Adopts #220 (tool-cordis + the gen-cordis-api gate: the runtime API
catalog regenerated with ctx.tasks/onCleanup on it) and #225 (shared
transcript renderer). Tool-catalog expectations take the union
(cordis_* + task_*); packages/README budget adopts master's 660
ceiling, which absorbs both new group rows.
Systematic trace through Zed (crates/agent_ui thread_view.rs +
crates/acp_thread): kind:execute routes a tool call onto the
terminal-card layout, whose header (render_collapsible_command) has NO
disclosure toggle, whose body content renders only when is_open — a
flag only a real terminal entity can ever set — and which suppresses
the Raw Input view outright. Every prior attempt (rawInput, pending
content, completed content) targeted slots that layout structurally
never renders; the one slot it always shows is the TITLE, which said
"Run code". codex-acp confirms the idiom: execute cards are titled
with the command itself.
presentCall now titles the card with the program (rawInput kept as the
canonical input slot); presentResult omits the title — an update
replaces only provided fields, so the program header persists — and
carries the captured output as content. Goldens re-recorded; the unit
test pins title-carries-program on both frames.
The sandbox execute wrapper JSON round-tripped the return and blindly cast it
to ToolExecuteReturn. A JSON-valid but wrong-shape return — a bare string,
{ content: 'ok' }, blocks without a type tag — sailed through: the registry
spreads result.content, so { content: 'ok' } became ['o','k'], passed the
session log's isJsonValue gate, and the DeepSeek serializer then flattened it
to '(no output)' — silent corruption of the next model request and every
replay, instead of a contained tool error.
The round-tripped value is now shape-checked against the two ToolExecuteReturn
forms (array of content blocks, or { content: blocks, meta? }); block checks
are structural only (plain object + string type tag) because the ContentBlock
union is merge-extensible. A wrong shape — and the formerly cryptic
forgot-return/bare-string cases — fails that one call with a teaching error
echoing a truncated preview of what was returned and the two valid forms.
New specs pin the object-form pass-through (meta included), six rejection
shapes, and the preview truncation; per-file 100% coverage holds.
The previous commit put the fenced program only on the pending card —
but an ACP tool_call_update's content REPLACES the card content (Zed
truncates to the new list, crates/acp_thread update_fields), so the
code vanished the moment the run completed and was effectively never
visible. presentResult now re-carries the fenced program before the
captured output via a shared fencedProgram helper; the completed card
body is program + output, rendered by Zed as syntax-highlighted
markdown behind the card disclosure. Goldens re-recorded (filtered
this time: DSH_SNAPSHOT=record vitest -u -t mode-turn); unit test pins
the two-block result content.
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.
start({ kind, label, owner, run }) preflights everything that can fail
(the attachSurface fence, validation, the owner-cleanup attach) BEFORE
invoking the producer's run() starter, then commits atomically —
'work started but never got a collectable id' is now structurally
impossible instead of a producer try/catch rollback obligation (the
P1 review fix, rebuilt on #185's declare/execute split). Producers
lose their catch-wraps; the leak tests now pin the stronger property
that a failed preflight never spawns anything. TaskRegistration splits
into TaskStart (identity + run) and TaskHooks (cancel/done/readOutput);
docs, type-equiv manifest, catalogs, and both RFCs move with it.
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.
ctx.tasks.wait arms a deadline() fusing the caller's abort with the
wait timeout and classifies the outcome with timeoutOf scoped to the
new TASK_WAIT_TIMEOUT code: a wait timeout resolves to the live
snapshot (the task keeps running), a caller abort rejects the wait —
same contract, no hand-rolled timer/listener plumbing, and a nested
foreign deadline can no longer misread as a wait timeout. task_output
deliberately declares NO ToolDefinition.timeoutMs: timeout-policy
turns a timed-out call into a structured TOOL_TIMEOUT failure, but a
timed-out wait is a SUCCESS that must still report [status: running]
(decision recorded in the runtime RFC alternatives).
Adopts #185 (dsh-timeout: clampTimeout/deadline/timeoutOf drive bash
run() timeout classification; runBash loses its own timer) and #108
(ask_user_question) across the task-runtime rework: bash-local keeps
the BashProcess handle shape with master's deadline mechanics, tool
catalogs/expectations carry both the task_* and ask-user tools, and
generated docs are regenerated on the union.
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.
One shared ctx.tasks registry (branded <kind>-N ids, owner-fenced
read/kill/wait/list, attachSurface misconfiguration fence, reported-flag
notice dedup, atomic register) + dsh-tool-tasks (task_output/task_list/
task_kill, completion-notice injection, background prompt habit).
