Every packages/*/* README now carries a canonical '## Known Limitations and
Deferred Work' section: condensed, evidence-backed bullets for consumer-visible
gaps (unimplemented features, platform caveats, MVP cuts) and consciously
postponed work (TODO/FIXME/XXX markers, RFC deferrals still open). The ten
pre-existing ad-hoc variants ('What is NOT here (TODO)', 'Deferred',
'Limitations (MVP)', 'Known limitations (tracked TODOs)', ...) are normalized
into the canonical heading.
A new doc-sync gate, scripts/verify-readme-limitations.ts, enforces the shape:
exactly one limitations-like heading per package README, byte-equal to the
canonical h2, with at least one bullet; near-miss headings fail so variants
cannot creep back. Packages with genuinely nothing to declare (dsh-brand,
dsh-timeout, dsh-subagent-mock, dsh-app-boot) are whitelisted in the script and
must NOT carry the section; whitelist entries are validated against the scanned
package set so a rename fails loud.
Wired into the doc-sync chain (package.json) and the run-gates doc-sync leaf
set; the standing rule lands in packages/AGENTS.md and the adding-a-package
cookbook; decision record in
docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md
(RFC index regenerated).
Also fixes two stale '(deferred)' markers claiming dsh-compact-basic is
unimplemented (the dsh-compact seam README's package table and the seam's
module doc comment).
CI has no rg, so the integration suite self-skips there and the
fake-executor suite must carry the per-file 100% coverage gate alone.
parseGlobArgs's valid-path branch was only exercised by integration
(node 24 / coverage failed at 95.45% branches on glob.ts); a fake-tier
test now threads a valid path through to the quoted `-- 'sub'` root.
glob leaked VCS internals when the model rooted the search AT a VCS
directory (path: '.git' or 'sub/.git'): the prune glob !**/.git is
matched against root-prefixed candidate paths, which never end in the
directory name when the walk starts inside it. Pair each VCS exclude
with a contents glob (!**/<name>/**), verified empirically to exclude
relative, nested, and absolute VCS roots while leaving broad searches
untouched. Pinned by the command-construction test and a real-rg
integration case rooting at .git.
Translate ctx.bash.run() REJECTIONS into the SEARCH_* taxonomy. The seam
contract has run() reject for infrastructure failures (a pre-aborted
signal, an unusable/deleted session workdir, a missing shell); the bare
await let those escape as plain Errors, so the tool registry produced
isError results without the structured SearchError { name, code } the
package documents. A pre-aborted spec.signal now maps to SEARCH_ABORTED
and any other start failure to SEARCH_FAILED, original error chained as
cause. Covered by fake-executor tests for both branches plus real-executor
integration tests pinning the exact pre-aborted-signal and deleted-cwd
paths.
Two functional gaps in the search tools change:
- Enforce rawOutputMaxBytes on UNTRUNCATED inline stdout too. The cap was
only checked on the truncated->raw-spill path, so an executor retaining
more inline than the search cap (or a deployment lowering the cap below
the bash retention) could smuggle an over-cap parse through, contradicting
the documented SEARCH_RAW_OUTPUT_OVERFLOW contract. Covered by a new
over-cap-inline test.
- Load @deepseek-ai/dsh-timeout-policy in the coding-agent tree. The search
tools declare timeoutMs but nothing in the demo enforced it, so the
advertised 30s budget silently degraded to the bash executor's 60s
backstop. The keyless smoke boots the amended tree.
Implements docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-
discovery.md: model-facing glob/grep in a new @deepseek-ai/dsh-tool-fs-search
package, executing fixed ripgrep templates through ctx.bash.resolve/run —
not ctx.fs provider methods — so filesystem backends stay free of a search
contract and sandboxed/remote executors substitute cleanly. The tools never
call ctx.bash.start(); the tool layer owns quoting (one singleQuote safety
boundary), rg --json parsing, ItemRetainer/TextRetainer retention, and the
first tool-owned ctx.spillFiles.saveText() handoff (item-level retention the
generic post-execute spill policy cannot recover).
