A picker showed directory names, so the settings page could only ever list
`standard` / `core-web` / `cordis` and hope the reader knew what they meant.
A preset may now publish display text in an optional `preset.yml` beside
its composition, and the section renders cards — name, description, and the
one in use — instead of rows.
The file carries display text ONLY. `id` is the directory name and `trust`
comes from the root a preset was discovered under, so neither is writable
there: otherwise a locally authored preset could name itself into the
shipped set. It is a separate file because a composition is a top-level list
of plugin rows — YAML cannot carry sibling keys beside it, and a fake
metadata row would hand the Loader something to load.
Every read failure degrades to no metadata; absent, malformed, wrongly
typed, and blank all mean the same thing and the picker falls back to the
id. Presentation is not capability: a preset whose name is broken still
mounts.
The editor gained name and description fields above the YAML, and clearing
both removes the file rather than storing a blank name.
A preset is a directory holding one `agent.cordis.yml`. Mounting it under an
agent's scope context during `setup(agentCtx)` gives that one session its own
tools and prompt sections while every other live session keeps its own.
No registry gains a tier. `dsh-tools` and `dsh-system-prompt` already file
registrations into the calling context's scope layer, and entry contexts chain
to the context a subtree was plugged into, so a composition mounted under
`agent.ctx` is that agent's alone and unwinds with it.
The mount audits itself because a directly-plugged subtree is absent from
`ctx.loader.entries()` and no boot audit covers it. It rejects an unscoped
target, a row that never became usable, and a row that published a service into
the root service realm — that last one is process-global rather than
per-session, and its collision with the next session surfaces as an unhandled
rejection `setup` never observes, leaving a half-composed agent that looks
healthy. The package invariant re-checks that rule on every service
notification, since a row publishing from a timer would escape a one-shot audit.
Raises the `packages/README.md` word ceiling from 920 to 980: the group table
must enumerate every group, and the new `preset/` row is necessary content.
Design: .agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md
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.
Review found four defects in the declared-provider work.
`PiAiAdapter` reused one `Models` collection and mutated it whenever the
configuration changed. `Models.streamSimple()` resolves its provider
lazily — when the stream is first consumed, which is after the adapter
awaits the route's credential — so a configuration change landing in
that window let an in-flight request finish under a configuration it
never resolved against, or fail on a provider that no longer existed.
Each resolution now produces an immutable snapshot and every operation
captures one before its first await, which is what makes the seam's
per-step freeze (`llm.prepareCall()`) hold end to end: switching models
mid-reply takes effect on the next step, never inside the one in flight.
`defaultMaxTokens` was materialized from the catalog's `Model.maxTokens`.
The two answer different questions: pi-ai requires that field as the
model's output capability, while the seam's is a cap the deployment
chose to send on requests naming none, so every request had started
carrying a number nobody picked. Only an explicitly configured cap
reaches the seam now.
The configurable-provider directory was refreshed by disposing its
registration and making a new one. A candidate set the registry refuses
— a profile keyed `deepseek-official`, which llm-deepseek declares —
left the whole directory withdrawn and the Models page empty, silently,
because the settings callback contains the failure. The seam's
registration handle now carries `replace()` with the same
validate-first atomicity `registerAdapter` has.
The protocol table offered every pi-ai streaming API, including four
whose authentication a profile cannot express: Bedrock signs with SigV4
over AWS credentials and a region, Vertex needs a project, a location,
and ADC, Azure needs provider environment plus an api-version, and Codex
uses OAuth. Offering them handed back routes that cannot authenticate.
Catalog routes still reach them through their own provider.
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.
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.
The remaining P1 from the #939 review, plus the P2 it shares a mechanism with.
Nothing carried a version, so two tabs editing one namespace silently
overwrote each other — reproduced as tab B's `reasoning` lost to tab A's
older draft. The seam's per-namespace write queue orders writes; it cannot
tell a fresh writer from one replaying a snapshot a predecessor superseded.
Each namespace now carries a monotonic `revision` over its RAW section. A
write may send `expectedRevision`, checked at the FRONT of the queue (not at
call time, which would race the very predecessor it guards against); a
mismatch rejects with `SettingsConflictError` → `settings-conflict` on the
wire, carrying both revisions. The editor captures the revision it opened at
and, on conflict, asks the user to reopen rather than replaying its snapshot.
The same counter fixes the missing broadcast. `settings/updated` is gated on
the resolved value — correct for consumers, wrong for configuration surfaces:
storing an override equal to the composition base leaves the resolved value
alone while changing what the document says (the field is now overridden, not
inherited) and moving every open editor's revision. `settings/document-updated
(ns, revision)` fires on any raw-section change, in-process or external, and
`host/settings-changed` now rides it.
That event also closes the stale model picker: editing a provider's `models`
changes no route, so `llm/adapters-updated` never fired and an open picker
kept serving the old catalog. A change to an exposed provider namespace now
emits `host/models-changed` too — that namespace holds the catalog.
Docs: both sides of the five touched README pairs, a type-equiv block for
`SettingsPathOp`, and an Agent Note recording what the plane exposes and who
may overwrite what. The deferred wire-redaction gaps (secrets behind
union/intersection/transform, `.default(...)` in the served envelope, schema
text in rejection messages, `new Function` rehydration, pi-ai's `headers`) are
recorded as TODO(settings-wire-redaction) and in Known Limitations rather than
half-fixed.
Both provider READMEs state what actually holds: credentials-local now
documents the physical-line editor, the read-modify-write under the
writer lock, and a Security boundary section saying plainly that the file
mode stops other OS users and not the model. sandbox-policy documents
readDenyPaths and its per-backend enforcement. The llm READMEs carry the
registration handle, pi-ai's credential-miss semantics, and DeepSeek's
same-generation snapshot; app-boot and the CLI README stop describing
$DSH_HOME/.env as an environment layer.
A new Agent Note records the round (and the prior seam note cross-links
it); the sandbox and core catalog pages gain readDenyPaths and
AdapterRegistrationHandle with their manifest entries. The headless
missing-credential snapshot re-records for the reworded guidance, pi-ai
gains the Loader-composition guard its twin already had, and the
deliberate provider symmetry is marked for the clone detector.
New credentials data-structure page (type-equiv manifested), group README,
rewritten llm-deepseek/llm-pi-ai READMEs (dynamic configuration, dict
profiles, credential chain), capability-seams/service-role registration,
Agent Note (bilingual), demo compositions mounting settings-local +
credentials-local with no inline key plumbing, installSettingsSection
consumer helper on the settings seam (deduplicating both adapters' wiring),
jscpd symmetry markers for the provider twins, runtime-closure additions for
python/sdk-runtime, and doc-budget ceilings AGENTS.md 1750→1755 /
packages/README.md 850→865 for the structural one-line group rows.
Conflicts were the parallel-edit set: packages/README group table (kept
master's session-title wording, re-added the settings row condensed),
doc-budgets AGENTS.md ceiling (took master's 1750), and regenerated
graph/catalog docs plus re-recorded translation pairs. packages/README.md
ceiling 845 -> 850: the table legitimately gained one row for the new
settings group and the row is already minimal.
