All agent/* and agent-loop/config-start-failed events take one payload
object carrying the agent subject; waterfall/serial payloads require a
signal and keep next as the final argument. PreStepContext and
RequestFailureContext are unfolded into payloads and retired.
goal/changed follows the same shape so agentEvents keeps its listener
error containment. ReactLoopAgent builds its scope carrier once in the
constructor. Regenerates scope resolvers, tool-cordis api catalog, and
docs catalogs; updates all affected listeners, tests, and the
core-data-structures docs (en + zh).
Once a pi-ai route became a declaration rather than a catalog lookup,
adding an OpenAI-compatible gateway meant knowing its model ids up
front. Most such endpoints publish that list at `GET /models`, but no
seam operation could ask: every one is keyed by a registered provider
route, and the provider being added has no route, no stored profile,
and no stored credential — the endpoint and key are values in a form.
Interrogation is therefore keyed by settings namespace, which a
configuration surface already holds from the configurable-provider
directory. `registerModelDiscovery` offers it per namespace,
`discoverModels` asks, and the request carries the draft itself. The
reply is candidates, not a catalog: every field but the id is optional
because most listings disclose nothing else, and adopting one is a
settings write like any other. Nothing here reads or writes settings or
credentials, so `settings.yaml` still decides what a route serves.
`llm.discoverModels` carries the same draft over the wire. Its apiKey is
the third and last payload a secret may ride, and it is never stored,
logged, or echoed; every refusal folds into `model-discovery-failed`,
naming the endpoint asked but never the credential offered.
The pi-ai side is a plain GET for OpenAI-compatible protocols only —
their listing shape is the one gateways, self-hosted servers, and the
official endpoints agree on. Others say so, sending the user to
hand-entry rather than reporting a guessed shape as an empty provider.
The reply is read under a four-megabyte ceiling held on the bytes
actually received, because the endpoint is a URL the user typed.
pi-ai resolves a request's apiKey override only through a provider that
declares an api-key method: resolveProviderAuth short-circuits to that
method when the override is present, and otherwise falls through to the
credential store and then to ambient discovery. A provider with no
api-key method at all therefore resolves to nothing, and the request
fails with "Provider is not configured" before any network I/O.
Two routes hit that. openai-codex ships OAuth alone, so moving off the
/compat dispatch broke a profile that names a key for it — the old path
handed the token straight to the provider. And a catalog route naming an
api was being rebuilt with the harness's own auth, so `openai: {api:
openai-completions}` stopped reading OPENAI_API_KEY, contradicting the
documented promise that omitting a credential keeps provider-native
discovery.
Auth is now one decision for both constructions. A catalog route keeps
its installed provider's auth, through an api override too: which
environment a provider reads belongs to the provider, not to the wire
format its models speak. A catalog provider with no api-key method gets
the harness method beside its own, but only when the profile names a
credential — a keyless codex profile keeps the honest refusal, since
this adapter holds no OAuth store to resolve through.
Materialization now spreads the installed entry instead of enumerating
the result, so a Model field this package does not model survives a
pi-ai upgrade; headers went missing from an nvidia route exactly that
way once already. providerInfo reports the configured displayName, which
also joins the registration facts so a rename re-registers rather than
leaving the old label in every selector. A refused registration swap
gets its own diagnostic naming the route, matching the directory swap
beside it.
The README documented endpoint interrogation this layer does not
implement, and still described unknown providers as kept-last-good after
they became legal declarations refused at the write point. The Agent
Note claimed per-model reasoning configurability the schema never had,
required capacities the route now defaults, and stated an apiKey
override that short-circuits unconditionally.
Three defects surfaced while driving the Models page.
A hand-declared model needed an explicit contextWindow and maxTokens,
but a provider listing usually returns ids and nothing else — so the
page happily wrote a profile the adapter then rejected, which took the
whole namespace down silently. Capacities now fall back to the route's
`defaultContextWindow` (262,144) and `defaultMaxTokens` (32,768). Both
are guesses by construction, which is why they are route fields a
deployment corrects once rather than constants buried in the adapter;
the fallback sizes the model and never becomes a per-request cap.
