The exact-disposer fix (5fbac8be B1) repaired agents.register but left the
same wrapper (return () => void dispose()) at seven sibling sites:
tools.register, tools.restrict, systemPrompt.section/tools/variable,
agents.setFactory, and subagents.registerProvider. A wrapper makes correct
composite usage unrepresentable — the exact disposer cannot be recovered, so
a generator effect yielding it leaves the inner effect disposing as a
CONCURRENT SIBLING on owner unload, silently reproducing B1's ordering
corruption. The exact disposer serves both usages (composite-nestable AND
fire-and-forget callable); all seven now return it, typed
() => Promise<void> | void, with the convention pinned by a discriminating
test: an async-link composite probe that passes with the exact disposer and
observes the sibling unregistration firing mid-drain with a wrapper.
Re-auditing also surfaced that B1 itself SHIPPED a full-lint failure: it
changed register()'s return type without updating cross-file consumers
(agent.spec.ts dispose() statements, tool-bash's disposer list), which the
staged-scoped pre-commit lint never saw — pnpm run lint was red at HEAD.
Those three sites and this change's own fallout are fixed together: tests
now await disposers (stronger — they observe the full unwind), sync
paths void them, and the two annotation sites carry the honest union type.
agents.register's README line had drifted the same way (B1 updated the
JSDoc, not the README) — all seven README signatures now match; services
catalog regenerated.
Both demo:code-mode UIs now share one mechanism: the base example plus a
same-shaped code-mode.cordis.yml include overlay (insert the worker
runtime, flip tools.mode). Previously the REPL side was a hand-forked
example (examples/code-agent) that had also silently diverged — it
dropped compaction and the subagent stack — so the demo's UI argument
switched agents, not just surfaces. The fork is retired: coding-agent
gains the overlay, a Code Mode README section absorbing code-agent's,
and both of its tests (the keyless boot guard, retargeted at the
overlay; the with-key RFC proof, which hand-mounts its own harness and
moves untouched). The RFC's composed-surface and e2e-tier lines, the
examples index, the AGENTS.md smoke table, and the dsh-tools README
link now describe the overlay shape.
Verified live: overlay keyless smoke, with-key code-mode e2e from its
new home, demo:code-mode banner + EOF exit, and the acp handshake.
The chained-fused-dispatch spelling fix (0dc2fe90) was whack-a-mole: each
unrecognized dispatch spelling silently drops a producer edge from the
generated matrix, and only a human reading the table catches it. Convert the
class to a build failure: the generator now hard-errors when any DECLARED
event ends with zero dispatchers — dead vocabulary or a missed spelling,
both actionable ('teach the scan or add a DYNAMIC_EVENT_DISPATCHERS
override'). Zero LISTENERS stays legal: seven current rows (agent/request,
system-prompt/assemble, tools/change, ...) are ordinary extension points
dispatched for out-of-repo plugins.
The guard caught a real one on its first run: subagent/provider-removed
routes through the same contained events.dispatch as subagent/start|end
(it fires inside the provider registration's disposer), but the
DYNAMIC_EVENT_DISPATCHERS override list never got an entry when that
containment routing was introduced — the committed matrix (on master too)
claimed the event has NO dispatcher while tool-subagent listens for it.
Override added; matrix regenerated with the producer edge restored.
Code Mode is the point; the UI is just the surface it happens to wear.
demo:code and demo:acp-code collapse into one dispatcher
(scripts/demo-code-mode.mjs): `pnpm run demo:code-mode [repl|acp]` —
repl (default) boots the stdio REPL over examples/code-agent, acp
serves examples/acp-agent's code-mode overlay; each UI runs the exact
node invocation its standalone script ran, and an unknown argument
fails loud with usage. All nine references across READMEs, the RFC,
the overlay header, and the keyless-smoke comment renamed. Smoked all
three paths: usage exit 2, ACP initialize handshake, REPL boot + EOF.
ds-review-bot round-3 finding: agentEvents(ctx, agent).emit(...) has a
call-expression receiver the generator's identifier check missed, silently
dropping agent-loop as agent/session-start's producer. The generator now
recognizes a call receiver whose callee is agentEvents; graph regenerated
with the producer edge restored.
ds-review-bot round-2 findings: (1) dsh-subagent's runtime import of
@deepseek-ai/dsh-scope was undeclared in its manifest and tsconfig
references (the root paths map masked it; the emitted package would import
an undeclared dependency) — wired as peer+dev with the project reference,
module graph regenerated. (2) The structured re-assert only ensured
PRESENCE, so a downstream listener injecting a same-named entry with the
wrong schema kept it model-visible while validateStructuredValue enforced
the real one; it now REPLACES any same-named tool/section with the run's
own. Pinned by a wrong-schema-injection test asserting exactly one entry
carrying the run's schema.
