The executable golden proves the packaged VFS and Python SDK boundary, but it does not pin the editor-facing ACP updates, and the existing ACP scenarios exercised Code Mode, subagents, and workflows only as separate stories.
Add a dedicated both-mode replay composition that mounts a Cordis marker, inspects it through a real Code Mode worker dispatch, runs a direct spawn child and a workflow-owned spawn child, then unmounts the marker. Commit normalized ACP frames, parent and child logs, and the composition-specific request-header pin.
Use cordis_inspect as the Code Mode sub-dispatch instead of registering another dynamic tool: the executable snapshot already owns tool-set mutation and header-delta coverage, while this keeps the ACP header contract stable and focuses the new golden on transport presentation and cross-feature composition.
A preset names a bundle of the two mechanism knobs — request =
workspace-write + ask, yolo = danger-full-access + never — so the editor
shows ONE 'Permissions' select where the sandbox-mode and approval-policy
tiers stay orthogonal capabilities (the Codex /approvals shape: presets over
two dials). ctx.permission (dsh-permission) owns the config-defined table,
validates the default preset's bundle against the composed knob defaults at
load (fails loud), and writes a switch THROUGH: one log-only
permission/preset event (the audit fact reverse-mapping cannot recover —
the planned 'agent' preset shares request's knob values and differs only in
composed policy) plus each knob event via its own setter, deduped — a
net-zero switch appends nothing. Every knob consumer keeps reading its own
fold, untouched.
The current preset DERIVES from the effective knob values — the fold breaks
bundle ties, a knob state outside the table is the reserved 'custom' value
(a state, not an error: shown while it holds, switchable FROM, never a
target), and defaultPreset disappears (zero-event state reverse-maps from
the composition defaults).
The ACP bridge drops the two per-knob selects for the one preset select
(advertised only when ctx.permission is composed); pending/anchor/no-op
semantics carry over unchanged, with the no-op echo acknowledged before
vocabulary validation so a client re-pushing a derived 'custom' current
never errors. The sandbox variant example composes the
service with a workspace-write default; the permission-switching,
escalation-approved and escalation-rejected scenarios are re-recorded under
it (escalations now target an outside-workspace /tmp path under
danger-full-access, self-cleaning) and config-options is re-authored on the
single-select wire.
sandbox-acp-agent's whole surface moves into examples/acp-agent following
the example's existing multi-variant shape (the code-mode/both-mode
overlays): sandbox.cordis.yml + its replay overlay, the four snapshot
scenarios (config-options / mode-switching / escalation-approved /
escalation-rejected) as a 'sandbox' header class over per-scenario
configPath — goldens byte-identical, zero re-recording — and
escalation.e2e.ts unchanged apart from the config path. One ACP example
remains; demo:sandbox-acp keeps its name and boots the variant. References
(both RFCs, group/package READMEs, the examples table and test map, the
e2e workflow comment) now point at the variant.
dsh-bash grows the per-call policy carrier: BashExecRequest.sandboxMode
(request-optional, spec required-but-nullable — the owner pattern; resolve()
is the one explicit defaulting step) and the BashExecutor.sandboxMode
capability fact (undefined in the base class — composition truth the tool
layer can read). dsh-bash-local carries the field verbatim and confines
nothing.
dsh-bash-sandbox extends LocalBashExecutor and hands ctx.sandbox the exact
argv it is about to spawn. A denial is a RESULT FACT (the command RAN;
result.sandbox.denied is orthogonal to exitCode/signal), classified
conservatively against the wrap own dialect; a RUNNER failure outranks
denial — foreground re-throws the structured SANDBOX_UNAVAILABLE, a settled
background task stamps sandbox.runnerFailed — so a broken sandbox never
reads as a failing command and the command never runs unconfined.
dsh-tool-bash renders the markers and teaches the model not to retry around
a policy denial; escalation and per-session switching are staged follow-ups.
The ACP bridge registers the first real approval answerer: an ask for an
agent it owns becomes session/request_permission attached to the already-
streamed tool call (one-shot allow_once/reject_once only), outcomes map
conservatively (unknown optionId never grants, client cancel → cancelled),
and foreign or call-less requests delegate down the waterfall. The snapshot
harness accepts scripted permissionAnswers (FIFO; an unscripted prompt
answers cancelled, fail closed) so recorded scenarios can drive the wire
keylessly.
