The creation header names the preset a session STARTED with and is frozen,
which is correct — it is a creation fact. Switching is legal only while a
session is blank, and that looked like enough: no history exists yet.
It is not, because the switch's effect outlives the blank window. The user
switches, then sends the first message; every turn from there runs under the
new composition while the header still names the old one. The session is
then locked around a misrecorded preset, and resume reads the header to
rebuild it — composing one preset's tools over a history another produced,
which is exactly the replay the blank-only lock exists to prevent, reached
by another route. A picker showed `standard` for a session running
`core-web`.
A switch is now an `agent-preset/selected` event appended after the swap
commits, and `resolveSessionPreset()` (last selection, else the header) is
what every reconstruction reads: the summary, resume, the conflict guard,
and the fork introduced one layer down.
A seat in the composer tool row, left of the model select, showing the preset
THIS session runs — its own recorded one, not the deployment default, because a
resumed session runs what it was created with. `SessionSummary` carries
`agentPreset` for that, alongside `cwd` and `origin`.
The switch exists only while the conversation has not started. After the first
turn the seat becomes a plain label rather than a disabled menu: a greyed
control reads as "temporarily unavailable", when in fact the choice is gone for
good. The seat never asks in that state, and the host refuses independently
with `agent-preset-locked`, so a stale client cannot slip one past it.
A rejected switch restores the previous value and surfaces the host's message
rather than leaving the seat showing something the session is not running.
`agentPreset.select` recomposes one session's agent from a different preset.
It is allowed only while the session is blank — once a turn has run, that
history was produced under the preset's tools and swapping them would strand
logged tool calls, so the attempt answers `agent-preset-locked`.
The agent and the session survive; only the preset subtree is swapped. That
was forced by what the host actually owns: api-proxy discards the `AgentHandle`
it creates, and there is no delete RPC, so neither disposing nor recreating the
session was available. Swapping the subtree is also the better answer — the
session id, its workspace attachment, and its projections all stay put.
`recompose` is unmount-then-mount because two compositions cannot coexist: both
would register the same tool names into one layer. So it resolves the new
preset BEFORE tearing anything down (an unknown id is a no-op) and restores
the previous composition when the new one fails to mount, rather than leaving
the agent with no tools at all. Both paths are pinned by test.
Also restores the English half of the `agentPreset.list` README paragraph,
which was lost before the previous commit — and `verify-translation-pairing
--write` recorded the pair as consistent anyway, because it records whatever
state it finds rather than checking the two sides say the same thing.
`agentPreset.list` gives a browser the deployment's roster so it can offer a
choice when starting a session. Each row carries the id, its `trust`, and
whether it is the current default.
`trust` is on the wire deliberately: a `user` preset is exactly as privileged
as the plugins it names, so a surface that offers one alongside a shipped
preset can say which is which rather than presenting both as vetted.
The domain is read-only. A preset is a composition on disk, so authoring one
is a filesystem act rather than an RPC; and a deployment composing no presets
answers with an empty roster rather than an error, because sharing the host
composition is a valid deployment.
The RPC map made every registration site a type error, so the route, the
response-schema table, the service delegate, and the browser fixture are all
wired rather than only the ones I remembered.
`config.default` becomes the composition base of an `agent-presets` settings
namespace, so the user document layers over the deployment's engineering
default and a person can change which preset new sessions get without a
restart.
The value is read per resolution rather than snapshotted: a hot-reloaded
document takes effect on the next session created, and every running session
stays on the preset it was composed from — which is the same rule the
session-header guard enforces from the other side.
`resolve()` read `config.default` directly, which would have made the whole
setting inert; it now goes through `defaultId` like every other caller.
The write-protection test is rewritten against a temp profile root. It was
passing vacuously: the un-overridden Loader REWRITES the composition it read —
stamping `disabled: true` onto the self-disposing row — so the committed
fixture had been mutated by the very run that proved the bug, and every later
run compared against the damaged file and passed. Building the preset in a
temp directory makes the assertion immune to its own failure mode, and it now
fails with a visible `+ disabled: true` when the override is removed.
