A Codex review pass on the draft caught four real gaps and two solid
suggestions; all addressed except one pushed back on the merits:
- hooks-claude/hooks-codex: stderrSummaryMaxChars was the one new knob
with NO range validation — a negative/NaN cap would silently
misbehave inside slice(). Both bridges now assert a positive integer
at the TOP of apply() (before the config-file parse's early return,
so a bad value fails the load loudly), with rejection tests.
- tool-fs: the read caps count lines/chars/bytes, so positive-FINITE
was too loose (a fractional readLimit would flow into windowing
arithmetic and the schema description). All four now require a
positive integer, matching tool-web's cap.
- Doc drift the gates cannot catch: tool-web's README tools table
still named WEB_SEARCH_MAX_RESULTS as the mechanism; compact-basic's
README/module doc and the compaction-capability-seam RFC still
described estimation as fixed char/4 rather than the charsPerToken
default.
- subagent-acp: the dispose graces were tested only at the
startAcpRun level, so a regression that stopped threading plugin
config into AcpRunSpec would have survived. A provider-path test now
drives the trap-escalation scenario through ctx.subagents.start with
small config graces and bounds dispose at 4s.
Pushed back on: converting compact-basic's charsPerToken to a
schemastery field. The package's whole config is deliberately
hand-rolled (resolveConfig, every threshold REQUIRED with no default —
a documented design posture); one schemastery field beside it would be
incoherent. The knob is cordis.yml-reachable, defaulted, and validated,
which is what the convention requires; migrating the package to
schemastery wholesale is pre-existing config-surface hygiene out of
this change's scope.
The audit swept every packages/*/* plugin for the new AGENTS.md
convention (no hardcoded tunables in plugins) and exposes each finding
as a defaulted, validated Config field. Defaults are the previously
hardcoded values throughout, so no deployment or golden changes.
- tool-fs (had NO Config): readLimit, readMaxLineLength, readMaxBytes,
readStreamMinSize. The caps thread through ReadToolCaps/ReadWindow —
read-render already documented that the consumer applies the caps, so
they become explicit per-request fields.
- tool-web: searchMaxResults (WEB_SEARCH_MAX_RESULTS stays as the
schemastery default). Also fixes the stale GREP_LIMIT references in
search.ts and the web-capability-seam RFC (no such constant exists).
- bash-local: graceMs (SIGTERM->SIGKILL escalation grace). The
RunInternals.graceMs test seam is gone: graceMs is now a required
SpawnSpec field filled from config, so tests exercise the real
config path and the defaults live in exactly one place.
- subagent-acp: disposeEofGraceMs / disposeGraceMs. The AcpRunSpec
fields become required for the same one-defaulting-layer reason.
- session-persistence-sqlite: journalMode ('wal' default; the
rollback-journal modes serve filesystems where WAL's shared-memory
files do not work, e.g. network mounts).
- hooks-claude + hooks-codex: stderrSummaryMaxChars for the persisted
hook/result stderr summary. The duplicated summarize() helpers merge
into hook-protocol's summarizeStderr(stderr, maxChars), beside the
HookResultRecord field it feeds, with the bound parameterized the
same way runHook's defaultTimeoutMs already is.
- compact-basic: charsPerToken for the token estimator (default 4, the
English-text heuristic; CJK-heavy deployments need ~1-2 or compaction
fires far too late). Also corrects the BasicCompactService class doc,
which claimed defaults the required-field config never had.
- fs-local: deletes the dead STREAM_MIN_SIZE constant and the dead
FsIoInternals.streamMinSize seam — the read-routing bound lives in
the consumer (tool-fs), where it is now config. This is item 1 of
the proposed prune-write-only-fs-surface RFC, annotated accordingly.
Every new field gets range validation (following the existing
assertPositiveFinite pattern), a README row, and tests covering the
configured behavior, the schema default, and load-time rejection.
Maintainer decision: the subagent seam's deferred capability vocabulary
(outputSchema/structured, toolFilter, sendMessage/resume) is
intentionally reserved — the seam advertises the full intended contract
ahead of its implementations so providers and consumers grow into a
stable shape. Moved to rejected/ with the rationale on the status line;
the consumer-evidence analysis stays as the record of what is currently
unimplemented.
