
|
||||
| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools) |
|
||||
| [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) |
|
||||
| [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
|
||||
| [`workspace-context`](../packages/context/workspace-context) | `context` | [`agent`](../packages/core/agent), [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
|
||||
| [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) |
|
||||
| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) |
|
||||
| [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
|
||||
@@ -449,12 +504,12 @@ flowchart TD
|
||||
| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) |
|
||||
| [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
|
||||
| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
|
||||
| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
|
||||
| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) |
|
||||
| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) |
|
||||
| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) |
|
||||
| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`home`](../packages/util/home), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
|
||||
| [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
|
||||
| [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
|
||||
| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
|
||||
| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
|
||||
| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |
|
||||
+19
-19
@@ -57,7 +57,7 @@ Raw stream chunk — token-level replay fidelity.
|
||||
|
||||
Types: [StreamChunk](core-data-structures/llm-streaming.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:242`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:253`](../packages/core/session/src/types.ts)
|
||||
|
||||
#### `assistant/message` — surface
|
||||
|
||||
@@ -69,7 +69,7 @@ Assembled assistant message for one step (derived history uses this). Carries th
|
||||
|
||||
Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:249`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:260`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `bash/*`
|
||||
|
||||
@@ -121,15 +121,15 @@ Source: [`packages/compact/compact/src/types.ts:22`](../packages/compact/compact
|
||||
|
||||
#### `context/message` — surface
|
||||
|
||||
In-session context injection (file-change notices, subdir AGENTS.md, skill content, cron notifications, …). Rendered into the derived history as tagged synthetic context — NOT a user prompt.
|
||||
In-session context injection (file-change notices, subdir AGENTS.md, skill content, cron notifications, …). Rendered into the derived history as synthetic context — NOT a user prompt. `envelope: 'raw'` lets a caller own the complete model-facing frame; `meta` is durable JSON state omitted from the model projection.
|
||||
|
||||
```ts persistence-catalog
|
||||
'context/message': { content: ContentBlock[]; source: MessageSource }
|
||||
'context/message': { content: ContentBlock[]; source: MessageSource; envelope?: ContextEnvelope; meta?: JsonValue }
|
||||
```
|
||||
|
||||
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:240`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:246`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `hook/*`
|
||||
|
||||
@@ -177,7 +177,7 @@ Durable record of a prompt veto and its reason. It is log-only: the blocked prom
|
||||
|
||||
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:234`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:238`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `request/*`
|
||||
|
||||
@@ -189,7 +189,7 @@ Full EpochHeader for the next request, appended inside its step before dispatch.
|
||||
'request/header': { header: EpochHeader; reason: RequestHeaderReason }
|
||||
```
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:277`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:288`](../packages/core/session/src/types.ts)
|
||||
|
||||
#### `request/header-delta` — log-only
|
||||
|
||||
@@ -199,7 +199,7 @@ Log-only amendment to the folded EpochHeader. System and tools use their delta c
|
||||
'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] }
|
||||
```
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:283`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:294`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `steering/*`
|
||||
|
||||
@@ -213,7 +213,7 @@ Steering content injected between steps of a running turn.
|
||||
|
||||
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:267`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:278`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `step/*`
|
||||
|
||||
@@ -225,7 +225,7 @@ Closes step `step` of turn `turn`.
|
||||
'step/end': { turn: number; step: number }
|
||||
```
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:227`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:231`](../packages/core/session/src/types.ts)
|
||||
|
||||
#### `step/start` — log-only
|
||||
|
||||
@@ -235,7 +235,7 @@ Opens step `step` of turn `turn` — one model call plus the tool executions it
|
||||
'step/start': { turn: number; step: number }
|
||||
```
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:225`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:229`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `todo/*`
|
||||
|
||||
@@ -249,7 +249,7 @@ Whole-list snapshot; the latest write wins on replay. It is log-only UI state an
|
||||
|
||||
Types: [TodoItem](core-data-structures/session.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:272`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:283`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `tool/*`
|
||||
|
||||
@@ -263,11 +263,11 @@ The model requested one tool invocation: `name` with the raw `arguments` JSON st
|
||||
|
||||
Types: [CallId](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:255`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:266`](../packages/core/session/src/types.ts)
|
||||
|
||||
#### `tool/code-dispatch` — log-only
|
||||
|
||||
One bridged sub-dispatch from a `run_code` program: the parent `run_code` call id, the deterministic sub-call id (`<parent>:code:<n>`), the tool `name` with its JSON-normalized `arguments` — the exact value dispatched, normalized before dispatch, so this append can never fail on payload shape — whether the sub-call errored, and a bounded `resultSummary` of its model-facing text.
|
||||
One bridged sub-dispatch from a `run_code` program: the parent `run_code` call id, the deterministic sub-call id (`<parent>:code:<n>`), the tool `name` with its JSON-normalized `arguments` — the exact value dispatched, normalized BEFORE dispatch, so this append can never fail on payload shape — whether the sub-call errored, and a bounded `resultSummary` of its model-facing text. Before bounding, occurrences of a non-root session workspace path are normalized to `.` so host-specific absolute path lengths cannot change the summary. Log-only: `deriveMessages()` ignores it, so sub-calls never re-enter model context; persistence and UIs get every call. Appended inside the parent `run_code`'s execution (the bridge drains its queue before returning), so the turn-enclosure invariant holds by construction.
|
||||
|
||||
```ts persistence-catalog
|
||||
'tool/code-dispatch': { parentCallId: CallId; subCallId: CallId; name: string; arguments: unknown; isError: boolean; resultSummary: string }
|
||||
@@ -275,7 +275,7 @@ One bridged sub-dispatch from a `run_code` program: the parent `run_code` call i
|
||||
|
||||
Types: [CallId](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/tools/src/code-mode.ts:25`](../packages/core/tools/src/code-mode.ts)
|
||||
Source: [`packages/core/tools/src/code-mode.ts:34`](../packages/core/tools/src/code-mode.ts)
|
||||
|
||||
#### `tool/result` — surface
|
||||
|
||||
@@ -287,7 +287,7 @@ A completed tool call's model-facing result, plus an optional tool-private `meta
|
||||
|
||||
Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:265`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:276`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `turn/*`
|
||||
|
||||
@@ -301,7 +301,7 @@ Closes turn `turn` with the TurnEndReason that ended it. The loop fires the awai
|
||||
|
||||
Types: [TurnEndReason](core-data-structures/session.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:223`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:227`](../packages/core/session/src/types.ts)
|
||||
|
||||
#### `turn/start` — log-only
|
||||
|
||||
@@ -313,7 +313,7 @@ Opens turn `turn`. `trigger` records what started it — a drained message batch
|
||||
|
||||
Types: [TurnTrigger](core-data-structures/session.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:217`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:221`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `user/*`
|
||||
|
||||
@@ -327,4 +327,4 @@ A user-visible prompt (queued message drained at turn start).
|
||||
|
||||
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:229`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:233`](../packages/core/session/src/types.ts)
|
||||
@@ -9,6 +9,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
|
||||
| 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 |
|
||||
@@ -61,6 +62,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
|
||||
| [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 |
|
||||
@@ -78,9 +80,13 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
|
||||
| [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 |
|
||||
| [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 |
|
||||
|
||||
### Simplification
|
||||
|
||||
@@ -145,8 +151,10 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
|
||||
| [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 |
|
||||
| [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 |
|
||||
| [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 |
|
||||
|
||||
@@ -81,7 +81,7 @@ Resolved targets must expose at least three concepts:
|
||||
- An opaque `targetKey`, used for stale guards and file-state lookup. The local backend might use a realpath-like key; a remote backend might use a workspace URI or file id. Consumers must not parse or assume this is a local absolute path.
|
||||
- A `displayPath`, used for model/UI-facing output. It may be a local absolute path, workspace-relative path, or remote URI depending on the backend.
|
||||
|
||||
Read and mutation results must include an opaque file `version`. A local backend can use mtime/size or a hash-like token; a remote backend can use a revision id. The `dsh-fs-policy` plugin records versions for stale checks; consumers may display related metadata but must not interpret the version token.
|
||||
Read and mutation results must include an opaque file `version`. The local backend derives its token from bigint stat metadata (`dev`, `ino`, `size`, `mtimeNs`, and `ctimeNs`) so same-size rewrites and inode replacement invalidate consumers reliably; a remote backend can use a revision id or hash-like token. The `dsh-fs-policy` plugin records versions for stale checks; consumers may display related metadata but must not interpret the version token.
|
||||
|
||||
The provider hands back decoded text: `readText` returns a whole regular text file, `streamText` streams the same text semantics for large files. Both own regular-file checks, bounded line/output handling is NOT theirs — line windowing, numbered-line rendering, and total-line accounting live in the executor (`dsh-tool-fs`), which reads through `ctx.fs` and renders the model-facing window. The provider owns UTF-8 decoding and binary/NUL rejection; it does not know about line windows or views.
|
||||
|
||||
|
||||
+4
-2
@@ -12,6 +12,8 @@ Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistenc
|
||||
|
||||
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.
|
||||
|
||||
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.
|
||||
|
||||
### The hook interface (`PersistenceBackend<TornMarker>`)
|
||||
|
||||
Six methods (five required + an optional lifecycle hook) — the only seam between the coordinator and storage:
|
||||
@@ -30,7 +32,7 @@ The single design choice that keeps the seam clean: the crash-repair "where is t
|
||||
|
||||
## Testing
|
||||
|
||||
The shared `runPersistenceContract` (public-API contract) keeps running for every backend. A new `runCoordinatorContract` (`tests/coordinator-contract.ts`) holds the write-path orchestration — adoption, HMR, collision, dispose-drain, crash-tail repair — and runs once per backend through a `CoordinatorFixture` (an in-memory reference + jsonl + sqlite). The per-backend specs shrank to storage mechanics only (JSONL: path safety, fsync rollback, bucket listing; SQLite: schema version, `scanRows`, transaction rollback). A through-coordinator torn-tail→load→`commitRepair` test per real backend (via a `corruptTail` fixture hook) keeps the coordinator's torn-marker repair branch covered under the 100% per-file gate — the contract crash test only produces synthetic closers, never a torn marker, so it could not reach that branch.
|
||||
The shared `runPersistenceContract` (public-API contract) keeps running for every backend. `runCoordinatorContract` (`tests/coordinator-contract.ts`) holds the write-path orchestration — adoption, HMR, collision, session and backend disposal drains, and crash-tail repair — and runs once per backend through a `CoordinatorFixture` (an in-memory reference + jsonl + sqlite). Coordinator-specific tests pin retirement map cleanup, same-id chain-tail races, failed-drain retry, and close ordering. The per-backend specs retain storage mechanics only (JSONL: path safety, fsync rollback, bucket listing; SQLite: schema version, `scanRows`, transaction rollback). A through-coordinator torn-tail→load→`commitRepair` test per real backend (via a `corruptTail` fixture hook) keeps the coordinator's torn-marker repair branch covered under the 100% per-file gate — the contract crash test only produces synthetic closers, never a torn marker, so it could not reach that branch.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
@@ -39,4 +41,4 @@ The shared `runPersistenceContract` (public-API contract) keeps running for ever
|
||||
|
||||
## Consequences
|
||||
|
||||
The coordinator adds one indirection and an opaque torn marker, but centralizes correctness-heavy orchestration previously duplicated by every backend. Its hook surface stays narrow: collision checks reuse `loadStored`, materialization stays atomic inside `appendBatch`, and listing bypasses the coordinator. New backends implement storage primitives rather than copy the event-buffer-flush lifecycle.
|
||||
The coordinator adds one indirection, an opaque torn marker, and detached session-retirement tasks, but centralizes correctness-heavy orchestration previously duplicated by every backend. Session disposal remains an observe-only event, so the session owner does not await persistence retirement; the coordinator contains failures, preserves uncommitted buffers, and makes backend teardown the quiescence boundary. Its hook surface stays narrow: collision checks reuse `loadStored`, materialization stays atomic inside `appendBatch`, and listing bypasses the coordinator. New backends implement storage primitives rather than copy the event-buffer-flush lifecycle.
|
||||
+2
-2
@@ -14,9 +14,9 @@ Add `stdin?: string` and `env?: Record<string, string>` to **both** `BashExecReq
|
||||
|
||||
Three deliberate choices:
|
||||
|
||||
1. **The model-facing tool omits `stdin` and `env`.** Shell syntax already covers those needs, so duplicate parameters would add surface without authority separation. The tool builds requests only from declared model arguments, signal, and owner; trusted in-process callers may set the seam fields directly.
|
||||
1. **The model-facing tool omits `stdin` and `env`.** Shell syntax already covers those needs, so duplicate parameters would add surface without authority separation. The tool builds requests only from declared model arguments, signal, and owner; trusted in-process callers may set the seam fields directly. Harness-owned variables use the separate `dshEnv` channel from the [managed environment decision](../feature/2026-07-10-agent-session-identity-and-log-location.md), so ordinary `env` cannot replace them.
|
||||
|
||||
2. **`env` merges AFTER the credential scrub, so an explicit caller entry always wins** — even a credential-shaped name. This is correct because the scrub's job is narrow: stop the harness's *ambient* `process.env` credentials from leaking into a spawned command. A caller that explicitly sets a var has named a value it already holds (not the ambient secret), so the scrub is not a constraint on it. `childEnv(extra?)` layers `scrub(process.env)` → `ENV_OVERRIDES` (the model-friendly `TERM=dumb` etc.) → `extra`, last-wins.
|
||||
2. **`env` merges AFTER the credential scrub, so an explicit caller entry wins even on a credential-shaped name.** The later managed-namespace decision reserves `DSH_*`: ambient entries are removed, ordinary `env` cannot set them, and trusted `dshEnv` merges last. The complete order is `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → ordinary `env` → `dshEnv`.
|
||||
|
||||
3. **`stdin`/`env` are required-absent-OK (plain optional) on the resolved spec, NOT required-but-nullable like `owner`.** `owner` is required-but-nullable because a *silently* missing owner yields an unowned, cross-session-readable task — a security footgun that a visible `undefined` guards against. `stdin`/`env` have no such hazard: a missing one means "no stdin / no extra env", which is the safe, ordinary case (every model-driven call). So they stay plain optionals, matching `signal`.
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ Filesystem resolution used one plugin-load cwd while bash used the session proje
|
||||
|
||||
Thread the caller's session cwd into path resolution, exactly as `dsh-tool-bash` already does for `workdir`. The **caller** (the tool) supplies the cwd; the provider does not read a session or agent.
|
||||
|
||||
- `FileSystem.resolve` widens to `resolve(path: string, opts?: { cwd?: string }): Promise<FsTarget>`. `opts.cwd` is the base a RELATIVE `path` resolves against; an absolute `path` ignores it; omitting `opts.cwd` uses the backend's own default. An options object (not a positional `cwd?`) leaves room for future resolution hints without another signature change.
|
||||
- `FileSystem.resolve` accepts `resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget>`. `opts.cwd` is the base a RELATIVE `path` resolves against; an absolute `path` ignores it; omitting `opts.cwd` uses the backend's own default. `opts.signal` cancels resolution when the backend performs I/O. The options object keeps both caller-owned resolution controls together without positional growth.
|
||||
- `dsh-fs-local.resolve` uses `resolveLocalTarget(opts?.cwd ?? this.config.cwd, path)`. `config.cwd` stays the default for a caller that supplies none (non-ACP / no-session use, and the single-session stdio demo where `process.cwd()` IS the workspace).
|
||||
- `dsh-tool-fs`'s `read`/`write`/`edit` derive the session cwd through a shared `sessionCwd(exec)` helper (`exec.agent?.session.header.cwd`, mirroring bash's `resolveWorkdir`) and pass it to `resolve`. A non-agent / headerless caller yields `undefined`, so the backend applies its default.
|
||||
|
||||
|
||||
@@ -44,7 +44,7 @@ Like MiniCode, the conversation advances append-only and resets only when model-
|
||||
## Consequences
|
||||
|
||||
- A request that is not explained by the log cannot be constructed by accident — not by the loop, not by a listener; mutating a built request throws; every header change is a durable, diffable log event.
|
||||
- Choosing between the advisory channels is a change-frequency decision, and the design makes the stable one structural: an `agent/session-prefix` contribution is composed once per loop instance and reused verbatim, so it extends the cacheable prefix at zero marginal cost and CANNOT bust the provider cache mid-session; content that changes mid-session flows through the append-only history channels — `agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter, at the price of accumulating in history and the log. Route session-frozen openers to the prefix and change notices to the history channels; a per-step request-only tail slot was deliberately dropped (no consumer, and a durable append covers every current update pattern).
|
||||
- Choosing between the advisory channels is a change-frequency decision, and the design makes the stable one structural: an `agent/session-prefix` contribution is composed once per loop instance and reused verbatim, so it extends the cacheable prefix at zero marginal cost and CANNOT bust the provider cache mid-session; content that changes mid-session flows through the append-only history channels — `agent.inject()` and tool/prompt-submit `additionalContexts` — each a durable `context/message` paid once and prefix-cached thereafter, at the price of accumulating in history and the log. Route session-frozen openers to the prefix and change notices to the history channels; a per-step request-only tail slot was deliberately dropped (no consumer, and a durable append covers every current update pattern).
|
||||
- What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and replace node), a real prompt/tool change (`request/header-delta`), a config switch (ditto), a process boundary with drift (`'resume'` snapshot differing from its predecessor). The provider's own reasoning-content exclusion is managed server-side.
|
||||
- The `step/start`-listener behavior change (above) is the one observable semantics change for plugins; `agent/pre-step` is the current-request seam.
|
||||
- Tool-result trimming (planned) needs no new mechanism: a logged single-node surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic.
|
||||
|
||||
@@ -0,0 +1,155 @@
|
||||
# RFC: Tool result retention library
|
||||
|
||||
Status: implemented
|
||||
|
||||
## Problem
|
||||
|
||||
Several model-facing tools already bound the amount of context they return, but each one owns a different local mechanism and vocabulary: bash keeps a tail plus spill files, web search caps source lists, web fetch caps body content, and `glob` / `grep` discovery needs an inline first page while keeping exact omission metadata for the full result set. A single `truncate(text)` helper cannot cover those cases: item tools need item counts and grouping outside the primitive, while text tools need byte budgets and UTF-8-safe head/tail cuts.
|
||||
|
||||
The shared abstraction the tools need is **retention**, not generic collection. A caller feeds items or text chunks into a bounded object and later receives the retained content plus exact omission metadata. Tool-specific code still owns business semantics: file grouping, line numbering, exit codes, provider error states, spill files, and model-facing prose. The common library owns only the mechanical question "what did we keep, and what did we omit?"
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-retention` lives under `packages/util/` (peer to `dsh-brand` and `dsh-timeout`) and owns bounded model-facing output. It is a library of pure classes and functions, **not** a Cordis service or plugin: it takes no `ctx`, registers nothing, holds no cross-call state, and emits no events. Tool packages import it directly when they need bounded output.
|
||||
|
||||
The library has two independent retainers:
|
||||
|
||||
- `ItemRetainer<T>` handles ordered logical units such as paths, grep matches, or search sources. It supports `head` retention only in v1, while keeping the retainer shape open to additional retention strategies later.
|
||||
- `TextRetainer` handles byte-oriented text streams such as bash stdout/stderr or web response bodies. It supports `head`, `tail`, and `headTail` retention while preserving UTF-8 boundaries at `finish()`.
|
||||
|
||||
Both retainers return a small `PushDecision` after each `push()` so callers can tell whether that unit/chunk was fully retained and whether the accumulated result is now truncated. Omission counts are exact because callers keep feeding every observed item/chunk.
|
||||
|
||||
```ts ignore-check
|
||||
/**
|
||||
* How much content the retainer omitted.
|
||||
*
|
||||
* `unknown` is reserved for callers that omit without a count; the retainers
|
||||
* themselves return `none` or `exact`.
|
||||
*/
|
||||
type Omitted =
|
||||
| { kind: 'none' }
|
||||
| { kind: 'exact'; count: number }
|
||||
| { kind: 'unknown' }
|
||||
|
||||
interface PushDecision {
|
||||
kept: boolean
|
||||
truncated: boolean
|
||||
}
|
||||
|
||||
/**
|
||||
* Final result for ordered logical units.
|
||||
*/
|
||||
interface RetainedItems<T> {
|
||||
items: T[]
|
||||
truncated: boolean
|
||||
seen: number
|
||||
kept: number
|
||||
omitted: Omitted
|
||||
}
|
||||
|
||||
/**
|
||||
* Final result for text streams.
|
||||
*
|
||||
* The returned `text` is safe to send to a formatter; the retainer does not add
|
||||
* tool-specific headers, exit markers, XML tags, or recovery instructions.
|
||||
*/
|
||||
interface RetainedText {
|
||||
text: string
|
||||
truncated: boolean
|
||||
omittedBytes: Omitted
|
||||
}
|
||||
```
|
||||
|
||||
### Strategies
|
||||
|
||||
Item retention supports a head window. Text retention supports head, tail, and headTail byte windows.
|
||||
|
||||
```ts ignore-check
|
||||
type ItemRetentionStrategy =
|
||||
| {
|
||||
/** Keep the first `maxItems` units. Use for `glob`, `grep`, and web sources. */
|
||||
kind: 'head'
|
||||
maxItems: number
|
||||
}
|
||||
|
||||
type TextRetentionStrategy =
|
||||
| {
|
||||
/** Keep the first `maxBytes` bytes. */
|
||||
kind: 'head'
|
||||
maxBytes: number
|
||||
}
|
||||
| {
|
||||
/** Keep the final `maxBytes` bytes. Requires reading to the end. */
|
||||
kind: 'tail'
|
||||
maxBytes: number
|
||||
}
|
||||
| {
|
||||
/** Keep a stable prefix and suffix, omitting the middle. Requires reading to the end. */
|
||||
kind: 'headTail'
|
||||
headBytes: number
|
||||
tailBytes: number
|
||||
}
|
||||
```
|
||||
|
||||
### Tool mapping
|
||||
|
||||
`read` is intentionally outside the v1 retention library. Its `read-render` helper owns a file-specific pagination contract: `offset` / `limit`, line numbers, `totalLines`, offset-out-of-range errors, per-line preview truncation, and a selected-output byte cap that can stop scanning mid-window. That is a line-window renderer, not a generic retention primitive. It may share future neutral notice helpers, but it should not pass its already-selected window through `ItemRetainer`.
|
||||
|
||||
`FsGlobEntry` and `FlatGrepMatch` below are the intended discovery-tool item shapes, not existing retention-library exports. `FsGlobEntry` is one backend-derived path, and `FlatGrepMatch` is one ungrouped grep match before the backend groups retained matches by file.
|
||||
|
||||
`glob` uses `ItemRetainer<FsGlobEntry>` with `{ kind: 'head', maxItems: globMaxResults }` after collecting the full sorted path list. The tool keeps the retained first page inline and may save the full list through the spill seam. Path mapping, skipped candidates, and `incomplete` stay outside the retainer.
|
||||
|
||||
`grep` uses `ItemRetainer<FlatGrepMatch>` with `{ kind: 'head', maxItems: grepMaxMatches }` before grouping. The executor parses ripgrep output, maps paths, applies per-line preview truncation, and pushes flat matches. After `finish()`, the tool groups retained matches by file and can save the full match list through the spill seam when the inline result is capped. Grouping is not part of the retainer because the cap is total matches, not files; per-match preview truncation and `incomplete` are also separate from result-level retention.
|
||||
|
||||
`bash` can use `TextRetainer` with `tail` or `headTail` and reads to process completion. The bash executor still owns spill files, exit status, signal, timeout, and background-task behavior; the retention helper only replaces ad hoc in-memory head/tail accounting where that behavior is desired. Long-running task ownership remains orthogonal to the [generic long-running tool runtime](2026-06-20-generic-long-running-tool-runtime.md).
|
||||
|
||||
`web_fetch` can use `TextRetainer` with `head` or `headTail`, or keep provider-owned body caps when the provider must read and decode internally. Either way, the fetch result's `truncated` remains a provider/tool fact, and the library only supplies retained text and omission metadata.
|
||||
|
||||
`web_search` can use `ItemRetainer<WebSearchSource>` with `head`. Current providers often return an array, so this is post-hoc but still standardizes notices.
|
||||
|
||||
### Notices
|
||||
|
||||
The library exposes a neutral notice shape and a tiny formatter hook, but tools provide the user-facing words. A grep footer says "Narrow the pattern, path, or include"; a web fetch footer says "Fetch a more specific URL or section"; bash may point to a spill file. The retainer cannot know those recovery actions.
|
||||
|
||||
```ts ignore-check
|
||||
interface RetentionNotice {
|
||||
scope: string
|
||||
strategy: 'head' | 'tail' | 'headTail'
|
||||
unit: 'items' | 'bytes' | 'chars' | 'lines'
|
||||
limit: number | { head: number; tail: number }
|
||||
kept: number
|
||||
omitted: Omitted
|
||||
}
|
||||
|
||||
const formatGrepNotice = (notice: RetentionNotice): string =>
|
||||
formatRetentionNotice(
|
||||
notice,
|
||||
({ kept }) => `Results capped at ${kept}. Narrow the pattern, path, or include to see more.`,
|
||||
)
|
||||
```
|
||||
|
||||
The formatter hook is deliberately small: a tool turns a `RetentionNotice` into its own footer text. The helper may standardize omission wording, but it does not own recovery guidance.
