DeepSeek/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: name the persistence-catalog gate for the tool/code-dispatch event

Browse Source 
Research finding: a SessionEventMap member is a log event — JSDoc prose
required, @mode is a hard error there, and docs/persistence-catalog.md
must be regenerated (todo/write is the log-only precedent). PR4's plan
now names both.
This commit is contained in:
Tianyi Cui
2026-07-08 01:02:37 +08:00
committed by lintianle
parent 00ee92b278
commit e90103ac05
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/rfc/proposed/feature/2026-06-15-code-mode.md
View File

@@ -46,7 +46,7 @@ Under `'code'` and `'both'` the registry registers `run_code` in itself as an or
### Observability: `tool/code-dispatch`
Each sub-dispatch appends one session event, declared by `dsh-tools` via `SessionEventMap` declaration merging (the map is merge-extensible for exactly this): `tool/code-dispatch` with `{ parentCallId, subCallId, name, arguments, isError, resultSummary }`. It is log-only — `deriveEventMessage()` ignores unknown event types by design, so sub-calls never re-enter model context — but persistence and UIs get every call. A `run_code` execution arriving without `exec.agent` (the loop always supplies it; direct programmatic calls may not) still runs and simply skips event logging, exactly as the `ToolExecution` contract allows.
Each sub-dispatch appends one session event, declared by `dsh-tools` via `SessionEventMap` declaration merging (the map is merge-extensible for exactly this; `todo/write` is the log-only precedent): `tool/code-dispatch` with `{ parentCallId, subCallId, name, arguments, isError, resultSummary }`. It is log-only — `deriveEventMessage()` ignores unknown event types by design, so sub-calls never re-enter model context — but persistence and UIs get every call. As a log event it carries JSDoc prose but **no `@mode` tag** (that vocabulary belongs to cordis bus events; the persistence-catalog generator hard-errors on one) and lands in the regenerated `docs/persistence-catalog.md`; appends happen inside `run_code`'s execution, so the turn-enclosure invariant is satisfied by construction. A `run_code` execution arriving without `exec.agent` (the loop always supplies it; direct programmatic calls may not) still runs and simply skips event logging, exactly as the `ToolExecution` contract allows.
### The code-runtime seam
@@ -87,7 +87,7 @@ Four stacked PRs, each gates-green (`typecheck`, `lint`, `test:coverage`, `test:
1. **This RFC revision** (docs-only): the file rewritten as above (renamed `2026-06-15-code-mode.md`, same first-proposed date), regenerated RFC index.
2. **`dsh-code-runtime`** (interface package): the group `packages/code-runtime/`, abstract `CodeRuntime`, vocabulary types, ctx-key declaration, group README + package README + catalog updates. Unit tier: HMR safety (dispose removes `ctx.codeRuntime`), contract docs. This package has no behavior to snapshot or e2e; its coverage story is unit-only by design.
3. **`dsh-code-runtime-worker`**: the implementation above. Unit tier (real workers, no mocks — they are cheap and local): output/value capture, log source attribution, error kinds (exception incl. non-erasable syntax, timeout vs abort vs worker-exit under OOM), compute-time-only timeout (a slow binding does not expire the run), binding bridge hostility cases (unknown name, duplicate id, post-settlement message), structured-clone fallback, cap truncation, `env` emptiness verified from inside the program, dispose-awaits-exit. A real-load-path test runs the built package (`lib/`) so the worker entry resolves both unbuilt (tsx) and built — the published-bin guard from [docs/testing.md](../../../testing.md).
4. **Native code mode in `dsh-tools`** + the end-to-end surface: mode config, provider switch, `tools:sdk` section, `jsonSchemaToTs`, `run_code` + dispatch bridge + serialization queue, `tool/code-dispatch` event; [docs/architecture.md](../../../architecture.md) (tool-pipeline section + `ctx.codeRuntime` service row) and the [adding-a-tool cookbook](../../../cookbook/adding-a-tool.md) cross-reference updated in the same change; an `examples/` leaf + `demo:code` script wiring the worker runtime with `mode: 'code'`; move this RFC to `implemented/`. Coverage named per tier now, per the plan-time rule: **unit** — codegen table (DSL subset, quoted names, `unknown` degradation, determinism), provider contribution per mode, `toolOrder × mode` rejection, missing-runtime/wrong-language loud failures, serialization non-overlap (a probe tool records enter/exit under `Promise.all`), abort stops the queue, binding rejection on `isError`, `CodeRunFailedError` → structured `isError`, event payloads, `deriveMessages()` ignores the event, HMR safety (mode flip via config reload removes tool + section); **e2e (with-key, self-skips)** — a real model, `mode: 'code'`, a task requiring two tool calls and curation, asserting the wire tool list was exactly `run_code` and the transcript's dispatch events; **snapshot (keyless replay)** — goldens for a `run_code` turn in `'code'` and `'both'`, pinning the SDK section text, the collapsed header tools, dispatch events, and the result card.
4. **Native code mode in `dsh-tools`** + the end-to-end surface: mode config, provider switch, `tools:sdk` section, `jsonSchemaToTs`, `run_code` + dispatch bridge + serialization queue, `tool/code-dispatch` event (+ regenerated `docs/persistence-catalog.md`); [docs/architecture.md](../../../architecture.md) (tool-pipeline section + `ctx.codeRuntime` service row) and the [adding-a-tool cookbook](../../../cookbook/adding-a-tool.md) cross-reference updated in the same change; an `examples/` leaf + `demo:code` script wiring the worker runtime with `mode: 'code'`; move this RFC to `implemented/`. Coverage named per tier now, per the plan-time rule: **unit** — codegen table (DSL subset, quoted names, `unknown` degradation, determinism), provider contribution per mode, `toolOrder × mode` rejection, missing-runtime/wrong-language loud failures, serialization non-overlap (a probe tool records enter/exit under `Promise.all`), abort stops the queue, binding rejection on `isError`, `CodeRunFailedError` → structured `isError`, event payloads, `deriveMessages()` ignores the event, HMR safety (mode flip via config reload removes tool + section); **e2e (with-key, self-skips)** — a real model, `mode: 'code'`, a task requiring two tool calls and curation, asserting the wire tool list was exactly `run_code` and the transcript's dispatch events; **snapshot (keyless replay)** — goldens for a `run_code` turn in `'code'` and `'both'`, pinning the SDK section text, the collapsed header tools, dispatch events, and the result card.
The four PRs land in order (each on the previous); per stacked-review practice, review fixes land on the PR that introduced them and merge down.