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 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.
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).
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.
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).
Three findings from the PR-4 convergence round:
(A) A root-undefined binding argument passed normalization untouched, so
the sub-call DISPATCHED and only then failed the tool/code-dispatch append
(Session.append rejects undefined event data) — a sub-call executed with
no log record, violating the nothing-executes-unlogged contract. And the
tool received the SAME object later handed to the append, so a tool
mutating its args desynced the logged record from what was dispatched (or
re-poisoned the append). jsonNormalizeArgs now rejects undefined up front
with a model-correctable message and returns TWO independent parses of the
canonical JSON text: the tool gets one, the event logs the sibling —
identical by construction, mutation-proof.
(B) The bridge built its bindings record with plain-object assignment, so
a registered tool named __proto__ hit the prototype setter and silently
vanished (the runtime host resolves binding names as own properties). The
record is now null-prototype with defineProperty, mirroring the
worker-side namespace build.
(B) The header-pin sanity assertions ran only inside NON-pinning
scenarios, so a class consisting solely of its pinning scenario (the two
Code Mode classes) would accept a re-recorded pin carrying several headers
or a header-delta. A fixtures meta-test now asserts every pinning fixture
directly.
The dsh-tools half of the Code Mode RFC (its fourth, final change): the
registry gains its first config — mode: native | code | both — and OWNS how
its tools reach the model. 'code' contributes exactly one wire tool,
run_code, plus a lazy tools:sdk prompt section declaring every other tool
as a generated TypeScript API (jsonSchemaToTs: total over the defineTool
subset, unknown degradation, lexicographic byte-identical rendering);
'both' ships both representations; 'native' is byte-for-byte the old
behavior. Non-native modes fail every assembly loudly without a
typescript-language ctx.codeRuntime.
run_code's dispatch bridge: JSON-normalizes each binding argument before
dispatch (what dispatches is what the tool/code-dispatch event logs — the
append can never fail on payload shape; BigInt/circulars reject that one
call), serializes all program tool calls through a per-run queue (even
Promise.all — no concurrency-safety metadata yet), routes every sub-call
through tools/pre-execute → tools/post-execute (a deny rejects the
program-side promise), drops sub-call additionalContext (no safe outlet
mid-run; pinned), owns a run-scoped abort that follows the outer signal in
and fires on settlement (in-flight sub-dispatch aborted, queued abandoned,
queue drained before returning), and converts a failed run into
CodeRunFailedError → a structured isError carrying kind + captured logs.
tool/code-dispatch joins SessionEventMap by declaration merging (log-only;
deriveMessages ignores it).
The composed surface: the tools config forwards through agent-core and
both app packages; examples/code-agent + demo:code run the worker runtime
under mode code (keyless boot smoke + a with-key e2e proving the collapsed
[run_code] header, the dispatch events, and the file the program wrote);
two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK
section, collapsed header, dispatch events, and result card — each its own
header-pinning class (the harness gains per-scenario config overlays and
per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the
RFC (moved to implemented/, restructured to decision-era headings) updated
in the same change.
The snapshot tier's machinery leaves examples/acp-agent/tests for
packages/support/acp-snapshot (@deepseek-ai/dsh-acp-snapshot), where the
coverage gate measures it and a second example can consume it instead of
forking it: harness.ts (runScenario, parameterized by an AgentUnderTest
{binScript, configPath, tsconfigPath} instead of module constants),
normalize.ts (moved verbatim), and suite.ts (defineAcpSnapshotSuite — the
per-scenario golden/log compares, record write-back, per-suite header pin
with its uniformity guard, and the fixture guard block, lifted from
acp.snapshot.ts). The example file collapses to its scenario table plus
one factory call; env reading (DSH_SNAPSHOT) stays at that edge.
The exactly-one-pin meta-test generalizes from the hardcoded text-turn
name to "exactly one per suite" — which scenario pins is the scenario
table's reviewable choice (per-suite pinning per the proposal RFC).
