Commit Graph

6 Commits

Author SHA1 Message Date
Tianyi Cui
6fdd048123 fix(agent-loop): harden lifecycle edge cases 2026-06-17 21:25:47 +08:00
Tianyi Cui
fb9636db44 feat(acp): ACP bridge — drive the coding agent from an editor over JSON-RPC stdio
Implements the RFC 010 MVP: a new `@deepseek-ai/dsh-acp` package bridges the
harness agent to the Agent Client Protocol (JSON-RPC 2.0 over newline-delimited
stdio), so Zed and other ACP editors can drive the coding agent — streaming
render, tool-call display, and resumable sessions via `session/load`.

- packages/acp: AgentSideConnection wiring; initialize/newSession/loadSession/
  prompt/cancel; a total TurnEndReason→StopReason codec; settle-once with a
  fallback chain (agent/turn-end → logged turn/end → idle); single-session
  guard; cwd-must-equal-launch-dir validation; load replays from the persisted
  event log (assistant/chunk→agent_message_chunk, tool/call/result→tool_call*).
- agent: add Agent.whenIdle() quiescence signal to the interface; LoopAgent
  implements it (resolves on the first running→idle/disposed transition). The
  bridge awaits it on disposal so teardown reaches quiescence, not just abort.
- examples: extract the shared provider/tool core into examples/base.yml;
  coding-agent nest-includes it; new examples/acp-agent serves the agent over
  ACP with JSONL persistence and no stdout logger (stdout is the protocol).
- Permission gate deferred (TODO(rfc010-permission-gate)): tools run with the
  executor's full authority; only the Agent→sessionId ownership seam is laid
  down. Cancel is best-effort for a not-yet-started queued turn
  (TODO(rfc010-cancel-prestep)). RFC 010 stays `proposed`.
- Docs: package README + Zed snippet; client-driver cookbook section; root and
  packages layout/commands; RFC 010 implementation-status note.

48 bridge tests + whenIdle coverage; 100% per-file coverage; e2e boots the
example as a subprocess and verifies a written file on disk (key-gated, with a
no-key stdout-purity check).
2026-06-16 18:44:31 +08:00
Tianyi Cui
4535bfab75 fix(agent-loop): decide turn balance + idle-injection flush from the log (review #32)
Session.append pushes the event BEFORE notifying session/event listeners,
so a throwing listener leaves the event in the log while the line after
the append (a boolean flag) never runs. Both turn-balance decisions were
gated on such flags, so a throwing listener could strand an open turn or
skip a durability checkpoint.

- loop.ts: the outer catch decided "turn/end owed" from `turnStarted`.
  A throwing listener on the turn/start append left turn/start logged but
  the flag false → catch rethrew and skipped turn/end → permanently open
  turn (violating ADR 0017). Now decided from the log (this turn's
  turn/start present), so the turn is always balanced; only a genuine
  pre-push failure (non-serializable trigger — turn/start never logged) is
  rethrown to the runLoop backstop. Removed the now-dead `turnStarted`.

- agent.ts inject(): the idle one-shot-turn flush was gated on a
  `turnRecorded` flag set after append('turn/end'); a throwing turn/end
  listener skipped the flush, losing the balanced in-memory injection turn
  on crash. Now the flush decision is read from the log, the synthetic
  turn/end append contains a throwing listener (turn stays balanced), and
  a failing idle flush is reported via agent/error (step 0 convention) AND
  the logger — mirroring the loop's post-turn/end flush path — with a
  throwing agent/error listener contained.

Rewrote the test that encoded the old (buggy) "turn/start listener throw
is rethrown, no turn/end" semantics to assert the balanced-turn contract,
and added regressions for the throwing-turn/end-listener flush and the
agent/error report. Updated Agent.inject JSDoc.
2026-06-15 23:44:54 +08:00
Tianyi Cui
b0bc0b5792 feat(agent-loop): turn-enclosure invariant + post-turn error model
Every session event now lives inside a turn (between turn/start and its
turn/end). The loop records queued user/message events AFTER turn/start;
an idle agent.inject() wraps its context/message in a one-shot injection
turn. This makes the turn the single durability/replay boundary so a
persistence backend can treat anything after the last turn/end as a
crash tail without dropping legitimate between-turn context.

A failure once the turn is already closed (rejecting session/flush, a
throwing agent/turn-end listener) has no in-turn position for a session
error event, so it is reported via agent/error + logger only; the turn
stays balanced. failTurn appends an error event only while the turn is
open.

The dsh-invariants plugin enforces turn-enclosure via a default case:
every non-boundary event type — including plugin-added merge-extensible
keys — must sit inside an open turn or it throws.

Documented in ADR 0017 + architecture.md.
2026-06-15 20:56:17 +08:00
Tianyi Cui
225ed051b1 Add branded ID types: CallId, SessionId, AgentId
Nominal string types via a unique-symbol brand (zero runtime cost):
an AgentId can no longer be passed where a CallId is expected. Each
core package brands the IDs it owns — CallId in dsh-llm (tool-call
correlation across blocks, chunks, session events, and execution
results), SessionId in dsh-session, AgentId in dsh-agent. Construction
goes through same-named factory functions; public string-in APIs
(sessions.create, agentLoop.create) keep accepting plain strings and
brand internally. Policy note in the brand module: brand IDs that
cross package boundaries, not every string.
2026-06-11 15:17:56 +08:00
Tianyi Cui
bfb034830f Enforce 100% per-file test coverage on packages/*/src
vitest coverage (v8 provider) with per-file 100% thresholds for
statements, branches, functions, and lines. Scope: our runtime source
only — types-only files, vendor/ (upstream code), and examples/
(exercised by the demo smoke test) are excluded. yarn test:coverage
runs the gate.

59 tests added to close every gap: llm generate-waterfall and adapter
disposal; assembler edge protocol (duplicate block-start, stragglers
after block-end, id fallback, usage omission, invariant violation);
the whole Inbox surface incl. the wakeup-overwrite race; LoopAgent
disposed-state throws and double-stop idempotence; config-driven agent
creation; loop backstop catches (throwing turn-start/turn-end
listeners, non-Error throws, non-JSON tool arguments); system-prompt
dynamic sections and disposer paths; tools errorMessage fallbacks and
the full schema-DSL emission matrix. Genuinely unreachable defensive
guards carry /* v8 ignore */ comments with stated reasons rather than
deletion (132 tests total).
2026-06-11 14:58:36 +08:00