That silent failure was the second defect. A schema-valid profile the
adapter could not serve was stored and only rejected later, disabling
every route in the namespace with nothing said. `dsh-settings` gains an
optional `validate` on registration — a check for what a schema cannot
express — and `llm-pi-ai` refuses an unserviceable section at the write
that produced it. A stored section that fails keeps the namespace's last
good value, as a schema failure already did, so an externally edited
document still cannot strand the owner. The plugin's own last-good
fallback goes with it: nothing reaching it can fail any more.
Third, a model with no reasoning metadata advertised the single level
`off`, which pi-ai translates to *omitting* the reasoning option — the
same request naming no effort produces. Selecting it disabled nothing,
so a provider whose default is to think kept thinking with `off` shown
as selected. Such a model now reports no reasoning capability at all,
which is the seam's way of saying the control is unavailable, and the
per-model `reasoning` flag is gone: without a thinkingLevelMap to spell
levels it could only invent them.
The protocol table narrows to the three a hand-declared route reaches
today, most-reached first so a surface offering a choice defaults to the
one gateways actually speak.
- gen-cordis-catalog / gen-persistence-catalog / gen-doc-graphs after the
error-reason and steering/message changes (line anchors and event
producer/consumer graph drifted).
- verify-translation-pairing --write --all: every bilingual pair touched
by the PR (agent notes, session/core docs, READMEs) plus the merge.
- queue-actions preserved golden re-recorded against the rebuilt client
(branch disabled on non-completed-turn tails is back in effect).
- agent/error: drop the stale "(plus the logger)" claim; the machine only
emits the event.
- agent/inbox/claimed: document that a rejected turn boundary ends the
claimed message without discard or re-emission, and that a later batch
may reuse the turn number.
- steer(): document that a rejected step leaves steering parked until the
next wake.
- Fix stray double-space in the inbox inserted/discarded callbacks.
- Sync core.md/core.zh.md mirrors and regenerate the cordis catalog.
Implements the durable-subagent-catalog RFC: SubagentControlService.listChildren()
enumerates a parent's direct continuable children from one sessionQuery trace,
validates each child's sole subagent/descriptor event (now carrying the durable
creation label), and returns one ordered SubagentListEntry[] with per-child
corrupt/unsupported/unavailable diagnostics. The list_agents tool ships as a
separately loadable plugin of dsh-tool-subagent-control requiring sessionQuery
at load; send_message stays usable without it.
Remove the host-user continuation capability and the public residency query,
then separate the seam's public event payloads from its internal lifecycle
control interfaces.
`followup()` now takes the exact live direct parent `Agent` instead of a
`SubagentAuthority` union. No production adapter ever supplied user authority,
so the `UserAuthorityGrant` brand token existed only to stop a forged
discriminant from bypassing the direct-parent check — deleting the branch
retires the token, its mint method, and that attack surface together.
Narrowing `parent` from `Agent | undefined` to `Agent` removes three special
cases, including the path where a parentless epoch dispatched its lifecycle
events unscoped. Scoped-versus-global dispatch is now decided by the event, not
by whether a caller happened to have a parent.
`activationState()` had no caller; `ActivationState`, `ActivationObserver`, and
`ContinuationHost` are package-private.
New `src/lifecycle.ts` owns the contained emitter, the one-shot run observer,
and the Activation observer, while `SubagentRunInfo`/`SubagentRunEndInfo` move
to `src/types.ts` beside the other consumer-facing contracts. Those payloads are
public API — dsh-jsonrpc, hooks-claude, and the package invariant all consume
them — whereas the observer is a contract between two in-package collaborators,
so they no longer share a home merely for both being lifecycle-shaped. The
service keeps ownership of the scope carrier: `scopeTarget()` composes the
service's own context filter, so a narrowed stand-in would silently change
scope filtering.