The fold-stdio RFC claimed the two e2e doc comments and packages/README
were the only non-runtime references; the package name also appears in
the generated module graph, sibling READMEs, and tsconfig references —
rescope the sentence to the runtime-importer census (the load-bearing
claim) and fold the mechanical references into the update list. The web
RFC's status-caller census now says 'the web packages' own tests'
(the seam's tests use the methods too, not only provider tests).
Deduplicate the parallel sweep from codex/exhaustive-simplification-rfcs
(merged in the parent commit) against the twelve RFCs already here, on
the merits per item:
Ported (rewritten to this set's evidence standard):
- fold-stdio-ui-helper — verified: dsh-stdio-agent is the only runtime
importer; the fold resolves the documented product-app-depends-on-
support-package tension. The false acp-agent analogy is replaced with
the real distinction (protocol product surface vs one app's front-door
scaffolding).
- generate-rfc-index-tables — verified: the classification RFC records
rejecting generation; the index tables are the repo's only
systematically conflicting docs region. Process framing made timeless.
Consolidated into existing owners:
- web searchStatus()/fetchStatus()/WebCapabilityStatus (verified: zero
production callers; the tool-web README and architecture.md claims are
drift) → drop-web-providers-change-event, renamed
drop-unconsumed-web-observation-surface.
- hook/result.durationMs (unread, nondeterministic, normalizer-scrubbed)
and the double-defaulted defaultTimeoutMs knob →
tighten-hook-protocol-contract.
- the exercised-but-unadvertised exec.arguments mutation path (a
tool-bash integration shim rewrites through it) → a sanction-or-seal
note in the pre-tool-input-rewrite proposal.
- the dormant-guard critique of subagent depth machinery → recorded in
prune-unimplemented-subagent-vocabulary as the considered-and-rejected
alternative, with the keep sharpened (uncapped-today acknowledged;
wiring the cap is the completion, not deletion). getProvider()/list()
and lastAssistantMessage recorded as examined-and-kept (bash-revert
precedent; observe-enrich recorded keep).
Not ported (with reasons):
- tools/change + system-prompt/change removal — recorded keeps in the
adapter-change RFC, unengaged by the sweep; no new facts.
- LlmService.models() — flagged by both surveys, but two lines with a
plausible consumer: TODO-or-drive-by territory per the RFC bar, not
a proposal.
- SchemaProp.default RFC — already XXX(unused-default)-tagged; the RFC
bar excludes TODO-tracked provisional cleanups.
- PreToolDecision 'ask' removal — FIXME(permissions)-anchored deferral
with the permission system as its named consumer.
- Codex bridge Config.model, merged systemMessages — wire-faithful
tested surface / README-documented deferral.
Their in-code TODO notes (acp-test-harness, hook-snapshot-noise,
catalog-type-links) and the stale hook-prompt-block name fixes ride the
merge unchanged.
Rewrite the hook-protocol RFC's process-relative wording (freshly-landed
/ days-old / week-old) as timeless evidence anchored to the recorded
RFCs, and sweep the same class from the steering, replay-config,
subagent-vocabulary, and vocabulary RFCs. Narrow the fs RFC's acceptance
criterion: replaceAll survives on the request spec and version on other
outcome types by design — name the exact removed surfaces instead of
claiming the spellings vanish.
The branch now bases on the hooks stack (PR #138's head), so every
'in-flight' reference to stack content became a current-state fact.
Audited all nine RFCs + three supplements claim-by-claim against the
merged tree (none invalidated; several strengthened):
- prune-dead-core-spine-surface: describe the landed tools/pre-execute →
dispatch → tools/post-execute pipeline — listeners return Decisions,
the registry builds every result and snapshots it to protect callId,
and a second (mutation-guard) test pins the field; drop the resolved
wait-for-interception hedge; scope the additionalContext ferry out.
- prune-producerless-vocabulary-variants: the ui-stdio fixture migrated
off the continuation trigger (llm-replay is the sole writer now); the
stack's own additions (rejected, prompt/blocked, hook/invoked+result)
all arrived with producers — the admission policy demonstrated live.
