- Mount WorkspacesService.startInitialSelection in the runtime apply (the
one-shot baseline follower shipped in 98633b5aa without a caller): a
restored current session wins, an explicit clear stays cleared, a failed
connect retries on the next baseline projection.
- Cover the policy in client-apply and the assembled workspace-flow
snapshot; startup now lands in the recent Workspace's blank session, so
the draft-carry scenario starts from the hero directly.
- Bring docs along: startup-selection paragraphs in the session-scope RFC
note (both languages), bilingual README pairs for the four new client
packages, doc-graph regeneration with client-declared events exempt from
the dispatcher requirement (client dispatch sites are structurally
invisible to the host-side ts.Program), and pairing re-records.
The briefing now maps each update at the narrowest safely aligned
granularity, widening deterministically on mapping failure: a change
confined to the pair's byte-identical code fences is computed outright
(--apply splices it into the counterpart and validates the result
against the pairing gate's structural signature before writing);
otherwise changed Markdown units — headings, paragraphs, table rows,
list items, fences, block quotes, HTML blocks, thematic breaks, link
definitions, matched by container-scoped kind sequences — each carry
their last-confirmed source, current source, and current counterpart
text; units that do not align fall back to depth-matched heading
sections (depth only, so translated heading text still maps); and when
sections do not align either, or both sides drifted, the briefing says
so and withholds the mapping. Terminology rows now match the changed
spans only, English terms on word boundaries with plural inflections,
and Chinese-target briefings track each relevant term's document-wide
first occurrence — a moved occurrence pulls the vacated and receiving
spans into the briefing with an explanatory note.
The unit mapping, mechanical code splice, and first-occurrence tracking
adopt the planner design from the incremental prompt-pipeline PR (#684),
whose provider-backed bake-off independently validated the same scope
ladder; this PR carries those mechanics into the agent-facing briefing
path so both consumers of the consistency records behave alike. The
prior line-hunk section mapping and its heading-text alignment (which
could not map cross-language sections) are replaced wholesale.
Docs: SKILL.md update path, i18n README pair, development.md pair, and
the briefed-updates Agent Note pair brought along; the development.md
fence edit was applied with --apply itself, and the prose updates were
made through the new unit/section briefings.
The dsh-translate-docs skill now triages updates onto a briefing-driven
path — gen-translation-brief output as the translator's whole working
set, orchestrator-applied mechanical fence edits, scoped record/check —
while the whole-document path for new pairs is unchanged. The i18n
README documents the scoped gate forms and the briefing tool;
development.md lists the new command; the new bilingual Agent Note
records the decision and the ten-example benchmark behind it (briefed
path ~1/3 the tokens and wall clock of the corpus-loading path at equal
judged quality; whole-document re-translation rejected on preservation
collapse). Counterpart updates in this commit were produced with the
new briefed path; the new note's Chinese side is a whole-document
translation.
Responding to review on #661: a public method on the generic ToolRegistry
service whose only caller is the run_code bridge was ad-hoc surface
widening. The bridge now receives it as a registry-private capability
closure in RunCodeBridgeOptions (the requireRuntime idiom, alongside the
cap), the method is private, and it leaves the generated service
catalog/API surfaces.
The pattern is now named as a code smell where reviewers look: the
packages/AGENTS.md capability-interface rule gains the inverse-smell
clause (ceiling 660→675 — the list is at capacity and the clause needs
one sentence), and dsh-code-review's capability-fit check tells reviewers
to flag single-consumer public service methods and require the closure
form.
Validate replay sidecars and cross-copy failure facts, make browser console tripwires and macOS temp paths deterministic, and wait for asynchronous TUI resume details. Keep the owning docs, translations, and generated catalog aligned.
Conflict resolution: scripts/type-equiv.manifest.json takes master's new
paired-derivative format (one primary entry per pair) and re-adds this
stack's CodeDispatchLog entry in that format. zh README pairs brought
along for the dispatch-log arm (spill-policy behavior/limitations bullets,
tools limitation bullet now pointing at the shipped bounding).
Master made bilingual pairing mandatory repo-wide; this PR's seam-split
edits to the tasks docs get their zh counterparts: a new pair for the
dsh-tasks-local README and minimal updates to the tasks core-data doc,
agent-spine-demo README, and the tasks family READMEs, with pairing
records re-recorded.
Responding to ds-review-bot round 2 on #661:
- logWork is bounded: past maxParallelSubCalls pending shaped-append tasks
the ordered commit lane holds (Promise.race drains one), so a slow spill
backend backpressures the run instead of accumulating unbounded pending
I/O and retained results. Tasks self-remove on settlement; run
settlement still drains every task inside the open turn. New spill test
drives three oversized reads against a hung backend at cap 1 and proves
the third dispatch cannot start until a save drains.
- shapeDispatchLog's catch uses errorMessage() (total), so a thrown value
with a throwing toString cannot escape the containment and lose the
settle event.
- CodeDispatchLog.content documented as the RENDERED result projection
(native tool/result vocabulary), not what the program received — the
program gets the structured value; doc pair + type-equiv re-synced.
- New RECORDED tui-agent snapshot scenario code-mode-dispatch-spill: the
real Loader-visible composition (worker runtime + spill-local + policy)
drives an oversized bash sub-call end-to-end; replay proves the durable
dispatch copy is bounded to preview + locator while the program value
stays whole (the outer result carries just the line count).
