A restriction was compiled against the global tool layer alone: only
global-layer tools were tested against `admits()`, and every chain-layer
tool was overlaid unfiltered afterward. That read the exempt set as "the
global layer" when what it means is "what this scope registers itself" —
two descriptions of the same set only while every model-facing tool sat in
the host composition.
Moving those rows onto the agent plane separated them. A preset's tools are
an ANCESTOR contribution to a joined agent, so a subagent's `toolFilter`
stopped constraining anything it was given; and with the global layer empty
`restrict()` rejected every name it received as unknown, failing the child
outright. With the same tools in the global layer the filter still admits
and applies normally, which is what makes this a regression of the move
rather than a standing limitation.
`view()` now filters everything a scope inherits — the global layer and
every ancestor layer on its chain — and exempts only the layer the scope
owns. That exemption is load-bearing rather than incidental: the delegation
runtime registers a child's `report` and structured-output tools into the
child's own layer, and a filter naming the capabilities the child may use
must not strip the machinery it answers through. Tool order, and with it
prefix-cache reuse, is unchanged: inherited names keep their global-then-
ancestor position and own-layer names still come last.
The diagnostic said "unknown global tool" while listing what is really the
inherited surface; it now names the surface it checks and says why an
own-layer name is not restrictable.
Fixes#2185
`session.create` also adopts an already-live session, and the preceding
commit newly allows adopting one under the preset it switched to while
blank. Its response still echoed `header.agentPreset`, so that adoption
answered with the preset the session had just left — contradicting the
request it had accepted and the row `session.list` serves for the same
session from `resolveSessionPreset()`. The echo now resolves the same way.
The `assertPresetUnchanged` parameter doc said `existing` was the preset
the session was created under; both callers now pass what it runs.
`composeFrom()` was documented as "infallible" and "cannot fail" beside two
`@throws`. It has no composition failure mode — no roster read, no mount, no
file — but it does reject a caller error, and the wording now says which.
The package-level "switched preset" test re-linked to the same preset id,
so it could not tell reading the parent's live scope chain from reading its
creation header. A second fixture preset makes the switch real.
The Web browser lane's subagent goldens gain the preset badge a child now
shows, which is the visible consequence of recording its composition. That
lane runs only under DSH_EXAMPLE_MODE=lib and was missed before.
The Agent Note records two limits found in review: a cold-resumed
continuable child joins its parent's current composition rather than the one
its header names, and `toolFilter` does not constrain a joined child. The
latter is a regression from the agent-plane move rather than anything this
change introduces — with the same tools in the global layer the filter
applies normally — and is tracked in #2185.
Refs #2185
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
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
Moving the task registry to the host plane put every preset's `tool-tasks`
listener on ONE `LocalTaskService`. `settle()` computes a single snapshot and
walks every registered listener with no scope filter, and it marks `reported`
only when a waiter is present — so a task settling without a waiter reached
each mount's listener with `reported` false and every one of them injected the
same completion into the same owner. Three shipped presets carry `tool-tasks`,
and a preset file edit adds a second generation of the same mount, so an agent
read N copies of one notice as model-visible durable context.
A mount now claims an owner only when the owner's scope chain reaches the
mount's own scope. An unscoped mount is the host-plane instance that serves
every agent, which keeps the TUI composition and every existing test intact.
Registry-side ownership was the alternative: mark `reported` once the first
listener claims it. It is wrong because `onTaskDone` is not a notice-only
seam — the `dsh-tasks` invariant companion registers a validating listener —
so first-claim-wins would silence observers that are not delivering anything.
The regression test mounts two scoped `tool-tasks` over one registry and
settles an unowned-wait task, which is the only path that reaches the notice
listeners at all: the shipped-composition e2e uses `wait: true`, and a waiter
marks `reported` before settlement, so that test structurally cannot cover it.
Also corrects the standing-mounts Agent Note, which still listed `tasks-local`
among the stateful PRESET plugins.
Refs #2141
Presets own the rows that decide what a session's `/` menu contains, but
both browser catalogs cache per session and had no invalidation edge for a
recompose: `commands/changed` is registry-wide and recomposing registers
nothing, so the menu kept serving the composition the session no longer ran.
The host stream now frames the logged `agent-preset/selected` commit as
`host/session-preset-changed`; the runtime bridges it to the typed
`session/preset-changed` event, `ui-command` soft-refreshes that session's
directory key and `ui-skill` invalidates its catalog entry.
Reaching the host on a second switch was a separate defect: the list-row
identity guard compared every summary field except `agentPreset`, and the
merge keeps the row's `updatedAt`, so a switched row looked unchanged and
served its cached instance forever. The hero chip compares the pick against
that row, so switching back to the creation-time preset sent no RPC at all.
A max-tokens step that assembled only tool-call blocks appends an
EMPTY-content assistant/message (the usage host). Three consumers each
hand-rolled output selection and all let it erase the child's real
answer: the in-process readResult and the Activation subagent/end
capture took the last message unfiltered, and the SDK backend let any
message beat its streamed-text fallback; the in-process driver also had
no streamed-text fallback for cancelled turns.
dsh-subagent now owns the canonical rule in src/assistant-output.ts
(last non-empty assistant message, else the accumulated text-delta
stream) and all three consumers apply it. Regression tests in all three
packages fail under the previous selections.
Closes#1514