|
||||
|
||||
`truncated` means the retainer omitted otherwise-available content because of a budget. It does not mean the upstream was incomplete. Tools keep separate fields for permission failures, skipped binary files, provider partial failures, unreadable candidates, invalid UTF-8, and any other "could not inspect" condition.
|
||||
|
||||
## Consequences
|
||||
|
||||
**What shipped.** `@deepseek-ai/dsh-retention` exports `ItemRetainer`, `TextRetainer`, the result types (`RetainedItems`, `RetainedText`), the strategy types (`ItemRetentionStrategy`, `TextRetentionStrategy`), `Omitted`, `PushDecision`, `RetentionNotice`, and the neutral notice helpers `describeOmitted` / `formatRetentionNotice` — with no dependency on Cordis or any tool package. Unit tests cover item-head retention with exact omission counts, text-head retention, text-tail retention, head-tail byte retention, zero budgets, UTF-8 boundary handling (2-, 3-, and 4-byte codepoints and invalid lead bytes at each cut), and unknown omission wording.
|
||||
|
||||
**What is documented but not yet migrated.** `glob`, `grep`, `bash`, `web_fetch`, and `web_search` have their mappings documented in the [package README](../../../../packages/util/retention/README.md), but not every tool has been migrated onto the library in this change; migration is deliberately separate follow-up work. `read` is documented as intentionally out of scope: its `read-render` line-window contract (`offset`/`limit`, `totalLines`, offset-range errors, per-line preview truncation, a byte cap over the selected window) is not generic retention, and one `Omitted` count cannot represent both sides of a line window.
|
||||
|
||||
**Boundaries the library holds.** `truncated` means the retainer omitted otherwise-available content because of a budget; it never means the upstream was incomplete. Tool-specific states — `incomplete`, permission failures, provider partial failures, binary skips, bash spill-path recovery, invalid UTF-8 — stay in tool-domain fields, outside the retainer. When a future change migrates a tool, that package's README and tests must prove the model-facing result text is unchanged except for deliberate notice wording.
|
||||
|
||||
**Tradeoffs accepted.** The v1 surface deliberately supports only item `head` retention and text `head` / `tail` / `headTail`; windows, grouped budgets, sort-aware caps, and upstream-stop control wait until a second consumer proves the need. Text retention counts bytes for process/body safety, leaving character- and line-level preview budgets as separate tool-owned concerns.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Post-hoc `truncate(text)` only.** Rejected: it matches Codex's history/tool-output truncation use case but loses item counts, grouping boundaries, UTF-8-safe byte windows, and exact omission metadata.
|
||||
|
||||
**One generic `Collector<T>` with pluggable callbacks.** Rejected for v1: it hides the two important resource modes. Logical item retention counts items; text retention counts bytes and preserves UTF-8 boundaries. Separate `ItemRetainer` and `TextRetainer` names make that difference explicit while keeping the API small.
|
||||
|
||||
**Put `read` windowing behind `ItemRetainer`.** Rejected for v1: `read` is the only current window consumer, and its semantics are file pagination rather than generic retention. A single `Omitted` count cannot represent both sides of a line window, and `read` also carries `totalLines`, offset-range errors, per-line preview truncation, and a byte cap over selected output. Keeping `read-render` tool-owned avoids growing the shared library around one special case.
|
||||
|
||||
**Make truncation part of `ToolExecutionResult`.** Rejected: the tool registry would have to understand tool-specific recovery guidance, grouping, line numbering, exit status, and provider semantics. Retention is a library used before a tool returns `ContentBlock[]`; the model-facing result remains tool-owned.
|
||||
|
||||
**Expose limits in every model-facing tool schema.** Rejected as the default: Claude Code's grep exposes `head_limit` / `offset`, but this harness keeps routine budgets as deployment config unless the model genuinely needs pagination control. A future read-like continuation field can be added per tool; it does not belong in the shared retention primitive.
|
||||
@@ -0,0 +1,189 @@
|
||||
# RFC: Tool output spill policy
|
||||
|
||||
Status: implemented
|
||||
|
||||
## Problem
|
||||
|
||||
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.
|
||||
|
||||
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.
|
||||
|
||||
## Decision
|
||||
|
||||
A thin spill storage seam plus a default spill policy plugin, in a new `packages/spill/` group:
|
||||
|
||||
| Package | Role |
|
||||
|---|---|
|
||||
| `@deepseek-ai/dsh-spill` | Interface: `ctx.spillStore`, vocabulary types, no storage implementation. |
|
||||
| `@deepseek-ai/dsh-spill-local` | Local backend: private, session-scoped file storage on the host filesystem. |
|
||||
| `@deepseek-ai/dsh-spill-policy` | Tool-result policy plugin: wraps final text results after dispatch and replaces oversized results with a retained preview plus a spill locator. |
|
||||
|
||||
There is no dedicated model-facing consumer package. The consumer is the existing `ctx.tools` execution pipeline: `dsh-spill-policy` consumes final tool results through the `tools/post-execute` waterfall, and the model follows the backend-supplied retrieval hint for the returned locator.
|
||||
|
||||
### Spill seam
|
||||
|
||||
The storage seam is minimal: save text and return a locator plus retrieval hint.
|
||||
|
||||
```ts ignore-check
|
||||
interface SpillStore {
|
||||
saveText(input: SaveTextSpill): Promise<SpillRef>
|
||||
}
|
||||
|
||||
interface SpillSource {
|
||||
toolName: string
|
||||
callId: CallId
|
||||
label: string
|
||||
}
|
||||
|
||||
interface SaveTextSpill {
|
||||
owner: { sessionId: SessionId }
|
||||
source: SpillSource
|
||||
suggestedName: string
|
||||
content: string
|
||||
}
|
||||
|
||||
type SpillLocator = Branded<'SpillLocator'>
|
||||
|
||||
interface SpillRef {
|
||||
locator: SpillLocator
|
||||
bytes: number
|
||||
retrievalHint: string
|
||||
}
|
||||
```
|
||||
|
||||
`SpillLocator` is a [branded](../../../../packages/util/brand) model-facing handle returned by the backend. The local backend renders it as a filesystem path; a remote or database backend can render a URI, key, or command token. Consumers treat it as opaque and render it with `retrievalHint` instead of assuming `read` is always the right retrieval mechanism. `SpillOwner.sessionId` is the save-time storage namespace: forked sessions inherit existing spill locators from the seeded log without copying or re-owning them, and new spills after the fork use the child session id. A retention-period cleanup may expire old locators with other old session artifacts; the spill seam does not define a per-session cleanup policy.
|
||||
|
||||
`dsh-spill-local` owns only storage details: session-scoped directory selection, safe names, path-traversal protection, the write, and returning `{ locator, bytes, retrievalHint }`. It does not own retention policy, tool-result replacement, search, or file inspection. Files land at `<root>/session-<hash>/<random>-<safeName>`, where `root` is a configured path or a lazily-created private (0700) per-process temp dir, the session subdir is a short `sha256(sessionId)` prefix, and the leaf is a random hex prefix plus the caller's `suggestedName` sanitized to one path segment (mirrors the JSONL backend's `encodeSegment`). The write is `open(path, 'wx', 0o600)` — exclusive and owner-only, so a planted symlink cannot redirect it. The locator is the path, and the retrieval hint tells the model it can use `read` or `grep` on that path.
|
||||
|
||||
### Spill policy
|
||||
|
||||
`dsh-spill-policy` is a `tools/post-execute` result transformer with one configuration knob:
|
||||
|
||||
```ts ignore-check
|
||||
interface Config {
|
||||
/** Omitted means no automatic spill policy. Present means apply to oversized plain text tool results. */
|
||||
maxInlineBytes?: number
|
||||
}
|
||||
```
|
||||
|
||||
When `maxInlineBytes` is omitted the plugin registers nothing (a true no-op). When set, it applies a default policy to final plain-text tool results:
|
||||
|
||||
1. Let the tool run normally, delegating via `next()` so a downstream listener settles the result first.
|
||||
2. Flatten the accepted final `ContentBlock[]` only when it is entirely plain text; a result with any non-text block is left untouched.
|
||||
3. If its UTF-8 byte size is at or below `maxInlineBytes`, leave it unchanged.
|
||||
4. If it is larger, call `ctx.spillStore.saveText()` with the full final text.
|
||||
5. Replace the model-facing result with a retained head/tail preview plus the spill reference.
|
||||
|
||||
The preview is an implementation default owned by the policy: a head/tail split of `maxInlineBytes` via the retention library's `TextRetainer`. Future config can expose preview sizing only after a second deployment needs it.
|
||||
|
||||
The replacement text is intentionally generic because the policy only knows the final formatted tool result, not the tool's internal resource:
|
||||
|
||||
```text
|
||||
<retained preview>
|
||||
|
||||
(Omitted N bytes. Full formatted result stored at: /.../session-.../....txt. Use read with offset/limit, or grep this path to search within it.)
|
||||
```
|
||||
|
||||
If `ctx.spillStore.saveText()` fails (permissions, ENOSPC, backend unavailable), or the call has no session owner, or no backend is loaded, the plugin logs the reason and returns the original result unchanged. Spill failure never turns a successful tool call into an `isError` result or hides the inline result.
|
||||
|
||||
The policy skips `read` to avoid a circular `read -> spill file -> read again` loop. Additional opt-out configuration is deferred until a real second tool needs it.
|
||||
|
||||
## Showcase: web_fetch
|
||||
|
||||
`web_fetch` is the first showcase because it returns a naturally large text result and needs no tool-specific spill code. The tool is ordinary:
|
||||
|
||||
```ts ignore-check
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'web_fetch',
|
||||
async execute(args, exec) {
|
||||
const result = await ctx.web.fetch({ url: args.url }, exec.signal ? { signal: exec.signal } : undefined)
|
||||
return [{ type: 'text', text: formatFetchOutput(result) }]
|
||||
},
|
||||
}))
|
||||
```
|
||||
|
||||
With `dsh-spill-policy` configured, a large formatted fetch result is automatically retained and spilled. A deployment demonstrates the behavior by setting the provider resource cap higher than the policy cap:
|
||||
|
||||
```yaml
|
||||
- id: web-fetch-local
|
||||
name: '@deepseek-ai/dsh-web-fetch-local'
|
||||
config:
|
||||
maxBodyChars: 500000
|
||||
|
||||
- id: spill-local
|
||||
name: '@deepseek-ai/dsh-spill-local'
|
||||
|
||||
- id: spill-policy
|
||||
name: '@deepseek-ai/dsh-spill-policy'
|
||||
config:
|
||||
maxInlineBytes: 50000
|
||||
```
|
||||
|
||||
This separation is important. `web-fetch-local` still owns resource caps (`maxResponseBytes`, `maxBodyChars`) to protect network, memory, and decoding work. `spill-policy` owns only the model-facing context cap after the result already exists. If the provider already returned `truncated: true`, the spill file contains the full formatted result the tool returned, not the full original webpage; the policy does not claim otherwise.
|
||||
|
||||
## Relationship to retention and early spill
|
||||
|
||||
Retention is separate from spill storage:
|
||||
|
||||
- `@deepseek-ai/dsh-retention` owns preview mechanics (`TextRetainer`, `ItemRetainer`, and omitted metadata).
|
||||
- `@deepseek-ai/dsh-spill` owns saving final text and returning a locator plus retrieval hint.
|
||||
- `@deepseek-ai/dsh-spill-policy` applies the default final-result policy in the tool pipeline, composing the two.
|
||||
|
||||
The final-result policy cannot replace tool-owned early spill. Some useful content is not present in final `ToolExecutionResult.content`:
|
||||
|
||||
- `bash` final output is already a tail plus a temp spill path; the complete stdout/stderr streams live in executor files.
|
||||
- `subagent` final output is the child final answer, not the child rollout.
|
||||
- Future tools may produce runtime artifacts that are never represented by their final `ToolExecutionResult.content`.
|
||||
|
||||
Those cases can consume `ctx.spillStore` directly in later work. They are not part of the first showcase.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- No new model-facing `artifact_read` or `artifact_search` tool in v1.
|
||||
- No per-tool retention configuration in v1.
|
||||
- No model-facing timeout/truncation arguments.
|
||||
- No migration of `read` output into spill files.
|
||||
- No replacement for provider/resource caps such as `web-fetch-local.maxBodyChars`.
|
||||
- No bash temp-file normalization or subagent rollout capture in the first cut.
|
||||
|
||||
## Deferred
|
||||
|
||||
- `saveFile()` / `linkOrCopy` for existing executor spill files, needed for bash normalization.
|
||||
- Tool-owned spill for subagent rollouts (`await run.result`, read in-process child session before `run.dispose()`, save JSONL).
|
||||
- Per-tool opt-out or per-tool policy declarations if the built-in `read` skip is insufficient.
|
||||
- Remote or database storage backends for ACP or remote environments where a local path is not meaningful.
|
||||
- Cleanup and retention policy for old spill files, likely tied to session cleanup.
|
||||
|
||||
## Testing
|
||||
|
||||
- `dsh-spill` unit tests pin the seam contract: registration as `ctx.spillStore`, one-implementation-per-context, and disposal release.
|
||||
- `dsh-spill-local` unit tests cover `saveText`, `encodeSegment` sanitization (separators/tilde/whole-segment dots/empty), the session-hash directory, owner-only permissions, distinct paths per save, the configured/private root, and a storage-failure rejection.
|
||||
- `dsh-spill-policy` unit tests drive real tools through `ctx.tools.execute`: disabled-mode no-op, oversized-text replacement, small/non-text passthrough, `read` skip, best-effort fallback (save failure / no backend / no owner), and downstream-composition (bounding a replaced result, preserving `additionalContexts`).
|
||||
- `dsh-tool-web` integration drives `web_fetch` through `ctx.tools.execute` with the real `spill-local` backend + policy, proving the model-facing text changes only by the deliberate spill notice while the spill file holds the full formatted result.
|
||||
- The `coding-agent` example loads `spill-local` + `spill-policy`, so its keyless Loader smoke exercises the real load path (the namespace-plugin export shape + `inject`).
|
||||
|
||||
## Consequences
|
||||
|
||||
The default policy only sees final formatted text. It cannot preserve provider-internal content that was already capped or runtime artifacts that were never part of the result. This is acceptable for the first cut because the showcase is final-result spill, not early spill; tool-owned early spill remains deferred work.
|
||||
|
||||
Returning real paths from the local backend keeps v1 simple and matches proven agent-tool behavior, while the seam itself only promises an opaque locator plus retrieval hint so remote backends can return non-file locators.
|
||||
|
||||
The local-backend value proposition depends on the existing `read`/`grep` tools being able to inspect the returned local path, even when the spill directory is outside the session cwd. That holds today because the filesystem policy records observations and write guards but does not confine reads to the workspace. A future workspace-confinement policy must either allow local spill paths explicitly or use a non-file spill backend whose retrieval hint points at a supported reader.
|
||||
|
||||
**Snapshot gap.** No ACP snapshot scenario covers the transcript-visible `web_fetch` spill notice yet. The ACP snapshot harness replays keyless and cannot hit the live web, and a `web_fetch` spill requires a real over-cap HTTP body; a deterministic scenario would need a seeded loopback fetch target the replay tree does not currently wire (the examples do not load `tool-web` at all). The behavior is covered instead by the `dsh-tool-web` integration test against a loopback server. Closing the gap is follow-up work: wire `tool-web` + a seeded fetch target into the ACP example, then record a `web-fetch-spill` scenario.
|
||||
|
||||
The policy can become too large if it starts owning tool-specific semantics. It stays narrow: plain-text final results only. Tool-owned early spill remains future work.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Require each tool to opt in with a retention declaration.** Rejected for v1: the goal is a default behavior similar to Claude Code's generic tool-result persistence. A single `maxInlineBytes` deployment knob is enough to prove the shape.
|
||||
|
||||
**Make `tool-results` a broad tool-result platform.** Rejected: a broad package name invites retention policy, result replacement, preview wording, search, and early spill into one seam. The shared storage part is smaller: save text and return a locator plus retrieval hint.
|
||||
|
||||
**Use `ctx.fs.writeText` or the model-facing `write` tool.** Rejected: workspace filesystem writes carry project-file semantics, write/edit policy, observation state, and user-facing side effects. Spill files are runtime artifacts, not model-authored workspace edits. The existing `read` tool may inspect them later, but creation belongs to the runtime spill seam.
|
||||
|
||||
**Let `web-fetch-local` fetch without caps and rely on spill-policy.** Rejected: spill-policy runs after the final tool result exists and cannot protect network, memory, or decoding resources. Provider resource caps stay mandatory.
|
||||
|
||||
**Merge retention into spill.** Rejected: retention and spill have different responsibilities. `TextRetainer`/`ItemRetainer` decide what preview is kept and what was omitted; spill storage only saves the final text the policy asks it to save.
|
||||
@@ -38,11 +38,11 @@ Three decisions, each elaborated in its own section below:
|
||||
|
||||
Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentation transport with one required parameter, `{ code: string }`. It is represented by a normal `ToolDefinition` for dispatch but stays outside the filterable capability layers, so restrictions cannot accidentally remove Code Mode's only entry point. Calls traverse the complete tool pipeline — `tools/pre-execute` → monotonic guards → `tools/execute` around dispatch → `tools/post-execute` → immutable `tools/result` notification — exactly like native calls; a permission plugin can inspect the program text before it runs, and final-result observers see the normalized outer outcome. Its `execute(args, exec)`:
|
||||
|
||||
1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding JSON-normalizes its arguments—rejecting lossy values before dispatch—waits on the serialization queue, executes with a deterministic call id and the outer token as `parent`, and logs `tool/code-dispatch`. Successful text becomes a string and non-text blocks become placeholders; tool errors reject the binding promise. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
|
||||
1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding JSON-normalizes its arguments—rejecting lossy values before dispatch—waits on the serialization queue, executes with a deterministic call id and the outer token as `parent`, defers returned contexts through the outer execution, and logs `tool/code-dispatch`. Successful text becomes a string and non-text blocks become placeholders; tool errors reject the binding promise. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
|
||||
2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`. The runtime receives the run-scoped signal, not only the caller's outer signal, so any way the outer run settles also aborts work inside the runtime.
|
||||
3. **Settle after quiescence.** When the runtime settles, the bridge aborts outstanding work and drains the dispatch queue before returning. Success returns captured output and presentation metadata. A runtime failure becomes `CodeRunFailedError`; backend rejection uses the registry's normal error boundary. Both produce structured error results, and no sub-call can append after `run_code` settles.
|
||||
|
||||
**Sub-call `additionalContext` is omitted.** Injecting it during `run_code` would break parent call/result adjacency, while one program can produce many contexts. Supporting it requires a plural channel or loop-level sub-dispatch buffer.
|
||||
**Sub-call contexts are deferred through the parent.** Injecting inside `run_code` would break parent call/result adjacency, so `ToolRunContext.deferContext()` collects every sub-result `additionalContexts` entry in dispatch order. The registry carries that array even when the program later throws, and the loop appends each entry only after the outer result and every sibling result in the step. An outer post-execute block discards tool-deferred entries and exposes only contexts explicitly attached by the blocking decision.
|
||||
|
||||
**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.
|
||||
|
||||
@@ -86,14 +86,14 @@ The SDK instructs the model to write an async erasable-TypeScript body, call too
|
||||
|
||||
## Consequences
|
||||
|
||||
Deployments switching to `'code'` must update any native-only `toolOrder`. Assembly listeners own the integrity of any rewritten protocol surface. Sub-dispatch remains serialized, and the bridge does not propagate per-call `additionalContext` until those contracts are designed for Code Mode.
|
||||
Deployments switching to `'code'` must update any native-only `toolOrder`. Assembly listeners own the integrity of any rewritten protocol surface. Sub-dispatch remains serialized, while per-call contexts retain their source, envelope, and metadata through the outer result.
|
||||
|
||||
## Testing
|
||||
|
||||
- **Worker runtime:** Real-worker tests cover output and value capture, failure kinds, compute and wall budgets, hostile binding traffic, empty environment, structured-clone fallback, output caps, and disposal to quiescence. A built-package test runs the worker entry under plain Node.
|
||||
- **Registry integration:** Tests cover code generation, all presentation modes, reserved-name and restriction rules, scoped visibility, authoritative assembly rewrites, `toolOrder`, runtime compatibility failures, full-pipeline sub-dispatch, parent-token correlation, serialization, cancellation and queue drain, JSON normalization, error propagation, log events, omitted `additionalContext`, and HMR cleanup.
|
||||
- **With-key e2e:** A real model composes two bash calls in one program; the test verifies the collapsed request header, correlated dispatch events, resulting file, and curated answer.
|
||||
- **Snapshot:** The `code-mode-turn` and `both-mode-turn` fixtures pin the SDK section, header tool list, dispatch events, and result card.
|
||||
- **Registry integration:** Tests cover code generation, all presentation modes, reserved-name and restriction rules, scoped visibility, authoritative assembly rewrites, `toolOrder`, runtime compatibility failures, full-pipeline sub-dispatch, parent-token correlation, serialization, cancellation and queue drain, JSON normalization, error propagation, log events, ordered context deferral across successful and failed programs, outer-block suppression, and HMR cleanup.
|
||||
- **With-key e2e:** A real model composes two bash calls in one program; another discovers nested workspace instructions through a Code Mode fs dispatch. The tests verify collapsed request headers, correlated dispatch events, resulting files, deferred context, and model behavior.
|
||||
- **Snapshot:** The `code-mode-turn`, `both-mode-turn`, and `code-mode-workspace-context` fixtures pin SDK text, header tool lists, dispatch events, deferred context, and result cards.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
|
||||
@@ -0,0 +1,87 @@
|
||||
# RFC: Workspace context instruction files
|
||||
|
||||
Status: implemented
|
||||
|
||||
## Problem
|
||||
|
||||
Repository guidance such as `AGENTS.md` belongs in a coding session's effective context so project conventions, build commands, and review rules arrive without repeated user pasting. The stdio and ACP products need the same behavior, isolated by session cwd: a global system-prompt section leaks one workspace's files into another live ACP session.
|
||||
|
||||
Neighboring products establish useful conventions but differ in details. Codex treats `AGENTS.md` as native, Claude Code uses `CLAUDE.md` and familiar system-reminder-style user context, and opencode supports both names with one winner per directory plus lazy nested discovery. The harness needs cross-tool compatibility without loading duplicate or contradictory files from the same scope.
|
||||
|
||||
The lifecycle has two distinct classes of content. The initial applicable chain is stable enough to live in the request prefix and benefit from provider prefix caching. Nested files, edits, candidate switches, and removals happen after the session starts and belong in durable append-only history rather than the frozen prefix.
|
||||
|
||||
## Decision
|
||||
|
||||
The implementation lives in `packages/context/workspace-context` as `@deepseek-ai/dsh-workspace-context`. It is a request-context extension, not a core service or a filesystem backend. `@deepseek-ai/dsh-agent-core` mounts it for both product front doors and forwards its config. The plugin consumes `agent/session-prefix`, `tools/post-execute`, and the optional `ctx.fs` capability.
|
||||
|
||||
The plugin does not statically inject `fs`. Providerless product trees therefore boot normally and the plugin no-ops until a filesystem provider exists. All production reads go through that provider. Candidate probes call `lstat` before `resolve`, so a repository-owned final-component symlink is rejected rather than followed outside the workspace. The session-prefix signal and dynamic tool execution signal propagate through resolution, metadata probes, and streaming reads, so cancellation does not wait for an unrelated filesystem scan. Once `lstat` identifies a regular-file winner, a provider exception or disagreement during resolve/stat is classified as unavailable: it is neither interpreted as a deletion nor allowed to fall through to a lower-priority candidate.
|
||||
|
||||
### File Names And Precedence
|
||||
|
||||
The default per-directory candidate list is `['AGENTS.md', 'CLAUDE.md']`. The list is configurable as `instructionFileCandidates`, and `AGENTS.md` is an ordinary first candidate rather than a hidden priority. In one directory, only the first existing regular-file candidate loads. With defaults, `AGENTS.md` is native and `CLAUDE.md` is a compatibility fallback.
|
||||
|
||||
Candidate entries are same-directory file names. Empty entries, `.`/`..`, and entries containing `/` or `\` are ignored. Lowercase names, local variants, and other same-directory names can be opted into explicitly; rule directories and import semantics are outside this contract.
|
||||
|
||||
The user-global file is fixed at `$DSH_HOME/AGENTS.md` and is not affected by `instructionFileCandidates`. `$DSH_HOME` defaults to `~/.dsh`, matching the harness-level home role of `~/.codex` or `~/.claude` rather than introducing a plugin-specific home. Tilde expansion and the default live in `dsh-paths` so future harness features share the same convention.
