core.md read as a type grab-bag: LLM wire vocabulary up front, the agent/loop story buried, and no correspondence to packages/core. It now opens on the packages/core control spine — the package-by-package loop map with a Page column into session/system-prompt/tools/scope — and keeps only what the spine group declares plus the repo-wide patterns: the Agent handle with its delivery/cancellation/interception contracts, the SessionEvent envelope, branded ids, the …Map pattern. The conversation vocabulary (Message/ContentBlock, the model request, adapters — 17 type-equiv blocks) moves to llm-streaming.md, which now declares packages/llm end-to-end; the duplicate ContentBlockMap paste near its seam section folds into the moved section, and the manifest, LINK_MAP, README table rows, website label (Core data structures → Core), and inbound anchors follow.
Every packages/<group>/README pair is now a thin front door in one shape: a why-first intro (bash's seam-pattern-first paragraph rewritten as 'shell execution for the agent'), the package table, and a closing pointer to the owning docs/subsystems page — the bash-style table stays the load-bearing middle. Load-bearing trailing paragraphs relocate rather than vanish: the fs no-timeout rationale becomes a filesystem.md section (both languages), session's four sectioned tables merge into one 12-row table, examples' legacy-bin H2 collapses to a pointer at jsonrpc-demo's README, and design rationale that already lives in an Agent Note or subsystem page is now linked instead of restated. All 40 pair records re-recorded.
git mv per the regrouping RFC: the five human-collaboration seams and
tui join packages/interaction/, app-boot becomes packages/boot/, and
jsonrpc joins the renamed scaffold/ (formerly sdk/) as its server half
beside client/protocol/create-sdk/helper/scripts/telemetry, whose
folders drop the legacy sdk- prefix. Three new group README triplets
replace the ui/ and sdk/ ones; tsconfig references/paths/globs,
knip keys, vitest globs, gate scripts, catalogs, docs, and the
lockfile follow. Adds the four settled FIXME rename markers
(dsh-sdk-server, dsh-sdk-telemetry, dsh-sdk-helper, dsh-sdk-scripts).
The scaffold folders diverge from their npm names until those renames
land, so tsconfig.base.json maps the three affected names explicitly
beside the group wildcard. Also repairs two pre-existing stale-path
classes the strengthened sweep surfaced: docs/web-styling.md's retired
web-ui host package and type-model spec fixture-literal joins.
app-boot's three Loader-composition specs time out at the default 5s
under full-suite parallel load on this filesystem (pre-existing;
pass isolated with --testTimeout=30000); interaction/scaffold/boot
suites otherwise green (687 passed).
All agent/* and agent-loop/config-start-failed events take one payload
object carrying the agent subject; waterfall/serial payloads require a
signal and keep next as the final argument. PreStepContext and
RequestFailureContext are unfolded into payloads and retired.
goal/changed follows the same shape so agentEvents keeps its listener
error containment. ReactLoopAgent builds its scope carrier once in the
constructor. Regenerates scope resolvers, tool-cordis api catalog, and
docs catalogs; updates all affected listeners, tests, and the
core-data-structures docs (en + zh).
TurnEndReasonMap aborted endings no longer map to 'cancelled': the ACP
spec reserves StopReason::Cancelled for the client's own session/cancel
notification (plus disposal, both settled out of band). A turn aborted by
a hook or another agent owner is ordinary quiescence and now settles as
end_turn, matching the README/note contract. interrupted keeps
'cancelled' as the crash-orphan marker.
- turn boundary now returns false for an empty admitted batch (claimed
input removed before the wake) instead of opening a turn and spending a
model call on nothing; the step boundary already had the symmetric guard.
- a max-token step stays sticky when steering or injected work continues
the turn: a later completed step no longer downgrades the outcome,
matching the TurnEndReasonMap contract.
- session/queue wire schema accepts the context placement (previously the
zod union rejected injected-context snapshots wholesale and the client
silently dropped the whole frame); schema tests cover all placements.
- headless runs settle at whole-agent idle instead of the first turn/end,
honoring the one-shot idle-to-idle contract.
- flush JSDoc names the real callers (checkpoint policy, goal-session,
teardown, self-flushing consumers); apiproxy zh README loses its stale
duplicate history section; ACP note/README record the delivered error
rejection and turnless-cancelled behaviors.
TurnEndReasonMap.error now carries a single `error: LlmFailure` field:
an LlmError keeps its structured facts, any other error flattens to
errorChain text under the UNKNOWN code. Consumers read message/code
directly instead of defending against an unknown union — this also fixes
errorChain() rendering structured failures as '[object Object]' in the
TUI and ACP error paths. Document the turn-stopping contract: a
concludesTurn result never short-circuits already-submitted next-step
work (same-step additionalContexts or racing steering still runs), data
decides.
