Files
deepseek-harness/docs/tool-execution-pipeline.md
T
Tianyi Cui aacedf2700 Merge current master into debug-pangwenjie
# Conflicts:
#	docs/cordis-catalog/events.md
#	docs/core-data-structures/core.md
#	docs/core-data-structures/tools.md
#	docs/event-producer-consumer.md
#	docs/rfc/implemented/feature/2026-06-30-interception-seams.md
#	docs/tool-execution-pipeline.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent-loop/tests/loop.spec.ts
#	packages/core/agent/README.md
#	packages/core/tools/src/index.ts
#	scripts/gen-doc-graphs.ts
2026-07-18 13:39:12 +08:00

54 lines
3.4 KiB
Markdown

<!-- Generated by scripts/gen-doc-graphs.ts - do not edit by hand.
Run `pnpm run gen-doc-graphs` to regenerate. -->
# Tool Execution Pipeline
This graph shows where policy, hooks, sandboxing, filesystem guards, result rewriting, final-outcome observation, and UI rendering fit without changing the loop. The transformable extension points are the `tools/pre-execute`, `tools/execute`, and `tools/post-execute` waterfalls; monotonic guards and `tools/result` are the owner-enforced boundaries around them.
```mermaid
flowchart TD
model["Assistant message contains tool-call block"]
toolCall["Session event: <code>tool/call</code><br/>logged before execution"]
presentCall["UI pending card<br/>presentCall(args)"]
pre["<code>tools/pre-execute</code> waterfall<br/>hooks, permission, sandbox"]
guards["Registered monotonic guards<br/>deny or abstain; identity protected"]
denied["denied or approval refused<br/>tool body skipped"]
approval["<code>ctx.approval</code> one-shot prompt<br/>absent or unanswerable: deny"]
around["<code>tools/execute</code> waterfall<br/>timeout, retry, metrics (around dispatch)"]
toolBody["Registered tool execute() body"]
fsGate["<code>fs/write-intent</code> or <code>fs/edit-intent</code><br/>tool-fs mutations only"]
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["Active-batch additionalContexts FIFO<br/>context/message after recorded tool results"]
toolResult["Session event: <code>tool/result</code><br/>single model-facing outcome"]
allResults["Tool batch settled<br/>recorded tool/result events complete"]
presentResult["UI completed card<br/>presentResult(args, result)"]
model --> toolCall
toolCall --> presentCall
toolCall --> pre
pre -->|allow| guards
guards -->|allow| around
guards -->|deny| denied
around --> toolBody
pre -->|deny| denied
pre -->|ask| approval
approval -->|allowed-once| guards
approval -->|rejected, cancelled, unavailable| denied
denied --> post
toolBody --> fsGate
fsGate --> toolBody
toolBody --> owned
toolBody --> around
around --> post
post --> final
final --> toolResult
toolResult --> presentResult
toolResult --> allResults
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 `additionalContexts` to preserve call/result adjacency.
Maintenance mode: curated Mermaid flow; exact tool schemas and event signatures live in generated catalogs.