The agent-scope-contexts RFC (implemented) records the decision tree:
the dsh-scope primitive over cordis extend/Context.filter/no-op fibers,
two-level flat scope with shadowing, restriction/grant semantics, the
scoped-dispatch rule with fused helpers, the setup window, and the
alternatives (explicit scope params, isolate, event-filtering-only,
vendored support) with why each lost. CONTEXT.md pins the glossary.
architecture.md gains the Agent Scope section, the dsh-scope spine row,
the scoped turn-flow line, and an extension-table row (ceiling 1640→1790:
the two-layer registration model is a new architectural axis; additions
are condensed to pointers). READMEs of every touched package re-state
their scoped facts; the stale structured-runtime README section is
replaced by the scoped-registration description.
scopeHost(ctx, services) is the sanctioned way to mint scopes in tests: it
names absent services loudly instead of the cryptic cordis without-inject
dead end, and catches the silent-no-op host (cordis resolves a
dependency-pending fiber's await without running the inject callback).
The ACP ToolPresenter resolves presentations through the session agent's
view (tools.get(name, agent)) so a scoped/shadowed tool renders with the
same definition that executed.
verify-scoped-dispatch (doc-sync + pre-push) pins the dev-invariants
carrier table against the declaration JSDoc set: an event enforced but
undocumented, documented but unenforced, or a registry-subject notification
leaking into the table fails the build. subagent/start|end docs gain their
scoped-dispatch sentence (a real gap the gate caught on first run).
The producer/consumer matrix reads dispatch sites statically; the fused
agentEvents dispatcher, the agent's loopCtx handle, the session store's
captured emitCtx, and carrier-first argument lists were invisible to it,
silently dropping agent-loop/session as producers of every scoped event.
The generator now recognizes those spellings; the Agent type-equiv doc
block gains readonly ctx.
The seam shipped without its own RFC — the reconstructable-requests RFC
was amended with the mechanics, but the decision record (why a
compose-once frozen prefix, and what the per-request before/after shape,
a system-prompt section, a durable history opener, per-turn composition,
and a dedicated session event each lost to) had no home. Implemented
lifecycle, feature class, dated to the first commit of the work.
createScope(ctx, key) mints a tagged context over a synchronously-usable
no-op-plugin fiber (one fact drives visibility AND lifetime); scopeOf reads
the tag through the prototype chain; scopeTarget(base, key) builds the
scope-filtered dispatch carrier over cordis Context.filter, composing the
base's own filter, branded Scoped<T> and runtime-marked for the dev
invariants. Scope.rawDispose exposes the exact cordis disposer so a
composite effect can nest the scope's teardown at its yield position.
- spill-policy validates maxInlineBytes as a non-negative integer at LOAD, so a
bad config fails the deployment instead of letting a negative value reach
TextRetainer and turn every oversized-result call into an isError.
- Document the spill seam vocabulary in docs/core-data-structures/spill.md
(SaveTextSpill/SpillOwner/SpillSource/SpillRef/SpillPath, verbatim + type-equiv
gated) and index it from core.md, matching the other capability seams.
The seam gained sessionPrefix between fullSystemPrompt and signal in
18d478bc, but the compact README member table and the compaction
core-data-structures page still showed the 3-arg form and listed only
agent/system/signal as what pre-step supplies. The generated service
catalog was already correct; only these two prose homes drifted.
A cancel/dispose landing inside the first agent/session-prefix waterfall
used to commit the listener chain's return value to the instance cache
before the interruption check dropped the turn; an abort-aware listener's
degraded fallback would then ship on every later request of the instance.
The commit now happens only after the composition survives the
interruption check — the cache only ever holds a fully composed prefix,
and the next turn recomposes under a live signal.
Oversized plain-text tool results now spill to a session-scoped file and
return a bounded preview plus the spill path, so a verbose result stays
readable via `read` without consuming the next model request in full.