- prune-unimplemented-subagent-vocabulary: enrichment landed as
lastAssistantMessage only (agentType was dropped in the stack's own
review — the same judgment this RFC extends); the seam RFC now names
tools/pre-execute deny, which exists, sharpening the re-add path.
- drop-inert-request-knobs / drop-image-content-block /
trim-acp-bridge-unreachable-surface: current-state rewordings (shipped
bridges set no request fields; only compact-basic has explicit image
arms; 13 hook goldens also pin agentInfo).
- generic-long-running-tool-runtime census: second production seam
consumer (hook-protocol runHook: resolve+run, stdin/env, foreground
only — background machinery stays single-consumer); scrub-duplication
blast radius.
- discover-package-inventory: identical 54-entry tsconfig reference
sets; the comparesLog scenario knob (fixture-derivable, like recorded).
- unify-agent-and-session-id: third divergence site (in-process subagent
children mint two UUIDs), the hooks bridge id-lookups, and ui-stdio's
labelBySession map as a consumer that deletes under unification.
New RFCs from the post-stack survey:
- remove-agent-steering-mirror: the last mirror-of-durable event; zero
production listeners; both retention RFCs deferred its fate, and the
'no durable twin' rationale is contradicted by the adjacent append.
- tighten-hook-protocol-contract: producer-less 'native' dialect,
parsed-and-discarded suppressOutput, and hook/result semantics
(truncation + decision-string) defined twice in the bridges instead
of the lib that owns the event.
- single-source-acp-replay-config: cordis.yml/cordis.snapshot.yml differ
by exactly one plugin entry, with no gate on the forced symmetry.
The core-spine RFC's acceptance criterion still asserted all three
surfaces 'appear only in this RFC', contradicting the corrected scope
(runLoop/Inbox stay as package-internal symbols; only the public
re-exports go). Also add the deepseek README image-skip row and the
compact-basic [image]-placeholder row to the image RFC's removal set.
Two overstated evidence claims, reworded to the precise fact:
- prune-dead-core-spine-surface: runLoop has no importer OUTSIDE the
package (its own agent.ts drives the loop with it); the dead surface
is the public re-export, not the function.
- generic-long-running-tool-runtime census: BashTask.done has no
consumer through the public seam, but is production-load-bearing
inside dsh-bash-local (disposal awaits it); only the public
completion surface is single-consumer.
Also fold the reviewer-located doc sites into the removal sets so the
implementing PRs need no re-discovery: the llm/pi-ai/compact-basic
README rows and the adding-an-llm-adapter cookbook line (prefill/image),
the content-block-vocabulary RFC's has-a-home consequence lines
(cache/prefill/image), the tools.md paste + type-equiv manifest row +
tools README row (callId), and the session-surface RFC's
full-rebuild-after-replacement sentence (invalidate).
Load both hook bridges in the ACP example (dsh-hooks-claude → ./hooks.json,
dsh-hooks-codex → ./codex-hooks.json) so the full-transcript snapshot tier can
exercise each dialect against the real app. An absent config file is a silent
no-op, so a scenario carries only the file it needs and the other bridge
vanishes — verified byte-identical against every pre-existing snapshot.
Add a scenario per hook point × its headline Decision outcome, both dialects:
UserPromptSubmit block (authored, keyless) + context-fold, PreToolUse deny/ask,
PostToolUse block/context, Stop force-continue. The mid-turn scenarios are
recorded against the real API with the hook active, so the model's reaction to
a denied/blocked/force-continued turn is part of the replayed transcript.
SessionStart and SubagentStart are deliberately excluded (detached best-effort
inject races the log position — a recorded golden fails 10/10 on its own
replay), as is SubagentStop (observe-only, zero transcript footprint — a golden
could never be proven to fail). Both stay on the bridges' unit coverage. See
docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md.
The result-time diff card sent view.title raw, so a completed edit/write
of an absolute in-workspace path flipped the card header back from the
relativized `Edit src/b.ts` to the absolute path — the pending card
relativizes, the result did not, and tool_call_update.title replaces the
header. Apply displayTitle to the result diff arm using the diff path,
mirroring the call-side card. Regression test proven red on the unfixed
arm.