RFC amendments on the way to implemented/: a shared src/search-core.ts (the
SEARCH_* vocabulary + bash-run/raw-spill/spill plumbing was byte-identical
across both tools — the missed-extraction smell), and a snapshot-gap note:
wiring the acp-agent tree changes the assembled prompt, so goldens need a
keyed re-record; the spill notice text is pinned by unit tests instead and
only the coding-agent example ships the tools for now.
New doc-sync gate verify-export-jsdoc walks every module-level exported
name under packages/*/*/src and requires description prose everywhere,
plus @param per parameter and @returns on non-void annotated returns for
function-like exports, public class methods, properties, and accessors.
The parsing + check helpers move out of gen-cordis-catalog.ts into a
shared scripts/jsdoc.ts so 'documented' means one thing on both gated
surfaces.
Deliberate exemptions (documented in the RFC): heritage-declared class
members (the seam declaration is the doc's one home — the one checker
query in an otherwise pure-AST walk), cordis plugin-protocol slots
(name/inject/reusable/Config/apply, top-level and static), constructors,
overload implementations, declare-module augmentation bodies, and
re-export statements (checked at the defining module).
The 203 under-documented exports the gate found at adoption are filled
in this change, so the gate lands green; generated catalogs/graphs are
regenerated for the shifted line pointers.
RFC: docs/rfc/implemented/process/2026-07-06-export-surface-jsdoc-gate.md
Round 1 P3: the "No timeouts on file IO" section left the file ending in a
blank line, which the trailing-newline whitespace gate rejects. Declined P2
(late abort after a timeout is lost): that is the RFC's decided trade-off —
mutually-exclusive first-abort classification — and re-latching aborted would
violate the acceptance criterion.
Timeout timing/classification was re-implemented three ways across the
tool-bearing capabilities, with the fusion of timeout+cancel and the
timeout-vs-cancel reason recovery being the error-prone parts. Extract that
shared half into a zero-dependency @deepseek-ai/dsh-timeout library
(clampTimeout/deadline/timeoutOf/TimeoutReason) and leave the non-shareable
hard-kill in each capability, per the timeout-library RFC.
bash: run() owns the deadline; runBash drops its killTimer and no longer
classifies (SpawnSpec/SpawnOutcome lose timeoutMs/timedOut/aborted), so the
public timedOut/aborted booleans become mutually-exclusive first-abort
classifications. web_fetch: the hand-rolled controller/timer/listener/
signal.reason dance is replaced by provider-owned deadline/timeoutOf, keeping
the WEB_FETCH_TIMEOUT / WEB_ABORTED contract. fs stays timeout-free (README
states why).
This branch's two RFCs (prompt-variables, provider-lifecycle events)
conform to the new contract in the same merge: 'Status: implemented'
dateless header, 'Rejected alternatives' -> 'Alternatives considered',
'What we give up' folded into '## Consequences' (per the uniform-format
RFC's own rejection of a costs-only closer), and the index regenerated
into the new INDEX.md. docs/rfc/README.md resolved to master's rewrite.
Review round 2 (tianyicui inline comments):
- dsh-system-prompt itself registers the harness:identity (-100) and
deployment:persona (0) sections — they must survive a swapped loop
plugin, so they leave dsh-agent-loop; the persona text is the plugin's
own validated 'persona' config. The model/cwd variables STAY on the
loop: runtime facts of the agents it drives.
- AgentOptions.systemPrompt is deleted with all its forwarding plumbing:
the app configs' systemPrompt keys become 'persona' routed through
dsh-agent-core (schema = z.intersect of the owners'), the ACP bridge
and tool-subagent stop carrying persona configuration, and subagent
children now render the deployment persona like every other agent.
- Example personas drop transport/interface trivia (ACP, CLI) — facts
irrelevant to the model.
- Root CONTEXT.md removed (not idiomatic); its persona definition was
wrong under the new ownership anyway.
- Docs, READMEs, the prompt-variables RFC, and generated catalogs
updated; new loop test pins the assemble-waterfall escape valve
(an emptied assembly sends NO system field).