- dsh-spill: minimal SpillFiles seam (saveText → session-scoped SpillPath)
- dsh-spill-local: private 0700 session dirs, traversal-safe names, exclusive
owner-only writes
- dsh-spill-policy: tools/post-execute transformer; no-op unless maxInlineBytes
is set; skips read; best-effort on save failure (never turns a success into
an isError)
web_fetch is the showcase — no tool-specific spill code. The coding-agent
example loads the stack so its keyless Loader smoke guards the namespace-plugin
export shape. Snapshot gap for a transcript-visible web_fetch spill is recorded
in the RFC's Consequences (ACP replay is keyless and cannot hit the web).
ds-review-bot critical (follow-up): on the first step of a resumed or
seeded/forked instance, auto-compaction ran before runStep composed
this instance's prefix, so the gate read the PREVIOUS instance's logged
prefix from the header fold — a contributor that grew across
resume/fork (skills added, AGENTS.md grown: exactly the
environment-dependent case) could under-gate and ship an over-window
first request.
The loop now composes agent/session-prefix before the instance's first
agent/pre-step (still once per instance; runStep just reads the cache),
and agent/pre-step carries the composed prefix to its listeners.
CompactService.compactIfNeeded gains the sessionPrefix parameter;
BasicCompactService.estimatePressure gates on the handed value — the
header-fold read is gone, so the estimate is exact at every step
including a resumed/forked instance's first. Composition moving before
the boundary snapshot also means a composing listener's session append
now joins the CURRENT request (documented on the seam).
New coverage: composition precedes pre-step and the seam receives the
composed prefix; cancel and disposal landing inside the composition
window drop the step cleanly; the compact gate test hands the prefix
directly.
Verifies the namespace plugin has no default export and preserves
name/inject/Config through Loader.unwrapExports — the same guard
pattern as dsh-tool-web, per the packages/AGENTS.md convention.
Connects to an external MCP server and registers its tools on
ctx.tools. Supports stdio (child process) and Streamable HTTP
transports. Credential-shaped env vars are scrubbed before forwarding
to child processes.
- Plugin lifecycle: connect, sync tools, re-sync on ToolListChanged,
dispose unregisters and closes
- Full JSDoc on all exports (@param/@returns on functions)
- 100% per-file coverage (apply lifecycle, args coercion, env scrubbing)
- Config catalog regenerated
The seam's structured-clone boundary admits values JSON does not (BigInt,
Map, circulars), while tool/code-dispatch events must be JSON-appendable —
left unhandled, a sub-call could execute and then fail at logging time.
The bridge now JSON-normalizes binding arguments BEFORE dispatch (a value
that does not survive rejects that one call), so the dispatched form and
the logged form are the same JSON value by construction.
Adds the missing core-data-structures coverage the catalog policy
requires for non-spine seam vocabulary: the code-runtime.md sub-page
with drift-checked type-equiv blocks for all six seam types, the core.md
sub-page row, the type-equiv manifest entries, and LINK_MAP entries so
the generated service signature links CodeRunRequest/CodeRunResult;
cordis/config catalogs regenerated.
New group packages/code-runtime/ with the interface package
@deepseek-ai/dsh-code-runtime, per the Code Mode RFC: abstract CodeRuntime
service (run() resolves program failures as an error field, rejects only
for seam misuse), the CodeRunRequest/CodeBindingNamespace/CodeRunResult/
CodeLogEntry/CodeRunFailure vocabulary, and readonly language/isolation
backend descriptors. Registered in the tsconfig maps, packages/README,
architecture service map, and the doc-graph service-role classification;
catalogs regenerated.
The RFC's one forward path token to the worker package becomes an npm-name
mention until PR3 creates that directory (verify-package-paths is
drift-scoped: the now-existing group made the token checkable).
docs/architecture.md ceiling 1630 -> 1640: the doc gained a genuinely new
capability-service row; the row itself is already minimal.
Budget expiry terminated the worker but nothing cancelled an in-flight
host-side sub-dispatch, and a late dispatch could append events after
run_code returned. The bridge now owns a run-scoped AbortController
(follows exec.signal; fired on any run settlement), sub-dispatches get
the run signal, and run_code returns only after the dispatch queue
drains — no post-settlement appends, per dispose-to-quiescence.
(A1) Scope the wire-collapse guarantee honestly: systemPrompt.tools() is
a public multi-provider API, so the mode governs the registry's
contribution (the only shipped source); deliberate extra providers own
what they add, and the shipped-configuration invariant is test-pinned.
