The pairing gate requires link target #9 to be byte-identical between
the language sides; my earlier 'fix' pointed the zh side at the zh
runbook and broke the contract. Reverted to the shared target and
re-recorded the pairing hash.
The spare tier is retired. Steady-state pool load is one serial standby
job per master push, so six always-on instances already are the
failover capacity; pre-registered offline runners are a silently
expiring guarantee (GitHub garbage-collects them after 30 days
offline). Incident-time extra capacity is a one-minute org-token
registration, now documented in the runbook.
- 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.
- gate-consolidation note: parseArgs strict mode DOES reject a
dash-leading token where a value is expected (verified with node);
only the duplicate-option behavior differs
- YAML roll-up item: scripts/verify-cordis-config.ts is a fourth
js-yaml !!js tag definition the inventory missed
Both EN+ZH, pairs re-recorded.
Head-to-head replay of the same ten historical examples, both arms in
one time window with identical prompts and pairwise blind judging:
prose quality and cost at parity (stylistic margins only); the shipped
briefing wins two objective outcomes — code-fence-only examples land
byte-identical to the human-reviewed updates with zero model tokens,
and the flagged first-occurrence move reproduces the human-reviewed
gloss relocation the section-only form leaves as a contract violation.
Chinese counterpart brought along via the briefed path and the pair
re-recorded.
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.
PR #679 implemented the swap and falsified the note's parity premise:
vitest's fake clock does not intercept node:timers/promises, so the
change traded deterministic fast tests (llm-retry ~4s->~10s real
sleeps, two pty teardown tests rewritten real-time, a weakened
workflow grace-timer guard) for ~10 deleted lines. Moved the note
proposed -> rejected with the verdict on the Status line; the frozen
proposal body is kept per the rejected-lifecycle contract.
Every PR that changes product-user-visible GUI behavior now includes a
demonstration GIF with real provenance (that branch's built tree, real
key, real model rounds). Recording stays side-effect-free; the skill
gains a bounded final publication step: GIFs go on an append-only
orphan assets branch (one per PR series) and embed via the blob URL
with ?raw=true, never on the PR branch itself.
Folds in the operational lessons from the Code Mode UI series:
.playwright-mcp/ screenshot roots (now gitignored), per-PR staging and
precise server teardown, one-call DOM polling for transient states,
exact-text completion predicates, prompt engineering for UI states,
and the export-before-invoke GIF_SKILL_DIR encoder pitfall.
Agent Note: implemented/process/2026-07-26-gui-pr-gif-evidence-and-assets-branch (+ zh pair); the 2026-07-23 recording note now defers publication policy to it.
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).