Producers opt in via their own enableRunInBackground config: bash
(stream kind; seam slimmed to resolve/run/start returning a BashProcess
handle, bash_output/bash_kill deleted) and subagent (final-output kind;
done settles after run.dispose()). Owner disposal drains tasks through
the new awaited ctx.agents.onCleanup seam in the loop's disposal chain.
Both RFCs moved to implemented/; docs, catalogs, snapshots re-pinned.
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.
The generated program rode only rawInput — the detail/expanded slot
many ACP clients never open — so the code a run executed was invisible
in the UI stream. presentCall now also carries it as a fenced ts block
in the card's content, which the bridge already forwards as tool_call
content. The two code-mode snapshot goldens are re-recorded live and
replay green; the presentation unit test pins the fenced block.
The workflow tool's wire schema changed (required meta object
parameter; body-only script). Request-header content is pinned by
exactly ONE scenario (text-turn) and scrubbed to {{system}}/{{tools}}
tokens everywhere else, so the schema change re-records exactly two
fixtures:
- text-turn — the pinned header itself (the one committed copy of the
tool schemas; every other scenario's live header is asserted equal to
this pin by the uniformity guard).
- workflow-run — its recorded interaction used the removed call shape
(meta embedded in the script), which the engine now rejects; the
authored prompt is updated to dictate the new shape (meta as a
parameter, body-only script) and the scenario re-recorded to a clean
single call.
Every other fixture stays byte-identical and replays green against the
new pin. Known pre-existing exception: fs-policy-reject's recording
carries a GNU-only sed -i fallback that fails BSD/macOS replay — kept
out of this change deliberately (the snapshot CI lane is ubuntu).
P1 review finding: extractMeta timed only the literal's vm evaluation;
materializing the RESULT then read properties ordinarily on the HOST
stack, so a meta literal smuggling a getter (get name() { while(true){} })
could wedge the host outside any timeout — defeating the exact spin
isolation the worker thread exists for.
Rather than harden the evaluator (descriptor walks, AST validation),
delete the mechanism: the workflow's identity now reaches the seam as a
plain JSON field (WorkflowStartRequest.meta), carried by the tool as a
schema-validated `meta` object parameter the model fills directly. The
engine only shape-validates data (validateMeta, every violation named)
and pre-parses the body; the scanner, the vm evaluation, and the
host-side materialization are gone, and with them the hole. A body
still opening with a Claude Code-style `export const meta` statement
gets a pointed SCRIPT_PARSE message (the likeliest authoring slip; a
CC script's body stays drop-in, only its meta header moves into the
parameter). syncTimeoutMs now governs exactly one thing: the initial
synchronous slice inside the worker.
The RFC's decision section is rewritten in place (implemented-RFC
rule); the embedded-meta format moves to alternatives-considered with
the hole as the reason. Tool description, presentation (title now reads
meta.name directly — the textual sniff is gone), seam vocabulary docs,
and catalogs follow.
The regression's script spun immediately after calling agent(), but the
agent() continuation (which posts the child-start RPC) only runs on a
microtask tick — the spin seized the worker's loop before the post, so
the host never saw a child inside the waitFor window. A few await-null
yields before the spin let the RPC out; the posted message needs no
further worker-loop turns to reach the host, so the wedge still holds
for the Cancel message the test is about.
Pure mechanical rename now that the package's internals are the
worker-thread engine: directory, package name, spec/e2e filenames,
module tags and logger prefixes, tsconfig/knip/run-gates/AGENTS.md
references, example cordis.yml plugin ids, doc links; catalogs
regenerated and the lockfile refreshed.
The outer ring catches up with the engine swap (the package's own
README/JSDoc rode the port commit):
- Seam module doc and README name the worker-thread engine as THE
implementation, with isolated-vm/separate-process sandboxing as the
deferred hardening; the seam service doc states the holder-owned-runs
contract (engine-fiber disposal deliberately leaves live runs to
their holders).
- Seam contract precision: agentsStarted documents the termination-path
degradation to the host-observed count; the events section scopes the
agent-start/agent-end pair to calls that STARTED a child run;
WorkflowRun wording drops the vm-era abandonment language.
- The dynamic-workflows RFC is rewritten in place to the shipped
mechanism (implemented-RFC rule): why worker threads, the thread's
concrete buys, the in-process node:vm first cut recorded under
alternatives considered; the tool section describes the usage policy
as the tool's own prompt section.