|
||||
|
||||
### Baseline Prefix
|
||||
|
||||
On the first request of an agent-loop instance, the plugin contributes one user-role message through `agent/session-prefix`. It loads the user-global file first, then finds the project root by walking upward from `agent.session.header.cwd` to a configured root marker (default `.git`), then loads one candidate from each directory from the root to the cwd. A `.git` file and a `.git` directory are both valid markers, covering linked worktrees and submodules. Without a marker, the cwd itself is the root.
|
||||
|
||||
The plugin prepends its contribution before `await next()` returns, so session-prefix contributions appear in plugin registration order. In the product spine workspace instructions are registered before a skills catalog and therefore appear first. The loop deep-freezes the composed prefix, logs it in `EpochHeader.messagePrefix`, and reuses it verbatim for that instance. It is request state, not `Session.deriveMessages()` history.
|
||||
|
||||
A resumed agent creates a new loop instance and recomposes the baseline from current files, with the new prefix anchored by the resume request header. This permits current baseline content on resume without mutating a prefix already used by an earlier instance.
|
||||
|
||||
The baseline is a user-role `<system-reminder>` with `Instructions from: <path>` sections and explicit authority and precedence language. This familiar model-facing frame avoids a harness-specific XML vocabulary. Project paths are root-relative and the user-global path is `~/.dsh/AGENTS.md` for the default home or `$DSH_HOME/AGENTS.md` for a configured home. A literal `</system-reminder>` inside file content is escaped. The package README owns the exact current [prompt shape](../../../../packages/context/workspace-context/README.md#prompt-shape).
|
||||
|
||||
### Dynamic Discovery And Refresh
|
||||
|
||||
After a successful first-party `read`, `write`, or `edit` call, the `tools/post-execute` listener reconciles the touched descendant chain and every scope already known to the session. A newly reached scope is returned through `additionalContexts` for the next request using an `Additional instructions from: <path>` system-reminder. Under Code Mode, `run_code` defers sub-dispatch contexts onto its outer result, so the same update is appended only after the parent result rather than being injected mid-call.
|
||||
|
||||
A content edit appends `Updated instructions from: <path>`, states that the new content replaces the previous content, and includes the complete current file. If precedence changes from one candidate to another, the message also names the previous path and says it no longer applies. If no candidate remains, the plugin appends `Instructions removed: <path>` and states that the previously loaded instructions no longer apply.
|
||||
|
||||
Dynamic messages use a raw `context/message` envelope because the plugin owns the complete system-reminder framing. Core context injection therefore supports `envelope: 'raw'`; callers that omit it retain the canonical `<context source="...">` wrapper. `context/message.meta` carries opaque JSON state that is persisted but never rendered to the model.
|
||||
|
||||
Shell commands are not discovery triggers. Local bash calls start fresh shells, and inferring reached paths from arbitrary command strings would require shell semantics the prompt plugin does not own.
|
||||
|
||||
### Duplicate Suppression And Change Detection
|
||||
|
||||
Every dynamic workspace context event stores versioned metadata with `{ action, scope, path, previousPath?, digest? }`, where `digest` is SHA-1 over the loaded content. The model-facing prompt has no HTML comments, hidden markers, or headings that are parsed back into state.
|
||||
|
||||
At reconciliation time the plugin scans plugin-owned `context/message` events and derives the latest state for each visible scope. A short per-session pending map begins only after the immutable top-level `tools/result` proves an `additionalContexts` entry survived every post-execute listener, then covers the interval before the loop appends that context to the log. Each entry records the open `{ turn, step }`: an equal durable `context/message` at or after its sequence boundary confirms and removes it, while a matching `step/end` arriving first means the loop discarded its context buffer, so the plugin removes both the pending entry and its version-cache fast path. A nested Code Mode result stages its changes under the parent's opaque execution token so repeated sub-dispatches in one run do not duplicate them; the parent result rolls that provisional state back and commits only contexts retained by outer policy.
|
||||
|
||||
An unchanged path and digest is suppressed. A logged removal is a tombstone, so a reappearing candidate becomes a new `set`. Resume works from persisted metadata. If compaction removes an instruction event from the visible surface, that state no longer suppresses a later load, matching the fact that the model can no longer see it. Only changes actually included under the byte budget enter metadata or pending state, so an omitted file remains eligible on a later touch.
|
||||
|
||||
The frozen baseline keeps an in-memory path/digest map for comparison. A later successful filesystem touch appends baseline edits or removals as dynamic messages; it never rewrites the prefix. During resumed prefix composition the plugin also reconciles visible dynamic scopes, so nested changes made while the agent was offline can append an update before the first resumed request.
|
||||
|
||||
There is intentionally no watcher. Detection occurs at the next successful structured filesystem touch or resumed prefix composition. A provider failure produces no removal; absence is only accepted when all configured candidates in that scope were probed successfully.
|
||||
|
||||
### Byte Budget And Bounded Reads
|
||||
|
||||
`maxBytes` is required and applies separately to a rendered baseline or one dynamic reconciliation batch; there is no implicit or unbounded render budget. Non-positive and non-finite values disable loading. When content exceeds the budget, broader files are omitted before the most-specific file is truncated. A visible `Workspace instruction budget ...` notice names omitted and truncated paths and byte counts, and output never exceeds the configured bytes.
|
||||
|
||||
`maxSourceBytes` is a positive per-file cap with a 1 MiB default. The loader checks reported size before reading and still consumes content through `streamText()` with a running UTF-8 byte count, so missing/stale metadata cannot force an unbounded allocation. An oversized winning candidate is unavailable rather than a reason to fall through to another same-directory name. The plugin deliberately keeps no process-wide cache and never retains instruction prose. It keeps only `{ path, version, digest }` per effective scope in a `WeakMap<Session, Map<scope, state>>`: a matching provider `FsVersion` plus matching effective prompt state skips the read, while a changed version triggers a bounded read and SHA-1 confirmation. SHA-1 remains the cross-provider content identity persisted in visible structured metadata; provider versions are only an in-memory invalidation fast path. Cache transitions for model-visible changes commit only when the corresponding context survives the complete tool-result policy chain, and are invalidated if that accepted context is later dropped with its aborted step before reaching the log.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Use a global `ctx.systemPrompt.section()`.** Rejected because one Cordis context can host sessions with different cwd values, while repository-owned text is lower-authority context rather than top-authority provider system content.
|
||||
|
||||
**Inject the baseline on every `agent/pre-step`.** Rejected because repeated history injection wastes tokens, complicates duplicate state, and prevents a structurally stable provider prefix. Prefix composition gives a frozen, logged, per-instance baseline while dynamic append-only messages handle changes.
|
||||
|
||||
**Load both `AGENTS.md` and `CLAUDE.md` in one directory.** Rejected because repositories in transition commonly duplicate guidance across both files. Ordered candidates make precedence explicit and configurable.
|
||||
|
||||
**Parse rendered headings or hidden comments to recover loaded state.** Rejected because instruction prose can contain the same text, causing silent false positives. Persisted JSON metadata provides an unambiguous state channel that is invisible to the model.
|
||||
|
||||
**Summarize files with a model.** Rejected because instruction files are already curated summaries; another model call is nondeterministic and can erase edge-case requirements. Deterministic full text with byte budgeting is simpler.
|
||||
|
||||
## Consequences
|
||||
|
||||
Workspace guidance is isolated per session and shared by both product front doors and every tool presentation mode. Initial instructions benefit from stable prefix caching, while nested and changed content remains durable and replayable. The generic session/agent context contract includes optional raw framing and JSON metadata, both propagated through prompt-submit and post-tool `additionalContexts` arrays without flattening entries.
|
||||
|
||||
Repository text remains untrusted input. Lower-authority user-role framing, explicit precedence language, delimiter escaping, and symlink rejection reduce risk but do not eliminate prompt injection. Permission and sandbox layers treat workspace files as data rather than authority.
|
||||
|
||||
The system is event-driven rather than watch-driven. Edits are not visible at the exact filesystem mutation instant unless that mutation goes through a structured tool; externally changed files are noticed on the next successful structured touch or resume. This keeps the design deterministic and provider-neutral.
|
||||
|
||||
## Deferred
|
||||
|
||||
Bash-derived path reporting, recursive startup scans, file watchers, lowercase defaults, `.claude/CLAUDE.md`, `.claude/rules/*.md`, import directives, ACP `additionalDirectories`, trust acknowledgements, and model-generated summaries are deferred. Same-directory private variants can be configured today; directory rule systems and imports need their own precedence and trust designs.
|
||||
@@ -12,8 +12,8 @@ The framing that shapes the whole design: **a bridge is a compatibility adapter,
|
||||
|
||||
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`:
|
||||
|
||||
- **`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`/`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. A CC hook's 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. A tool call's payload carries the real `tool_name` in the bridge's reduced `tool_input: { command }` shape.
|
||||
- **`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.
|
||||
|
||||
### Outcome → Decision mapping
|
||||
|
||||
@@ -35,9 +35,9 @@ The CC bridge's `ask` result is a real permission path, not a terminal bridge de
|
||||
|
||||
`agent.inject()` defaults a missing `MessageSource` to `{ kind: 'user' }`, so every bridge `inject()` and `HookContext` passes `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }`. Unit coverage pins the resulting `context/message.source` as the plugin rather than the user.
|
||||
|
||||
### Adding context is not a veto — delegate, then fold
|
||||
### Adding context is not a veto — delegate, then prepend
|
||||
|
||||
A context-only hook must call `next()` and then fold its `additionalContext` into the downstream decision; returning allow or accept directly would bypass later policy listeners. Post-tool block and accept decisions both preserve added context. Prompt allow preserves it, while prompt block drops it because the prompt never reaches the model. Only an explicit hook denial or block short-circuits the waterfall.
|
||||
A hook that only attaches `additionalContext` (no block/deny) is NOT a decision the bridge should return on its own: returning `allow`/`accept` from a waterfall listener WITHOUT calling `next()` short-circuits every later `agent/prompt-submit` / `tools/post-execute` listener, so a policy/sandbox plugin registered after the bridge would never see the prompt. Each bridge therefore delegates via `next()` before adding its context to the downstream decision. Both seams carry ordered `additionalContexts` arrays, so the bridge prepends its separately sourced entry while preserving every downstream source, envelope, and metadata field; a downstream prompt block still drops all context because the prompt never reaches the model, while post-tool block semantics may explicitly retain contexts. Code Mode ferries the same array through the outer `run_code` result. Only a real `deny`/`block` from the hook itself short-circuits. Tests assert a later listener can still block a prompt a context-only hook allowed and that retained prompt and post-tool contexts remain separate.
|
||||
|
||||
### CLAUDE_PROJECT_DIR defaults to the session workspace
|
||||
|
||||
|
||||
@@ -14,9 +14,9 @@ The canonical surface separates transformable policy, around-dispatch control, a
|
||||
|
||||
**Agent events** (`dsh-agent`):
|
||||
- `agent/session-start(agent, source)` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`.
|
||||
- `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching `additionalContext`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below).
|
||||
- `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching separately sourced `additionalContexts[]`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below).
|
||||
|
||||
**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing context recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern.
|
||||
**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing content and source recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern. It is not a `context/message`, so its type does not offer a context envelope or durable context metadata.
|
||||
|
||||
### The tool pipeline gives each phase one kind of authority
|
||||
|
||||
@@ -25,7 +25,7 @@ Every call follows `tools/pre-execute` → guards → `tools/execute` → dispat
|
||||
- **`tools/pre-execute`** is the extensible waterfall gate. Its `PreToolDecision` allows, denies, or asks. Deny skips `tools/execute` and core dispatch. Ask resolves through the optional approval seam: only `allowed-once` continues through guards and dispatch; rejection, cancellation, an unavailable channel, a missing approval service, or an agent-less call becomes a normalized denial. Every outcome still reaches post-policy and final observers.
|
||||
- **`ctx.tools.guard()`** installs synchronous scope-aware policy after the whole pre-execute waterfall. A guard may deny or abstain, never force-allow, so listener ordering cannot resurrect an operation that a final invariant forbids.
|
||||
- **`tools/execute`** is the around-dispatch waterfall for timeout, retry, and metrics plugins. A wrapper delegates to core dispatch with `next()`, may add, replace, or remove only `exec.signal` before doing so, and receives the already-normalized result of a thrown or unknown tool; returning its own valid result short-circuits dispatch.
|
||||
- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, optionally replaces content, or attaches `additionalContext`; in-place mutation of the result is not a transform channel, because the registry rebuilds the outcome from a protected snapshot plus the returned decision.
|
||||
- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, optionally replaces content, or attaches `additionalContexts`. The returned decision is the supported transform channel; after the waterfall, the registry materializes the complete outcome once before final observation.
|
||||
- **`tools/result`** is the synchronous contained notification after every transform, lossless-JSON materialization, and the outer error boundary. It receives the same frozen execution identity and an immutable snapshot of the authoritative result; observer failures are contained per listener and cannot change or reject `ToolRegistry.execute()`'s returned outcome.
|
||||
|
||||
Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, malformed-result, non-JSON result, and identity-shape failures resolve as JSON-safe `isError` results rather than escaping the turn. A post-execute listener can therefore inspect a thrown tool, and a final observer sees exactly what the caller receives and the session log can persist.
|
||||
@@ -34,9 +34,9 @@ Core dispatch and the tool body sit inside normalization boundaries, so tool, li
|
||||
|
||||
### Three load-bearing loop decisions
|
||||
|
||||
1. **Open the turn before prompt policy.** A fully blocked batch becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. Every veto also records `prompt/blocked` with the original prompt and reason, so mixed batches retain blocked inputs. Allowed `additionalContext` is injected into the open turn.
|
||||
1. **Open the turn before prompt policy.** A fully blocked batch becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. Every veto also records `prompt/blocked` with the original prompt and reason, so mixed batches retain blocked inputs. Every allowed `additionalContexts` entry is injected into the open turn.
|
||||
|
||||
2. **Post-tool `additionalContext` is buffered and appended AFTER all `tool/result`s.** `content`/`feedback` shape the result `execute()` returns, but `additionalContext` is a SEPARATE `context/message`, and a single step can carry multiple tool calls. Appending context right after each result would interleave `result(c1) → context → result(c2)` and break tool-call/result adjacency. So `execute()` surfaces `additionalContext` on its `ToolExecutionResult`, and the loop buffers every per-call context for the step and appends them as `context/message`(s) only after every `tool/result` is appended.
|
||||
2. **Post-tool `additionalContexts` are buffered and appended AFTER all `tool/result`s.** `content`/`feedback` shape the result `execute()` returns, but each context is a SEPARATE `context/message`, and a single step or composite tool can produce many. Appending context immediately would interleave `result(c1) → context → result(c2)` or place nested context before its outer result, breaking tool-call/result adjacency. `ToolRunContext.deferContext()` therefore collects nested-dispatch context through failures, `execute()` surfaces the ordered array on `ToolExecutionResult`, and the loop appends every entry only after every `tool/result` in the step. An accepted outer call preserves deferred contexts before decision contexts; an outer block discards deferred contexts and exposes only contexts explicitly supplied by the blocking decision.
|
||||
|
||||
3. **A forced `continue` `reason` is enqueued through the steering channel**, so the next step's top-of-loop drain records it as steering for the continued turn — next-*step* steering within the SAME turn, not a next-*turn* prompt (matching the existing `hasSteering` force-continue override).
|
||||
|
||||
|
||||
@@ -15,7 +15,7 @@ The obvious third option — let a plugin edit the request's `messages` on the w
|
||||
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()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — [the interception-seams RFC](2026-06-30-interception-seams.md)), each a durable `context/message` paid once and prefix-cached thereafter.
|
||||
- **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.
|
||||
- **Composed before the pressure gate.** Composition precedes the instance's first `agent/pre-step`, and the seam hands the composed value through: `agent/pre-step` carries a `sessionPrefix` parameter and `CompactService.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` counts it in its token-pressure estimate — a gate reading the previous instance's folded prefix instead would under-gate a resumed or forked instance whose contributor grew, skipping compaction and shipping an over-window first request. A composition interrupted by a cancel/dispose landing inside the waterfall 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.
|
||||
|
||||
@@ -14,7 +14,7 @@ The guard is a loop-hygiene plugin, not a model-facing tool. It counts consecuti
|
||||
|
||||
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 three listeners and holds all state in plugin-local maps keyed by `AgentId` — 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.
|
||||
|
||||
- **`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, folds a reminder onto the downstream decision's `additionalContext` — 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.
|
||||
- **`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.
|
||||
- **`agent/status` (emit)** — on `disposed`, drop the agent's state, bounding the maps over harness lifetime.
|
||||
|
||||
@@ -29,7 +29,7 @@ Two deliberate rules, both documented in [the package README](../../../../packag
|
||||
|
||||
### Reminder delivery
|
||||
|
||||
Reminders use `additionalContext` with the plugin source, preserving the original `tool/result`. The first threshold emits a short nudge; later thresholds include the tool, count, and a bounded argument preview while comparison still uses the full canonical string. Existing downstream context is concatenated under the guard's source because `HookContext` supports one source.
|
||||
Reminders ride `additionalContexts` as their own entries (source `{kind: 'plugin', plugin: 'repeat-tool-guard'}` — the label is load-bearing per `HookContext`), never a `content` replacement: the `tool/result` event stays the tool's own output for audit, and the loop appends buffered contexts as `context/message`s after the step's results, which the session renders as tagged synthetic-user envelopes and derived history replays. Thresholds escalate: the first configured threshold gets a short "you are repeating yourself, analyze the previous result" nudge; each later threshold gets the detailed form naming the tool, the repeat count, and the canonical arguments (head-truncated at `argumentsPreviewChars`, default 500 — a looping `write`-sized payload must not ride into the next request unbounded; the chain key always compares the full canonical string), and stating that the calls made no progress. The pi original hardcodes the gentle text to the literal count 3; the guard keys it to `thresholds[0]`, fixing that bug in the port. A downstream hook bridge contribution remains a separate array entry, so both plugins retain their source, envelope, and metadata.
|
||||
|
||||
### Config
|
||||
|
||||
@@ -53,7 +53,7 @@ Reminders use `additionalContext` with the plugin source, preserving the origina
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Append the reminder into the tool result** (`accept` with replaced `content` — the pi extension's mechanism, which patches result content because that is the only channel its API offers) — rejected: it makes the logged `tool/result` lie about what the tool returned, and `additionalContext` exists precisely as the separate sanctioned channel for post-execute commentary, with loop-level buffering that preserves call/result adjacency.
|
||||
- **Append the reminder into the tool result** (`accept` with replaced `content` — the pi extension's mechanism, which patches result content because that is the only channel its API offers) — rejected: it makes the logged `tool/result` lie about what the tool returned, and `additionalContexts` is the separate sanctioned channel for post-execute commentary, with loop-level buffering that preserves call/result adjacency.
|
||||
- **Count in `tools/pre-execute` with a pending-reminder map** (the pi two-phase shape) — rejected: post-execute alone sees `(exec, result)` together and also fires for denied calls, so one listener with no cross-event state covers strictly more attempts with less machinery.
|
||||
- **Escalate to `block` at the highest threshold** — rejected for the initial scope: a blocked call punishes legitimate identical repeats (polling a long-running terminal, re-checking a file the agent expects to change), and an advisory reminder keeps the model in control. Revisit with evidence; the decision shape (`PostToolDecision`) already supports it.
|
||||
- **A per-deployment external hook via the CC/Codex bridges** (a `PostToolUse` script) — rejected as the answer: it works for one deployment, but a shipped, unit-tested, `cordis.yml`-configurable plugin is the harness-native form, without per-call subprocess cost.
|
||||
@@ -65,7 +65,8 @@ Reminders use `additionalContext` with the plugin source, preserving the origina
|
||||
|
||||
- The reminder is advisory by design: idempotent polling patterns that repeat identical calls on purpose still receive nudges past the thresholds, and the pressure valves are config (`thresholds`, `exclude`) plus reminder text that explicitly allows finishing when enough evidence has been gathered. Each trigger costs reminder tokens on the next request; thresholds bound the frequency.
|
||||
- Chain state is in-memory only: a session resumed from persistence starts with a fresh chain, so a loop spanning a resume draws its reminders later than a live one — accepted, the guard is a heuristic nudge, not a logged invariant, and persisting counter state would buy little for real complexity.
|
||||
- When multiple post-execute producers attach context on one call, the fold concatenates under the guard's `source`; ordering between plugins follows listener registration order. The seam cannot represent mixed provenance — a limit inherited from `HookContext`, not owned by this plugin.
|
||||
- When multiple post-execute producers attach context on one call, each contribution stays a separate `HookContext`; ordering follows waterfall nesting and each entry retains its own provenance.
|
||||
- Implementing the snapshot tier surfaced a hidden assumption in the suite kit: the fixture guard equated "authored model scenario" with "override-driven". The `Scenario` table now carries an explicit `overridden` flag, and the sidecar's presence is checked BOTH ways against it (an unregistered stray sidecar would silently replace the derived script) — the suite kit is stricter than it was before this plugin existed.
|
||||
|
||||
## Deferred
|
||||
|
||||
|
||||
@@ -0,0 +1,166 @@
|
||||
# RFC: Bash-backed grep and glob discovery tools
|
||||
|
||||
Status: implemented
|
||||
|
||||
## Problem
|
||||
|
||||
The harness needs model-facing `glob` and `grep` tools, but making them `ctx.fs` provider methods turns a local product convenience into a universal filesystem backend contract. Local workspace discovery is naturally a process-backed `rg` workflow; remote or virtual filesystem backends may expose their own search API, may not share a local `ripgrep` view, or may not support discovery at all. The v1 should not require every filesystem backend to implement search before the file read/write/edit seam has proven that need.
|
||||
|
||||
Search output also has two distinct budgets. The tool needs enough raw `rg` output to compute a stable logical result, but the model should receive only a bounded preview plus a recovery path when the formatted result is larger than the inline budget. The generic spill policy only sees the final tool result, so it cannot recover matches that a search tool already omitted. Search therefore needs tool-owned retention and best-effort formatted-result spill.
|
||||
|
||||
## Decision
|
||||
|
||||
`glob` and `grep` are model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, backed by the bash seam, not by new `ctx.fs` provider methods. The package registers model-facing filesystem discovery tools, but execution uses `ctx.bash.resolve(request)` followed by `ctx.bash.run(spec)` with fixed `rg` command templates assembled by the tool. The tool layer owns schemas, argument validation, shell quoting, result parsing, result formatting, retention, formatted-result spill handoff, and timeout declaration. The bash executor owns request defaulting/capping, subprocess execution, process-group termination, environment scrubbing, raw output capture, and backend substitution across local, sandboxed, or remote bash implementations.
|
||||
|
||||
The tools do not use `ctx.bash.start()` and do not create model-visible background tasks. They run as ordinary foreground tools from the agent loop's perspective: the tool call returns only after the `rg` command exits, times out, is aborted, or fails. `defineTool({ timeoutMs })` declares the cooperative tool-call budget, `@deepseek-ai/dsh-timeout-policy` enforces it through `exec.signal`, and the tool forwards that signal into the bash request before `resolve()` / `run()`. The bash backend's own timeout remains a second safety cap; whichever aborts first wins.
|
||||
|
||||
The tools align `path` with Claude Code's search tools while binding resolution to the bash workdir, not to `ctx.fs`. The tool derives the bash request workdir from `exec.agent?.session.header.cwd`, mirroring `dsh-tool-bash` and `dsh-tool-fs`; when no session cwd exists, it omits `request.workdir` so the bash implementation applies its configured cwd or process cwd through `resolve()`. For `grep`, `path` is an optional ripgrep target and may be a file or directory; omitted means the resolved bash workdir. For `glob`, `path` is an optional directory search root; omitted means the resolved bash workdir. Relative `path` values resolve against that workdir. Returned paths are displayed relative to the resolved bash workdir when possible and are intended to be follow-up-readable only in co-located deployments where the bash workdir and filesystem `read` root are the same workspace. v1 documents that deployment requirement but does not perform runtime cross-service validation. Remote or virtual filesystem search is deferred until there is a shared workspace/root contract or a provider-specific search backend.
|
||||
|
||||
The package does not inject `fs`. It injects `tools`, `systemPrompt`, and `bash`; it deliberately reads `spillStore` with `ctx.get('spillStore')` instead of static inject because formatted-result spill is optional. Existing `@deepseek-ai/dsh-tool-fs` deployments that only want `read` / `write` / `edit` do not need to load bash.
|
||||
|
||||
### Package shape
|
||||
|
||||
The v1 package stays small. Inside `@deepseek-ai/dsh-tool-fs-search`, the source layout is:
|
||||
|
||||
```text
|
||||
src/index.ts
|
||||
src/glob.ts
|
||||
src/grep.ts
|
||||
src/search-core.ts
|
||||
src/shell-quote.ts
|
||||
```
|
||||
|
||||
`glob.ts` and `grep.ts` own their parameter validation, command construction, result parsing, formatting, and registration. `shell-quote.ts` is one shared helper because shell quoting is the safety boundary both tools must use; `search-core.ts` is the other (an implementation-time amendment to the original four-file plan): the `SEARCH_*` error vocabulary, the bash-run + raw-output acquisition, the formatted-spill handoff, and workdir-relative display are byte-identical between the two tools, and duplicating that delicate plumbing per tool is exactly the missed extraction the symmetry convention flags. Command builders must not hand-roll quoting or concatenate unquoted model-controlled values into the shell command.
