The section is a strict subset of the plugin config: `agents` is consumed
once when the service starts, so a stored change there could only look like
it had an effect. The cap resolves through a getter over the settings source,
which the scheduler destructures at the start of each tool group, so a
committed change bounds the next group without disturbing the one in flight.
`resolveMaxParallelToolCalls` becomes the section validator, refusing a value
at the write instead of at that group.
The deferred-resume effect-shape assertion now allows the one plugin effect
the optional settings wiring adds at the fiber's own level; a resumed agent
joining it there is still the regression it pins.
The 导出 button fetches GET /api/session.export and saves the ZIP (root
artifact plus subagent descendants). The plugin exposes exportLog through
the view's inject face, resolves the tab label through the locale service,
and disables the button while in flight; fixture mode answers 404 so the
error bar explains the gap.
Streams one ZIP of the root session artifact plus each subagent descendant
verbatim (the persistence readRaw bytes) from GET /api/session.export as a
host-only download — no wire envelope, absent from IApiClient. The downloads
domain owns the query schema, the fetch handler answers the GET alongside the
SSE routes, and compression runs on the host with fflate's streaming Zip API.
The persistence contract gains a concrete readRaw default (undefined for
backends without a per-session artifact) and the JSONL backend overrides it
with the decode of its physical zstd frames, so a consumer can read the
stored artifact text verbatim — the session-log export depends on it.
Tool and prompt-section visibility is inherited along dsh-scope's parent
chain, and an agent's scope key is minted with no parent. Per-session agent
presets moved every model-facing row onto the agent plane and made
AgentPresets.mount() the one thing that binds that link, from the api-proxy's
session create, resume, and fork paths. The two in-process subagent drivers
installed only the per-child persona and tool filter, so a child's scope chain
had length one and its registry view resolved the global layer alone — which
is empty wherever a preset roster is composed. One-shot children reached the
model with no tools, continuable ones with only the host-plane `report`, and
neither carried its parent's persona, workspace context, or skill catalog.
AgentPresets.composeFrom() joins one agent to the standing composition another
already runs on. It is a bind, not a mount: the child gets its parent's exact
generation, so a composition edited since the parent started cannot fork it
onto another one, and it is synchronous, which is what lets a child creation
window use it. applyChildComposition() now takes the parent and performs the
join first, making a child composed without it unrepresentable at the call
sites. childSessionMeta() records the joined id so a cold read rebuilds the
composition the child actually ran under.
The audit that followed found two api-proxy readers on the wrong authority:
presenterScopeFor() and the live-agent branch of assertPresetUnchanged() both
read header.agentPreset, which goes stale the moment a blank session switches
preset. A switched session's cold transcript resolved presenters in the older
composition's layer and silently degraded to generic cards, and the gateway
refused to adopt a live session under the preset it actually runs while
accepting the one it left. Both now resolve through resolveSessionPreset(),
matching the resume branch fifteen lines above. The owning architecture Agent
Note carried the stale claim that the header records what a session runs; it
is corrected to name the header/log pair and its three readers.
Fixes#2165
`ScopedLayers.effect` already returns an exact `() => void`, so the inherited
`() => void dispose()` wrapper voided a void — two lint rules, four errors.
The scoped layer's own teardown had no test, which is the registry-contribution
disposal contract the testing policy requires and the only path that calls
`TaskLayer.isEmpty()`: `ScopedLayers` prunes a scope's layer when its last
contribution disposes. The new case mounts one plugin contributing both a
surface and a listener into one scope, then unloads it and observes that the
agents which joined that scope are refused again.
Refs #2141
One host registry serves every composition in the process, so its two
service-wide collections answered per-owner questions process-wide. `start()`
asked only whether SOME surface was attached, so an agent whose own composition
loads no `tool-tasks` could start work it has no tool to collect or stop as soon
as any other preset attached one — and the answer changed depending on which
sessions happened to be open. `settle()` walked every registered listener, so a
task settling without a waiter injected one completion notice per mounted
preset into the same owner.
Both collections now sit in `ScopedLayers`, the layered-registry primitive
`tools` and `skills` already use: a registration files into its registering
context's scope, and a read unions the global layer with the owner's scope
chain. A surface or listener registered from an unscoped context lands in the
global layer and serves every owner, which is exactly the host-plane
composition's own controls, so the TUI path is unchanged without a special
case.
This supersedes the consumer-side filter in the previous commit. That filter
produced the right notices but sat in the wrong layer: it left the `start()`
gate process-wide, it could not be enforced against a producer that resolves
the registry directly, and it made a Consumer carry scope knowledge that the
other layered registries keep in the registry. `tool-tasks` is scope-agnostic
again and the `dsh-scope` edge moves to `tasks-local`.
`start()`'s refusal is now owner-relative, so its model-visible text names the
agent rather than the process. The shipped `minimal` preset keeps
`enableRunInBackground: false`, no longer as the safety boundary — the registry
owns that now — but so an agent that could never collect a task is not offered
the parameter at all.
Refs #2141
The capability's namespace is owned by the seam because it names the
capability, not an implementation: a host composes exactly one provider of
ctx.bash, so both executor families register the same namespace with their
own schema and composition entry without ever colliding, and a settings
document carried between platforms keeps resolving on both.
Both executors read their config through a source thunk, so a stored change
reaches the next command. The constructor checks the schema cannot express
become the section validator, refusing a bad value at the write instead of
at the next command. pwsh re-resolves its executable only when the declared
path changed, so an unrelated settings change never re-probes the filesystem.
Address ds-review-bot on #2127:
- assistant-output: the rule has ONE implementation, the incremental
AssistantOutputFold (push/pushText/collect); finalAssistantOutput folds a
complete suffix, the SDK backend folds notification events, and the ACP
backend folds raw chunk text into the same streamed fallback.
- subagent/end.lastAssistantMessage: 'no output' is encoded once — absent,
never [], on both lifecycle shapes (observeRun now omits empty output).
- tool-subagent: a non-completed foreground result stays isError but appends
the child's preserved partial text after the stop-reason headline.
- Authored keyless snapshot scenario subagent-max-tokens-partial pins the
assembled transcript: the child's committed log carries the usage-only
empty message and the parent's tool result carries the partial answer.
- Rule-boundary sentence (message wins over later streamed text) and the
consumer half recorded in the Agent Note; comments trimmed to pointers.
