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).
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
Add the implemented skill-system RFC, a core data-structures page, and JSDoc for the skill public vocabulary so the generated catalogs and review-facing docs describe the new service/tool contract.
A new capability family at packages/workflow/ in the bash seam shape,
modeled on Claude Code's dynamic workflows: the model writes a JavaScript
orchestration script (export const meta = {...} + plain-JS body), a runtime
executes it, and the script — not the conversation — holds the loop, the
branching, and the intermediate results.
- dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary
(WorkflowRun whose result NEVER rejects) + observe-only workflow/* events
carrying data snapshots (id + meta, never the live run), per-listener
contained like subagent/*.
- dsh-workflow-vm: in-process node:vm engine. Meta extraction via a
string/comment-aware scanner (template interpolation rejected; literal
evaluated alone in an empty timed context; statement blanked line-
preservingly so stacks keep script line numbers). Hooks: agent(prompt,
{label, phase, schema, model}) over ctx.subagents, parallel(), pipeline()
(no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline:
hook misuse (unknown/deferred options, bad arguments, unsupported
schemas, tripped caps, seam start failures, cancellation) throws fatal
WorkflowErrors the combinators RE-THROW — never dissolved into the
per-item null reserved for child failures. Realm boundary: inbound values
materialized by descriptor walks that never invoke accessors (defineProperty
copies, __proto__-safe); outbound values rebuilt in-realm via the
context's own JSON.parse. Determinism bans (Date.now/Math.random/argless
new Date) kept so future resume support cannot break scripts. Caps and
timeouts are validated Config. Every hook promise carries a no-op
rejection consumer (app-boot exits on unhandled rejections).
- dsh-tool-workflow: the model-facing workflow tool, synchronous like
dsh-tool-subagent (start → await → try/finally dispose; abort bridged;
non-completed → isError). Generic render card titled by a textual
meta.name sniff. The tool description carries the authoring contract.
Wired into examples/{coding-agent,acp-agent} with explicit-ask-only
guidance. Coverage at every tier: unit (meta scanner, materializer incl.
counting-getter and __proto__ regressions, combinator semantics,
concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon),
integration over the real spawn stack, with-key e2e (real two-phase run +
the tool through the registry pipeline), and a recorded ACP snapshot
scenario (workflow-run, 1 child session). RFC:
docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred
work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's
layout line.
A static harness:identity section at order -100 — the first occupant of
the documented negative band — states that the agent is powered by the
DeepSeek Harness SDK before the deployment's persona renders. Harness
attribution is a harness fact: it lives on the loop plugin, not in each
deployment's persona, so every agent (subagents included) carries it and
no YAML can forget it. A deployment that must drop it can remove the
section in the system-prompt/assemble waterfall.
Order-band docs updated in all five homes (PromptSection JSDoc, the
system-prompt and agent-loop READMEs, architecture.md, the RFC).
The seam vocabulary (SubagentStartRequest.outputSchema, SubagentResult
.structured) existed but no in-process backend honored it — spawn/fork
advertised outputSchema: false. This lands the missing half:
- dsh-tools gains a structured-output JSON Schema subset (json-schema.ts):
StructuredOutputSchema, assertSupportedOutputSchema (rejects loud outside
the enforced subset, every violation listed), validateStructuredValue
(path-qualified issues, total). outputSchema's seam type becomes this raw
JSON-Schema subset instead of the author-facing SchemaSpec DSL — the schema
travels verbatim to the model as a forced tool's parameters.
- dsh-subagent-inprocess gains the shared structured runtime: one global
structured_output capture tool (placeholder parameters) + a prepend:true
agent/request listener doing FINAL-REQUEST enforcement (strip for plain
agents, per-run schema for structured children — survives downstream
request-replacing listeners) + an agent/turn-continuation veto that stops
a child's turn once captured (no wasted extra model step). Lifetime is
refcounted by backends (plugin lifetime) AND live runs (start→settle).
- startInProcessRun drives the capture: subset asserted before the child
exists, instruction appended to the child's system prompt, clean-finish
nudge loop (structuredNudgeRetries, backend Config, default 1), captured
value on result.structured; a clean finish without a capture settles
'error' (never a silent success with a missing field).
- spawn + fork flip outputSchema: true and inject 'tools'.
The AgentOptions.systemPrompt doc said the persona 'may reference'
variables without saying that every complete {{...}} group IS interpreted,
strictly, and that literal {{...}} prose has no escape syntax yet (the
RFC's recorded deferral). A persona author reads this line first; it now
carries the contract. (ds-review-bot inline finding: the escape mechanism
itself stays deferred per the RFC — pre-release, no external consumers,
and the failure is loud with the fix in the message.)
Codex round-1 findings, both confirmed:
- renderPrompt: variable lookup now uses Object.hasOwn (an unregistered
{{constructor}} previously resolved through Object.prototype and spliced
function source into the prompt), and a {{ that opens no complete group
while a }} still follows ({{{model}}}, {{a{b}}) now throws instead of
passing or partially interpolating. A lone {{ with no }} after it stays
verbatim; substituted values are never re-scanned.