|
||||
|
||||
### Schemas and config
|
||||
|
||||
`glob` exposes the small discovery shape:
|
||||
|
||||
```ts
|
||||
interface GlobArgs {
|
||||
pattern: string
|
||||
path?: string
|
||||
}
|
||||
```
|
||||
|
||||
`grep` exposes the OpenCode-style minimal shape:
|
||||
|
||||
```ts
|
||||
interface GrepArgs {
|
||||
pattern: string
|
||||
path?: string
|
||||
include?: string
|
||||
}
|
||||
```
|
||||
|
||||
Routine budgets stay out of the model-facing schema. `@deepseek-ai/dsh-tool-fs-search` owns these defaulted, validated config fields:
|
||||
|
||||
| Field | Default | Role |
|
||||
|---|---:|---|
|
||||
| `globMaxResults` | `100` | Max paths retained inline; matches Claude Code's default `GlobTool` result limit. |
|
||||
| `grepMaxMatches` | `250` | Max flat matches retained inline; matches Claude Code's default `GrepTool` `head_limit`. |
|
||||
| `grepMaxLineBytes` | `2000` | Max bytes retained for one matched-line preview, applied with `TextRetainer({ kind: 'head', maxBytes: grepMaxLineBytes })`. |
|
||||
| `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.
|
||||
|
||||
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 `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.
|
||||
|
||||
`include` is one positive glob filter, not a list and not an exclude syntax. Reject comma-separated or negated include patterns up front with a structured argument error. Every model-controlled value used in a shell command, including `pattern`, `path`, and `include`, must pass through the package-private shell quoting helper.
|
||||
|
||||
### Execution
|
||||
|
||||
`glob` builds a fixed `rg --files` command rooted at the resolved directory search root (`path` when supplied, else the bash workdir): `rg --files --glob <pattern> --sort=modified --no-ignore --hidden`, plus VCS metadata excludes for `.git`, `.svn`, `.hg`, `.bzr`, `.jj`, and `.sl`. This aligns with Claude Code on hidden/ignored-file discovery and modified-time ordering while keeping VCS internals out of broad searches. The tool parses one path per line, maps results back to paths relative to the bash workdir when possible, pushes each path into `ItemRetainer({ kind: 'head', maxItems: globMaxResults })`, and formats the full sorted path list for a spill artifact when the retained result is capped.
|
||||
|
||||
`grep` builds a fixed line-oriented `rg --json` command against the supplied file/directory target (`path` when supplied, else the bash workdir) so file path, line number, and line text are parsed without colon-splitting ambiguity. It consumes `match` records, treats malformed JSON or malformed match records as `SEARCH_FAILED`, maps result paths relative to the bash workdir when possible, applies per-line preview retention with `grepMaxLineBytes`, pushes each match into `ItemRetainer({ kind: 'head', maxItems: grepMaxMatches })`, then groups only the retained preview matches by file for inline output. The spill artifact stores the full formatted match list, not only the omitted tail, so the retrieval hint points at the same logical result the model saw.
|
||||
|
||||
Raw `rg` stdout is an internal transport detail. The tool requests `stdoutMaxBytes: rawOutputMaxBytes` through `ctx.bash.resolve()` and parses `stdout.text` only when the executor returns untruncated stdout within that cap. If stdout is larger than `rawOutputMaxBytes`, or the executor still returns `stdout.truncated`, the tool fails with a clear search error telling the model to narrow `pattern`, `path`, or `include`. The tool never exposes raw `rg` output or bash raw spill paths to the model.
|
||||
|
||||
Only stdout is a parse source. Stderr is diagnostic text for invalid patterns, missing `rg`, and search failures; if bash truncates stderr, the tool uses the retained stderr tail with a truncation note and does not read `stderr.spillPath`.
|
||||
|
||||
If `ctx.bash.run()` reports `aborted` because the tool timeout or caller cancellation fired, the tool returns a structured failure rather than pretending there were no matches. If bash reports its own timeout first, the tool likewise fails with a clear timeout message. Nonzero ripgrep exit semantics are tool-owned: exit 0 is success with matches, exit 1 is success with no matches, invalid pattern / missing `rg` / inaccessible search workdir are failures.
|
||||
|
||||
Search failures use a package-owned `HarnessError` subclass with `SEARCH_*` codes, not `FsErrorCode`, because these tools are not `ctx.fs` provider operations. The v1 vocabulary is `SEARCH_INVALID_PATTERN`, `SEARCH_FAILED`, `SEARCH_RAW_OUTPUT_OVERFLOW`, and `SEARCH_ABORTED`. Model argument validation failures such as missing required fields, blank strings, or unsupported negated/list `include` values remain ordinary tool argument errors.
|
||||
|
||||
### Formatted result spill
|
||||
|
||||
`ctx.spillStore` is optional and used only for model-facing formatted results. This is the first tool-owned spill call pattern in the codebase, and it is intentional because search retention is item-level policy: `globMaxResults` caps paths and `grepMaxMatches` caps matches while the tool still holds the complete logical result. The generic `dsh-spill-policy` caps final text bytes on `tools/post-execute`; by then a search tool would already have omitted later paths or matches, so the policy cannot recover them.
|
||||
|
||||
When a search produces more logical results than the inline cap and `ctx.spillStore` is present, the tool saves the complete formatted result with `saveText()`. The spill owner is the calling agent's session header id (`exec.agent?.session.header.id`); without that owner, the search keeps the inline result and reports that the complete result could not be saved. The spill source is the tool execution identity: `{ toolName: exec.name, callId: exec.callId, label: 'result' }`. The suggested filenames are `grep-results.txt` and `glob-results.txt`; the spill backend still treats them as hints, never paths.
|
||||
|
||||
When spill storage is absent, the call has no session owner, or saving fails, the tool still returns the inline page and a footer explaining that the complete result could not be saved. Search success must not turn into an `isError` result solely because formatted-result spill storage is unavailable.
|
||||
|
||||
The bash raw output stream and the formatted search spill artifact are different artifacts. Raw `rg` stdout is parsed only in memory within the requested bash stdout cap; the formatted spill artifact is the stable model-facing recovery locator produced by `ctx.spillStore.saveText()`.
|
||||
|
||||
### Result shape
|
||||
|
||||
A capped `glob` result with successful formatted spill returns the inline page and a spill notice:
|
||||
|
||||
```text
|
||||
<first N paths>
|
||||
|
||||
(Showing N of M paths. Full sorted result stored at: /.../session-abc123/9f8e7d-glob-results.txt. Use read with offset/limit, or grep this path to search within it.)
|
||||
```
|
||||
|
||||
A capped `grep` result with successful formatted spill returns grouped preview matches and a spill notice:
|
||||
|
||||
```text
|
||||
Found N of M matches
|
||||
|
||||
<file>
|
||||
Line 12: ...
|
||||
|
||||
(Full grep result stored at: /.../session-abc123/9f8e7d-grep-results.txt. Use read with offset/limit, or grep this path to search within it.)
|
||||
```
|
||||
|
||||
If the complete logical result fits under the inline cap, no formatted spill artifact is created. If the complete logical result is too large but formatted spill is unavailable, the footer says that the result was capped and the complete result could not be saved. The `truncated` / omitted count is a budget fact, not an incomplete-search fact; timeout, invalid regex, missing `rg`, inaccessible workdirs, raw-output overflow, binary skips, and parse failures stay in tool-domain error or incomplete fields.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**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.
|
||||
|
||||
**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.
|
||||
|
||||
**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.
|
||||
|
||||
**Expose Claude Code's full `GrepTool` schema.** Rejected for v1: `output_mode`, context flags, multiline, `head_limit`, `offset`, `case_insensitive`, and type filters make the model-facing surface into a ripgrep wrapper. This harness keeps routine budgets and continuation mechanics in deployment policy and spill artifacts.
|
||||
|
||||
**Keep early-stop search and skip formatted spill artifacts.** Rejected for this proposal: early stop is more efficient but gives the model no path to inspect later results. The chosen v1 optimizes result recoverability and implementation simplicity, with `timeoutMs`, `rawOutputMaxBytes`, bash backend caps, and formatted spill artifacts as safety backstops.
|
||||
|
||||
**Expand the bash seam with a raw-output reader first.** Rejected: a portable `readRawOutput(ref, maxBytes)` API would add reference lifetime, permission, and backend storage semantics. A per-run `stdoutMaxBytes` request is the narrower seam: search either receives complete stdout within `rawOutputMaxBytes` or fails clearly.
|
||||
|
||||
## Testing
|
||||
|
||||
- Tests prove an aborted `exec.signal` reaches the bash backend (same-reference spec assertion plus the `SEARCH_ABORTED` result), and cover command construction/quoting (malicious patterns, paths with spaces, leading-dash values, quotes, newlines, glob metacharacters — unit assertions plus a real `bash -c` round-trip for every hostile value), `grep.path` as file and directory targets, `glob.path` as a directory search root, invalid pattern handling, no matches, malformed `rg --json` output, matched-line preview truncation, raw-output overflow, timeout/abort, formatted spill success/failure, the package-owned `SEARCH_*` error codes, and the no-background-task invariant.
|
||||
- The first-party tool-owned spill precedent is covered directly: spill backend present, spill backend absent, `saveText()` failure, and missing spill owner.
|
||||
- The package has real Loader-path coverage for the namespace plugin export shape (`name`, `inject`, `Config`, and `apply`, with no default export).
|
||||
- A real-executor integration suite (`dsh-bash-local` + a real `rg`) verifies the world: hostile patterns stay inert, per-session cwd resolution, VCS-metadata exclusion, modification-time ordering, and real ripgrep stderr classification. It self-skips where `rg` is not on PATH (a CI accommodation mirroring the keyless e2e skip); the fake-executor suite alone carries the per-file 100% coverage gate.
|
||||
- Snapshot gap note for the transcript-visible spill notice: this landed with the gap note, not a snapshot. The snapshot tier replays the acp-agent tree, and adding the search plugin there changes the assembled system prompt — every golden would need re-recording with a real key, which the implementing environment did not hold. The spill notice's exact transcript text is pinned by unit tests (`formatGlobOutput`/`formatGrepOutput` and the through-the-registry spill tests); wiring the plugin into the acp-agent tree plus a `test:snapshot:record` pass is the follow-up for the next key-holding session.
|
||||
|
||||
## Consequences
|
||||
|
||||
- `glob` and `grep` are model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, not `ctx.fs` provider methods and not part of the existing `@deepseek-ai/dsh-tool-fs` root plugin. The package injects `tools`, `systemPrompt`, and `bash`; it does not inject `fs`, and `ctx.spillStore` stays optional via `ctx.get('spillStore')`.
|
||||
- The schemas are exactly `glob(pattern, path?)` and `grep(pattern, path?, include?)`; search caps and timeout are defaulted, validated Config fields (`globMaxResults`, `grepMaxMatches`, `grepMaxLineBytes`, `rawOutputMaxBytes`, `timeoutMs`).
|
||||
- The tools execute through `ctx.bash.resolve(request)` → `ctx.bash.run(spec)`, forward `exec.signal`, never call `ctx.bash.start()`, and never expose a bash task id. The bash request workdir comes from `exec.agent?.session.header.cwd` when available; the resolved `spec.workdir` drives execution and relative-path display.
|
||||
- The tools request `stdoutMaxBytes: rawOutputMaxBytes` from the bash seam, parse only untruncated stdout within that cap, and treat over-cap or still-truncated raw output as a clear search failure; raw `rg` output is never exposed to the model.
|
||||
- Oversized complete formatted results are saved through `ctx.spillStore.saveText()` when available while inline results stay bounded; spill failure, a missing backend, or a missing owner preserves the inline result and reports the unsaved remainder — never an `isError`.
|
||||
- The package README, the generated config catalog, and exported JSDoc document the Config fields and `SEARCH_*` codes; the coding-agent example ships the tools (the acp-agent tree waits on the snapshot re-record above); the fs group README records the co-located bash/filesystem deployment requirement.
|
||||
|
||||
## Risks
|
||||
|
||||
Full-run `grep` can be slower than an early-stop search on broad patterns. The v1 accepts that cost for simpler implementation and complete-result recovery, bounded by tool timeout, bash timeout, `rawOutputMaxBytes`, and output caps. If this proves too slow, the direct-ripgrep or foreground-streaming alternatives remain available.
|
||||
|
||||
Shell command construction is the sharpest safety edge. Because `ctx.bash` accepts a command string rather than an argv vector, the implementation must centralize shell quoting and test malicious patterns, paths with spaces, leading-dash patterns, quotes, newlines, and glob metacharacters.
|
||||
|
||||
The v1 assumes a co-located bash/filesystem deployment. If bash searches one workspace and the `read` tool resolves paths against another, returned paths may not be follow-up-readable. The package documents this requirement but does not verify it at runtime.
|
||||
|
||||
Spill locators are backend-owned. The current local backend returns local filesystem paths and works in deployments where `read`/`grep` can open those files; remote or workspace-confined deployments can use a backend whose locator and retrieval hint point at a supported retrieval mechanism.
|
||||
@@ -0,0 +1,85 @@
|
||||
# RFC: Expose agent session identity and JSONL location to tools and hooks
|
||||
|
||||
Status: implemented
|
||||
|
||||
## Problem
|
||||
|
||||
An agent can identify its workspace through `session.header.cwd`, but a model using bash cannot reliably identify the session that owns the call or the durable transcript that records it. Searching `./.sessions` guesses deployment config and JSONL layout; custom roots, alternate persistence backends, resume, forks, and concurrent parent/child agents make that guess unreliable. Hooks have the same need for transcript location, while future plugins may need to expose other harness-owned environment facts to shell commands.
|
||||
|
||||
The boundary must preserve two properties: the owner of a fact decides how to resolve it, and every child receives a per-execution snapshot rather than process-global mutable state. In particular, a nested harness must not leak its ambient `DSH_*` values into a child whose current agent, persistence backend, or configuration differs.
|
||||
|
||||
## Decision
|
||||
|
||||
Extend the [`SessionPersistence`](../../implemented/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'
|
||||
|
||||
interface SessionLocation {
|
||||
readonly kind: string
|
||||
readonly path: string
|
||||
}
|
||||
|
||||
interface SessionPersistence {
|
||||
locate(meta: SessionHeader): SessionLocation | undefined
|
||||
}
|
||||
```
|
||||
|
||||
`path` is an absolute local path to the backend's dedicated log for `meta`; `kind` identifies the representation. JSONL returns `{ kind: 'jsonl', path }` using its resolved root and path helpers. SQLite and any backend without an honest local per-session artifact return `undefined`. The query creates and flushes nothing, so it can report a lazy target path before that file exists.
|
||||
|
||||
The model-facing bash package owns a `ctx.bashEnv` registry. A contributor declares its stable name, every `DSH_*` key it may return, a description for each key, and `resolve(execution: ToolExecution)`. Duplicate contributor names, duplicate key ownership, reserved keys, malformed declarations, undeclared runtime output, and non-string output fail loudly. Registration is a Cordis effect and is removed with the contributing plugin fiber. `list()` exposes declarations without running resolvers, keeping the environment surface enumerable for diagnostics and future prompt/UI consumers.
|
||||
|
||||
The registry rebuilds a trusted overlay for every foreground and background bash `ToolExecution`:
|
||||
|
||||
- `DSH_HOME` is always the absolute configured Harness home. The standalone [`@deepseek-ai/dsh-home`](../../../../packages/util/home/README.md) utility owns its precedence: explicit `dshHome`, then ambient `$DSH_HOME`, then `~/.dsh`.
|
||||
- `DSH_SHELL=1` is always present and identifies a model bash child managed by DeepSeek Harness.
|
||||
- `DSH_SESSION_ID` is present when the execution has an agent and equals `agent.session.header.id`.
|
||||
- The built-in persistence translator contributes `DSH_SESSION_JSONL` only when `ctx.sessionPersistence.locate(header)` returns `kind: 'jsonl'`.
|
||||
|
||||
Session persistence remains the fact owner: JSONL does not depend on tool-bash or register shell variables itself, and hooks continue to consume `locate()` directly. Tool-bash is the translation layer from the persistence fact into a shell convention. Other plugins that need shell-visible facts depend on the registry and register their own keys; they do not modify `process.env`.
|
||||
|
||||
The bash seam exports `DSH_ENV_PREFIX` as the single namespace source and derives `DshEnvironmentKey` from its `typeof`. Tool-bash derives built-in names and model guidance from that constant, while executors use it for filtering and channel validation. The seam carries the managed overlay separately as `BashExecRequest.dshEnv` / `BashExecSpec.dshEnv`. Ordinary `env` remains the general in-process plugin surface used by hooks, but cannot contain managed keys; symmetrically, `dshEnv` cannot contain ordinary keys. The local executor rejects either wrong channel before spawn, removes every inherited ambient managed key, applies its ordinary scrub/terminal environment/explicit `env`, and finally merges the trusted `dshEnv` snapshot. This guarantees that a missing value means absent now rather than inherited from an outer or previous harness. The model-facing tool still ignores model-supplied `env`/`stdin` arguments.
|
||||
|
||||
The bash tool description teaches only the durable convention: current harness environment facts are available through managed `$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.
|
||||
|
||||
## Peer product findings
|
||||
|
||||
Peer products separate stable identity from physical storage. Codex injects stable `CODEX_THREAD_ID` into spawned shells while recorder and hook surfaces own transcript paths. Claude Code supplies `session_id` and `transcript_path` as structured hook/status input. OpenCode carries identity in structured tool context; Kimi Code expands a session placeholder; Reasonix keeps the active session path on its controller. The portable rule is to inject identity at the invocation boundary, let storage resolve location, and never use a process-global current-session variable in a concurrent harness.
|
||||
|
||||
## Lifecycle and persistence semantics
|
||||
|
||||
A fresh session receives its id before the first turn, so its first bash call can read `DSH_SESSION_ID` and a JSONL target. The JSONL file may still be absent until the first successful turn-end checkpoint, and during an open turn it contains only the last flushed prefix. `DSH_SESSION_JSONL` is a location hint, not an authorization credential or freshness guarantee.
|
||||
|
||||
Resume reuses the loaded header and therefore the same id and location. Fork and spawn create new session ids and locations. Parent and child calls resolve from their own `ToolExecution.agent`; each command receives an immutable snapshot even when calls overlap. A persistence service replacement affects later collections because the translator queries `ctx.get('sessionPersistence')` at execution time; the registry itself is effect-scoped and HMR-safe.
|
||||
|
||||
`dshHome` is session-independent deployment context. Agent-core resolves one value through `@deepseek-ai/dsh-home` and routes it to both tool-bash and local skill discovery; standalone consumers call the same resolver. If top-level `dshHome` and `skills.local.dshHome` are both supplied and resolve differently, composition fails instead of exposing contradictory homes. Persistence may change independently without freezing its facts into the session prefix.
|
||||
|
||||
## Testing
|
||||
|
||||
Unit coverage pins registry declaration validation, effect disposal, per-execution collection, the `dshHome` precedence, and the local executor's `DSH_*` scrub/rebuild order. Request-recording tests cover foreground/background snapshots, no-agent calls, absent/JSONL persistence, ignored model `env`, and parent/child isolation. JSONL/SQLite locator contract tests and both hook bridge suites pin available and unavailable transcript dialects.
|
||||
|
||||
A keyless full-loop integration drives the real agent loop, JSONL persistence, tool-bash, and bash-local on the first turn. The child prints `DSH_HOME`, `DSH_SHELL`, session id, JSONL target, and an inherited stale sentinel; the test verifies current values, absence of the stale variable, pre-flush file absence, and the eventual persisted header. Snapshot coverage pins the generic bash description in the recorded request header. No with-key test is required because the contract is deterministic local execution rather than model choice.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Only an id plus `find`.** Search cannot know a custom root or backend layout and races under multiple sessions.
|
||||
|
||||
**Only an absolute path.** A path can be unavailable, lazy, or representation-specific and is not stable session identity.
|
||||
|
||||
**Global `process.env`.** Concurrent agents would overwrite one another and nested harnesses would inherit stale current-session values.
|
||||
|
||||
**Put persistence instructions in the session prefix.** A session prefix is frozen while the active service can change across HMR or future backend switching; persistence-specific guidance would become stale.
|
||||
|
||||
**A typed waterfall event.** Listeners cannot declare ownership without running, and later listeners can silently overwrite keys. A registry detects key conflicts at registration and remains enumerable.
|
||||
|
||||
**Have each persistence backend register bash env directly.** That reverses the dependency from storage into one consumer and forces bash into deployments that do not use it. `locate()` is also still required by hooks.
|
||||
|
||||
**A model-facing `session_info` tool.** It adds schema and another call while bash already supplies the query surface; the registry generalizes to future environment facts without one tool per fact.
|
||||
|
||||
## Consequences
|
||||
|
||||
Every model bash child receives current Harness home and shell identity, and agent calls additionally receive stable session identity. JSONL-backed calls get an optional target path; non-file persistence omits it honestly. The complete `DSH_*` namespace inside these children is managed by the harness: ambient values are removed, current trusted values are re-added, and ordinary callers cannot use `env` to bypass ownership checks.
|
||||
|
||||
The namespace is discoverable but not secret. Paths can reveal configured roots, lazy targets can be absent or stale, and a command can override variables inside its own shell syntax. Consumers treat them as correlation and environment facts, verify transcript metadata when attribution matters, and rely on sandbox/filesystem policy rather than variable secrecy for authorization.
|
||||
@@ -4,13 +4,13 @@ Status: implemented
|
||||
|
||||
## Problem
|
||||
|
||||
Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source.
|
||||
Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, relationship tracing, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source.
|
||||
|
||||
Full-text search is related but materially larger. Designing provider registration, extraction, synchronization, invalidation, ranking, and cursor contracts before a real backend exists creates two speculative state machines: one in the interface service and another in the eventual database package.