Extraction parity: pnpm run test:snapshot is 36 passed + fs-policy-reject
failing BEFORE AND AFTER (BSD-sed environment failure, reproduced at the
base commit in a clean worktree — the recorded golden's sed -i syntax is
GNU-only), with zero byte changes under examples/acp-agent/tests/snapshots/.
Coverage for the new src files lands in the next commit.
The Date.now()/Math.random()/argless-new-Date() bans existed solely to
keep scripts resume-compatible for the deferred journaling/resume
feature. Pre-support for an unimplemented feature is speculative cost:
scripts may now read the clock freely; implementing resume reintroduces
the bans as a script-contract tightening. The RFC's shipped-state
description is updated in place, the tool DESCRIPTION drops the
constraint sentence (the pinned text-turn header follows), and the
engine README's trust-premise paragraph now leans on absent globals
alone.
The tool-order feature canonicalizes the model-facing list (alphabetical
absent a configured toolOrder), so the header-pinning text-turn fixture is
re-recorded on the stacked tree — every other fixture stores the header as
scrubbed tokens and needed nothing. AGENTS.md condensed back under its
ceiling after the merge union.
Residuals from the Codex re-review:
1. A system delta's insert was flattened to one token, so deltas differing
only in inserted-line count compared equal. Now one {{system}} token per
inserted line — position AND extent survive, content does not.
2. The live uniformity guard folded only request/header snapshots, so a
mid-run header CHANGE (request/header-delta) could diverge from the pin
invisibly. Non-pinning runs now assert zero header-delta events: a
scenario that legitimately changes its header mid-run exists to show
that change, so it must pin (fail-loud until it does).
Codex review findings on the pinned-header change:
1. scrubRequestHeaders flattened a request/header-delta's whole
system/tools payload to one token, so two meaningfully different deltas
compared equal. Now the structural facts survive — keepStart/keepEnd
line positions, added/removed/changed tool NAMES — and only the bulk
(inserted prompt lines, schema bodies) is tokenized.
2. The one-pin design rested on an unasserted premise (all sessions
compose the same header). Every non-pinning scenario now asserts, live,
that each request/header its run produces equals the pinned fixture's
header (both sides normalized against their own volatile values), so a
session-dependent header fails loud until it gets its own pin.
Verified the guard bites: perturbing the pinned fixture's prompt fails
a non-pinned scenario with the intended message.
3. RFC de-slopped per docs/AGENTS.md: no PR reference, no SHOULD
spec-speak; Decision/Verification/Consequences updated for 1 and 2.
Restack on the carved-out foundation (#192), per review feedback on #170.
The seam files resolve to the carve-out's revision — its prompt-order
neutrality fix (backends no longer inject 'tools'; the structured runtime
gates its own capture-tool registration) restores the subagent tools to
master's front position, so every recorded fixture is re-recorded on the
stacked tree and the authored error-finish/cancel headers re-patched to the
stacked tool list ([subagent, subagent_fork, workflow, todo_write, ...]).
Every session.jsonl fixture embedded the full composed system prompt and
complete tool-schema list in its request/header event (~8 KB on one line,
identical across the suite), so any prompt or tool-schema edit forced a
re-record or hand-edit of every fixture — see the dynamic-workflows PR for
the churn pattern this removes.
Now exactly one scenario (text-turn, flagged pinsHeader) commits and
compares that content verbatim; every other fixture stores and compares it
as {{system}}/{{tools}} tokens via the new pure scrubRequestHeaders
normalizer (applied to both compare sides and to record-mode writes, so a
re-record cannot reintroduce the content). request/header-delta payloads
are scrubbed the same way; config/reason stay verbatim — a model swap
SHOULD churn every fixture, a prompt edit should not. Replay is unaffected:
script derivation reads only assistant/chunk events.
Fixture meta-guards enforce the split: non-pinning fixtures must be fixed
points of the scrub, the pinning fixture must not be, and exactly one
scenario pins. Committed fixtures migrated through the same function.
Docs: pinned-header RFC (implemented/testing), base snapshot RFC + testing
policy + llm-replay module doc/README updated.
Tianyi Cui
kingwl
Yichen Jiang
imccyu
Hypatia May