Merge remote-tracking branch 'origin/master' into feat/acp-2-bridge

# Conflicts:
#	.agents/skills/dsh-code-review/SKILL.md
#	AGENTS.md
#	docs/rfc/proposed/2026-06-14-acp-agent-client-protocol.md
This commit is contained in:
Tianyi Cui
2026-06-18 03:31:04 +08:00
80 files changed
+564 -384

No files matched your search

@@ -301,7 +301,7 @@ describe('disposed vs aborted branching', () => {
})
})
describe('structured tool error propagation (RFC 005 pt 2)', () => {
describe('structured tool error propagation (the runtime-validation RFC, part 2)', () => {
it('forwards a tool HarnessError onto the tool/result session event', async () => {
const { HarnessError } = await import('@deepseek-ai/dsh-llm')
// First model turn calls the tool; second turn (after the tool result is
+4 -4
View File
@@ -1,8 +1,8 @@
/**
* Property-based tests for the agent loop's inbox/turn scheduling (RFC 001 →
* ADR 0013). Deterministic by construction: schedules are driven through the
* `agent/status` settle signal (no wall-clock sleeps), so a flake is a finding,
* not timing noise.
* Property-based tests for the agent loop's inbox/turn scheduling (the
* property-testing RFC). Deterministic by construction: schedules are driven
* through the `agent/status` settle signal (no wall-clock sleeps), so a flake
* is a finding, not timing noise.
*
* Invariants: every sent message appears exactly once in the log (none lost);
* turn numbers strictly increase; status transitions follow the legal machine
+2 -2
View File
@@ -39,7 +39,7 @@ function waitForIdle(ctx: Context, agent: LoopAgent): Promise<void> {
})
}
describe('RFC 009: AgentLoop factory create/resume', () => {
describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => {
const adapter = new MockAdapter([textResponse('hi')])
const { ctx } = await persistentHarness(adapter)
@@ -128,7 +128,7 @@ describe('RFC 009: AgentLoop factory create/resume', () => {
it('an idle inject() is flushed durably on its own (survives without explicit flush/dispose)', async () => {
// Lifecycle 1: run a turn, then inject context while idle. The idle inject
// wraps its context/message in a one-shot turn AND checkpoints it (ADR 0017)
// wraps its context/message in a one-shot turn AND checkpoints it (the turn-enclosure RFC)
// — without an explicit flush or clean dispose, the notice must still reach
// disk, since a crash before the next turn would otherwise lose it.
const adapter1 = new MockAdapter([textResponse('answer')])
@@ -619,7 +619,7 @@ describe('P1-6: step/start is appended before agent/step-start is emitted', () =
const agent = ctx.agentLoop.create('a-step-order', { model: 'mock' })
// Capture, at the moment agent/step-start fires, whether the matching
// step/start event is already in the log (append-before-emit, ADR 0003).
// step/start event is already in the log (append-before-emit, the event-sourcing RFC).
const observed: { turn: number; step: number; lastEventType: string | undefined; sawStepStart: boolean }[] = []
ctx.on('agent/step-start', (subject, turn, step) => {
if (subject !== agent) return
@@ -828,7 +828,7 @@ describe('P1-5: a started turn (and any open step) is always closed on a boundar
// loop must therefore still owe (and append) a turn/end — deciding "owed"
// from the log via isTurnOpen, not a "turn started" flag that the throw
// skipped. Otherwise the turn stays permanently open and poisons the next
// turn/replay (ADR 0017). (Uses the plain harness — NOT the invariants
// turn/replay (the turn-enclosure RFC). (Uses the plain harness — NOT the invariants
// oracle — because the throwing listener is itself a session/event
// subscriber.)
const adapter = new MockAdapter([textResponse('turn 2')])
@@ -868,7 +868,7 @@ describe('P1-5: a started turn (and any open step) is always closed on a boundar
// Regression: a normal turn completes, closeTurn(true) appends turn/end and
// emits agent/turn-end whose listener throws. The error must NOT be appended
// as a session event after turn/end — that would sit past the commit
// boundary and be dropped as a crash tail on resume (ADR 0017). It is
// boundary and be dropped as a crash tail on resume (the turn-enclosure RFC). It is
// surfaced via agent/error instead, and the log's last event is turn/end.
const adapter = new MockAdapter([textResponse('done'), textResponse('next ok')])
const ctx = await balancedHarness(adapter)