Also record the overwrite diff-basis pre-read as a bounded follow-up
(TODO(overwrite-diff-bound) + RFC non-goal): overwriting a large file
reads the whole prior text into memory for a UI-only diff.
Redesign per review: neither language is canonical. A pair is three
sibling files — foo.md, foo.zh.md, foo.i18n.yaml — and either language
may be authored first (a Chinese-first RFC is as legitimate as an
English-first one). The sidecar record holds the FULL git blob hash of
both sides as of the last confirmed-consistent state, replacing the
in-file one-directional fingerprint; editing either side without
re-confirming the pair goes red. New --write mode re-records a pair
after both sides are brought in line, making the confirmation a
reviewable yaml diff. Pairs merge whole (completeness enforced).
- gate rewritten around pair anchors (union of .zh.md and .i18n.yaml
remnants) so half-deleted pairs are caught from either side; red/green
proven for en-only edit, zh-only edit, missing record, and a record
for an excluded file
- verify-rfc-classification now skips .zh.md counterparts (same RFC,
indexed via its English filename; the pairing gate owns consistency)
- docs/i18n/README.md + translation-rules.md reframed bidirectionally
(terminology table binds both directions; typography section governs
the Chinese side); zh counterparts updated; skill workflow updated
- RFC amended to the shipped design, records the English-canonical
in-file-fingerprint model as considered-and-revised; RFC translated
(docs/rfc/.../2026-07-02-bilingual-docs-and-pairing-gate.zh.md) and
added to the required frontier
- generated docs stay excluded with the follow-up recorded: teach the
generators to emit Chinese, then de-list
Codex's stale-prose pass found seven more spots still describing the
result diff as ALWAYS an applied contextual hunk, or a create/binary
overwrite as rendering "only the call-time card": the DiffCallView JSDoc
and the acp bridge diff-arm comment, the FsWriteOutcome.before and
readTextForDiff JSDoc, and three RFC lines. All now say: the result diff
is the applied change — a contextual hunk when there is a before-image,
else a whole-file diff (create / undiffable binary) — and a successful
mutation always returns the result diff so the model-facing text can't
clobber it. Regenerate the cordis catalog (source line shift).
A Write CREATE rendered its completed tool_call_update as the model-facing
result TEXT (`<path>…</path>…Created file`), which — because an ACP
tool_call_update.content REPLACES the call's content — clobbered the
new-file diff the pending call installed. So Zed showed the diff, then
replaced it with raw XML-ish text; only overwrite/edit looked right
(their result re-sends a diff).
write's presentResult now ALWAYS returns a diff card for a successful
write: the applied contextual hunk from `meta` when there is one
(overwrite), else an args-derived whole-file diff (`oldText: null`) for a
create or an unchanged-content overwrite. This matches claude-agent-acp,
where the create diff rides on the update and no result text replaces it.
An error still falls through to generic rendering so its message shows.
edit is unchanged (it always has a hunk; no whole-file fallback).
Re-recorded fs-write / fs-write-overwrite goldens; the create's completed
update is now a {type:'diff'} block, not the XML result text.
Address the applied-hunk-diffs review:
- CRLF write overwrite emitted bogus every-line-changed hunks: write's
`before` was LF-normalized but `after` kept the raw model content, so a
CRLF rewrite of an LF file diffed every line. Normalize write's `after`
to LF so both sides share the diff basis (edit already did). Regression
test proves it fails on the raw-after path.
- The tool-private `meta` payload is now typed `unknown` (opaque) at every
seam instead of `JsonValue`. This drops the `dsh-tools -> dsh-session`
package edge that existed only to name the type, and removes the
`FileDiff` index signature that had been widening the type solely for
JsonValue-assignability. Serializability is still enforced at runtime by
`Session.append`'s isJsonValue check, which was always the real guard.