Agent Note updated (both languages).
The static CI gates run per-branch on the merged tree: the cordis
catalog/api, config-catalog, and type-equiv manifest updates for the
tools/code-dispatch-log waterfall and CodeDispatchLog payload previously
landed only on the shiki branch (09734f23b); this branch's own tree needs
the same regenerated outputs and manifest entries.
The coverage gate flagged three untaken paths in the bridge scheduler:
- the exclusive-head inFlight re-check was dead (the shared guard above
already returns for an exclusive head with any in-flight sibling) — removed;
- the commit-cursor undefined-dispatched break was structurally unreachable
once entries join commitQueue only after start() ran synchronously —
reordered the pump so the invariant holds by construction, annotated;
- the finish (final-result) commit arm and the pump re-entry guard gain a
covering test (throwing tools/pre-execute listener) and a defensive
annotation respectively; mid-run unregistration test renamed to match its
actual post-result settlement path.
Also covers the direct-construction maxParallelSubCalls default (index.ts)
and commits the regenerated persistence catalog for the new dispatch pair.
ui-sidebar shell landed on master (#643: geometry-only shell, the
browsing region moved to the sidebar.workspaces slot); this branch's
sidebar.settings foot seat re-applies on top — the hardcoded foot row
becomes the seat, the seat rides the railIn crossfade, and the shell
spec's renderSlot stub key-splits region vs settings.
ds-review-bot findings on the parallel bridge: sub-dispatches now run
through the registry's staged scheduler view (the loop's own seam) —
ordered prepare (pre-execute/guards) at submission-ordered start time,
only the dispatch/body stage overlapping, and a head-of-line commit
cursor running post-execute, context deferral, and the settle event in
submission order (new spec pins post order + context order under
out-of-order completion). Queued dispatches reclassify via
executionMode() immediately before starting, so a registry mutation
while queued flips them exclusive (native lazy-reclassification
semantics). Config and tool catalogs regenerated; the tool-catalog
metadata now names the start/settle pair and the scheduling contract.
New tools/code-dispatch-log waterfall (run via registry.shapeDispatchLog,
contained — a throwing listener falls back to the unshaped content) lets
listeners reshape the tool/code-dispatch event's content before the
bridge appends it. dsh-spill-policy registers a second arm sharing the
model-facing arm's exact replacement pipeline (same maxInlineBytes cap,
preview + locator, within-cap invariant, best-effort fallbacks), with
artifacts labeled dispatch under the sub-call id. The program's value is
untouched; read sub-calls ARE bounded (a log copy is not model context,
and read produces the biggest logs). Resolves the tools README's
uncapped-dispatch-log Known Limitation.
The bridge replaces its serialization queue with a pool that reuses the
native concurrency contract: submissions classify through
registry.executionMode (fail-closed isConcurrencySafe), start strictly in
submission order, overlap up to the validated maxParallelSubCalls config
(default 10; 1 restores serial), and exclusive calls drain the pool, run
alone, and bar later calls. Each started sub-call logs a
tool/code-dispatch-start event at pool entry; the existing
tool/code-dispatch settles the pair (started ⇔ settles exactly once;
abandoned queued calls log neither). SDK prompt guidance now states the
true Promise.all contract — re-recorded across every code/both-mode
snapshot (plus the stale cordis-dynamic-toolchain fixture gaining the
required description arg).
Client: CodeSubCall widens to RunningToolCall | ToolResultNode — starts
land the running shape (rows wear the native running ring), settles
replace in place preserving start order, callTime pairs to the start
time. Fixture emits start/settle pairs; jsdom pins the running sub-row;
runtime specs pin in-place settlement and out-of-order completion.
The tasks/ family now matches the capability-seam shape: @deepseek-ai/dsh-tasks
keeps the abstract TaskService (ctx.tasks contract, vocabulary types, snapshot
invariant companion) and the new @deepseek-ai/dsh-tasks-local carries the
process-local registry (LocalTaskService: in-memory store, settlement,
owner-cleanup effects, teardown, TASK_WAIT_TIMEOUT). Compositions and test
harnesses now load dsh-tasks-local; producers, TaskKindMap merges, and
dsh-tool-tasks keep importing the seam only.
Producer misconfiguration diagnostics name dsh-tasks-local because loading the
implementation is the fix. The registry behavior suite moves to tasks-local;
the seam keeps a stub-subclass registration test and the probe-based invariant
suite.
The ReplayConfig.overrideFile JSDoc still described only whole-script
replacement; it now names both sidecar forms and links ReplayOverrideDoc
(config catalog regenerated: source line shifted).
The override sidecar now accepts { patches: [{ at, entry }] } alongside the
legacy whole-script ReplayEntry[] replacement: the JSONL-derived script is
kept and only the named call indexes are swapped (at == length appends, for
a retry attempt following an injected transient throw). Out-of-range or
non-integer indexes fail loud with the derived length in the diagnostic.
This is the mock-LLM error capability the web e2e scenarios drive: 'call N
throws AUTH/SERVER, everything else replays as recorded'.
Generated docs follow the ui-models rename and the removed
ui-settings-general package; the English note side picks up the
feature-owner self-registration doctrine.
Tianyi Cui
imccyu