Define the in-file RFC contract in docs/rfc/README.md § The file format:
the header block (`# RFC: <title>` plus a dateless Status enum
cross-checked against the lifecycle folder), the per-lifecycle body
skeleton (a Problem opener everywhere; Proposal/Alternatives considered/
Acceptance criteria/Risks in proposed/; present-tense Decision/
Consequences with proposal-era headings banned in implemented/; the
frozen proposal shape in rejected/), and a mandatory Alternatives
considered section with a date-fenced grandfather comment for pre-format
RFCs whose alternatives are not reconstructible from the record.
Enforce it with a new doc-sync gate, scripts/verify-rfc-format.ts, and
normalize all 112 RFCs to it: ~15 Status-line spellings collapse to the
enum, 29 Context openers become Problem, the 39 legacy-format XXX debt
markers are resolved and banned from reappearing, proposal-era sections
in implemented RFCs are rewritten to shipped reality (including the
web/fs/subagent seam RFCs' migration plans and test checklists, closing
the doc-tiers deferred-work item on the web seam), every RFC gains an
Alternatives considered section or the grandfather comment, and the
bilingual pair is re-mirrored and re-recorded.
Move the generated index tables out of README.md into a fully generated
docs/rfc/INDEX.md — gen-rfc-index now writes the whole file, and
verify-rfc-classification checks its freshness and rejects index-shaped
rows in the curated README — which makes room for the format contract to
live in the README front door instead of a separate FORMAT.md.
The decision record, and the first RFC written in the new format, is
docs/rfc/implemented/process/2026-07-05-uniform-rfc-format.md.
Reconciliations beyond textual conflicts:
- product rename (DeepSeek Code -> DeepSeek Harness SDK) applied to the
PR-added assertion in system-prompt.spec.ts that master's rename
commit could not reach
- architecture.md: master's rewrite kept; this PR's prompt-assembly
semantics re-added in the new doc's voice (Turn Flow footnote +
service-spine row), within the 1630-word ceiling
- cordis catalog regenerated into master's split events.md/services.md
(events-and-services.md deleted); module graph and doc graphs
regenerated to pick up this PR's new events and dependency edges
One principle: every fact in the assembled prompt has exactly one owner.
- dsh-system-prompt: merge-extensible AssembleContext on assemble();
a variable(name, provider) registry; {{name}} interpolation in
renderPrompt, strict (unknown/valueless/malformed references throw);
duplicate section and variable names rejected; assembly carries
resolved section text + variables through the assemble waterfall.
- dsh-agent declares AssembleContext.agent; dsh-agent-loop registers
the agent:persona section (order 0 - identity renders before tool
guidance) and the model/cwd variables, and drops its string join:
renderPrompt(assembly) IS the full prompt.
- Tool guidance moves to its owners: descriptions carry per-tool
semantics; sections only cross-call habits (tool:bash exit-code
habit at order 105; read's not-shell nudge). todo/subagent need no
section - their descriptions already carry the contract.
- SubagentProvider.inheritsParentContext (spawn/acp false, fork true);
dsh-tool-subagent derives truthful per-provider wording and resolves
the provider at load (backend must be listed first).
- Example personas shrink to identity + behavior with {{model}} (and
{{cwd}} in the ACP tree); the welcome banner stops enumerating tools.
RFC: docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
gen-cordis-catalog.ts now emits docs/cordis-catalog/events.md and
docs/cordis-catalog/services.md instead of the combined
events-and-services.md: a reader is either finding what to listen to or
what to call, and each axis now scans and deep-links as its own page.
Headings promote one level (scopes and ctx.<key> entries become H2), the
dispatch-mode legend lives on the events page, and the inherited tier
splits accordingly. --check verifies both files and names whichever is
stale.
