Keep DeepSeekHarness.run() reusable, but make ownership of its lazy
runtime process explicit. Document the context-manager/close contract and
update every construction example to use a context manager so repeated runs
remain valid without encouraging leaked subprocesses.
Contain notification predicate failures at the subscription boundary. Remove
only the subscriber whose callback raised, deliver that exception through its
queue, and continue dispatching to healthy subscribers so arbitrary callback
code cannot terminate the shared reader thread or strand later requests.
Enforce one in-flight prompt per server session with an atomic activePrompt
guard. Route overlap through the existing -32603 handler-error response and
clear the guard in finally, preserving parallel prompts across sessions and
sequential reuse without changing JSON-RPC request or notification shapes.
Use StringDecoder for line framing so a UTF-8 code point split across Buffer
chunks is not corrupted. Add a queued-write flush barrier, and make memoized
shutdown await it before disposal and exit while retaining exactly-once
cleanup when shutdown calls race or flushing fails.
Cover callback isolation, same-session exclusion, cross-session concurrency,
split multibyte input, delayed writes, racing shutdown, and flush failure with
deterministic tests.
Drain idle injection flushes before agent teardown, snapshot approval and subagent provider inputs, and gate subagent lifecycle events on real child readiness. Align the RFCs and generated contracts with the hardened behavior.
The three-entry cordis.yml (dsh-sandbox-local + dsh-bash-sandbox at a
read-only default + dsh-approval) served over ACP: the first live approval
composition. Recorded snapshot scenarios pin the wire end to end —
config-options advertisement, the mode-switching arc as the suite pinned
header (both switches, the prompt-section delta, one changed-by-the-user
notice per knob, a confined write landing under the switched mode), and
both escalation branches over scripted permissionAnswers (a grant runs
confined under workspace-write; a rejection executes nothing and pins the
fail-closed text). The with-key escalation e2e drives a real model +
real runner + the real bridge answerer, world-verified; ci.yml snapshot
lane and e2e.yml install bubblewrap so the confined replays actually
execute.
Both RFCs move to implemented/ (Decision/Consequences form, deferred
phases tracked in their own sections), with every cross-reference flipped.
effective(session) = findLast(the session own knob events)?.value ?? the
composition-config default. One log-only event per knob, owned by its
domain (bash/sandbox-mode in dsh-bash, approval/policy in dsh-approval),
each exporting the same three-piece kit: the event declaration, a pure
fold, and THE write path — a switch IS its event; no owner service, no
facts map. Restart immunity and multi-session isolation fall out of the
log replay by construction.
Execution follows the fold on both sides: the bash tool stamps
escalation grant > session override > executor default, and the approval
seam prepends the never-gate that auto-rejects before any interactive
answerer. Visibility is two layers per knob: a per-agent prompt section
states the effective value on every request (logged through
request/header*, so what-the-model-was-told replays from the log), and an
agent/pre-step narrator injects at most one coalesced delta notice with
positional attribution (user switch vs operator/config drift). The ACP
bridge advertises one capability-gated select per composable knob with
currentValue folded per session, validates set_config_option against the
closed vocabularies, and anchors idle switches at the next turn
prompt-submit under the turn-enclosure contract.
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.
Master advanced 11 commits mid-merge (the Code Mode registry integration:
mode config, run_code, the tools:sdk section, the ACP run_code cards and
unified demos). The fusion makes Code Mode scope-aware end to end:
- wireSchemas(scope): the mode-aware wire contribution is computed from the
CALLING SCOPE's visible set (scoped tools join, shadowing and restrictions
apply) and feeds the {schemas, knownNames} provider protocol.
- knownNames under the mode collapse: a per-scope RESTRICTION is runtime
state, so the universe stays pre-restriction (a restricted-away tool in
toolOrder is a normal absence) — but the MODE collapse is deployment
config, so under mode 'code' the universe is [run_code] and a toolOrder
naming a native tool fails every assembly loud (master's tested decision,
kept).
- The tools:sdk section renders per assembly CONTEXT: the SDK declares
exactly the calling agent's callable set, using the section-text provider
signature this branch already had.
- run_code bindings enumerate schemas(exec.agent) — a program can bind
exactly what its prompt promised; sub-dispatches already threaded
exec.agent through registry.execute, so scoped resolution and carriers
flow unchanged.
- dsh-tools declares both sides' new deps (dsh-scope + dsh-session);
lockfile and all generated catalogs/graphs/api-catalog regenerated.
Gates green on the merged tree: typecheck, lint, per-file 100% coverage
(2710 tests), snapshots (41), doc-sync, module graph, build, hygiene, demo
smoke.
Master brought 50 commits (the tool-cordis group, dsh-code-runtime + worker,
the tools/execute around-dispatch seam + timeout-policy, repeat-tool-guard,
agent/session-prefix, the ui reorganization). Beyond the ten textual
conflicts, the merge reconciles master's new seams with this branch's
scoped-registration world:
- tools/execute (new waterfall around core dispatch): dispatched with the
SAME exec.agent carrier as the pre/post waterfalls — an agent.ctx wrapper
times/retries only its own agent's calls — and its base thunk resolves the
tool through the caller's visible view (get(exec.name, exec.agent)), so a
scoped/shadowed tool dispatches and a restricted-away global stays
UNKNOWN_TOOL. Declared this: Scoped<ToolRegistry> with the scope-filtered
doc sentence; invariants table + verify-scoped-dispatch pin it (21 events).
- agent/session-prefix (new waterfall, once per loop instance): composed via
the fused agentEvents dispatcher (scope-filtered like every agent-subject
event), declared this: Scoped<Agent>, table-pinned. agent/pre-step keeps
master's new sessionPrefix parameter with this branch's Scoped this.
- timeout-policy reads the budget through the caller's visible view
(get(exec.name, exec.agent)): a scoped tool's own timeoutMs governs its
calls; a global name-twin's budget is never misapplied to a shadowing
per-agent variant.
- tool-cordis: cordis_inspect's tools section lists the CALLING agent's view
(its description promises "what you can call"); the sandbox tool façade's
reads resolve through the mount's own scope, mirroring where its register
lands writes; sandboxRegisterTool's return type carries the exact-disposer
union honestly. dsh-scope declared as peer+dev with the project reference.
- doc-sync chain unions master's verify-cordis-api with this branch's
verify-scoped-dispatch; the generated catalogs, event matrix (the
zero-dispatcher guard passes over master's new events), module graph, and
the cordis api-catalog are regenerated on the merged surface.
Full gate sequence green on the merged tree: typecheck, lint, per-file 100%
coverage (2668 tests), snapshots (38), doc-sync, module graph, build,
hygiene, demo smoke.
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).