- tool-subagent: the apply-time provider lookup assumed a load order the
cordis Loader does not guarantee (siblings start concurrently). The seam
now announces subagent/provider-added/-removed and the tool mirrors the
provider's lifecycle: registers when the provider is (or becomes)
available, unregisters when it goes away, re-derives wording on reload.
No load-order requirement remains.
- loop.spec containment test now proves live continuation: after the
contained render failure, a waterfall listener rescues {{cwd}} and the
same agent completes a real model turn.
RFC/READMEs updated to the shipped contract; cordis catalog regenerated.
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
Merging master brought the producerless-vocabulary prune that removed
TurnTriggerMap's continuation variant: the source pointers above
SessionEventMap shifted by one line (the staleness CI caught on the
merge tree), and the new turn/start JSDoc still named the pruned
variant.
- The owning top-level interface SessionEventMap must now be the SINGLE
EXPORTED declaration in @deepseek-ai/dsh-session: a non-exported local
interface (even inside the owning package) and a second exported copy
are hard errors, so a same-named helper can no longer be catalogued as
the on-disk vocabulary.
- Any SessionEventMap declaration carrying an extends clause is a hard
error: inherited keys join keyof SessionEventMap but have no catalog
row, so heritage is a silent-skip path the gate must reject.
Three new spec cases; RFC and module doc updated to match.
- A SessionEventMap member that is not a property signature with an
explicit payload type is now a hard error instead of silently skipped —
a method-form or type-less member joins keyof SessionEventMap and must
not escape the catalog.
- A top-level interface SessionEventMap outside @deepseek-ai/dsh-session
(ownership read from the package manifest) is now a hard error — an
unrelated same-named local interface was previously catalogued as the
on-disk vocabulary.
- JSDoc tag detection runs on the trimmed line, so an extra-indented
'* @mode' can no longer bypass the forbidden-tag check and leak into
prose.
Four new spec cases cover these; RFC and module doc updated to describe
the enforced (not just assumed) invariants.
docs/persistence-catalog/log-events.md enumerates every SessionEventMap
member — the owning dsh-session vocabulary plus the dsh-compact and
dsh-hook-protocol declaration merges — with payload, surface/log-only badge,
JSDoc prose, and declaration site. scripts/gen-persistence-catalog.ts is a
pure AST pass in the gen-cordis-catalog mold: verify-persistence-catalog
(--check) joins doc-sync, so a stale committed catalog fails pre-push and CI.
The walk enforces JSDoc completeness (every member needs description prose;
@mode is rejected as a category error — log events do not dispatch on the
cordis bus), derives the surface badge from the SurfaceEventType union with a
stale-member cross-check, and hard-errors on duplicate declarations. Payloads
render through the TypeScript printer so newline-separated multi-line type
literals still emit valid one-line fragments.
Documented the five previously JSDoc-less core events (turn/step boundaries,
tool/call), removed the two stray @mode tags on the hook/* merges, and
replaced the hand-restated event enumerations (session.md hook/* table,
compact README table, hook-protocol README bullets, session README name-list
— whose merge note had already drifted) with links to the catalog. RFC:
docs/rfc/implemented/process/2026-07-04-persistence-log-catalog.md.
Codex review: the RFC claims the fixtures prove each guard fires, but the
binding-pattern guards (events + services), the service no-prose branch,
and the empty-@param/@returns-description branches had no focused tests.
Add the five missing cases; every violation branch in the generator now
has a matching fixture.
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.
GenerateOptions.prefill had no production setter and both adapters
rejected it with LlmError('UNSUPPORTED') — its entire observable
behavior was two throws, each pinned by one adapter test. DeepSeek's
chat-prefix completion is a Beta feature on a base URL neither adapter
targets. ToolSchema.strict was threaded through defineTool, the
registry's schemas() allowlist, the deepseek wire mapping, a per-tool
payload-patching pass in the pi-ai adapter, and a tool-catalog render
row, yet no shipped tool set it and the internal endpoint story for
strict mode was never built.
Remove both fields end-to-end: the vocabulary in dsh-llm, the adapter
guards and wire branches, the dsh-tools threading, the tool-catalog
Strict row, the pinning tests, the core.md pastes, the adapter README
rows, and the cookbook line that used prefill as the UNSUPPORTED
example (now stated generically). The pi-ai payload fixup keeps the
half with a job: pi-ai stamps strict:false on every serialized tool,
so the fixup scrubs it unconditionally for wire parity with the
hand-rolled twin (per-tool set/delete machinery gone). temperature/
stop/maxTokens are untouched — honored end-to-end by both adapters.
Each knob returns with its first real producer: prefill with an
adapter that implements chat-prefix completion, strict with a tool
that wants it and a beta-endpoint story.