Every reference updated in the same change (no compat redirects,
pre-release stance): architecture.md, AGENTS.md, docs/AGENTS.md tier row,
filesystem/subagent core-data-structures pages (the ctx.fs anchor
survives — slugs are heading-level-independent), fs README, four RFCs,
the tool-catalog and persistence-catalog generator intros (both
regenerated), and the bilingual development.md pair (re-recorded).
gen-cordis-catalog now hard-errors (aggregated, not fail-fast) when an
event lacks description prose or a payload @param, or a public service
method lacks JSDoc, a @param per parameter, a @returns on a non-void
result, or an explicit return type annotation. The this receiver and the
trailing waterfall next are exempt on events (mode machinery owned by
@mode); a stale @param naming no real parameter errors, mirroring the
@mode contradiction check. parseJsDoc now ends prose at the first block
tag (standard JSDoc semantics), so the tags never change the rendered
catalog — only Source: line pointers moved.
Fills the ~139 gaps found across the 15 surface files, extends the spec
with negative-path fixtures for every new guard plus the exemptions,
records the decision as an implemented process RFC, and extends the
AGENTS.md typed-events bullet with the authoring rule. Runs inside
verify-cordis-catalog -> doc-sync, so CI and pre-push enforce it with
zero new wiring.
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.
The fs seam split left four pieces of pre-split surface populated on
every call and read by nobody:
- STREAM_MIN_SIZE + FsIoInternals.streamMinSize in dsh-fs-local: the
backend has no read routing (readWholeText/streamWholeText are
separate primitives the caller picks), and the real 10 MiB routing
constant lives in dsh-tool-fs's read tool. Delete the dead mirror and
the knob whose JSDoc claimed an override that did not exist; the
remaining FsIoInternals knobs stay (the atomic-write tests use them).
- FsTarget.inputPath: a "diagnostics only" field every backend and test
fake had to fabricate, with zero production readers (policy and error
messages use targetKey/displayPath). listDir gave children the bare
entry name, which was nobody's input.
- FsEditOutcome.replacements/.replaceAll: replacements had no reader
(the single-match policy is enforced by the FS_AMBIGUOUS_EDIT /
FS_EDIT_NOT_FOUND throws, whose message keeps the internal count);
replaceAll only echoed the replace_all argument back to
formatEditOutput, which now takes it from the parsed args. The
outcome shrinks to { version, before, after }, parallel to
FsWriteOutcome's backend-discovered fields. Emitted text is unchanged
for both branches (no snapshot churn).
- FileReadOutcome.limit/.version: formatReadOutput renders
offset/lines/totalLines/truncatedByBytes only, and the fs/observed
emit uses info.version directly.
Backends shed four fabrication obligations and gain none. Doc pastes
(core-data-structures/filesystem.md), the dsh-fs README resolve row,
and the test fakes shrink with the types. RFC moved to
implemented/simplification and amended to the shipped shape
(FsEditSpec -> FsEditRequest name fix; manifest rows needed no change).
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.
Three comments still implied the result diff is always an applied hunk or
that write returns undefined on no-hunk: the toolResultUpdate JSDoc (a diff
result "emits the applied-hunk blocks, which replace the call-time snippet"),
the empty-diffs test comment ("an empty write returns undefined" — write now
falls back to a whole-file diff), and diffsFromMeta's JSDoc ("a bad meta
yields no diff card" — only true for edit; write falls back to a whole-file
diff). Each now states the write whole-file fallback. Regenerate the catalog.
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).
The writeText comment still said a null `before` (a create or an
undiffable binary file) means "a consumer renders no result-time diff,
only the call-time whole-file card." That is stale since write's
presentResult renders a whole-file diff for a null before-image. Correct
it: a null `before` gives no contextual-hunk basis, so the consumer falls
back to a whole-file diff — the tool still renders a result diff card, not
the raw result text.
The write-diff-card fix made write's presentResult return an args-derived
whole-file diff (oldText:null) for a create / unchanged overwrite, but the
DiffResultView contract and its mirrored docs still said `diffs` is ALWAYS
the applied contextual hunks computed from before/after. Correct the type
JSDoc, the write execute-side comment, and the four mirrored surfaces
(tools.md, tools README, acp-feature-support, adding-a-tool cookbook) to
say: typically the applied hunks, or a whole-file diff when there is no
before-image (a create) — and that a mutation returns the diff result even
when it duplicates the call-time card, since a tool_call_update.content
replace would otherwise clobber the diff with the model-facing text.
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.
Dudu-0223
Tianyi Cui
Yichen Jiang