- gen-doc-graphs: six workflow/* DYNAMIC_EVENT_DISPATCHERS entries (the
catalog no longer claims nothing dispatches them) and the seam-note
wording; core-data-structures gains its workflow.md index row;
packages/README + AGENTS.md layout line + example cordis.yml comments
say worker-thread; catalogs regenerated.
In-place port of dsh-workflow-vm from the in-process node:vm execution
to one worker thread per run (the workflow-workerthread engine of
PR #215, adopted as THE engine): the script's vm context moves inside
the worker, agent() bridges to ctx.subagents over the message port
(host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the
abandon channel — the host's grace timer force-settles and TERMINATES
instead), start() pre-parses the body host-side to keep the seam's
synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run
cancelled before start from ever executing the body. start() no longer
blocks the host, termination is real, and the value boundary is
serialization by construction. The package keeps its name until the
follow-up rename commit; scripts see the identical hook surface, and
the seam-contract tests hardened ahead of this swap pass unchanged.
The run and child-RPC surfaces are class-shaped rather than literal
bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its
own clone, separate from event payloads') and start() returns the
instance directly — interface parity with the seam is compiler-checked;
worker-side, ChildRpcBridge (implements ChildPort; callId allocation +
pending book-keeping settled by onChild* entry points) and
RpcChildHandle (every member an RPC keyed by its callId) carry names in
stacks. ChildPort's method is startAgent — it names what it starts,
matching the script-side agent() hook and the agentsStarted /
workflow/agent-* vocabulary; the Child* type names deliberately stay
(the worker side is cordis- and subagent-free; these are reduced JSON
projections, not the seam's types).
Review findings from the reference PR are folded in rather than
re-introduced:
- cancel() drives BOTH child-cancel channels host-side: the request
signal aborts AND each registered child's explicit cancel() is
called — a worker wedged in a synchronous spin cannot relay its own
ChildCancel RPCs (regression: cancel-only provider + wedged worker).
- All host warn paths render through the total renderThrown; a child
dispose() rejecting a value whose coercion throws still acks
ChildDisposed instead of wedging the script's finally (regression).
- built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md
CI sequence — the built lib/worker.js resolution contract now runs in
an automated gate.
- workflow/end payload pinned on the worker-death path (with the
cancelled and grace-force-settle pins riding the ported spec).
- Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms)
for starved CI hosts.
Workspace plumbing: the "./worker" subpath export sanctions the second
runtime bundle (check-workspace-constraints), tsdown builds two
single-entry passes, tsx becomes a devDependency for the unbuilt worker
spawn.
cordis provide() accepts any value and cross-mount composition advertises
ctx.provide('name', value), but the façade's readService unconditionally
proxied every declared service — new Proxy('42') throws "Cannot create proxy
with a non-object as target or handler", so a consumer of a primitive-valued
service crashed on first read with an error naming neither the service nor
the fix. A primitive or null value now passes through unwrapped (after the
denyContext check); only object- and function-valued services are proxied —
a primitive has no method that could hand back a Context, so nothing is lost.
New cross-mount spec pins both read paths (ctx.<name> and ctx.get) for a
number and a null provided value.
The sandbox docs overclaimed a containment contract the design never makes:
"capability access is routed through cordis services, never Node built-ins,
so everything a mounted plugin does stays inspectable and disposable". The
host-realm helpers on the sandbox global (harness, console, btoa) are
reachable functions, so mount code that goes looking can reach the host realm
through one of them — accepted under the trust stance, because the ctx a
mount ultimately receives is fully privileged anyway. Reword the sandbox
module doc, the README trust stance, and the RFC sandbox-semantics section to
say exactly that: the traps and small global surface STEER honest code onto
the cordis services; they are not a security boundary.
Three engine-agnostic pins, landed BEFORE the worker-thread port so the
port commit demonstrates contract preservation against them:
- tool-workflow: the tool:<toolName> prompt-section registration was
entirely unasserted — assemble() now pins the section present under
the CONFIGURED name and gone after fiber dispose (the packages
AGENTS.md dispose-and-assert-cleanup rule; tool-bash is the template).
- tool-workflow: drop the dead `??` re-defaulting of already-
schemastery-resolved config (the hidden-fallback shape AGENTS.md
bans) and the direct-apply test that existed only to cover those
branches; both engines' `config as ResolvedConfig` is the pattern.