- Sync the docs the new result/meta surface left stale: ToolResultView's
diff card + ToolExecutionResult.meta in tools.md/session.md type-equiv
blocks, the acp/tools READMEs, and the adding-a-tool cookbook; regenerate
the cordis catalog and module graph.
fs write/edit now emit a result-time contextual-diff tool_call_update
(the applied hunk with ±3 context lines, one hunk per replace_all site),
matching what claude-agent-acp sends and what makes an editor render the
change in place. The call-time snippet diff stays; the result hunk
supersedes it (ACP content-replace).
Mechanism:
- A persisted tool-private `meta` channel: execute may return
`{ content, meta }`; `meta` (JsonValue) rides on the tool/result event
and is handed back to presentResult, so the diff reproduces on replay
(event-sourced). JsonValue is now exported from dsh-session.
- The backend returns raw before/after text (storage facts) on
FsWriteOutcome/FsEditOutcome; the tool computes the hunk via the npm
`diff` package's structuredPatch. A create has no before → no result
diff; a failed/aborted mutation carries no meta.
- ToolResultView gains a DiffResultView; the bridge's result-side switch
renders it as {type:'diff'} content blocks.
RFC: docs/rfc/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md
(justifies the npm `diff` runtime dep over vendoring and the meta channel);
the render-intent-union RFC's Non-goal is updated to record this shipped.
All fs snapshot goldens re-recorded; edit/overwrite gain the contextual
result diff, create/read/policy-reject unchanged in structure.
Establish EN->ZH bilingual documentation for the README and docs tree:
- docs/i18n/README.md — the pairing contract: sibling foo.md <-> foo.zh.md,
English canonical, blob-hash source fingerprints, language switchers,
scope/exclusions, and a manifest-driven rollout ratchet.
- docs/i18n/translation-rules.md — how to translate: faithfulness, structure
preservation, terminology discipline over docs/i18n/terminology.md, and
typography rules grounded in MDN/K8s/Vue/clreq conventions.
- .agents/skills/dsh-translate-docs — the committed agent workflow, following
the dsh-code-review pattern of deferring to docs as sources of truth.
- scripts/verify-translation-pairing.ts + manifest — a doc-sync gate: required
pairs exist; every existing .zh.md is fresh (fingerprint = current source
blob), switcher-linked, structure-matched, and non-orphaned; excluded
(generated) docs stay unpaired. --list prints the translation work list.
- RFC (implemented/process) recording the decision and the alternatives.
- Dogfood: README.zh.md and the two i18n docs translated under their own rules.
Gates: doc-sync green including the new gate; red/green proven for stale
fingerprint, orphan, and excluded-file violations.
Replace the "bag of optional fields" tool-presentation types
(ToolCallPresentation / ToolResultPresentation / ToolTerminal) with a
card-tagged discriminated union — the standing FIXME(tool-presentation).
A tool declares one render intent per call/result and the ACP bridge
switches on `card`:
ToolCallView = generic | terminal | diff
ToolResultView = generic | terminal
The `diff` card is new: fs write/edit now emit an ACP {type:'diff'}
content block (an editor's inline diff), which the old shapes could not
express. The bridge also relativizes a file card's title against the
session cwd (mirroring claude-agent-acp's toDisplayPath) while keeping
locations/diff paths raw, and derives the no-capability fenced console
fallback from a terminal result's output. read gains the window-in-title
(`Read foo.txt (5 - 8)`) and an always-set location line, matching the
reference adapter field-for-field.
Migrates all three producer families (tool-fs, tool-bash, tool-todo) and
the sole consumer (the ACP bridge) together — the source does not compile
piecewise. Adds snapshot coverage for the terminal _meta path (a new
capability-advertising scenario) and re-records the fs goldens to show the
diff cards. Applied-hunk (result-time, context-line) diffs need a new
result/event shape and are a follow-up.
RFC: docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md
The loop recorded every model token delta as a durable `assistant/chunk`
session event AND emitted an identical live `agent/stream-chunk` Cordis event
one line later. Same StreamChunk, same turn/step; the emit added only the live
Agent handle, which the sole consumer discarded. This is the boundary-mirror
duplication the event-domain work removed for turn/step boundaries, applied to
the token stream — a follow-up the boundary RFC explicitly deferred.
