SubagentStartRequest.parent, its core-data type-equiv mirror, and the
ACP backend Agent Note still said the out-of-process backend ignores
request.parent — no longer true: with cwd unconfigured it reads exactly
the session header's cwd, and a parent session without one now rejects
at start. State the one-field read at each owning contract, record the
workspace-resolution decision in the Agent Note, and align the README's
accessibility wording with the search-permission guard.
statSync().isDirectory() is true for a mode-600 directory, but a
subprocess cwd needs X_OK — spawn would fail EACCES, deferring a
self-contained configuration error past the load/start boundary the
resolution owns. Probe accessSync(X_OK) alongside the type check so
"not an accessible directory" is literally what the guard verifies.
The consolidated resolver scopes the anonymous id to $DSH_HOME rather
than the machine. Update the module contract, README, and Agent Note to
say per-harness-home explicitly instead of over-claiming a machine-global
identity, and record why DSH_HOME scoping is the intended single-root
meaning rather than a regression.
Review fixes for #462:
- resolveDshHome now treats an empty or whitespace-only $DSH_HOME as
unset, so a blank override never resolves the home to cwd via
resolve(''). Restores the guard telemetry's old resolver carried.
- The default-env telemetry test asserts only that globalConfigDir()
returns an absolute path, so a machine DSH_HOME without a .dsh suffix
cannot break it.
Automatic compaction fires mid-conversation, right after the loop warmed
the provider's KV cache with the last routed request. The default
summarizer then issued a separate request whose prefix shared nothing
with that warm request — a bespoke summarizer system prompt followed by
the older history flattened to one rendered transcript string — so a
differing first token invalidated the entire cached prefix and every
compaction re-processed the whole replayed history twice.
Move the compaction directive from the FRONT (a fresh system prompt) to
the END (a trailing user message), and replay the last routed request's
own system prompt, tools, message prefix, and shadowed-region messages
verbatim via session.requestHeader() + deriveEventMessage. The auxiliary
call is now a genuine prefix-extension of the warm request, so the
provider reuses the cached tokens up to the trailing instruction.
SummarizationInput carries the replayed prefix instead of a flat string;
the now-unused renderTranscript/renderContentBlocks path is removed with
its spec. Cache reuse is best-effort (head compaction guarantees a hit;
a mid-range compaction or a differently-routed summarizer forgoes it),
correctness is not.
Delete @deepseek-ai/dsh-home and make dsh-paths the sole owner of the
single-root harness home ($DSH_HOME || ~/.dsh). Migrate tool-bash,
skill-local, and agent-spine-demo off dsh-home, and fold telemetry's
divergent globalConfigDir onto the shared resolver, dropping its second
XDG/APPDATA policy and the deepseek-harness namespace so the anonymous
id lives under the harness home. Add dshHomeDisplay() for symbolic
user-facing paths, replacing workspace-context's bespoke check.
The test 'labels the default DSH home as ~/.dsh when HOME points at the
configured default' mocks node:os to return a temporary home directory
and expects discoverBaselineInstructionFiles to fall back to the default
~/.dsh path. However, when DSH_HOME is externally set (e.g. in the DSH
agent environment), resolveDshHome(undefined) reads that external value
instead of falling back to defaultDshHome(), causing the test to look for
AGENTS.md in the wrong directory and return an empty result.
Stub DSH_HOME to undefined so the test controls the full resolution path.
The master merge brought the tool registry's per-scope restriction layer
(tools.restrict), which makes dsh-mode's prepend assemble filter a duplicate
enforcement shape: it re-implemented the registry's SDK-section rendering
(renderToolsSdk + the RUN_CODE_NAME exclusion) and hid the exit tool from
prompts only — dispatch stayed open and the execute-time re-check was the
real gate. The service now reconciles a per-agent deny restriction on
agent.ctx at agent/created and at every boundary flush, so wire schemas, the
Code Mode tools:sdk section, AND dispatch resolve exit_plan_mode through the
one registry view (a default-mode call answers UNKNOWN_TOOL, byte-identical
to a no-dsh-mode deployment). The execute-time folded-mode re-check stays as
defense in depth for a direct foreign mode/set append no boundary has
reconciled yet.
Two zero-consumer surfaces removed per the pre-release stance:
- AgentOptions.mode creation seeding (declaration merge + agent/created
listener); a caller selects through set() before the first turn, and the
deferred subagent inheritance returns together with its consumer.
- The dropped-definition boundary notice (droppedNoticed + narration):
custom mode definitions have no production consumer, so nothing can be
dropped; fold-to-default degradation is unchanged.
The stdio removal had left plan mode ACP-only while docs still claimed a
/mode command. dsh-mode now registers /mode on the plugin-owned command
registry through an optional ctx.inject(['commands']) child (type-only peer
edge on dsh-commands), so the TUI and the ACP slash-command surface both
gain it; examples/tui-agent composes dsh-mode. ACP/TUI expected outputs
refreshed keyless for the available_commands_update delta.
Docs updated in place (mode READMEs, the plan-mode Agent Note's realization
sections); catalogs and graphs regenerated.
The earlier fix only widened the vitest timeout, but the real race is the
patient probe reading the 1s launcher under the 5000ms *default* probe budget:
under a full parallel run spawnSync blocks the worker and fork/exec latency can
push the launcher's wall-clock past 5000ms, so the patient probe wrongly reads
unusable and the assertion fails. Give the patient probe a generous explicit
15000ms budget (still far below its 1s launcher runtime margin) so only the
250ms impatient probe races the launcher; keep a 30s vitest timeout above the
patient budget.
Resolve conflicts:
- packages/ui/tui/src/index.ts: keep the color-scheme detection block; drop the
obsolete static autocomplete list (master moved to refreshCommandAutocomplete).
- docs/config-catalog.md: regenerate (tui Config source line shifted to :104).
`bounds the default probes` runs a real launcher that sleeps 1s under the
5000ms default probe budget, all wrapped in vitest's 5000ms default test
timeout. The blocking spawnSync races that wrapper and tips over under the
load spike of a full parallel run — a pre-existing, load-sensitive flake
(noted as unrelated in this PR's original description). Give the test an
explicit 20s timeout so its bounded subprocess work never races the default.
A direct runtime import of the session package made the unbuilt worker depend on sibling lib output. Use a parity-tested local JSON snapshotter and pin the isolated source closure with a real-worker test.
Yichen Jiang
Tianyi Cui
NI0317
Turtle
Huanqi Cao
kingwl
Dudu-0223