A prompt now resolves only when the agent reaches quiescence: the
correlated turn/end arms an endReason instead of settling immediately,
so steering or injected work that runs further turns before idle no
longer splits one prompt across the automation wire. Token-limit turn
endings settle as end_turn per the README contract (they are not
prompt-level stop reasons); model errors still reject immediately, and
explicit ACP cancellation stays 'cancelled'.
ACP waits for every owned Agent disposal and throws one AggregateError when any Session teardown fails. The aggregate message embedded each rejected value with String(failure) because the connection-close logger itself renders only the outer error message. String preserves only an Error name and message, so causes and AggregateError members disappeared from the operational warning.
Render each per-session rejection with the existing errorChain diagnostic helper before joining it into the outer message. The original rejected values remain in AggregateError.errors for programmatic inspection, while the message now carries cause chains and nested aggregate members through the String-based logger.
Exercise a disposal failure containing both AggregateError members and a nested cause, while retaining the existing barrier that proves the second Session finishes disposal before any warning is emitted. All 10 ACP disposal tests pass and the ACP TypeScript project builds cleanly.
The connection-close teardown path threw a bare `AggregateError` whose
message counts the failed sessions, and its only production consumer logs
through `String(error)` — which renders the message alone. Compared with
the previous `Promise.all` behavior, every actual disposal failure reason
disappeared from operational logs.
Join the per-session reasons into the aggregate message, matching the
subagent seam's own aggregate disposal messages, and pin the reason in
the dispose spec's warning assertion.
Round 1 traded one teardown ordering problem for another. The observer now
splits capture from emission, which satisfies both consumers at once:
- Terminal facts are captured while the child is still registered, so consumers
that resolve it for the child's log and scope still work.
- The edge is emitted only after handle disposal settles, so a rejecting scoped
cleanup is reported as a failed epoch instead of a successful one.
Also:
- Keep the Activation in the map until disposal settles. Removing it first let a
racing followup() see no Activation and cold-resume into the still-registered
agent, and let a concurrent forest drain skip a still-disposing child and
release its parent first.
- Derive terminal telemetry from this epoch's event suffix rather than the whole
session, so a cold resume whose prompt is blocked no longer reports the
previous epoch's answer and turn reason.
- Cancel the ACP bridge's own prompts before awaiting the descendant drain: a
drain can block on persistence, and the top-level agents must not keep running
model and tool work for its whole duration.
Pins that the bridge releases the Activation forest before its own sessions, and
that a failed drain is reported without stranding that teardown. Reads the one
teardown method structurally so the bridge keeps no dependency on the subagent
seam.
A continuable Activation outlives the turn that started it and owns descendant
teardown, so the bridge must drain that forest child-first before releasing the
top-level agents whose runtime the descendants depend on.
Also rewrites the authored continuable snapshot transcript for the Task-free
tool surface; the scenario's keyless replay is still under diagnosis.
agent-loop: behavior tests for retry-while-busy, cancelled recovery
windows, no-facts stream failures, idle-listener preemption, rejected
driver promises under whenIdle, finish-chunk failures after step close,
presentationMeta persistence, pre-aborted and torn-down create/resume
signals, and configured-start failures over existing artifacts or after
teardown. The remaining guards that no public path can reach carry
justified v8 ignore annotations naming the invariant that starves them.
acp bridge: cover the retry-adoption path (a retry turn resolves the
prompt the failed turn deferred), the no-retry quiescence rejection, and
the admission-blocked cancelled settlement; the synchronous send-throw
catch is annotated as a future-proofing guard since the machine's send()
contains listener failures.
The automation bridge inherited two master-era assumptions the message
machine no longer honors. A prompt blocked at pre-turn admission opens no
turn, so no turn/end could ever settle it — the bridge now watches
whenIdle() and reports a turnless slot as cancelled (the disposed-agent
guard moved to a registry identity check before send). A failed turn no
longer rejects at its turn/end either: agent.retry() closes the failed
turn and opens a successor on the same history, so the bridge holds the
terminal error and lets a retry-triggered turn/start adopt the prompt,
rejecting only at quiescence with no successor.
Also: refresh the empty-response-retry fixture for retry-as-turn logging,
adapt master-side tests to the unified send()/UserMessageData API and
registry-fact disposal, resync the doc pairs both sides touched, trim
architecture.md back under its word ceiling, and regenerate the event and
persistence catalogs.