Also drops now-unused dsh-tasks-local and dsh-tool-tasks dev dependencies, and
corrects the README claim that a pre-residency failure emits a terminal edge —
that path only ever rethrew.
- Make host-user authority unforgeable. `{ kind: 'user' }` was a bare
discriminant, so any plugin holding `ctx.subagents` — including
model-generated cordis_mount code, which the advanced ACP composition ships
alongside continuable subagents — could construct it and skip the
direct-parent check for any known child id. It now carries an opaque grant
that only SubagentService.userAuthority() mints, which composition hands to
trusted host adapters; a model-facing tool uses parent authority from its own
execution context.
- Reconcile a delivery discarded inside its own admission window. An enqueue
listener that cancels fires the discard before followup() returns, so the
discard listener could not clear an id it had not seen; submit() retained it
and residency stayed `running` until an explicit drain.
- Recheck the caller signal after materialization. An abort landing between
publication and inbox acceptance still submitted the prompt and returned both
ids; it now rolls the child back.
- Stop promising the model transcript access that no shipped continuable config
mounts. The tools now state only that a background child does not report back.
- Restate the implemented note as shipped state rather than a proposal, so it
works as current authority.
All five findings were real:
- The terminal lifecycle edge derived its stop reason from teardown success, so a
child that errored, hit its token ceiling, or was cancelled reported as
completed once its checkpoint and disposal succeeded. It now reads the child's
own last message turn/end, which is authoritative.
- Live delivery never rechecked the caller signal after authorization yielded, so
an abort that won before acceptance still enqueued the message and returned an
id. Admission now re-checks at the boundary that owns the decision.
- Drain flushed before cancelling, letting a running turn keep appending events
the checkpoint could not cover and letting model work continue through a slow
flush. It now cancels to quiescence first.
- subagent/end fired after AgentHandle.dispose() unregistered the child, so the
hooks bridge could not resolve it for the child's cwd and scope. The edge now
publishes while the child is still registered.
- activationState() read Agent.status alone, which stays idle between an accepted
waking send and the microtask that admits it, so a synchronous inbox observer
could see settled with a queued turn. Residency now also counts messages this
manager admitted but has not seen leave the inbox.
Adds the new continuable types to the cordis-catalog type-link map and
regenerates the cordis api/service/event catalogs, tool catalog, config
catalog, and doc graphs.
Implement the continuable background subagents RFC: a durable child
session with a series of Task-backed activations, each disposing its
run before the Task settles.
- dsh-subagent: rename SubagentRun.sendMessage to strict steer, drop
run-level resume, add SubagentProvider.resume dispatch via
SubagentService.resume, the continuation start field, and the
versioned model-hidden subagent/descriptor session event.
- dsh-subagent-inprocess/-spawn/-fork: publish the control-allocated
child id, append the descriptor inside the initial turn, implement
cold resume from the child's own transcript under the live parent
scope, and strict running-only steer.
- dsh-subagent-control (new): SubagentControlService owning stable
child ids, descriptor snapshot/fold/authorization, Task-backed
activation with settle-then-dispose ordering, the process-local
active-run association, and steer-or-resume sendMessage routing.
- dsh-tool-subagent: background route branches on the provider's
resume capability (continuable via the control service; one-shot
task for ACP), returning both child and task ids.
- dsh-tool-subagent-control (new): the globally named send_message
tool rendering steered/started routes.
Keyless coverage spans Task ownership and disposal ordering, running
delivery, cold follow-up, descriptor rejection and rollback, known-id
reconstruction, kill during lookup, admission races, and a new
subagent-continuable ACP snapshot scenario.
Resolve the agent-loop import conflict by retaining both durable request context and runtime policy context. Refresh the combined session fixtures and regenerate documentation catalogs. Mark PDF artifacts as binary so staged whitespace checks do not parse PDF bytes as text.