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-session-query` owns `ctx.sessionQuery`, a small trusted exact-read service over one logical corpus. It exposes `listSessions()`, `listEvents(sessionId)`, and bounded `readEvent(request)`. It does not expose filters, lineage or provenance traversals, text extractors, search requests, provider registration, or derived-index synchronization.
|
||||
`@deepseek-ai/dsh-session-query` owns `ctx.sessionQuery`, a small trusted exact-inspection service over one logical corpus. It exposes `listSessions()`, `listEvents(sessionId)`, bounded `readEvent(request)`, `traceSession(sessionId)`, and `traceEvent(request)`. It does not expose filters, text extractors, search requests, provider registration, or derived-index synchronization. The separate [tracing decision](2026-07-13-session-query-tracing.md) owns lineage and event-relationship semantics.
|
||||
|
||||
The service observes the optional `ctx.sessionPersistence` binding dynamically but retains no persisted cache or invalidation listener. Each cross-corpus list asks the active backend for authoritative metadata, then overlays a fresh live-store list. Matching ids become one `SessionRecord`: the live header wins and `live`/`persisted` independently report source availability. Immutable header disagreement is `SESSION_QUERY_SOURCE_CONFLICT`.
|
||||
|
||||
@@ -18,13 +18,13 @@ An exact target read first checks the live store and snapshots the live header a
|
||||
|
||||
## Surface semantics
|
||||
|
||||
`dsh-session` exports `foldSurface(events)`, and `SurfaceManager` uses the same transition functions for its incremental cache. The fold returns detached current nodes and each replacement's actual removed seqs. `listEvents()` uses that result to classify every raw event as `current`, `shadowed`, or `log-only`, so inspection cannot disagree with model-history derivation about positional replacement semantics.
|
||||
`dsh-session` exports `foldSurface(events)`, and `SurfaceManager` uses the same transition functions for its incremental cache. The fold returns detached current nodes and each replacement's actual removed seqs. `listEvents()` and `traceEvent()` use that result to classify every raw event, so inspection cannot disagree with model-history derivation about positional replacement semantics.
|
||||
|
||||
`readEvent()` returns the complete target plus raw neighbors by contiguous seq. `before` and `after` default to zero and are independently bounded by `readWindowMax`, default 50. The result carries a cloned `SessionHeader`, not a source-availability record, because determining a live target's persisted flag would violate the guarantee that live exact reads do not depend on persistence health.
|
||||
|
||||
## Security boundary
|
||||
|
||||
The service is context-wide trusted infrastructure, not an authorization layer. A future model-facing history tool or human UI applies explicit caller/session scope. This phase adds no model-facing tool and changes no transcript or snapshot surface.
|
||||
The service is context-wide trusted infrastructure, not an authorization layer. A future model-facing history tool or human UI applies explicit caller/session scope. The service adds no model-facing tool and changes no transcript or snapshot surface.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
@@ -32,10 +32,9 @@ The service is context-wide trusted infrastructure, not an authorization layer.
|
||||
- **Query only persistence** — rejected because checkpoints can lag the current live log.
|
||||
- **Cache persisted metadata and listen for writes/removals** — rejected because exact reads can ask the authoritative sources directly, while cache invalidation adds lifecycle and concurrency state before scale requires it.
|
||||
- **Define a provider-neutral search protocol now** — rejected because no provider consumes it. The first SQLite FTS package should own one reconciliation/transaction state machine; a smaller shared seam can be extracted later only when a second implementation proves the boundary.
|
||||
- **Include lineage, provenance, and generic filters in phase one** — rejected because no current consumer requires them and canonical logs remain sufficient to add them with evidence later.
|
||||
|
||||
## Consequences
|
||||
|
||||
Phase one has one source-resolution state variable: the currently mounted persistence service. There are no provider queues, fingerprints, extractor registries, observation generations, or derived index updates. Exact reads remain usable in live-only deployments and deterministic when persistence is present.
|
||||
The service has one source-resolution state variable: the currently mounted persistence service. There are no provider queues, fingerprints, extractor registries, observation generations, or derived index updates. Exact reads and event traces remain usable in live-only deployments and deterministic when persistence is present.
|
||||
|
||||
Cross-corpus listing and persisted exact reads perform backend I/O on each call. That is deliberate: correctness comes from current authoritative state, and scale-oriented search belongs to the phase-two database. Full-text search is unavailable until that package defines and implements its complete contract.
|
||||
Cross-corpus listing, lineage tracing, and persisted event operations perform backend I/O on each call. That is deliberate: correctness comes from current authoritative state, and scale-oriented search belongs to the proposed database package. Full-text search is unavailable until that package defines and implements its complete contract.
|
||||
@@ -0,0 +1,34 @@
|
||||
# RFC: Session query relationship tracing
|
||||
|
||||
Status: implemented
|
||||
|
||||
## Problem
|
||||
|
||||
Session relationships are encoded across immutable headers, positional surface operations, and logged provenance arrays. A consumer reconstructing those relationships directly would need to duplicate corpus precedence, surface folding, malformed-log handling, deterministic lineage ordering, and cloning. Positional replacement and provenance are different graphs, so collapsing them into one generic edge type would also lose meaning.
|
||||
|
||||
## Decision
|
||||
|
||||
`ctx.sessionQuery` exposes `traceSession(sessionId)` and `traceEvent({ sessionId, seq })` alongside its exact reads. Both are one-shot views over the existing live-preferred corpus: session tracing consumes one complete corpus listing, while event tracing consumes one loaded logical log and one canonical surface fold. The service retains no lineage, reverse-index, or replacement state after a call.
|
||||
|
||||
`SessionLineageTrace` returns the target, known parents in immediate-to-outward order, and recursive descendant trees whose siblings sort by creation time and then session id. `complete: true` carries the known root; `complete: false` carries the first unresolved parent id. A cycle connected to the target fails with `SESSION_QUERY_INVALID_LINEAGE`.
|
||||
|
||||
`SessionEventTrace` keeps positional and provenance relationships separate. `replacedBy` is the immediate positional replacer, `replacementChain` follows replacers to the final node, and `replacedEventSeqs` lists the actual surface nodes directly removed by the target. `sourceEventSeqs` preserves direct logged source order, while `derivedEventSeqs` lists later direct reverse references in log order. Provenance is not expanded transitively.
|
||||
|
||||
## Validation boundary
|
||||
|
||||
Event tracing checks target existence before surface analysis. Both event listing and tracing then use `dsh-session`'s one-pass surface fold, which accepts or rejects the loaded log as a whole: event seqs are zero-based and contiguous, surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is an earlier seq, and every positional replacement names and cites all surface nodes it removes. Every contract failure uses `SESSION_QUERY_INVALID_SURFACE`; there is no weaker classification-only surface standard.
|
||||
|
||||
All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Expose standalone tracing helpers** — rejected because the source-precedence and detachment boundary belongs to `ctx.sessionQuery`; public helpers would invite callers to bypass it.
|
||||
- **Combine replacement and provenance edges** — rejected because a positional replacement can shadow surface nodes while also citing non-surface construction inputs, and consumers need to distinguish those meanings.
|
||||
- **Return transitive provenance closure** — rejected because it obscures logged direct evidence, increases result size, and lets one malformed distant edge alter otherwise local output.
|
||||
- **Best-effort traces over malformed provenance** — rejected because a structurally plausible partial graph would look authoritative. Exact inspection fails loudly when the canonical relationship contract is broken.
|
||||
|
||||
## Consequences
|
||||
|
||||
Consumers receive deterministic relationship views without a cache or second corpus. Event tracing performs whole-log validation and allocation on each call, while lineage tracing lists the complete logical corpus on each call. Those costs keep the source of truth explicit and are separate from the content-bearing full-text-search and filtering API.
|
||||
|
||||
The feature has unit and service-level coverage but no snapshot or end-to-end fixture because it introduces no model-facing consumer, transcript change, or cross-process protocol.
|
||||
@@ -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: 105bf53550f087fdefb1e6fe0ec493f8628d3e18
|
||||
2026-07-14-time-context-plugin.zh.md: 60e9004b1453e75e1bcd84870ad7f18d200a95d8
|
||||
2026-07-14-time-context-plugin.md: aa24c6246718cfe0bb3ed63d0791cf890514d9fe
|
||||
2026-07-14-time-context-plugin.zh.md: e939ff1d0cb250f3fa7a7db34b50d92760e3374d
|
||||
@@ -6,6 +6,8 @@ English | [中文](2026-07-14-time-context-plugin.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The dynamic system-prompt storage and refresh decision in this record is superseded by [Durable per-step time context](2026-07-16-durable-per-step-time-context.md). The opt-in package, zoned formatting, and validation remain; the follow-up owns the current model-visible and durability contract.
|
||||
|
||||
An agent request has no live clock unless a deployment puts one in prompt text or gives the model a query tool. Static text becomes stale, while a tool call adds overhead to ordinary reasoning about dates, deadlines, or idle time. Without elapsed time, the model cannot distinguish an immediate follow-up from one sent hours after the preceding message.
|
||||
|
||||
Prompt assembly can derive both facts per step from durable session timestamps, and request-header logging can record the exact rendered value. Accumulating stale readings in conversation history or waking idle agents would violate the existing request lifecycle.
|
||||
|
||||
@@ -6,13 +6,15 @@ 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。
|
||||
|
||||
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。
|
||||
|
||||
提示词组装流程可以在每个步骤中根据持久会话时间戳派生这两项信息，请求头日志则可以记录实际渲染的确切值。在会话历史中累积陈旧读数或唤醒空闲 agent 都会违反现有请求生命周期。
|
||||
|
||||
## 决策
|
||||
|
||||
`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。`context/` 产品分组用于容纳既不定义工具、也不定义服务的有界请求上下文增强。`dsh-agent-spine-demo` 和仓库提供的示例都不会加载该 package；只有当 token 与信息披露成本可接受时，部署方才显式挂载它。
|
||||
`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。`context/` 产品分组用于容纳既不定义工具、也不定义服务的有界请求上下文增强。`dsh-agent-spine-demo` 和仓库提供的示例都不会加载该包；只有当 token 与信息披露成本可接受时，部署方才显式挂载它。
|
||||
|
||||
该插件注册顺序值为 10 的全局系统提示词区段 `context:time`，位置在部署方角色设定之后、工具指导之前。对于活跃轮次，它会输出带数字 UTC 偏移和 IANA 时区、形似 ISO 的时间戳，以及从轮次开始前最后一条模型可见消息起算的紧凑整秒时长。未绑定 agent 或 agent 处于空闲状态时，该区段为空。
|
||||
|
||||
@@ -46,7 +48,7 @@ agent loop（智能体循环）会在发送前通过 `request/header` 和 `reque
|
||||
- **省略配置时仍默认使用 UTC**——不予采纳，因为显式启用的时钟应跟随部署环境，除非运维方选择 UTC。需要 UTC 的部署仍可配置 `timeZone: UTC`。
|
||||
- **引入时区探测库**——不予采纳，因为 Node 的 `Intl` 运行时已经能够提供进程的 IANA 时区，而且额外依赖同样无法推断远程用户的时区。
|
||||
- **在 `dsh-agent-spine-demo` 中挂载插件**——不予采纳，因为时区、信息披露、token 预算和新鲜度都属于部署策略。选择加入能保持默认上下文稳定。
|
||||
- **将 package 放入 `core/`**——不予采纳，因为 `core/` 负责产品 API 主干，而该插件是没有服务键的可选叶节点。
|
||||
- **将包放入 `core/`**——不予采纳，因为 `core/` 负责产品 API 主干，而该插件是没有服务键的可选叶节点。
|
||||
|
||||
## 后果
|
||||
|
||||
|
||||
@@ -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
|
||||
2026-07-16-durable-per-step-time-context.md: 12d8191eb72b3fabd3164f13a77d9944631b906e
|
||||
2026-07-16-durable-per-step-time-context.zh.md: 977ffb7276011ac9ae9b8a72a726bb23baba0a2d
|
||||
@@ -0,0 +1,70 @@
|
||||
# RFC: Durable per-step time context
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-16-durable-per-step-time-context.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
A request-only clock can tell the model the current time, but replacing that value in the system prompt removes the evidence behind earlier time-sensitive reasoning. Multi-step turns need requests to retain the readings that shaped preceding steps. The request must remain reconstructable after restart, and automatic compaction must account for the same timing context the model receives.
|
||||
|
||||
A process-local refresh cache makes displayed time depend on state that cannot survive resume or be reconstructed from the durable session. Durable interval scheduling can reduce append frequency without introducing that hidden state.
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-time-context` is an opt-in function plugin in `packages/context/time-context/`. It registers a prepended `agent/pre-step` listener and, when an injection is due, calls `agent.inject()` for a pre-step attempt whose signal is not already aborted. The injected `context/message` carries source `{ kind: 'plugin', plugin: 'time-context' }` and append surface metadata; a suppressed attempt appends nothing.
|
||||
|
||||
The listener records preparation context before a possible `step/start`. Its prepended registration runs before ordinary automatic compaction listeners, so pressure estimation and any resulting surface rewrite observe a newly appended reading. A later pre-step listener can cancel or fail the attempt before the step opens; the reading remains because the durable log is append-only and this plugin performs no rollback.
|
||||
|
||||
The optional `timeZone` config resolves the Node process's IANA zone once at plugin load when omitted; an explicit value is validated by `Intl.DateTimeFormat`. The timestamp includes the numeric UTC offset and resolved IANA zone.
|
||||
|
||||
The optional `refreshIntervalMs` config is manually validated at plugin load as a non-negative safe integer. Omission or `0` injects on every eligible preparation attempt. A positive value scans the raw session events for the most recent `context/message` with this plugin's source and injects when none exists, wall time moved backward, or the event is at least the configured age. The raw event timestamp governs even after compaction shadows the message, so scheduling persists across turns and process resume without a timer or process-local cache.
|
||||
|
||||
### Text and elapsed baselines
|
||||
|
||||
An injected first-step reading is:
|
||||
|
||||
```text
|
||||
Time sampled while preparing turn <turn>, step 1: <timestamp>
|
||||
Elapsed since the preceding model-visible message: <duration-or-unavailable>.
|
||||
```
|
||||
|
||||
The baseline is the latest preceding user, assistant, tool-result, context, or steering message. This includes the accepted prompt that opened an ordinary message turn. If no model-visible message exists, the duration is `unavailable`.
|
||||
|
||||
An injected later-step reading is:
|
||||
|
||||
```text
|
||||
Time sampled while preparing turn <turn>, step <step>: <timestamp>
|
||||
Elapsed since the preceding step context: <duration-or-unavailable>.
|
||||
```
|
||||
|
||||
Their baseline is the durable event timestamp of the preceding time-context message in the same turn. If interval suppression leaves no earlier same-turn reading, the duration is `unavailable`. Duration formatting uses compact whole-second units and clamps backward wall-clock movement to zero. The explicit turn and step make every retained reading attributable to its historical preparation attempt after later turns append more context.
|
||||
|
||||
### Durability and request reconstruction
|
||||
|
||||
Each reading remains a normal surface node until compaction shadows it; positive interval scheduling never removes existing readings. A later request therefore sees the cumulative unshadowed readings that affected earlier preparation and steps, rather than a system-prompt value rewritten in place.
|
||||
|
||||
The plugin contributes nothing to system-prompt assembly. `request/header` and `request/header-delta` contain no time-context text; request reconstruction obtains the complete durable surface prefix at each `step/start`. Readings and requests need not map one-to-one because a failed preparation can leave a reading while interval suppression can prepare a request without appending one. The plugin depends on the agent registry for its lifecycle listener and does not require the system-prompt service at runtime.
|
||||
|
||||
## Testing
|
||||
|
||||
Unit and real-loop tests pin formatting, both elapsed baselines, interval omission and zero, threshold boundaries, cross-turn and per-session scheduling, backward-clock behavior, invalid config, resumed raw-event lookup after compaction, aborted-signal behavior, later-listener cancellation and failure, listener disposal, source and surface metadata, cumulative multi-step visibility, and absence from request headers. A keyless subprocess e2e boots the real Loader and stdio app, drives two turns, and verifies the persisted context events externally.
|
||||
|
||||
## Supersedes
|
||||
|
||||
This decision supersedes the dynamic system-prompt storage and refresh policy in [Optional time-context plugin](2026-07-14-time-context-plugin.md). It keeps the package location, opt-in deployment stance, timestamp formatting, process-zone default, and load-time validation. Durable history replaces the `context:time` prompt section, process-local refresh cache, and request-header deltas; `refreshIntervalMs` controls durable append frequency instead of prompt replacement.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Keep the dynamic system-prompt section and process-local refresh cache** — rejected because replacement erases earlier readings, cache state is not replayable, and a frozen request envelope would make the value stale for an entire loop instance.
|
||||
- **Replace the preceding context surface node** — rejected because replacement preserves the old node's position or shadows intervening conversation; neither represents when the new reading became visible.
|
||||
- **Inject from a background timer** — rejected because idle time has no pending request to consume the value, and timer-driven injection would create durable turns solely to report time passing.
|
||||
- **Expose time only through a tool** — rejected because ordinary temporal reasoning would require an avoidable tool round trip and would not guarantee a reading before every step.
|
||||
- **Use `agent/session-prefix`** — rejected because one loop-instance prefix cannot represent distinct step timestamps and does not accumulate historically attributable readings.
|
||||
|
||||
## Consequences
|
||||
|
||||
- Omission or `0` records every eligible preparation attempt; a positive interval reduces append frequency and history growth while preserving durable scheduling across resume.
|
||||
- Timing context remains append-only until compaction shadows older surface nodes, including a preparation reading left by a later cancellation or failure.
|
||||
- The first-step duration normally measures from the prompt that opened the turn, while later-step durations measure model and tool processing since the preceding step context.
|
||||
- An omitted `timeZone` still reflects the deployment process rather than a remote user, and elapsed time still uses durable harness append boundaries rather than client-origin timestamps.
|
||||
@@ -0,0 +1,70 @@
|
||||
# RFC: 持久的逐步骤时间上下文
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-16-durable-per-step-time-context.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
仅存在于请求中的时钟可以告诉模型当前时间，但在系统提示词中替换这个值会移除先前时效性推理所依据的证据。在包含多个步骤的轮次中，请求需要保留影响先前步骤的读数。系统必须能在重启后重建请求，自动压缩（compaction）也必须核算模型实际收到的同一份时间上下文。
|
||||
|
||||
进程本地刷新缓存使显示的时间依赖无法在恢复后保留、也无法从持久会话重建的状态。持久的间隔调度可以减少追加频率，而不引入这种隐藏状态。
|
||||
|
||||
## 决策
|
||||
|
||||
`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。它注册一个前置的 `agent/pre-step` 监听器，并在需要注入时，为信号尚未取消的预步骤尝试调用 `agent.inject()`。注入的 `context/message` 携带来源 `{ kind: 'plugin', plugin: 'time-context' }` 和追加表层元数据；受间隔抑制的尝试不会追加任何内容。
|
||||
|
||||
监听器在可能出现的 `step/start` 之前记录准备上下文。它采用前置注册，因此先于普通自动压缩监听器运行，使压力估算和由此产生的表层重写都能观察到新追加的读数。后续预步骤监听器可能在步骤开启前取消尝试或使其失败；持久日志仅追加，且本插件不执行回滚，因此该读数会保留下来。
|
||||
|
||||
省略可选配置 `timeZone` 时，插件在加载时解析一次 Node 进程的 IANA 时区；显式值由 `Intl.DateTimeFormat` 校验。时间戳包含数字 UTC 偏移和解析后的 IANA 时区。
|
||||
|
||||
插件在加载时手动校验可选配置 `refreshIntervalMs`，其值必须为非负安全整数。省略或设为 `0` 时，每次符合条件的准备尝试都会注入。设为正数时，插件扫描原始会话事件，查找来源属于本插件的最新 `context/message`；不存在此类事件、系统挂钟向后移动，或该事件已达到配置时长时，插件执行注入。即使压缩已隐藏消息，调度仍以原始事件时间戳为准，因此该机制无需计时器或进程本地缓存，也能跨轮次和进程恢复持续生效。
|
||||
|
||||
### 文本与时长基线
|
||||
|
||||
第一个步骤的注入读数为：
|
||||
|
||||
```text
|
||||
Time sampled while preparing turn <turn>, step 1: <timestamp>
|
||||
Elapsed since the preceding model-visible message: <duration-or-unavailable>.
|
||||
```
|
||||
|
||||
基线是前一条用户消息、助手消息、工具结果、上下文消息或 steering（中途引导）消息。对于普通消息轮次，这包括开启轮次的已接受提示词。如果不存在模型可见消息，时长为 `unavailable`。
|
||||
|
||||
后续步骤的注入读数为：
|
||||
|
||||
```text
|
||||
Time sampled while preparing turn <turn>, step <step>: <timestamp>
|
||||
Elapsed since the preceding step context: <duration-or-unavailable>.
|
||||
```
|
||||
|
||||
其基线是同一轮次中上一条时间上下文消息的持久事件时间戳。如果间隔抑制导致同一轮次中没有更早的读数，时长为 `unavailable`。时长采用紧凑的整秒单位，并在系统挂钟向后移动时钳制为零。显式的轮次号和步骤号使每个保留的读数在后续轮次追加更多上下文后，仍可归属于对应的历史准备尝试。
|
||||
|
||||
### 持久性与请求重建
|
||||
|
||||
每个读数都作为普通表层节点保留，直至压缩将其隐藏；正数间隔调度绝不会移除已有读数。因此，后续请求会看到影响先前准备过程和步骤且尚未被隐藏的累计读数，而不是一个被原地改写的系统提示词值。
|
||||
|
||||
插件不向系统提示词组装贡献任何内容。`request/header` 和 `request/header-delta` 不包含时间上下文文本；请求重建从每个 `step/start` 取得完整的持久表层前缀。读数与请求无需一一对应，因为失败的准备过程可能留下读数，而间隔抑制也可能使请求准备过程不追加读数。插件通过 agent 注册表使用生命周期监听器，运行时不需要系统提示词服务。
|
||||
|
||||
## 测试
|
||||
|
||||
单元测试和真实 agent loop（智能体循环）测试固定格式化、两种时长基线、间隔省略和零值、阈值边界、跨轮次和各会话独立调度、挂钟后退行为、无效配置、压缩后基于恢复会话的原始事件查找、已取消信号行为、后续监听器取消和失败、监听器 dispose（资源释放）、来源与表层元数据、多步骤累计可见性，以及请求头中不存在时间上下文。无密钥子进程 e2e 测试通过真实 Loader 和 stdio 应用启动，驱动两个轮次，并从外部校验持久化的上下文事件。
|
||||
|
||||
## 取代的决策
|
||||
|
||||
本决策取代[可选时间上下文插件](2026-07-14-time-context-plugin.md)中的动态系统提示词存储和刷新策略。它保留包位置、选择加入式部署、时间戳格式、进程时区默认值和加载时校验。持久历史取代 `context:time` 提示词区段、进程本地刷新缓存和请求头增量；`refreshIntervalMs` 用于控制持久追加频率，而非提示词替换。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
- **保留动态系统提示词区段和进程本地刷新缓存**——不予采纳，因为替换会抹去先前读数，缓存状态无法回放，而且冻结的请求内容集合会使该值在整个 agent loop 实例期间保持陈旧。
|
||||
- **替换前一条上下文表层节点**——不予采纳，因为替换会保留旧节点的位置或隐藏中间的会话内容；两者都不能表达新读数何时开始可见。
|
||||
- **通过后台计时器注入**——不予采纳，因为空闲期间没有待处理请求消费该值，而且计时器驱动的注入会仅为报告时间流逝而创建持久轮次。
|
||||
- **只通过工具提供时间**——不予采纳，因为普通时间推理会产生本可避免的工具往返，也不能保证每个步骤之前都有读数。
|
||||
- **使用 `agent/session-prefix`**——不予采纳，因为一个 loop 实例前缀无法表示不同的步骤时间戳，也不会累计具有历史归属的读数。
|
||||
|
||||
## 后果
|
||||
|
||||
- 省略 `refreshIntervalMs` 或设为 `0` 时，每次符合条件的准备尝试都会留下记录；正数间隔会减少追加频率和历史增长，同时使持久调度在恢复后继续生效。
|
||||
- 时间上下文仅追加并保留到压缩隐藏旧表层节点为止，其中也包括后续取消或失败所留下的准备读数。
|
||||
- 第一个步骤的时长通常从开启轮次的提示词起算，后续步骤的时长则反映自上一条步骤上下文以来的模型与工具处理时间。
|
||||
- 省略 `timeZone` 时仍采用部署进程而非远程用户的时区，时长仍采用 harness 的持久追加边界而非客户端来源时间戳。
|
||||
@@ -14,9 +14,9 @@ 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 concurrently and prints one timing/output block per gate.
|
||||
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 build gate makes the hook self-contained from a clean worktree. `publint` and `verify-node-next-types` wait for that build output, while source-only gates continue in parallel.
|
||||
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.
|
||||
|
||||
[scripts/publint-all.ts](../../../../scripts/publint-all.ts) discovers the package list from `packages/<group>/<pkg>` and runs `publint` with a worker pool sized from `availableParallelism()`. `DSH_PUBLINT_CONCURRENCY` can cap or raise the worker count for local machines and CI runners with different resource profiles. Results are buffered per package and printed in deterministic package order, so parallel execution does not scramble each package's log block.
|
||||
|
||||
|
||||
@@ -35,7 +35,7 @@ This RFC decided the four-layer split, the provider contract, and the freshness
|
||||
`@deepseek-ai/dsh-fs` shrinks to provider text IO plus guarded text mutation:
|
||||
|
||||
```ts ignore-check
|
||||
abstract resolve(path: string): Promise<FsTarget>
|
||||
abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget>
|
||||
abstract stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined>
|
||||
abstract readText(target: FsTarget, signal?: AbortSignal): Promise<string>
|
||||
abstract streamText(target: FsTarget, signal?: AbortSignal): Promise<AsyncIterable<string>>
|
||||
|
||||
@@ -0,0 +1,108 @@
|
||||
# RFC: Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall
|
||||
|
||||
Status: proposed
|
||||
|
||||
## Problem
|
||||
|
||||
Compaction is a one-way door. The summary the model sees carries no reference to what it shadows — the `shadowedRange` provenance lives only on the log-only `compact/summary` event — and no tool lets the model read a shadowed span back. Whatever the summarizer drops is gone from the model's reachable world, even though the append-only log holds every byte. Repeated compaction compounds this: the head checkpoint is rewritten every pass, so the request prefix takes a full prompt-cache miss each time, and earlier summaries are re-summarized generation after generation.
|
||||
|
||||
The root cause is one artifact playing two conflicting roles. An **index** wants to be frozen, chronological, and cheap; the model's **working memory** wants a global view, re-prioritization, and mutability. A single summary can be neither well.
|
||||
|
||||
No mainstream coding harness gives the model in-loop recall, and none of the surveyed implementations makes compaction prefix-cache-aware. An event-sourced session — originals durable, seq-addressable, replay-exact — is the natural substrate for both.
|
||||
|
||||
## Proposal
|
||||
|
||||
Split the checkpoint into two classes and make shadowed history reachable.
|
||||
|
||||
### Frozen index checkpoints
|
||||
|
||||
Newly stale history splits into chunks by deterministic policy: accumulate toward `chunkTokens`, snap edges to balanced tool-pairing cuts (`isToolPairingBalanced`), prefer turn boundaries, and place the final boundary as close to the retain boundary as balance allows, so the trailing slice shrinks to roughly one turn. Each chunk is compacted by one `compactRegion` call into an **index stub** (`stubTokens`, ~100–200 tokens):
|
||||
|
||||
- two or three lines of what happened;
|
||||
- a keyword line of low-frequency literal anchors — exact error strings, values, config keys — grouped by kind;
|
||||
- a code-composed footer: `[checkpoint c<summarySeq>: shadows conversation span #<start>–#<end>; originals retrievable via history_read]`. Pointers are assembled from provenance, never model-authored.