RFC: docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md
(moved from proposed/, amended to shipped reality); the content-block
vocabulary RFC's consequence line now records prefill as producer-gated.
The vocabulary maps grow by declaration merging, and the admission policy
stated on TurnEndReasonMap is that a variant lands with its first emitter.
Three declared items had no producer and no consumer:
- CacheHint and the cache?: CacheHint fields on TextBlock/ToolResultBlock:
nothing constructs a block with cache:, and neither adapter reads .cache —
DeepSeek prompt caching is automatic (hints map OUT of responses, never IN).
- MessageSourceMap.agent: zero constructors; the subagent backends send the
parent prompt with no source (logs as user), and the envelope renderer
interpolates source.kind without routing on it.
- TurnTriggerMap.continuation: the loop structurally cannot emit it —
continuation is further steps within a turn, never a new turn — and its only
writer was an llm-replay test fixture that needed any non-message trigger
(now an injection trigger).
Each variant returns the day it gains a real producer, via the same
merge-extensible maps. Docs updated in the same change: the MessageSourceMap
paste in core.md, the TurnTriggerMap paste in session.md (manifest untouched —
both symbols survive), the content-block vocabulary RFC's cache-hints
consequence line, and the RFC moved to implemented/ and amended to shipped
reality (the image block's own cache field had already left with the
drop-image RFC).
agent/steering was the last transient mirror of a durable session event:
drainSteering appended the durable steering/message {turn, content, source}
and emitted the identical fact one line later. Zero production listeners
existed — every steering consumer (hook bridges, goldens, deriveMessages)
reads the durable event — and the one regression test subscriber asserted
a fact the log already records.
Remove the declaration (dsh-agent types + JSDoc list + README row), the
emit in drainSteering (its ctx parameter goes too), and the emit line in
the loop-pseudocode blocks (loop.ts module doc, architecture.md); the
cordis catalog is regenerated. The regression test now pins source
preservation on the durable steering/message event. Live-notification
needs keep their surviving homes: agent/queued at enqueue time,
session/event at drain time.
RFC: docs/rfc/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md
(moved from proposed/, amended to shipped reality). The three implemented
RFCs that stated the retention — the boundary-mirror removal, the
stream-chunk removal, and event-domain-semantics — are amended to point
at that RFC as the record of the removal, per implemented/AGENTS.md.
The rejected retire-mid-turn-steering RFC keeps its frozen text (it
records the declined proposal); the steering capability itself —
steer(), the durable event, continuation forcing — is untouched.
- Restore the universal JSDoc rule the rewrite dropped (module doc
comment + semantic JSDoc on every export), in root AGENTS.md § Type
safety and documentation — the generated-catalog RFC cites it as the
rule the generator enforces at the source.
- Repoint the six remaining citations of moved content that the
section-name grep missed (rule-title quotes and prose references):
agent-loop agent.ts, acp index.ts, acp turns.spec.ts, the Exa e2e
header, the real-api-e2e RFC, the doc-sync-enforcement RFC amendment,
and rfc/implemented/AGENTS.md's section-name casing.
- Fix two docs/testing.md overstatements: the unit tier also runs
examples/*/tests specs, and keyless-by-nature examples have no
with-key smoke.
- Displacement trims keep root AGENTS.md at 1,498/1,500.
Codex review of the vocabulary relocation found two doc-accuracy issues:
- presentation.ts's JSDoc used {@link ToolDefinition...}, which the
TypeScript language service cannot resolve because presentation.ts
deliberately does not import index.ts (that would create the cycle the
split avoids). Demote those three to plain `ToolDefinition` code text;
same-file and imported @links (TerminalResultView, ContentBlock) stay.
- docs/core-data-structures/tools.md's source header listed only index.ts
and schema.ts; add presentation.ts, which now owns the presentation
vocabulary the page documents.
The tool render-intent vocabulary (ToolCallView/ToolResultView + members,
FileLocation, FileDiff, ToolCallKind) is the UI-facing surface of
dsh-tools; it lived inline in index.ts alongside the registry and
execution core. Move it to its own presentation.ts module so index.ts is
the registry + execute waterfall and the presentation vocabulary is a
separate, one-directional dependency.
presentation.ts owns ONLY render-intent types and references none of the
execution types; index.ts imports the view types for ToolDefinition's
presentCall/presentResult signatures (clean acyclic index -> presentation).
The opaque `meta` presentation channel (ToolExecuteReturn, ToolResult,
ToolExecutionResult) is execution plumbing and stays in index.ts.
Public surface unchanged: index.ts re-exports the vocabulary, so consumers
(tool-fs/tool-bash/tool-web/tool-todo, the ACP bridge) keep importing from
@deepseek-ai/dsh-tools with zero churn. No producer/bridge/test edits; a
pure internal relocation with no observable-output change (snapshot goldens
untouched).
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 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).
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.