The premise is settled: chunk persistence is authoritative (the proposal to
stop persisting chunks was rejected — replay/snapshots depend on it), so
`assistant/chunk` on `session/event` is the load-bearing token stream and
`agent/stream-chunk` is pure redundancy.
- Remove the `agent/stream-chunk` declaration + emit; drop the now-unused
StreamChunk import from dsh-agent's types.
- Migrate `dsh-ui-stdio` (the only live consumer; ACP already reads
assistant/chunk off session/event) to render assistant/chunk in its existing
session/event listener. Consolidating to one listener also makes the
inReasoning dim-SGR flag deterministic across chunk/boundary events (they no
longer race across two listeners).
- Repoint the agent-loop tests (cancel/loop) and ui-stdio tests to the
session/event assistant/chunk feed.
- New RFC (implemented/simplification/2026-07-02-remove-stream-chunk-mirror);
amend the boundary RFC's retained-list entry to cross-link; update
architecture, cookbook, event-domain-semantics, the ACP proposal, and the
regenerated cordis catalog.
Snapshot goldens unchanged (ACP never used the mirror), confirming no
editor-facing transcript change.
Codex convergence findings on the delegate-and-fold fix (code path verified
correct, prose only):
- The hook-bridges RFC claimed a downstream `block` "carries the bridge context
too" for BOTH seams. True for `tools/post-execute` (PostToolDecision.block has
an additionalContext field) but false for `agent/prompt-submit`
(PromptDecision.block is `{kind,reason}` with no context field). The code is
already correct — a blocked prompt drops the context, which is right since the
prompt never reaches the model. Reworded the RFC to state the per-seam
difference accurately.
- Two test comments narrated "Before the fix…", which the current-state-only
doc rule forbids. Reworded to describe the behavior, not its history.
- Documented on concatContext (both bridges) why the merged block carries a
single source: a HookContext holds one MessageSource and the seam cannot
represent mixed provenance; rendering distinguishes only by source.kind, so a
downstream plugin's text stays framed as plugin context.
Load dsh-fs-local + dsh-fs-policy + dsh-tool-fs after tool-todo (mirroring the
acp-agent wiring), and steer the system prompt to prefer read/write/edit for
file ops with bash for shell/tests/search. Update the welcome line and the
FIXME(config-comments) bash note.
Doc sweep now that both demos ship the fs tools and the seam resolves per-session
cwd: architecture.md and the event-gate RFC no longer say the demos do file ops
through bash / that no config wires the tools; the coding-agent + examples
READMEs and the AGENTS.md layout blurb list the fs tools; the acp-agent README
drops the launch-dir caveat (per-session cwd now works, so the server can launch
anywhere).
(stdio-agent is single-session, so fs-local's cwd = process.cwd() is the
workspace. Keyless boot smoke is blocked locally by an unrelated inotify
watcher-limit ENOSPC that also hits demo:echo; the config parses and the same fs
stack boots green in the acp-agent snapshot tier.)
Address review on the hook-bridges PR — two composability/compatibility bugs
in both the CC and Codex bridges:
1. A hook that only attaches additionalContext (no block/deny) returned
`allow`/`accept` WITHOUT calling next(), short-circuiting every later
agent/prompt-submit / tools/post-execute listener. A policy/sandbox plugin
registered after the bridge never saw the prompt. Now the context-only path
delegates via next() and folds its context onto the downstream decision
(concatContext): a downstream block/deny still wins and carries the bridge
context; a downstream allow/accept keeps its own content rewrite and gains
the context. Only a real hook deny/block short-circuits.
2. CLAUDE_PROJECT_DIR was empty in the default ACP wiring (no projectDir
configured), breaking common unmodified hooks that reference
$CLAUDE_PROJECT_DIR. It now defaults per-run to the agent's session
workspace (the same cwd the hook runs in); an explicit config.projectDir
still wins.
Regression tests per bridge: a later listener blocks a prompt a context-only
hook allowed; both contexts survive when the downstream also adds one; the
default CLAUDE_PROJECT_DIR reaches the hook. Each proven red on the pre-fix
code.