|
||||
|
||||
A committed stub is never rewritten and never re-enters a later compaction region. A stub call's input is layered: the fixed preamble and the byte-identical pass-start state checkpoint (the shared prefix across all calls in the phase), then the keyword lines of all previously committed stubs — so a new entry indexes what is distinctive to its chunk instead of repeating the directory — the one or two most recent committed stubs for chronological continuity, and the slice itself. Sibling stubs from the same pass are not inputs (the concurrent phase forbids it; turn-aligned boundaries carry local continuity instead), and the state checkpoint is background only, never material to summarize into the stub. A slice consisting of recalled content is stubbed by code alone — a pointer line, no LLM call. A failed stub call degrades the same way: its slice gets a code-only pointer stub and the pass continues, making the state rewrite the only hard LLM dependency in a pass.
|
||||
|
||||
### The state checkpoint
|
||||
|
||||
One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of today's summary.
|
||||
|
||||
An inflation guard bounds the whole pass: if the post-compaction size is not strictly below the pre-compaction size, nothing commits and the turn proceeds; the attempt defers until more stale history accumulates. The guard compares one metric on both sides — provider-reported usage from the request path, falling back to the character estimator on both sides.
|
||||
|
||||
### Pass execution
|
||||
|
||||
- Chunk slices are surface position ranges. A pass runs two phases: all summarize calls execute concurrently, buffered off-surface; then regions commit strictly left to right — chunks first, trailing slice last — so the state checkpoint lands after every stub through contiguous single-node replaces. Wall-clock stays near one summarize call.
|
||||
- The superseded state checkpoint folds into the next pass's first chunk as ordinary history: no tombstone, no new primitive. Its stub omits it, `history_read` renders it labeled `[prior state checkpoint]`, and its footer travels with the rendered text, keeping every trailing slice reachable through the two-hop chain.
|
||||
- Range selection is frozen-aware: the compactable span begins after the last committed index checkpoint, at the surface head only when none exists. A legacy session's existing head checkpoint is adopted as state-class — its text the merge base, its node folded like any superseded state.
|
||||
- A crash in the summarize phase commits nothing; a crash mid-commit leaves a left-to-right prefix committed, and the resumed pass reads its merge base from the log's latest state-class `compact/summary` event and commits the remaining regions unconditionally — restoring `[stubs…][state][tail]` outranks shrinking.
|
||||
|
||||
### The recall tools
|
||||
|
||||
A new package `@deepseek-ai/dsh-tool-recall` (consumer-only, over the `dsh-session` and `dsh-compact` vocabularies) registers two model-facing tools:
|
||||
|
||||
- `history_read(checkpoint, offset?)` — renders the shadowed span of any checkpoint in the log, including superseded ones, as `User:`/`Assistant:`/`Tool result:` transcript, paginated by a configured budget with a continuation cursor.
|
||||
- `history_search(query, checkpoint?, limit?)` — case-insensitive literal scan over every shadowed span; returns snippets with checkpoint ids and coverage metadata (`scanned`/`matched`/`truncated`). The zero-match hint notes the scan is literal and points at direct `history_read` of a plausible checkpoint.
|
||||
|
||||
Both read `exec.agent.session.events` (the tool-todo access pattern; non-agent callers rejected), render only surface-type message events, and return ordinary `tool/result`s — recalled bytes land at the context tail, logged, so reconstructability holds with no special casing. There is no new storage and no sidecar index: the session log is the archive, `compact/summary` provenance is the index metadata, and the tools are a read path over both. The tool schemas and the package's one system-prompt section are static strings; checkpoint ids reach the model only through footers. The transcript renderer moves from `compact-basic` into `dsh-session`, shared by summarizer and tools.
|
||||
|
||||
### Cache and cost
|
||||
|
||||
The request prefix after a pass is `[system][stubs…][state][tail]`. Frozen stubs are byte-stable across passes, so the miss begins at the token replacing the previous state checkpoint and stays O(new chunks + state + tail) — against position zero today. Recall output lands at the tail, leaving the prefix untouched. Per-pass summarize input is roughly twice today's plus an m·S background term, bounded by a `chunkTokens` floor (a small multiple of the state cap) and a validated `stubTokens`/`chunkTokens` ratio ceiling; a shared-prefix input layout (preamble, then the byte-identical pass-start state, slice content in the tail) lets sibling calls earn cached-rate rereads.
|
||||
|
||||
### Packaging
|
||||
|
||||
The design ships as a new backend `dsh-compact-recallable` on the existing `ctx.compact` seam, enabled by default in the shipped example configs; `compact-basic` remains as the reference implementation and the seam's design twin, in the pattern of the paired LLM adapters. The seam JSDoc's "at most one auto-generated checkpoint, always at the head" clause is relaxed to name both backend behaviors.
|
||||
|
||||
### Relation to in-flight work
|
||||
|
||||
- **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.
|
||||
- **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
|
||||
|
||||
Specified during review, deferred until observation calls for them:
|
||||
|
||||
- Guard degradation ladder (code-only rollup of the oldest stub prefix, footers preserved, rolled-up ids remain recall targets; then one summary after the frozen boundary) — on observed guard livelock or stub-region pressure.
|
||||
- Echo detection on stub outputs (sentence-scale n-grams, short literals exempt, retry then strip) — on observed division-of-labor leakage.
|
||||
- Periodic state refresh from chunk originals — on observed drift in the handoff probe.
|
||||
- `stateFallbackThreshold` (full-detail state prompt below a stub count) — on short-session regression.
|
||||
- Lazy registration of the recall tools — on measured context tax in never-compacting sessions.
|
||||
- Amortized stub drafting at pre-step: as soon as stale-but-uncompacted content accumulates past `chunkTokens`, draft that chunk's stub at the next pre-step (a log-only draft event, written while the chunk's surrounding context is still live) and let the compaction pass commit drafts instead of summarizing in bulk — the deterministic, replay-exact equivalent of background compaction (the Claude Code session-memory pattern; OpenClaw demonstrates the synchronous semantics are identical). Trigger: observed pass latency, or stub-quality gains from drafting near-live proving out.
|
||||
- Split summarizer models; model-chosen chunk boundaries; cross-session recall; semantic search fallback — each behind its own evidence.
|
||||
- Richer `history_search` query forms — regex, and structured queries over logged JSON tool results (sql/jq-style, or agent-authored queries against an indexed store) — on demand from observed search misses; literal matching ships first because the recall path stays a pure function of the log.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Staged delivery** (ship recall tools alone over today's backend; gate the checkpoint split on observed recall usage) — rejected: untrained models under-use any new tool, so the gate would measure training absence rather than design value, while the training side needs the complete mechanism to build environments against; the pre-release window is when persisted-format changes are cheapest; and the cache economics are first-party knowledge, not a hypothesis awaiting telemetry. The implementation still lands as stacked PRs with the recall tools first — construction order, not a decision gate.
|
||||
- **All-frozen full-size summaries, no state checkpoint** — rejected: unbounded permanent-prefix growth, self-accelerating toward thrashing, with nothing left to re-prioritize.
|
||||
- **Pure stubs, no state checkpoint** — rejected: presumes the model knows what it is missing; fails on unknown unknowns.
|
||||
- **LLM aging/consolidation of frozen chunks** — rejected as a routine mechanism: summary-of-summary loss and frozen-prefix churn; the code-only rollup is its surviving form, deferred.
|
||||
- **Full prefix as chunk-summarizer input** — rejected: O(N²); the state document gives the same background at O(state).
|
||||
- **One summarize call emitting all outputs** — rejected: the summarize path has no structured-output enforcement; parsing one free-text response apart is the fragile seam the fail-closed design avoids.
|
||||
- **Model-chosen chunk boundaries** — deferred: parse-and-validate cost against unproven value; chunk policy sits behind config.
|
||||
- **Model-authored pointers** — rejected: pointers must be exact; deterministic assembly is.
|
||||
- **FTS/vector index sidecar** — rejected in-session: the live log is in memory and bounded, a literal scan under budget suffices; an index earns its keep at cross-session scope.
|
||||
- **Semantic search fallback / secondary-model extraction in the recall path** — rejected: an LLM or embedding call there breaks keyless replay determinism; recall stays a pure function of the log.
|
||||
- **Raw events instead of rendered transcript** — rejected: leaks log-only vocabulary and chunk noise; the model reads what a model once saw.
|
||||
- **Doing nothing (resume/fork as recovery)** — rejected: it makes recovery a human act.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- Auto-compaction over a long session yields `[stubs…][state][tail]` after every completed pass; prior stubs stay byte-identical across passes; committed stubs never fall inside a later region; the superseded state checkpoint folds without a tombstone, renders labeled, and stays reachable and searchable through the two-hop chain.
|
||||
- Every checkpoint's surface text ends with the deterministic footer; footers round-trip through replay byte-identically; the state checkpoint's provenance records its wider input range.
|
||||
- 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.
|
||||
|
||||
## Risks
|
||||
|
||||
- **Recall is a learned behavior**: untrained models will under-use it, and the bench report exists to track the gap while training closes it. Until then the state checkpoint keeps the floor at today's summary quality.
|
||||
- **Unknown unknowns remain**: a detail absent from summaries and keywords draws no recall. Recall converts "unreachable even when suspected" into "reachable when suspected".
|
||||
- **The stub directory occupies attention**: dozens of stable index cards per request may dilute focus; the bench measurement in the acceptance criteria tracks it against `compact-basic`.
|
||||
- **Cost**: per-pass summarize input is roughly twice today's; short sessions sit near today's cost and quality, and the design pays off with session length.
|
||||
- **State drift and division-of-labor leakage** are observable through the handoff probe and stub review; their counters are specified follow-ups.
|
||||
- **Two backends** are a maintenance surface; the seam contract and the shared recall consumer bound it, and the bench comparison decides the default over time.
|
||||
@@ -4,7 +4,7 @@ Status: proposed
|
||||
|
||||
## Problem
|
||||
|
||||
The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, filters, pagination, cancellation, and rebuild behavior.
|
||||
The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, pagination, cancellation, and rebuild behavior.
|
||||
|
||||
Splitting those concerns across a speculative provider coordinator and a database implementation would create two coupled reconciliation state machines. The first real implementation should own the source observation, extraction, SQLite transaction, generation, and query as one lifecycle.
|
||||
|
||||
@@ -20,7 +20,7 @@ Persisted documents survive restarts. Live overrides are connection-local and sh
|
||||
|
||||
The implementation must define both cross-session and within-session scopes from executable use cases. Each searchable event is one document with session metadata, event metadata, surface classification, normalized semantic text, and a bounded plain-text snippet. Session results group by their strongest matching event; numeric backend scores remain private.
|
||||
|
||||
Filters compile to parameterized SQL before ranking. Query syntax is treated as data. Ordering includes stable tie fields. Opaque cursors bind to normalized request shape and the smallest relevant generation; unrelated session changes should not invalidate a within-session cursor. Cancellation must stop caller waiting and interrupt SQLite work where the runtime permits.
|
||||
Search returns content-bearing result records rather than metadata-only headers. Chainable filters operate on that exact result shape and are designed and implemented with the search API instead of becoming a provider-specific pre-ranking contract. Query syntax is treated as data. Ordering includes stable tie fields. Opaque cursors bind to normalized request shape and the smallest relevant generation; unrelated session changes should not invalidate a within-session cursor. Cancellation must stop caller waiting and interrupt SQLite work where the runtime permits.
|
||||
|
||||
Tokenizer choice remains an implementation experiment. FTS5 trigram supports substring recall but rejects useful terms shorter than three characters and increases index size; the proposal must benchmark that tradeoff against the default Unicode tokenizer before making it contract.
|
||||
|
||||
@@ -41,7 +41,7 @@ Reconciliation may use stable fingerprints to avoid rewriting unchanged persiste
|
||||
|
||||
- Restart tests cover unchanged, new, changed, and deleted persisted sessions without rebuilding the whole index.
|
||||
- Reopening preserves persisted rows and removes live rows; live rows shadow and then reveal their persisted base.
|
||||
- Tests cover both search scopes, metadata filters, surface defaults, snippets, escaping, deterministic ties, pagination, scoped stale cursors, cancellation, dynamic persistence mount/unmount, and recovery after a failed transaction.
|
||||
- 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/`.
|
||||
|
||||
+60
-1
@@ -20,6 +20,7 @@ This table connects model-visible tool names to the plugin package and service s
|
||||
| `@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; the request-header ToolsDelta 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` | - | - |
|
||||
| `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. |
|
||||
| `@deepseek-ai/dsh-tool-tasks` | `task_kill`, `task_list`, `task_output` | `ctx.tools`, `ctx.tasks`, `ctx.systemPrompt` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The kind-agnostic background-task control surface: a background bash command and a background subagent are read, listed, and killed through the same three tools. Loading the plugin attaches the control surface that arms producers' `ctx.tasks.start()`. |
|
||||
@@ -126,7 +127,7 @@ Owned by the tool registry as a reserved transport outside filterable capability
|
||||
|
||||
### `bash`
|
||||
|
||||
Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.
|
||||
Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.
|
||||
|
||||
```json
|
||||
{
|
||||
@@ -330,6 +331,64 @@ Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts
|
||||
|
||||
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`
|
||||
|
||||
Find files whose paths match a glob pattern. Returns matching paths sorted by modification time, including hidden and ignored files (VCS metadata directories are excluded). Returns the first 100 paths inline; a capped result reports where the complete list was saved.
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"pattern": {
|
||||
"type": "string",
|
||||
"description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\")."
|
||||
},
|
||||
"path": {
|
||||
"type": "string",
|
||||
"description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"pattern"
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-search/src/index.ts)
|
||||
|
||||
### `grep`
|
||||
|
||||
Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns the first 250 matches inline; a capped result reports where the complete match list was saved. Use read on a matched file for surrounding context.
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"pattern": {
|
||||
"type": "string",
|
||||
"description": "Regular expression to search for (ripgrep syntax)."
|
||||
},
|
||||
"path": {
|
||||
"type": "string",
|
||||
"description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it."
|
||||
},
|
||||
"include": {
|
||||
"type": "string",
|
||||
"description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"pattern"
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-search/src/index.ts)
|
||||
|
||||
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`
|
||||
|
||||
@@ -20,7 +20,7 @@ flowchart TD
|
||||
owned["Tool-owned session events<br/><code>todo/write</code>, <code>fs/observed</code>, <code>hook/invoked</code>, <code>hook/result</code>, <code>tool/code-dispatch</code>"]
|
||||
post["<code>tools/post-execute</code> waterfall<br/>accept, block, replace, add context"]
|
||||
final["<code>tools/result</code> synchronous notification<br/>frozen authoritative outcome"]
|
||||
context["Buffered additionalContext<br/>context/message after all tool results"]
|
||||
context["Buffered additionalContexts<br/>context/message after all tool results"]
|
||||
toolResult["Session event: <code>tool/result</code><br/>single model-facing outcome"]
|
||||
allResults["All calls in the step settled<br/>and tool/result events recorded"]
|
||||
presentResult["UI completed card<br/>presentResult(args, result)"]
|
||||
@@ -48,6 +48,6 @@ flowchart TD
|
||||
allResults --> context
|
||||
```
|
||||
|
||||
Filesystem read-before-edit checks stay below `tool-fs` on `fs/*` events. Generic pre/post waterfalls host hooks and approval policy; `ctx.approval` resolves asks before monotonic guards, and owner policy that must not be reordered remains a registered guard. Around-dispatch concerns such as timeouts wrap `tools/execute`, while `tools/result` observes the immutable outcome after transforms, lossless-JSON validation, and outer error normalization. This lets hooks span tool families without coupling the tools to one policy service. Code Mode sends both the reserved `run_code` transport and its serialized sub-calls through the pipeline; sub-calls carry the parent token, log `tool/code-dispatch`, surface denials as binding rejections, and omit `additionalContext` to preserve call/result adjacency.
|
||||
Filesystem read-before-edit checks stay below `tool-fs` on `fs/*` events. Generic pre/post waterfalls host hooks and approval policy; `ctx.approval` resolves asks before monotonic guards, and owner policy that must not be reordered remains a registered guard. Around-dispatch concerns such as timeouts wrap `tools/execute`, while `tools/result` observes the immutable outcome after transforms, lossless-JSON validation, and outer error normalization. This lets hooks span tool families without coupling the tools to one policy service. Code Mode sends both the reserved `run_code` transport and its serialized sub-calls through the pipeline; sub-calls carry the parent token, log `tool/code-dispatch`, surface denials as binding rejections, and omit `additionalContexts` to preserve call/result adjacency.
|
||||
|
||||
Maintenance mode: curated Mermaid flow; exact tool schemas and event signatures live in generated catalogs.
|
||||
@@ -7,7 +7,7 @@ pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env)
|
||||
pnpm run demo:code-mode acp # the same server in Code Mode: one wire tool, run_code
|
||||
```
|
||||
|
||||
The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`fs.cordis.yml`](fs.cordis.yml) adds the unconfined in-process filesystem stack for its dedicated scenarios; [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK. See [Code Mode](../../packages/core/tools/README.md#code-mode).
|
||||
The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`fs.cordis.yml`](fs.cordis.yml) adds the unconfined in-process filesystem stack and local tool-result spill storage for its dedicated scenarios; [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK. See [Code Mode](../../packages/core/tools/README.md#code-mode).
|
||||
|
||||
## stdout is the protocol
|
||||
|
||||
|
||||
@@ -12,6 +12,8 @@
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: both
|
||||
persona: |
|
||||
|
||||
@@ -10,6 +10,8 @@
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: both
|
||||
persona: |
|
||||
|
||||
@@ -14,6 +14,8 @@
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: both
|
||||
persona: |
|
||||
|
||||
@@ -12,6 +12,8 @@
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: both
|
||||
persona: |
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
# Keyless replay counterpart of code-mode-workspace-context.cordis.yml. It
|
||||
# enables the filesystem entries needed by this scenario and swaps in replay.
|
||||
- id: base
|
||||
name: '@cordisjs/plugin-include'
|
||||
config:
|
||||
path: ./cordis.yml
|
||||
patches:
|
||||
- id: llm-deepseek
|
||||
name: '@deepseek-ai/dsh-llm-deepseek'
|
||||
disabled: true
|
||||
- id: acp-agent
|
||||
name: '@deepseek-ai/dsh-acp-demo'
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: code
|
||||
persona: |
|
||||
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and factual.
|
||||
- insert:
|
||||
- id: fs-local
|
||||
name: '@deepseek-ai/dsh-fs-local'
|
||||
config:
|
||||
cwd: !!js process.cwd()
|
||||
- id: fs-policy
|
||||
name: '@deepseek-ai/dsh-fs-policy'
|
||||
- id: tool-fs
|
||||
name: '@deepseek-ai/dsh-tool-fs'
|
||||
- id: code-runtime
|
||||
name: '@deepseek-ai/dsh-code-runtime-worker'
|
||||
- id: llm-replay
|
||||
name: '@deepseek-ai/dsh-llm-replay'
|
||||
@@ -0,0 +1,31 @@
|
||||
# Code Mode workspace-context snapshot recording overlay. The scenario needs
|
||||
# filesystem tools to trigger nested instruction discovery after a read.
|
||||
- id: base
|
||||
name: '@cordisjs/plugin-include'
|
||||
config:
|
||||
path: ./cordis.yml
|
||||
patches:
|
||||
- id: acp-agent
|
||||
name: '@deepseek-ai/dsh-acp-demo'
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: code
|
||||
persona: |
|
||||
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and factual.
|
||||
- insert:
|
||||
- id: fs-local
|
||||
name: '@deepseek-ai/dsh-fs-local'
|
||||
config:
|
||||
cwd: !!js process.cwd()
|
||||
- id: fs-policy
|
||||
name: '@deepseek-ai/dsh-fs-policy'
|
||||
- id: tool-fs
|
||||
name: '@deepseek-ai/dsh-tool-fs'
|
||||
- id: code-runtime
|
||||
name: '@deepseek-ai/dsh-code-runtime-worker'
|
||||
@@ -14,6 +14,8 @@
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: code
|
||||
persona: |
|
||||
|
||||
@@ -13,6 +13,8 @@
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: code
|
||||
persona: |
|
||||
|
||||
@@ -33,7 +33,7 @@
|
||||
- id: permission
|
||||
name: '@deepseek-ai/dsh-permission'
|
||||
|
||||
# The ACP server app: the agent-core spine + JSONL persistence + the ACP bridge.
|
||||
# The ACP server app: the agent-spine-demo spine + JSONL persistence + the ACP bridge.
|
||||
# Persistence root: $DSH_SNAPSHOT_SESSIONS_ROOT when the snapshot harness sets it
|
||||
# (so it can harvest / isolate the log), else ./.sessions for the demo.
|
||||
- id: acp-agent
|
||||
@@ -41,6 +41,8 @@
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
# Keep the persona to identity and behavior; tool plugins own tool guidance.
|
||||
# The loop resolves {{model}} and each ACP session's client-supplied {{cwd}}.
|
||||
persona: |
|
||||
|
||||
@@ -17,5 +17,13 @@
|
||||
name: '@deepseek-ai/dsh-fs-policy'
|
||||
- id: tool-fs
|
||||
name: '@deepseek-ai/dsh-tool-fs'
|
||||
- id: spill-local
|
||||
name: '@deepseek-ai/dsh-spill-local'
|
||||
config:
|
||||
root: !!js process.env.DSH_SNAPSHOT_SPILL_ROOT ?? './.spill'
|
||||
- id: spill-policy
|
||||
name: '@deepseek-ai/dsh-spill-policy'
|
||||
config:
|
||||
maxInlineBytes: 800
|
||||
- id: llm-replay
|
||||
name: '@deepseek-ai/dsh-llm-replay'
|
||||
@@ -15,3 +15,11 @@
|
||||
name: '@deepseek-ai/dsh-fs-policy'
|
||||
- id: tool-fs
|
||||
name: '@deepseek-ai/dsh-tool-fs'
|
||||
- id: spill-local
|
||||
name: '@deepseek-ai/dsh-spill-local'
|
||||
config:
|
||||
root: !!js process.env.DSH_SNAPSHOT_SPILL_ROOT ?? './.spill'
|
||||
- id: spill-policy
|
||||
name: '@deepseek-ai/dsh-spill-policy'
|
||||
config:
|
||||
maxInlineBytes: !!js process.env.DSH_SNAPSHOT && 800 || 50000
|
||||
@@ -25,7 +25,9 @@ const AGENT = {
|
||||
// The Code Mode overlay configs (include-patched variants of cordis.yml; the
|
||||
// replay swap resolves each one's sibling `*cordis.snapshot.yml`).
|
||||
const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
|
||||
const CODE_MODE_WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../code-mode-workspace-context.cordis.yml', import.meta.url))
|
||||
const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
|
||||
const WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../workspace-context.cordis.yml', import.meta.url))
|
||||
const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url))
|
||||
const FS_CONFIG = fileURLToPath(new URL('../fs.cordis.yml', import.meta.url))
|
||||
|
||||
@@ -51,6 +53,7 @@ const SCENARIOS: Scenario[] = [
|
||||
// Its prompt and tool-schema sidecars pin the composed header.
|
||||
{ name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true },
|
||||
{ name: 'tool-call-turn', hasModelTurn: true, recorded: true },
|
||||
{ name: 'bash-spill', hasModelTurn: true, recorded: false, headerClass: 'fs', configPath: FS_CONFIG },
|
||||
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
|
||||
{ name: 'todo-plan', hasModelTurn: true, recorded: true },
|
||||
{ name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
|
||||
@@ -68,6 +71,19 @@ const SCENARIOS: Scenario[] = [
|
||||
// the fixture scripts five identical todo_write calls and pins BOTH reminder
|
||||
// tiers (gentle at 3, detailed at 5) as context/message in transcript and log.
|
||||
{ name: 'repeat-tool-guard', hasModelTurn: true, recorded: false },
|
||||
// Authored replay: a root AGENTS.md pins the session prefix, then a read in
|
||||
// nested/ discovers its narrower AGENTS.md as a raw, metadata-bearing
|
||||
// context/message. The scenario-specific config keeps home/root discovery
|
||||
// hermetic, and the resulting prefix needs its own pinned header class.
|
||||
{
|
||||
name: 'workspace-context',
|
||||
hasModelTurn: true,
|
||||
recorded: false,
|
||||
overridden: true,
|
||||
pinsHeader: true,
|
||||
headerClass: 'workspace-context',
|
||||
configPath: WORKSPACE_CONTEXT_CONFIG,
|
||||
},
|
||||
{ name: 'cancel', hasModelTurn: true, recorded: false, overridden: true },
|
||||
{ name: 'subagent-spawn', hasModelTurn: true, recorded: true, childSessions: 1 },
|
||||
{ name: 'subagent-multi', hasModelTurn: true, recorded: true, childSessions: 2 },
|
||||
@@ -116,6 +132,17 @@ const SCENARIOS: Scenario[] = [
|
||||
// tools:sdk section rides in the prompt, and the program's tool calls land as
|
||||
// tool/code-dispatch events. Each overlay composes and pins its own header class.