(A2) Replace pause-on-pending-RPC timeout with two independent budgets:
computeMs metered by worker.performance.eventLoopUtilization() busy time
(unfoolable by an un-awaited decoy dispatch; probe-verified) plus a
never-pausing maxWallMs ceiling.
(A3) Specify sub-call additionalContext as deliberately suppressed in
the MVP (immediate inject would break call/result adjacency; the plural
channel is named follow-up work).
(B) Orphan-process caveat vs bash-local's group kill; null-prototype
binding namespaces (__proto__/constructor names); per-PR doc artifacts
(packages/README row, architecture service map in PR2, config/tool/
persistence catalogs per owning PR); engines range corrected to
^22.19.0 || >=24.0.0.
Research finding: a SessionEventMap member is a log event — JSDoc prose
required, @mode is a hard error there, and docs/persistence-catalog.md
must be regenerated (todo/write is the log-only precedent). PR4's plan
now names both.
Own adversarial pass finding: a static inject on the registry would gate
ctx.tools (and every tool plugin) on a code runtime existing even under
mode 'native'. The RFC now names the sanctioned pattern: soft
ctx.get('codeRuntime') at use time (the agent-loop sessionPersistence
precedent) with absence failing loud in the provider thunk.
Supersedes the add-on-plugin + node:vm-stub draft in place (still proposed/):
code mode becomes a first-class ToolRegistry presentation mode
('native' | 'code' | 'both'), execution goes behind a new ctx.codeRuntime
capability seam whose shipped backend is one fresh Node worker thread per
run (type-strip, empty env, resource limits, hard terminate), at
bash-equivalent trust with no unsafe-flag ceremony. Renames the file to
2026-06-15-code-mode.md and regenerates the RFC index.
The credential env scrub (SENSITIVE_ENV_PATTERN/buildChildEnv), the
spawn-failure capture (spawnFailure), the child-exit waits
(waitForExit/exitsWithin), and the stdin-EOF -> SIGTERM -> SIGKILL dispose
ladder move out of subagent-acp into a new pure library package (the
subagent-inprocess shape), with the ladder taking its two grace periods as
parameters — defaults stay in the plugin Config. New isolated-config-dir
helpers (mkdtemp create, best-effort remove; a pinned dir is never removed)
land alongside for the CLAUDE_CONFIG_DIR / CODEX_HOME redirection the RFC
names.
The ACP backend migrates onto the library with no semantic change: its suite
passes with import-path edits only. bash-local keeps its sibling copy, per
the RFC's blast-radius call.
RFC: docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md
Two ds-review-bot findings:
The seam JSDoc claimed extending 'await next()' composes in
registration order — false for the append form: the waterfall unwinds
innermost-first, so appending places later-registered contributions
first. The canonical contribution is now documented as the PREPEND
'[mine, ...await next()]' (registration order on the wire), with the
append form's reverse-order behavior stated explicitly; the ordering
test now uses the canonical pattern in both listeners.
scrubRequestHeaders tokenized only system/tools, so a fixture recording
a composed session prefix would carry its raw text (workspace-specific
churn/leak). The scrubber now maps each header/delta messagePrefix
entry to a {{messagePrefix}} token — count stays a structural fact,
absence stays absent, the empty-array transition stays visible — with
normalize.spec coverage for the header, delta, absence, and odd-shape
paths.
Brings in the refreshed base (master merged through the stack after #203
and #205 landed), including the acp-snapshot extraction (#204), and
re-ports this PR's snapshot-suite extensions onto the extracted package:
- dsh-acp-snapshot's Scenario gains headerClass and configPath; the suite
factory pins the request header PER CLASS (construction rejects a
missing or duplicated class pin), forwards a scenario's configPath to
the harness (RunOptions.configPath overrides AgentUnderTest.configPath),
and a new fixtures meta-test asserts every pinning fixture carries
exactly one request/header and no deltas.
- The acp-agent example's thin scenario table re-registers code-mode-turn
and both-mode-turn with their overlay configs and per-class pins; the
committed fixtures replay unchanged.
- The package's synthetic suites cover the new surface (explicit
headerClass on one suite, the default on the other, a configPath
override through the fake bin, and the two construction throws).
Tianyi Cui
Yichen Jiang
Dudu-0223
pku-xht
lintianle
pku-xht