- workflow-vm: workflow/end was asserted only on completed runs — the
cancelled path and the grace force-settle path now pin the event and
its stopReason/error/agentsStarted payload (an observer's only death
signal on those paths).
emitWorkflowEvent's catch rendered the thrown value with a bare
String(error), which itself throws when the value's toString /
Symbol.toPrimitive throws — breaking the documented containment
guarantee: such a listener could fail the run mid-emit, starve later
listeners, and turn the detached workflow/end settle hook into an
unhandled rejection. Render through a local total fallback instead
(String in a try, a fixed label when even coercion throws); local
because the seam sits below every engine and cannot import an engine's
renderer. Regression: a listener throwing a coercion-trap value — the
emit does not propagate and later listeners still run.
Reviewer-agent C1 on the audit delta: "byte-identical" overstated the
untampered-path guarantee — a 190-order section registered AFTER the
structured runtime sorts before the instruction in the registry's stable
sort but after it in the re-assert's band insertion. Intra-band section
order carries no contract, so the behavior is right and unchanged; the
module doc and both in-code comments now say exactly that instead of
claiming byte identity.
Codex follow-up findings on the carrier commit, both verified:
B: the invariant guard only protected the bind path — an overlay key
colliding with a non-configurable, non-writable OWN prop of a (pathological)
base would have the get trap report the overlay value, which the engine
rejects as a proxy invariant violation (TypeError at read time). The pin
check now runs FIRST and covers both invariant-pinned shapes (non-writable
own data prop reported as-is; getterless non-configurable accessor reported
undefined via the delegated read) before overlay and bind alike. Such a base
forgoes scope filtering by construction — correctness of the read beats
filtering for a base no production code ships.
C: `constructor` is looked up for identity, never invoked as a subject
method — binding it broke `carrier.constructor === Subject` for no benefit;
it now returns raw (the same special-case withProps had). Both pinned in
scope.spec: the frozen-own-filter collision yields the base's value without
throwing, and class identity survives the carrier.
ds-review-bot delta-round finding, verified: cordis hands the carrier to
listeners as `this`, and the event declarations type it Scoped<Agent> — so
driving the subject through it (this.send(...) in an agent/* listener) is a
SUPPORTED shape. The withProps-based carrier delegated gets with the PROXY
as receiver, so ReactLoopAgent's send/steer/cancel — which read the
native-private #carrier through a getter — threw TypeError when called that
way (private members do not exist on proxy receivers).
scopeTarget now builds its own proxy: overlay props (the composed filter and
the carrier mark) answer from a null-shadowed literal via hasOwn (`in` would
let Object.prototype's toString/constructor shadow the subject's), every
other get delegates with the BASE as receiver (getters see the real object)
and returns functions bound to the base (method calls execute on the real
receiver), sets land on the base. A proxy-invariant guard reports frozen own
function props unchanged (binding them would violate the get invariant).
This kills the class at the seam — any subject with native privates works,
today's agents and whatever carries them next — instead of patching the one
#carrier field.
Pinned both ways: a scope.spec matrix (native-#private method/getter through
the carrier mutates the real object; set delegation; frozen-own-prop
invariant; overlay non-shadowing) and the bot's exact end-to-end scenario
(an agent/session-start listener calling this.send drives a real turn) —
both fail with TypeError against the withProps carrier.
The master merge (5309ea54) resolved the module-graph conflict by hand,
placing the subagent-subprocess dependency-table row ahead of util/timeout's;
the generator's deterministic order (group order, util first) wants them
swapped, so the freshness gate (gen-module-graph --check) failed CI's static
job. Regenerated on the merged tree — a two-line swap; every other generated
catalog was already resolution-fresh (regen-all changed nothing else).
Two review findings (#220) on the sandbox context façade:
- Undeclared services were reachable: the façade resolved any live global via
ctx.get(name), so ctx.bash worked without inject: ['bash']. A cross-mount
consumer could then depend on a provider cordis never saw — unmounting the
provider would neither park the consumer nor unwind its registered tools,
leaving a model-visible tool that fails only at execution. The façade now
reads ctx.fiber.inject and refuses any service the mount did not declare
(with a teaching error naming the inject fix), so the dependency is always
visible to cordis and its activation/unload semantics bind.
- ctx.tools.get returned the live ToolDefinition, including execute — mount
code could call another tool directly and bypass ToolRegistry.execute and
its pre/post-execute hooks and accounting. get now returns the same
read-only name/description/parameters view as schemas(), never an invocable.
Adds inject-gate and schema-view regression cases to sandbox-context.spec.ts
(undeclared property/get denied, declared allowed, the cross-mount zombie-tool
scenario refused at call time, get exposes no execute). Package stays at
per-file 100% coverage. RFC, mount description, and tool-catalog updated.
Tianyi Cui
Yichen Jiang
imccyu
Dudu-0223
kingwl
lintianle
pku-xht
pku-xht