|
||||
{ name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG },
|
||||
// A nested fs dispatch inside run_code discovers workspace instructions. The
|
||||
// context/message must follow the outer result while retaining workspace
|
||||
// provenance, which proves Code Mode carries deferred tool context end to end.
|
||||
{
|
||||
name: 'code-mode-workspace-context',
|
||||
hasModelTurn: true,
|
||||
recorded: true,
|
||||
pinsHeader: true,
|
||||
headerClass: 'code-workspace-context',
|
||||
configPath: CODE_MODE_WORKSPACE_CONTEXT_CONFIG,
|
||||
},
|
||||
{ name: 'both-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'both', configPath: BOTH_MODE_CONFIG },
|
||||
// The default tree owns the single Permissions select. Snapshot mode starts
|
||||
// in danger-full-access so established fixtures stay runner-independent;
|
||||
|
||||
@@ -27,7 +27,7 @@ The available tools:
|
||||
|
||||
```ts
|
||||
declare const tools: {
|
||||
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */
|
||||
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */
|
||||
bash(args: {
|
||||
/** The bash command to execute. */
|
||||
command: string;
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{ "op": "prompt", "text": "Use the bash tool to print a large deterministic output, then reply DONE." }
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,23 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
|
||||
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Use the bash tool to print a large deterministic output, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_spill","name":"bash","argumentsDelta":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_spill","name":"bash","arguments":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_spill","name":"bash","arguments":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","name":"bash","arguments":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}}
|
||||
{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","content":[{"type":"text","text":"SPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: /tmp/dsh-acp-snapshot-spill/session-e194e47db58a/69c4a2d26b7e-bash.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
|
||||
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
|
||||
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":20,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":21,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,6 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
|
||||
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_spill","title":"node -e \"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\"","kind":"execute","status":"in_progress","rawInput":"node -e \"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\"","content":[{"type":"content","content":{"type":"text","text":"Print large deterministic output"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_spill","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nSPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: {{spillLocator:bash.txt}}. Use read with offset/limit, or grep this path to search within it.)\n```"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
|
||||
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
|
||||
@@ -27,7 +27,7 @@ The available tools:
|
||||
|
||||
```ts
|
||||
declare const tools: {
|
||||
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */
|
||||
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */
|
||||
bash(args: {
|
||||
/** The bash command to execute. */
|
||||
command: string;
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -27,7 +27,7 @@ The available tools:
|
||||
|
||||
```ts
|
||||
declare const tools: {
|
||||
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */
|
||||
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */
|
||||
bash(args: {
|
||||
/** The bash command to execute. */
|
||||
command: string;
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{ "op": "prompt", "text": "Using ONE run_code program, call tools.read on nested/task.txt. After the program finishes, answer the workspace handshake question using the newly discovered instructions: What is the Code Mode workspace handshake?" }
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,189 @@
|
||||
{"type":"session","version":0,"id":"65fbb8a6-624c-4d6a-bf5d-a7a7d14f2b49","createdAt":1783921765266,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-uorU26"}
|
||||
{"type":"turn/start","seq":0,"time":1783921765269,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783921765269,"data":{"content":[{"type":"text","text":"Using ONE run_code program, call tools.read on nested/task.txt. After the program finishes, answer the workspace handshake question using the newly discovered instructions: What is the Code Mode workspace handshake?"}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783921765275,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783921765275,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n</system-reminder>"}]}]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783921766287,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1783921766287,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783921766483,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1783921766519,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1783921766520,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1783921766520,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
|
||||
{"type":"assistant/chunk","seq":10,"time":1783921766520,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" write"}}}
|
||||
{"type":"assistant/chunk","seq":11,"time":1783921766537,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}}
|
||||
{"type":"assistant/chunk","seq":12,"time":1783921766538,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}}
|
||||
{"type":"assistant/chunk","seq":13,"time":1783921766538,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}}
|
||||
{"type":"assistant/chunk","seq":14,"time":1783921766573,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_code"}}}
|
||||
{"type":"assistant/chunk","seq":15,"time":1783921766573,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" program"}}}
|
||||
{"type":"assistant/chunk","seq":16,"time":1783921766574,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}}
|
||||
{"type":"assistant/chunk","seq":17,"time":1783921766574,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reads"}}}
|
||||
{"type":"assistant/chunk","seq":18,"time":1783921766598,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}}
|
||||
{"type":"assistant/chunk","seq":19,"time":1783921766598,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" file"}}}
|
||||
{"type":"assistant/chunk","seq":20,"time":1783921766599,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" called"}}}
|
||||
{"type":"assistant/chunk","seq":21,"time":1783921766624,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nested"}}}
|
||||
{"type":"assistant/chunk","seq":22,"time":1783921766654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"/t"}}}
|
||||
{"type":"assistant/chunk","seq":23,"time":1783921766654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ask"}}}
|
||||
{"type":"assistant/chunk","seq":24,"time":1783921766654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}}
|
||||
{"type":"assistant/chunk","seq":25,"time":1783921766654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}}
|
||||
{"type":"assistant/chunk","seq":26,"time":1783921766655,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}}
|
||||
{"type":"assistant/chunk","seq":27,"time":1783921766684,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" answer"}}}
|
||||
{"type":"assistant/chunk","seq":28,"time":1783921766717,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
|
||||
{"type":"assistant/chunk","seq":29,"time":1783921766717,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" hand"}}}
|
||||
{"type":"assistant/chunk","seq":30,"time":1783921766717,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"shake"}}}
|
||||
{"type":"assistant/chunk","seq":31,"time":1783921766743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" question"}}}
|
||||
{"type":"assistant/chunk","seq":32,"time":1783921766743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" based"}}}
|
||||
{"type":"assistant/chunk","seq":33,"time":1783921766743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" on"}}}
|
||||
{"type":"assistant/chunk","seq":34,"time":1783921766743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}}
|
||||
{"type":"assistant/chunk","seq":35,"time":1783921766776,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'s"}}}
|
||||
{"type":"assistant/chunk","seq":36,"time":1783921766776,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}}
|
||||
{"type":"assistant/chunk","seq":37,"time":1783921766798,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}}
|
||||
{"type":"assistant/chunk","seq":38,"time":1783921766799,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" file"}}}
|
||||
{"type":"assistant/chunk","seq":39,"time":1783921766799,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
|
||||
{"type":"assistant/chunk","seq":40,"time":1783921766799,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}}
|
||||
{"type":"assistant/chunk","seq":41,"time":1783921766799,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}}
|
||||
{"type":"assistant/chunk","seq":42,"time":1783921766799,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" start"}}}
|
||||
{"type":"assistant/chunk","seq":43,"time":1783921766845,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}}
|
||||
{"type":"assistant/chunk","seq":44,"time":1783921766845,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reading"}}}
|
||||
{"type":"assistant/chunk","seq":45,"time":1783921766845,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
|
||||
{"type":"assistant/chunk","seq":46,"time":1783921766845,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" file"}}}
|
||||
{"type":"assistant/chunk","seq":47,"time":1783921766845,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
|
||||
{"type":"assistant/chunk","seq":48,"time":1783921766926,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":49,"time":1783921766926,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":""}}}
|
||||
{"type":"assistant/chunk","seq":50,"time":1783921766952,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"{"}}}
|
||||
{"type":"assistant/chunk","seq":51,"time":1783921766952,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"\""}}}
|
||||
{"type":"assistant/chunk","seq":52,"time":1783921766952,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"code"}}}
|
||||
{"type":"assistant/chunk","seq":53,"time":1783921766952,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"\""}}}
|
||||
{"type":"assistant/chunk","seq":54,"time":1783921766952,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":": "}}}
|
||||
{"type":"assistant/chunk","seq":55,"time":1783921766978,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"\""}}}
|
||||
{"type":"assistant/chunk","seq":56,"time":1783921766978,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"const"}}}
|
||||
{"type":"assistant/chunk","seq":57,"time":1783921766978,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" content"}}}
|
||||
{"type":"assistant/chunk","seq":58,"time":1783921767011,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" ="}}}
|
||||
{"type":"assistant/chunk","seq":59,"time":1783921767011,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" await"}}}
|
||||
{"type":"assistant/chunk","seq":60,"time":1783921767011,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" tools"}}}
|
||||
{"type":"assistant/chunk","seq":61,"time":1783921767011,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":".read"}}}
|
||||
{"type":"assistant/chunk","seq":62,"time":1783921767011,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"({"}}}
|
||||
{"type":"assistant/chunk","seq":63,"time":1783921767050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" file"}}}
|
||||
{"type":"assistant/chunk","seq":64,"time":1783921767050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"_path"}}}
|
||||
{"type":"assistant/chunk","seq":65,"time":1783921767050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":":"}}}
|
||||
{"type":"assistant/chunk","seq":66,"time":1783921767050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" \\\""}}}
|
||||
{"type":"assistant/chunk","seq":67,"time":1783921767050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"n"}}}
|
||||
{"type":"assistant/chunk","seq":68,"time":1783921767050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"ested"}}}
|
||||
{"type":"assistant/chunk","seq":69,"time":1783921767068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"/t"}}}
|
||||
{"type":"assistant/chunk","seq":70,"time":1783921767068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"ask"}}}
|
||||
{"type":"assistant/chunk","seq":71,"time":1783921767068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":".txt"}}}
|
||||
{"type":"assistant/chunk","seq":72,"time":1783921767068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"\\\""}}}
|
||||
{"type":"assistant/chunk","seq":73,"time":1783921767068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" });\\n"}}}
|
||||
{"type":"assistant/chunk","seq":74,"time":1783921767068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"return"}}}
|
||||
{"type":"assistant/chunk","seq":75,"time":1783921767095,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":" content"}}}
|
||||
{"type":"assistant/chunk","seq":76,"time":1783921767095,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":";"}}}
|
||||
{"type":"assistant/chunk","seq":77,"time":1783921767095,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"\""}}}
|
||||
{"type":"assistant/chunk","seq":78,"time":1783921767121,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","argumentsDelta":"}"}}}
|
||||
{"type":"assistant/chunk","seq":79,"time":1783921767205,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to write a single run_code program that reads a file called nested/task.txt and then answer the handshake question based on what's in that file. Let me start by reading the file."}}}}
|
||||
{"type":"assistant/chunk","seq":80,"time":1783921767205,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","arguments":"{\"code\": \"const content = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn content;\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":81,"time":1783921767205,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3195,"outputTokens":106,"cacheReadTokens":0,"reasoningTokens":43}}}}
|
||||
{"type":"assistant/chunk","seq":82,"time":1783921767205,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":83,"time":1783921767208,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to write a single run_code program that reads a file called nested/task.txt and then answer the handshake question based on what's in that file. Let me start by reading the file."},{"type":"tool-call","id":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","arguments":"{\"code\": \"const content = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn content;\"}"}],"usage":{"inputTokens":3195,"outputTokens":106,"cacheReadTokens":0,"reasoningTokens":43}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":84,"time":1783921767208,"data":{"turn":1,"step":1,"callId":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","arguments":"{\"code\": \"const content = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn content;\"}"}}
|
||||
{"type":"tool/code-dispatch","seq":85,"time":1783921767270,"data":{"parentCallId":"call_00_6APApmaKLRDlXKMdIcWL5139","subCallId":"call_00_6APApmaKLRDlXKMdIcWL5139:code:1","name":"read","arguments":{"file_path":"nested/task.txt"},"isError":false,"resultSummary":"<path>./nested/task.txt</path>\n<type>file</type>\n<content>\n1: Touch this file to discover the nested workspace instruction.\n\n(End of file - total 1 lines)\n</content>"}}
|
||||
{"type":"tool/result","seq":86,"time":1783921767271,"data":{"turn":1,"step":1,"callId":"call_00_6APApmaKLRDlXKMdIcWL5139","content":[{"type":"text","text":"<path>/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-uorU26/nested/task.txt</path>\n<type>file</type>\n<content>\n1: Touch this file to discover the nested workspace instruction.\n\n(End of file - total 1 lines)\n</content>"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[84],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":87,"time":1783921767272,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nWhen asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"envelope":"raw","meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested","path":"nested/AGENTS.md","digest":"ae22936ed26dc76b7107005ed6d5e2482a88668a"}]}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":88,"time":1783921767272,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":89,"time":1783921767272,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":90,"time":1783921768339,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"assistant/chunk","seq":91,"time":1783921768340,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
|
||||
{"type":"assistant/chunk","seq":92,"time":1783921768466,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" nested"}}}
|
||||
{"type":"assistant/chunk","seq":93,"time":1783921768474,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"/t"}}}
|
||||
{"type":"assistant/chunk","seq":94,"time":1783921768500,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ask"}}}
|
||||
{"type":"assistant/chunk","seq":95,"time":1783921768501,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}}
|
||||
{"type":"assistant/chunk","seq":96,"time":1783921768535,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" told"}}}
|
||||
{"type":"assistant/chunk","seq":97,"time":1783921768535,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}}
|
||||
{"type":"assistant/chunk","seq":98,"time":1783921768535,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
|
||||
{"type":"assistant/chunk","seq":99,"time":1783921768535,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}}
|
||||
{"type":"assistant/chunk","seq":100,"time":1783921768564,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"Touch"}}}
|
||||
{"type":"assistant/chunk","seq":101,"time":1783921768565,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}}
|
||||
{"type":"assistant/chunk","seq":102,"time":1783921768565,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" file"}}}
|
||||
{"type":"assistant/chunk","seq":103,"time":1783921768565,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
|
||||
{"type":"assistant/chunk","seq":104,"time":1783921768565,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" discover"}}}
|
||||
{"type":"assistant/chunk","seq":105,"time":1783921768565,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
|
||||
{"type":"assistant/chunk","seq":106,"time":1783921768595,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" nested"}}}
|
||||
{"type":"assistant/chunk","seq":107,"time":1783921768595,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" workspace"}}}
|
||||
{"type":"assistant/chunk","seq":108,"time":1783921768595,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instruction"}}}
|
||||
{"type":"assistant/chunk","seq":109,"time":1783921768595,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":".\""}}}
|
||||
{"type":"assistant/chunk","seq":110,"time":1783921768595,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}}
|
||||
{"type":"assistant/chunk","seq":111,"time":1783921768595,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
|
||||
{"type":"assistant/chunk","seq":112,"time":1783921768621,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" nested"}}}
|
||||
{"type":"assistant/chunk","seq":113,"time":1783921768621,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"/"}}}
|
||||
{"type":"assistant/chunk","seq":114,"time":1783921768647,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AG"}}}
|
||||
{"type":"assistant/chunk","seq":115,"time":1783921768648,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ENTS"}}}
|
||||
{"type":"assistant/chunk","seq":116,"time":1783921768648,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":".md"}}}
|
||||
{"type":"assistant/chunk","seq":117,"time":1783921768648,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instructions"}}}
|
||||
{"type":"assistant/chunk","seq":118,"time":1783921768688,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" say"}}}
|
||||
{"type":"assistant/chunk","seq":119,"time":1783921768703,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}}
|
||||
{"type":"assistant/chunk","seq":120,"time":1783921768740,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}}
|
||||
{"type":"assistant/chunk","seq":121,"time":1783921768740,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"When"}}}
|
||||
{"type":"assistant/chunk","seq":122,"time":1783921768741,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}}
|
||||
{"type":"assistant/chunk","seq":123,"time":1783921768741,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" for"}}}
|
||||
{"type":"assistant/chunk","seq":124,"time":1783921768741,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
|
||||
{"type":"assistant/chunk","seq":125,"time":1783921768741,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Code"}}}
|
||||
{"type":"assistant/chunk","seq":126,"time":1783921768773,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Mode"}}}
|
||||
{"type":"assistant/chunk","seq":127,"time":1783921768773,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" workspace"}}}
|
||||
{"type":"assistant/chunk","seq":128,"time":1783921768773,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" hand"}}}
|
||||
{"type":"assistant/chunk","seq":129,"time":1783921768773,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"shake"}}}
|
||||
{"type":"assistant/chunk","seq":130,"time":1783921768773,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}}
|
||||
{"type":"assistant/chunk","seq":131,"time":1783921768773,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" answer"}}}
|
||||
{"type":"assistant/chunk","seq":132,"time":1783921768790,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}}
|
||||
{"type":"assistant/chunk","seq":133,"time":1783921768790,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}}
|
||||
{"type":"assistant/chunk","seq":134,"time":1783921768790,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"CODE"}}}
|
||||
{"type":"assistant/chunk","seq":135,"time":1783921768790,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_M"}}}
|
||||
{"type":"assistant/chunk","seq":136,"time":1783921768790,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ODE"}}}
|
||||
{"type":"assistant/chunk","seq":137,"time":1783921768790,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_CONT"}}}
|
||||
{"type":"assistant/chunk","seq":138,"time":1783921768824,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"EXT"}}}
|
||||
{"type":"assistant/chunk","seq":139,"time":1783921768825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}}
|
||||
{"type":"assistant/chunk","seq":140,"time":1783921768825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}}
|
||||
{"type":"assistant/chunk","seq":141,"time":1783921768825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}}
|
||||
{"type":"assistant/chunk","seq":142,"time":1783921768825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}}
|
||||
{"type":"assistant/chunk","seq":143,"time":1783921768825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}}
|
||||
{"type":"assistant/chunk","seq":144,"time":1783921768846,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":".\"\n\n"}}}
|
||||
{"type":"assistant/chunk","seq":145,"time":1783921768846,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"So"}}}
|
||||
{"type":"assistant/chunk","seq":146,"time":1783921768847,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
|
||||
{"type":"assistant/chunk","seq":147,"time":1783921768847,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" answer"}}}
|
||||
{"type":"assistant/chunk","seq":148,"time":1783921768847,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
|
||||
{"type":"assistant/chunk","seq":149,"time":1783921768873,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
|
||||
{"type":"assistant/chunk","seq":150,"time":1783921768874,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" hand"}}}
|
||||
{"type":"assistant/chunk","seq":151,"time":1783921768903,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"shake"}}}
|
||||
{"type":"assistant/chunk","seq":152,"time":1783921768903,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" question"}}}
|
||||
{"type":"assistant/chunk","seq":153,"time":1783921768903,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}}
|
||||
{"type":"assistant/chunk","seq":154,"time":1783921768903,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}}
|
||||
{"type":"assistant/chunk","seq":155,"time":1783921768903,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"CODE"}}}
|
||||
{"type":"assistant/chunk","seq":156,"time":1783921768929,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_M"}}}
|
||||
{"type":"assistant/chunk","seq":157,"time":1783921768930,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ODE"}}}
|
||||
{"type":"assistant/chunk","seq":158,"time":1783921768930,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_CONT"}}}
|
||||
{"type":"assistant/chunk","seq":159,"time":1783921768930,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"EXT"}}}
|
||||
{"type":"assistant/chunk","seq":160,"time":1783921768930,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}}
|
||||
{"type":"assistant/chunk","seq":161,"time":1783921768963,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"`."}}}
|
||||
{"type":"assistant/chunk","seq":162,"time":1783921768963,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":163,"time":1783921768963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}}
|
||||
{"type":"assistant/chunk","seq":164,"time":1783921768963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" **"}}}
|
||||
{"type":"assistant/chunk","seq":165,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"Code"}}}
|
||||
{"type":"assistant/chunk","seq":166,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" Mode"}}}
|
||||
{"type":"assistant/chunk","seq":167,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" workspace"}}}
|
||||
{"type":"assistant/chunk","seq":168,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" hand"}}}
|
||||
{"type":"assistant/chunk","seq":169,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"shake"}}}
|
||||
{"type":"assistant/chunk","seq":170,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"**"}}}
|
||||
{"type":"assistant/chunk","seq":171,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}}
|
||||
{"type":"assistant/chunk","seq":172,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}}
|
||||
{"type":"assistant/chunk","seq":173,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" `"}}}
|
||||
{"type":"assistant/chunk","seq":174,"time":1783921769024,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"CODE"}}}
|
||||
{"type":"assistant/chunk","seq":175,"time":1783921769046,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_M"}}}
|
||||
{"type":"assistant/chunk","seq":176,"time":1783921769046,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ODE"}}}
|
||||
{"type":"assistant/chunk","seq":177,"time":1783921769047,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_CONT"}}}
|
||||
{"type":"assistant/chunk","seq":178,"time":1783921769047,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"EXT"}}}
|
||||
{"type":"assistant/chunk","seq":179,"time":1783921769047,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_OK"}}}
|
||||
{"type":"assistant/chunk","seq":180,"time":1783921769047,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"`"}}}
|
||||
{"type":"assistant/chunk","seq":181,"time":1783921769101,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The nested/task.txt told me to \"Touch this file to discover the nested workspace instruction.\" and the nested/AGENTS.md instructions say: \"When asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\"\n\nSo the answer to the handshake question is `CODE_MODE_CONTEXT_OK`."}}}}
|
||||
{"type":"assistant/chunk","seq":182,"time":1783921769101,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The **Code Mode workspace handshake** is: `CODE_MODE_CONTEXT_OK`"}}}}
|
||||
{"type":"assistant/chunk","seq":183,"time":1783921769101,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":277,"outputTokens":90,"cacheReadTokens":3200,"reasoningTokens":71}}}}
|
||||
{"type":"assistant/chunk","seq":184,"time":1783921769101,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":185,"time":1783921769101,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The nested/task.txt told me to \"Touch this file to discover the nested workspace instruction.\" and the nested/AGENTS.md instructions say: \"When asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\"\n\nSo the answer to the handshake question is `CODE_MODE_CONTEXT_OK`."},{"type":"text","text":"The **Code Mode workspace handshake** is: `CODE_MODE_CONTEXT_OK`"}],"usage":{"inputTokens":277,"outputTokens":90,"cacheReadTokens":3200,"reasoningTokens":71}},"sourceEventSeqs":[90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":186,"time":1783921769101,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":187,"time":1783921769101,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,137 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
|
||||
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" write"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_code"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" program"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reads"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" called"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nested"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"/t"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ask"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" answer"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" hand"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"shake"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" question"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" based"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" on"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" what"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" in"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" start"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" by"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reading"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_6APApmaKLRDlXKMdIcWL5139","title":"const content = await tools.read({ file_path: \"nested/task.txt\" });\nreturn content;","kind":"execute","status":"in_progress","rawInput":"const content = await tools.read({ file_path: \"nested/task.txt\" });\nreturn content;"}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_6APApmaKLRDlXKMdIcWL5139","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: Touch this file to discover the nested workspace instruction.\n\n(End of file - total 1 lines)\n</content>"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nested"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"/t"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ask"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" told"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Touch"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" this"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" discover"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nested"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" workspace"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instruction"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\""}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nested"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"/"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AG"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENTS"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".md"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instructions"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" say"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"When"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" for"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Code"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Mode"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" workspace"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" hand"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"shake"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" answer"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"CODE"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_M"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ODE"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_CONT"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"EXT"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_OK"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nothing"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" else"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\"\n\n"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"So"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" answer"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" hand"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"shake"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" question"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"CODE"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_M"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ODE"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_CONT"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"EXT"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_OK"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`."}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"The"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" **"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"Code"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" Mode"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" workspace"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" hand"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"shake"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"**"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":":"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" `"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"CODE"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"_M"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ODE"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"_CONT"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"EXT"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"_OK"}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"`"}}}}
|
||||
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
|
||||
+157
@@ -0,0 +1,157 @@
|
||||
You are an AI agent powered by the DeepSeek Harness SDK.
|
||||
|
||||
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and factual.
|
||||
|
||||
|
||||
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
|
||||
|
||||
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
|
||||
|
||||
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
|
||||
|
||||
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
|
||||
|
||||
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
|
||||
|
||||
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
|
||||
<!-- dsh-user-approval-policy:never -->
|
||||
|
||||
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
|
||||
|
||||
## 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:
|
||||
|
||||
- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.
|
||||
- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.
|
||||
- Calls execute sequentially, even under `Promise.all`.
