ds-review-bot critical: compactIfNeeded estimated pressure from the
derived history + system prompt only, but every loop-built request also
carries EpochHeader.messagePrefix in front of the history — a
deployment at the window edge would under-estimate by exactly the
prefix, skip compaction, and ship an over-window request.
BasicCompactService now gates on estimatePressure(): the session prefix
read from the log's folded header + the derived history + the system
prompt. The fold is exact from the instance's second request on (and
from a resumed instance's first — the previous instance logged its
prefix); it is absent only before a fresh session's first request,
where the history is a single prompt and compaction is moot. Compaction
itself still shrinks history only — a prefix that alone approaches the
window is a configuration error no compactor fixes, same as the
documented single-unit-overflow stance.
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.
Review discussion converged on the industry shape (Claude Code caches
user context per conversation; Codex separates initial context from
diffs; Kimi appends at continuation boundaries to protect prompt
caching): stable openers belong in a compose-once prefix, mid-session
changes belong in append-only history — not in a per-request slot.
agent/session-prefix fires ONCE per loop instance, lazily on its first
request-building step: the composed Message[] is deep-frozen, cached on
the transmission bookkeeping, recorded as EpochHeader.messagePrefix on
the anchoring 'initial'/'resume' snapshot, and reused verbatim for
every request the instance sends — prefix stability is structural, not
a producer discipline, and a resume recomposes with attributable drift.
The request is messagePrefix + boundary snapshot.
The per-step RequestAdvice/RequestAdviceContext surface and the
messageSuffix header field are dropped: the tail slot had no consumer,
and every current update pattern (new AGENTS.md discovered, memory
update, skills change) routes through the existing append-only history
channels — inject(), tools/post-execute additionalContext,
prompt-submit additionalContext — each paid once and prefix-cached
thereafter. The messagePrefix delta arm stays for codec totality; the
loop never produces one in practice.
A single stable required check that needs every other job in ci.yml, so
branch protection no longer enumerates matrix leg names that change as
lanes and node versions evolve. if: always() keeps the job running when
a dependency fails (a skipped required check would count as passing);
any non-success result — failure, cancelled, or skipped — fails it.
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.
tianyicui's review: the seam name did not say what the event or its
types do. 'advice' reads both ways — advisory content for the model,
and AOP before/after advice woven around a join point (here the
derived history) without modifying it — so RequestAdvice.before/after
are self-describing. Types follow: RequestAdvice / RequestAdviceContext;
the logged EpochHeader fields keep their positional names
(messagePrefix/messageSuffix).
Also sharpens the core.md wording the review flagged as ambiguous:
before-advice sits in front of the ENTIRE derived history, directly
after the system slot (the conventional home for session-stable openers
— an AGENTS.md digest, a skills catalog), after-advice follows the
history's last message. Catalogs and doc graphs regenerated.
A client-callback throw only becomes a JSON-RPC error RESPONSE to the
agent's session/request_permission — runScenario itself kept going, so a
tolerant agent could treat the error as a denial and the scenario would
pass, or worse, record: the impossible click baked into fixture and
golden, green on every replay. The mismatch is now captured as a harness
error while the agent is answered plain cancelled (a well-defined path
it cannot reinterpret), and the step loop rejects the run on it as soon
as the in-flight step settles. The spec asserts the rejection instead of
the agent-side error echo.
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.
The package, coverage, and permission scripting all shipped on this
branch, so the RFC moves to implemented/ with the lifecycle rewrite:
Proposal becomes a present-tense Decision, Acceptance criteria and Risks
fold into Testing/Consequences with what actually pinned each one (the
zero-byte extraction parity, the 100% per-file coverage via the fake
bin, the vitest-in-src caveat, the per-suite pin cost).
InputScript gains an optional permissionAnswers queue, consumed FIFO by
the harness's requestPermission handler. Each entry selects by option
KIND (allow_once, reject_once, …): option ids are agent-issued randoms a
committed script cannot know, while kinds are the ACP-stable vocabulary,
so the client maps kind → the offered optionId at answer time. An absent
or exhausted queue answers cancelled — existing scenarios and goldens
are untouched — and a scripted kind the request never offered throws,
surfacing as a JSON-RPC error on the permission request: the scenario
scripted an impossible click.
This is what lets an approval-flow suite (the sandbox composition) drive
allow/reject round-trips deterministically from input.json, per the
shared-acp-snapshot RFC.
A scripted fake ACP agent bin (tests/fixtures/fake-acp-agent.ts) speaks
real newline JSON-RPC through the REAL runScenario spawn path (tsx
loader, temp cwd, env plumbing); every behavior — prompt outcome,
session/new rejection, persisted logs, filesystem noise — comes from a
behavior.json beside the fixture, so specs script whole subprocess runs
from data. harness.spec.ts drives every step op, both expect-error arms,
the permission-stub default, env forwarding, workspace seeding, and the
harvest ordering/noise/fallback branches. suite.spec.ts runs the factory
for real at collection time: a replay suite over committed synthetic
fixtures and a record suite over a temp copy (write-back never touches
the committed tree; ACP_SNAPSHOT_SPEC_BOOTSTRAP=1 re-bootstraps it),
plus direct cases for the exported pure helpers. The suite factory's
pure helpers (childFixturePaths, fixtureContext, normalizedHeaders,
headerDeltaCount) are exported for those direct specs.
Two branches carry justified v8 ignores, both structurally unreachable:
the waiter in-bounds guard (noUncheckedIndexedAccess) and waitForExit's
already-exited race guard (both call sites sit one synchronous frame
after stdin.end()/kill()). The fake bin substitutes the session/new cwd,
not process.cwd(), into scripted logs — the realpath difference
(/private on darwin) is exactly what the real bin's header carries.
packages/support/acp-snapshot/src is at 100% statements, branches,
functions, and lines under the per-file gate.
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 harness, normalizers, and suite/guard logic live inside
examples/acp-agent/tests, outside the coverage gate and copyable-only
for a second suite. Propose @deepseek-ai/dsh-acp-snapshot under
packages/support: parameterized runScenario, verbatim normalizers, a
defineAcpSnapshotSuite factory with per-suite header pinning, and
scripted permissionAnswers so an approval round-trip is expressible at
the snapshot tier — the sandbox composition is the immediate consumer.
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.
Yichen Jiang
Tianyi Cui
Wenlu Wang
imccyu