|
||||
- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
|
||||
|
||||
The available tools:
|
||||
|
||||
```ts
|
||||
declare const tools: {
|
||||
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */
|
||||
bash(args: {
|
||||
/** The bash command to execute. */
|
||||
command: string;
|
||||
/** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */
|
||||
description: string;
|
||||
/** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */
|
||||
timeoutMs?: number;
|
||||
/** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */
|
||||
workdir?: string;
|
||||
/** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */
|
||||
run_in_background?: boolean;
|
||||
/** The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval. */
|
||||
sandbox_permissions?: "workspace-write" | "danger-full-access";
|
||||
/** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */
|
||||
justification?: string;
|
||||
}): Promise<string>;
|
||||
/** Edit an existing UTF-8 text file by replacing literal text. */
|
||||
edit(args: {
|
||||
/** Path to edit, resolved by the filesystem backend. */
|
||||
file_path: string;
|
||||
/** Literal text to replace. Must match exactly. */
|
||||
old_string: string;
|
||||
/** Literal replacement text. Use an empty string to delete the match. */
|
||||
new_string: string;
|
||||
/** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */
|
||||
replace_all?: boolean;
|
||||
}): Promise<string>;
|
||||
/** Read a UTF-8 text file and return line-numbered content. */
|
||||
read(args: {
|
||||
/** Path to read, resolved by the filesystem backend. */
|
||||
file_path: string;
|
||||
/** 1-based first line to return. Defaults to 1. */
|
||||
offset?: number;
|
||||
/** Maximum number of lines to return. Defaults to 2000. */
|
||||
limit?: number;
|
||||
}): Promise<string>;
|
||||
/** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
|
||||
skill(args: {
|
||||
/** The exact skill name from the available skills list. */
|
||||
name: string;
|
||||
}): Promise<string>;
|
||||
/** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */
|
||||
subagent(args: {
|
||||
/** A short (3-5 word) description of the delegated task, for display. */
|
||||
description: string;
|
||||
/** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
|
||||
prompt: string;
|
||||
/** Run as a background task and return its id; collect with task_output or stop with task_kill. */
|
||||
run_in_background?: boolean;
|
||||
}): Promise<string>;
|
||||
/** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */
|
||||
subagent_fork(args: {
|
||||
/** A short (3-5 word) description of the delegated task, for display. */
|
||||
description: string;
|
||||
/** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */
|
||||
prompt: string;
|
||||
/** Run as a background task and return its id; collect with task_output or stop with task_kill. */
|
||||
run_in_background?: boolean;
|
||||
}): Promise<string>;
|
||||
/** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */
|
||||
task_kill(args: {
|
||||
/** Task id returned by the tool that started the background work. */
|
||||
task_id: string;
|
||||
/** Optional short reason, recorded in the log and forwarded to the task. */
|
||||
reason?: string;
|
||||
}): Promise<string>;
|
||||
/** List your background tasks (running and finished) with their ids, kinds, and statuses. */
|
||||
task_list(args: Record<string, unknown>): Promise<string>;
|
||||
/** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */
|
||||
task_output(args: {
|
||||
/** Task id returned by the tool that started the background work. */
|
||||
task_id: string;
|
||||
/** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */
|
||||
wait?: boolean;
|
||||
/** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */
|
||||
timeout_ms?: number;
|
||||
}): Promise<string>;
|
||||
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
|
||||
todo_write(args: {
|
||||
/** The COMPLETE task list, replacing any previous list. */
|
||||
todos: ({
|
||||
/** What the task is — a short imperative line. */
|
||||
content: string;
|
||||
/** pending (not started) | in_progress (now) | completed (done). */
|
||||
status: "pending" | "in_progress" | "completed";
|
||||
})[];
|
||||
}): Promise<string>;
|
||||
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
|
||||
workflow(args: {
|
||||
/** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */
|
||||
script: string;
|
||||
/** The workflow identity block (plain JSON — never code). */
|
||||
meta: {
|
||||
/** Short kebab-case workflow name. */
|
||||
name: string;
|
||||
/** One-line description of what the workflow does. */
|
||||
description: string;
|
||||
/** Optional guidance on when this workflow applies. */
|
||||
whenToUse?: string;
|
||||
/** Optional phase declarations matched by phase() calls. */
|
||||
phases?: {
|
||||
/** The phase title phase() calls match by exact string. */
|
||||
title: string;
|
||||
/** Optional one-line description of the phase. */
|
||||
detail?: string;
|
||||
/** Optional model override this phase is expected to use. */
|
||||
model?: string;
|
||||
}[];
|
||||
};
|
||||
/** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */
|
||||
args?: Record<string, unknown>;
|
||||
}): Promise<string>;
|
||||
/** Create or fully replace a UTF-8 text file. */
|
||||
write(args: {
|
||||
/** Path to write, resolved by the filesystem backend. */
|
||||
file_path: string;
|
||||
/** Full UTF-8 text content to write. */
|
||||
content: string;
|
||||
}): Promise<string>;
|
||||
}
|
||||
```
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"initial": [
|
||||
{
|
||||
"name": "run_code",
|
||||
"description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "The program: the body of an async TypeScript function."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"code"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
Workspace snapshot root instruction.
|
||||
+1
@@ -0,0 +1 @@
|
||||
When asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.
|
||||
+1
@@ -0,0 +1 @@
|
||||
Touch this file to discover the nested workspace instruction.
|
||||
@@ -131,8 +131,8 @@
|
||||
{"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
|
||||
{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"b76bc320-c954-4f8a-b7d6-30821793dae8","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
|
||||
{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"b76bc320-c954-4f8a-b7d6-30821793dae8","outcome":"allowed-once"}}
|
||||
{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"f2837399-691e-4913-abf4-9cd40aa31ac2","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
|
||||
{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"f2837399-691e-4913-abf4-9cd40aa31ac2","outcome":"allowed-once"}}
|
||||
{"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}}
|
||||
|
||||
@@ -155,8 +155,8 @@
|
||||
{"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
|
||||
{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"66efb593-279a-472b-b647-c50d34045bc0","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
|
||||
{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"66efb593-279a-472b-b647-c50d34045bc0","outcome":"rejected"}}
|
||||
{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"e5a72cf8-322c-4ec1-a082-55903876dc53","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
|
||||
{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"e5a72cf8-322c-4ec1-a082-55903876dc53","outcome":"rejected"}}
|
||||
{"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}}
|
||||
|
||||
@@ -55,8 +55,8 @@
|
||||
{"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}}
|
||||
{"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}}
|
||||
{"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}}
|
||||
{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"af257151-c371-4be2-a9ab-fbf4b6d18eb1","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
|
||||
{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"af257151-c371-4be2-a9ab-fbf4b6d18eb1","outcome":"rejected"}}
|
||||
{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"6f7aaf62-f3cf-435f-8338-e8de72dbfbbf","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
|
||||
{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"6f7aaf62-f3cf-435f-8338-e8de72dbfbbf","outcome":"rejected"}}
|
||||
{"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{ "op": "prompt", "text": "Read nested/task.txt with the read tool, then reply DONE." }
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,22 @@
|
||||
[
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
|
||||
{ "type": "tool-call-delta", "index": 0, "id": "call_workspace_read", "name": "read", "argumentsDelta": "{\"file_path\":\"nested/task.txt\"}" },
|
||||
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_workspace_read", "name": "read", "arguments": "{\"file_path\":\"nested/task.txt\"}" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
|
||||
{ "type": "finish", "reason": { "kind": "tool-calls" } }
|
||||
]
|
||||
},
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
{ "type": "block-start", "index": 0, "blockType": "text" },
|
||||
{ "type": "text-delta", "index": 0, "text": "DONE" },
|
||||
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "DONE" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 2 } },
|
||||
{ "type": "finish", "reason": { "kind": "stop" } }
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,24 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
|
||||
{"type":"turn/start","seq":0,"time":1783778297065,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783778297066,"data":{"content":[{"type":"text","text":"Read nested/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783778297069,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783778297070,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}]}]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_workspace_read","name":"read","argumentsDelta":"{\"file_path\":\"nested/task.txt\"}"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":9,"time":1783778297070,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":10,"time":1783778297070,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}
|
||||
{"type":"tool/result","seq":11,"time":1783778297072,"data":{"turn":1,"step":1,"callId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":12,"time":1783778297072,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"envelope":"raw","meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":13,"time":1783778297072,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":14,"time":1783778297072,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":15,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":16,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
|
||||
{"type":"assistant/chunk","seq":17,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":18,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
|
||||
{"type":"assistant/chunk","seq":19,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":20,"time":1783778297073,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":21,"time":1783778297073,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":22,"time":1783778297073,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,6 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
|
||||
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_workspace_read","title":"Read nested/task.txt","kind":"read","status":"in_progress","locations":[{"path":"nested/task.txt","line":1}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_workspace_read","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
|
||||
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
|
||||
@@ -0,0 +1,21 @@
|
||||
You are an AI agent powered by the DeepSeek Harness SDK.
|
||||
|
||||
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and factual.
|
||||
|
||||
|
||||
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
|
||||
|
||||
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
|
||||
|
||||
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
|
||||
|
||||
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
|
||||
|
||||
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
|
||||
|
||||
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
|
||||
<!-- dsh-user-approval-policy:never -->
|
||||
|
||||
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
|
||||
@@ -0,0 +1,348 @@
|
||||
{
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"command": {
|
||||
"type": "string",
|
||||
"description": "The bash command to execute."
|
||||
},
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
|
||||
},
|
||||
"timeoutMs": {
|
||||
"type": "number",
|
||||
"description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
|
||||
},
|
||||
"workdir": {
|
||||
"type": "string",
|
||||
"description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
|
||||
},
|
||||
"run_in_background": {
|
||||
"type": "boolean",
|
||||
"description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."
|
||||
},
|
||||
"sandbox_permissions": {
|
||||
"type": "string",
|
||||
"description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
|
||||
"enum": [
|
||||
"workspace-write",
|
||||
"danger-full-access"
|
||||
]
|
||||
},
|
||||
"justification": {
|
||||
"type": "string",
|
||||
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"command",
|
||||
"description"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "edit",
|
||||
"description": "Edit an existing UTF-8 text file by replacing literal text.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"file_path": {
|
||||
"type": "string",
|
||||
"description": "Path to edit, resolved by the filesystem backend."
|
||||
},
|
||||
"old_string": {
|
||||
"type": "string",
|
||||
"description": "Literal text to replace. Must match exactly."
|
||||
},
|
||||
"new_string": {
|
||||
"type": "string",
|
||||
"description": "Literal replacement text. Use an empty string to delete the match."
|
||||
},
|
||||
"replace_all": {
|
||||
"type": "boolean",
|
||||
"description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path",
|
||||
"old_string",
|
||||
"new_string"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "read",
|
||||
"description": "Read a UTF-8 text file and return line-numbered content.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"file_path": {
|
||||
"type": "string",
|
||||
"description": "Path to read, resolved by the filesystem backend."
|
||||
},
|
||||
"offset": {
|
||||
"type": "number",
|
||||
"description": "1-based first line to return. Defaults to 1."
|
||||
},
|
||||
"limit": {
|
||||
"type": "number",
|
||||
"description": "Maximum number of lines to return. Defaults to 2000."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "skill",
|
||||
"description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "The exact skill name from the available skills list."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"name"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "subagent",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "A short (3-5 word) description of the delegated task, for display."
|
||||
},
|
||||
"prompt": {
|
||||
"type": "string",
|
||||
"description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
|
||||
},
|
||||
"run_in_background": {
|
||||
"type": "boolean",
|
||||
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "subagent_fork",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "A short (3-5 word) description of the delegated task, for display."
|
||||
},
|
||||
"prompt": {
|
||||
"type": "string",
|
||||
"description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
|
||||
},
|
||||
"run_in_background": {
|
||||
"type": "boolean",
|
||||
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "task_kill",
|
||||
"description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the tool that started the background work."
|
||||
},
|
||||
"reason": {
|
||||
"type": "string",
|
||||
"description": "Optional short reason, recorded in the log and forwarded to the task."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "task_list",
|
||||
"description": "List your background tasks (running and finished) with their ids, kinds, and statuses.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "task_output",
|
||||
"description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the tool that started the background work."
|
||||
},
|
||||
"wait": {
|
||||
"type": "boolean",
|
||||
"description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."
|
||||
},
|
||||
"timeout_ms": {
|
||||
"type": "number",
|
||||
"description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"todos": {
|
||||
"type": "array",
|
||||
"description": "The COMPLETE task list, replacing any previous list.",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"description": "What the task is — a short imperative line."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "pending (not started) | in_progress (now) | completed (done).",
|
||||
"enum": [
|
||||
"pending",
|
||||
"in_progress",
|
||||
"completed"
|
||||
]
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"content",
|
||||
"status"
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"todos"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "workflow",
|
||||
"description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"script": {
|
||||
"type": "string",
|
||||
"description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
|
||||
},
|
||||
"meta": {
|
||||
"type": "object",
|
||||
"description": "The workflow identity block (plain JSON — never code).",
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "Short kebab-case workflow name."
|
||||
},
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "One-line description of what the workflow does."
|
||||
},
|
||||
"whenToUse": {
|
||||
"type": "string",
|
||||
"description": "Optional guidance on when this workflow applies."
|
||||
},
|
||||
"phases": {
|
||||
"type": "array",
|
||||
"description": "Optional phase declarations matched by phase() calls.",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"title": {
|
||||
"type": "string",
|
||||
"description": "The phase title phase() calls match by exact string."
|
||||
},
|
||||
"detail": {
|
||||
"type": "string",
|
||||
"description": "Optional one-line description of the phase."
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "Optional model override this phase is expected to use."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"title"
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"name",
|
||||
"description"
|
||||
]
|
||||
},
|
||||
"args": {
|
||||
"type": "object",
|
||||
"description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"script",
|
||||
"meta"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "write",
|
||||
"description": "Create or fully replace a UTF-8 text file.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"file_path": {
|
||||
"type": "string",
|
||||
"description": "Path to write, resolved by the filesystem backend."
|
||||
},
|
||||
"content": {
|
||||
"type": "string",
|
||||
"description": "Full UTF-8 text content to write."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path",
|
||||
"content"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
snapshot root marker
|
||||
@@ -0,0 +1 @@
|
||||
Root snapshot instruction.
|
||||
@@ -0,0 +1 @@
|
||||
Nested snapshot instruction.
|
||||
@@ -0,0 +1 @@
|
||||
snapshot task
|
||||
@@ -2,7 +2,7 @@
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
# Keyless replay counterpart of workspace-context.cordis.yml. Patches do not
|
||||
# compose across includes, so this applies the scenario config and model swap
|
||||
# directly to the live tree.
|
||||
- id: base
|
||||
name: '@cordisjs/plugin-include'
|
||||
config:
|
||||
path: ./cordis.yml
|
||||
patches:
|
||||
- id: llm-deepseek
|
||||
name: '@deepseek-ai/dsh-llm-deepseek'
|
||||
disabled: true
|
||||
- id: acp-agent
|
||||
name: '@deepseek-ai/dsh-acp-demo'
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
dshHome: !!js process.cwd() + '/.dsh'
|
||||
projectRootMarkers:
|
||||
- .dsh-project
|
||||
persona: |
|
||||
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and factual.
|
||||
- insert:
|
||||
- id: fs-local
|
||||
name: '@deepseek-ai/dsh-fs-local'
|
||||
config:
|
||||
cwd: !!js process.cwd()
|
||||
- id: fs-policy
|
||||
name: '@deepseek-ai/dsh-fs-policy'
|
||||
- id: tool-fs
|
||||
name: '@deepseek-ai/dsh-tool-fs'
|
||||
- id: llm-replay
|
||||
name: '@deepseek-ai/dsh-llm-replay'
|
||||
@@ -0,0 +1,31 @@
|
||||
# Workspace-context snapshot overlay: keep project-root and user-global
|
||||
# discovery inside the scenario's temporary cwd. The app config patch replaces
|
||||
# the whole base config, so the base fields are restated verbatim.
|
||||
- id: base
|
||||
name: '@cordisjs/plugin-include'
|
||||
config:
|
||||
path: ./cordis.yml
|
||||
patches:
|
||||
- id: acp-agent
|
||||
name: '@deepseek-ai/dsh-acp-demo'
|
||||
config:
|
||||
model: deepseek-v4-flash
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
dshHome: !!js process.cwd() + '/.dsh'
|
||||
projectRootMarkers:
|
||||
- .dsh-project
|
||||
persona: |
|
||||
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and factual.
|
||||
- insert:
|
||||
- id: fs-local
|
||||
name: '@deepseek-ai/dsh-fs-local'
|
||||
config:
|
||||
cwd: !!js process.cwd()
|
||||
- id: fs-policy
|
||||
name: '@deepseek-ai/dsh-fs-policy'
|
||||
- id: tool-fs
|
||||
name: '@deepseek-ai/dsh-tool-fs'
|
||||
@@ -14,6 +14,8 @@
|
||||
model: deepseek-v4-flash
|
||||
resumeSessionId: !!js process.env.RESUME_SESSION_ID
|
||||
persistenceRoot: './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
tools:
|
||||
mode: code
|
||||
welcome: 'code-mode agent ready. Give it a multi-tool task.'
|
||||
|
||||
@@ -49,6 +49,14 @@ flowchart LR
|
||||
cfg --> plugin_coding_fs_policy
|
||||
plugin_coding_tool_fs["tool-fs<br/>@deepseek-ai/dsh-tool-fs"]
|
||||
cfg --> plugin_coding_tool_fs
|
||||
plugin_coding_tool_fs_search["tool-fs-search<br/>@deepseek-ai/dsh-tool-fs-search"]
|
||||
cfg --> plugin_coding_tool_fs_search
|
||||
plugin_coding_timeout_policy["timeout-policy<br/>@deepseek-ai/dsh-timeout-policy"]
|
||||
cfg --> plugin_coding_timeout_policy
|
||||
plugin_coding_spill_local["spill-local<br/>@deepseek-ai/dsh-spill-local"]
|
||||
cfg --> plugin_coding_spill_local
|
||||
plugin_coding_spill_policy["spill-policy<br/>@deepseek-ai/dsh-spill-policy"]
|
||||
cfg --> plugin_coding_spill_policy
|
||||
```
|
||||
|
||||
| Plugin id | Package / module |
|
||||
@@ -70,6 +78,10 @@ flowchart LR
|
||||
| `fs-local` | `@deepseek-ai/dsh-fs-local` |
|
||||
| `fs-policy` | `@deepseek-ai/dsh-fs-policy` |
|
||||
| `tool-fs` | `@deepseek-ai/dsh-tool-fs` |
|
||||
| `tool-fs-search` | `@deepseek-ai/dsh-tool-fs-search` |
|
||||
| `timeout-policy` | `@deepseek-ai/dsh-timeout-policy` |
|
||||
| `spill-local` | `@deepseek-ai/dsh-spill-local` |
|
||||
| `spill-policy` | `@deepseek-ai/dsh-spill-policy` |
|
||||
|
||||
Source config: [`examples/coding-agent/cordis.yml`](cordis.yml).
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# REPL agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo`
|
||||
# supplies the agent spine, generic task controls, logging, JSONL persistence,
|
||||
# readline UI, and `main` agent.
|
||||
# supplies the agent spine, workspace instructions, generic task controls,
|
||||
# logging, JSONL persistence, readline UI, and `main` agent.
|
||||
# HMR remains a leaf because it requires Loader internals; `demo:repl` passes
|
||||
# `--expose-internals`. The app bin loads the gitignored root `.env`; this file
|
||||
# reads `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` through `!!js`.
|
||||
@@ -37,6 +37,8 @@
|
||||
# under ./.sessions); unset starts a fresh session each run.
|
||||
resumeSessionId: !!js process.env.RESUME_SESSION_ID
|
||||
persistenceRoot: './.sessions'
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
welcome: 'agent REPL ready. Give it a coding task.'
|
||||
# Keep the persona to identity and behavior; tool plugins own tool guidance.
|
||||
# The loop resolves {{model}} from this agent's configuration.
|
||||
@@ -109,3 +111,29 @@
|
||||
|
||||
- id: tool-fs
|
||||
name: '@deepseek-ai/dsh-tool-fs'
|
||||
|
||||
# Bash-backed discovery tools (glob/grep): fixed ripgrep commands through the
|
||||
# local bash executor above — not ctx.fs. Capped results save the complete
|
||||
# formatted list through the spill backend below (ctx.spillStore, optional).
|
||||
- id: tool-fs-search
|
||||
name: '@deepseek-ai/dsh-tool-fs-search'
|
||||
|
||||
# The tool-call timeout enforcer: arms each declared ToolDefinition.timeoutMs
|
||||
# (the search tools above declare 30s) as a deadline on exec.signal. Without
|
||||
# it a declared budget is advisory and only the bash executor's own timeout
|
||||
# backstop applies.
|
||||
- id: timeout-policy
|
||||
name: '@deepseek-ai/dsh-timeout-policy'
|
||||
|
||||
# Tool-output spill stack: a local backend that saves oversized tool text under
|
||||
# a private session-scoped dir, and the tools/post-execute policy that replaces
|
||||
# an over-budget plain-text result with a preview + the spill locator/retrieval
|
||||
# hint. A leaf pair after the app (needs ctx.tools). The policy is a no-op until
|
||||
# a tool returns more than maxInlineBytes of plain text.
|
||||
- id: spill-local
|
||||
name: '@deepseek-ai/dsh-spill-local'
|
||||
|
||||
- id: spill-policy
|
||||
name: '@deepseek-ai/dsh-spill-policy'
|
||||
config:
|
||||
maxInlineBytes: 50000
|
||||
@@ -1,10 +1,10 @@
|
||||
import { mkdtemp, readFile, rm } from 'node:fs/promises'
|
||||
import { mkdtemp, mkdir, readFile, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools'
|
||||
@@ -14,6 +14,9 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
|
||||
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
|
||||
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
|
||||
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
|
||||
import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
|
||||
import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context'
|
||||
|
||||
/**
|
||||
* With-key Code Mode proof: a real model receives only `run_code`, composes two
|
||||
@@ -23,6 +26,7 @@ import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
|
||||
|
||||
const PERSONA = 'You are coding-agent. You work by writing TypeScript programs for run_code: '
|
||||
+ 'batch related tool work into one program and print or return ONLY the findings that matter.'
|
||||
const WORKSPACE_PROBE = 'dragonfruit-8675309'
|
||||
|
||||
let ctx: Context | undefined
|
||||
let workdir: string | undefined
|
||||
@@ -52,6 +56,22 @@ async function codeModeHarness(cwd: string): Promise<Context> {
|
||||
return harness
|
||||
}
|
||||
|
||||
async function workspaceCodeModeHarness(): Promise<Context> {
|
||||
const harness = new Context()
|
||||
await harness.plugin(LlmService)
|
||||
await harness.plugin(SessionStore)
|
||||
await harness.plugin(SystemPrompt, { persona: PERSONA })
|
||||
await harness.plugin(ToolRegistry, { mode: 'code' })
|
||||
await harness.plugin(AgentRegistry)
|
||||
await harness.plugin(LocalFileSystem, { cwd: '/' })
|
||||
await harness.plugin(ToolFs)
|
||||
await harness.plugin(WorkspaceContext, { maxBytes: 65536 })
|
||||
await harness.plugin(AgentLoop, { agents: [] })
|
||||
await harness.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
|
||||
await harness.plugin(WorkerCodeRuntime, {})
|
||||
return harness
|
||||
}
|
||||
|
||||
function waitForIdle(harness: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = harness.on('agent/status', (subject, status) => {
|
||||
@@ -107,4 +127,43 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
|
||||
expect(finalText).toContain('alpha-7')
|
||||
expect(finalText).toContain('beta-9')
|
||||
}, 180_000)
|
||||
|
||||
it('delivers nested workspace instructions discovered by an fs sub-call after the outer result', async () => {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-workspace-e2e-'))
|
||||
await mkdir(join(workdir, '.git'), { recursive: true })
|
||||
await mkdir(join(workdir, 'pkg/deep'), { recursive: true })
|
||||
await writeFile(join(workdir, 'pkg/AGENTS.md'), `If asked for the Code Mode workspace handshake, reply with exactly ${WORKSPACE_PROBE} and nothing else.\n`)
|
||||
await writeFile(join(workdir, 'pkg/deep/task.txt'), 'Touch this file to discover the nested instructions.\n')
|
||||
ctx = await workspaceCodeModeHarness()
|
||||
const handle = await ctx.agents.create({
|
||||
agentId: AgentId('e2e-code-mode-workspace'),
|
||||
sessionId: SessionId('e2e-code-mode-workspace-session'),
|
||||
meta: { cwd: workdir },
|
||||
agentOptions: { model: 'deepseek-v4-flash' },
|
||||
})
|
||||
|
||||
handle.agent.send([{
|
||||
type: 'text',
|
||||
text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
|
||||
}])
|
||||
await waitForIdle(ctx, handle.agent as ReactLoopAgent)
|
||||
|
||||
const events: SessionEvent[] = [...handle.agent.session.events]
|
||||
const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
|
||||
const outerResult = events.find(event => event.type === 'tool/result')
|
||||
const workspaceContext = events.find(event => event.type === 'context/message'
|
||||
&& typeof event.data.meta === 'object'
|
||||
&& event.data.meta !== null
|
||||
&& !Array.isArray(event.data.meta)
|
||||
&& event.data.meta.kind === 'workspace-instructions')
|
||||
expect(dispatch).toBeDefined()
|
||||
expect(outerResult).toBeDefined()
|
||||
expect(workspaceContext).toBeDefined()
|
||||
expect(workspaceContext!.seq).toBeGreaterThan(outerResult!.seq)
|
||||
const finalMessage = events.findLast(event => event.type === 'assistant/message')
|
||||
const answer = finalMessage?.type === 'assistant/message'
|
||||
? finalMessage.data.content.filter(block => block.type === 'text').map(block => block.text).join('')
|
||||
: ''
|
||||
expect(answer).toContain(WORKSPACE_PROBE)
|
||||
}, 180_000)
|
||||
})
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user