Review follow-ups on this layer. The exported schema is
`AgentPresetSettingsSchema`, symmetric with the `AgentPresetSettings`
interface it resolves and self-describing at an import site. The `session.create`
JSDoc promised "the deployment's default preset" for an omitted `agentPreset`,
which this layer makes false — it now names the effective default. The
constructor records why it does not use `installSettingsSection`: that helper
re-judges what a consumer DERIVED across attach and detach, and nothing here is
derived. The provider-unload test disposes the fiber `ctx.plugin()` handed back
instead of reaching into `ctx.reflect.store`, and the write-protection wait says
why slack is the right shape for an absence assertion.
The real composition covers the layering too. `apps/cli` boots the shipped
`cordis.yml`, stores `agent-presets.default`, and asserts an unnamed session
composes from it — the package suite proves the layering against a hand-built
context, this proves the roster and the settings provider are wired to each
other. That test also pins the settings row at a temp file: it defaulted to
`$DSH_HOME/settings.yaml`, so a developer's own stored default decided the
outcome of a file whose whole point is that only the shipped root does.
The Agent Note records the per-resolution read and its correspondence with the
session header, and the vacuous-test finding above.
None of these change behavior; each said something that was not true.
`SessionCwdConflict`'s doc block had been left stranded above the
`AgentPresetConflict` inserted under it, so one class carried a comment
about the other and the second carried none.
The roster comment named a `.system` directory that does not exist; the
shipped root is `config/agent-presets/`, and `system` is the trust its
entries carry.
The real-composition test attributed the disabled `api-gateway` row to
"side effects outside this process" alongside the port and the exporter.
It is disabled for a different reason — the api-proxy cannot mount in
this layer at all — and hiding that behind the same phrase would leave a
later layer unable to tell whether the line can come out.
One test claimed to refuse an adoption while asserting only that the
header records the preset; it now says what it checks.
`PERSONA_SECTION`/`PERSONA_ORDER` existed twice, once in the registry
that declares the slot and once restated in the row that replaces it —
a drift that would land a preset's persona beside the deployment's
instead of shadowing it. The registry exports them now.
The preset conflict message read "already runs agent preset undefined"
for a session that records none, which is the shape a deployment with no
roster produces; it names that case instead, with the regression that
reaches it through the gateway.
Finally, `PresetTree.write()` drops the `loader/config-update` the
inherited method emits — recorded on the override, since a future
edit-while-running flow needs its own persistence path.
A preset publishes its services behind `isolate` realms, which is what
makes them per session — and what makes them invisible to every host
context. The api-proxy kept reading the root realm, so requests that are
ABOUT a session but arrive from outside it answered for a singleton that
no longer exists: `goal.pause`/`clear` and `skill.list` returned "this
deployment does not mount @deepseek-ai/dsh-goal / dsh-skill" for sessions
whose composition mounts exactly that. Verified against a running host
before and after.
`agentPresets.serviceFor(agent, name)` addresses the instance instead,
reading the same subtree-ownership relation `leakedServices` already
uses, inverted. It is read addressing for a caller holding the agent: a
host row that `inject`s a service cannot use it, because injection
resolves before any session exists — which is why `tools` and
`subagents` stay host-plane and this is not a way around that.
Tool presenters had the same shape and the same cure: `viewFor` looked
definitions up without a scope while the global layer is empty by
design, so every card degraded to the generic renderer. It now takes the
owning agent.
Cold resume through `agentFor()` mounted no preset at all, so every
generic entry point — prompt, models, commands — rebuilt a restarted
session on host tools and the deployment persona. It composes the
recorded preset now, as the other resume path already did.
Two consequences of moving the agent plane behind presets, both invisible
until the host plane stopped carrying model-facing rows.
`sessions.fork` built its child with a bare `installTarget` and a `meta`
without `agentPreset`. That was harmless while every tool sat in the host
plane — the child inherited them for free. It now comes up with an EMPTY
tool set. The child composes the parent's preset instead, for the same
reason a resumed session keeps its own: the seeded history was produced
under those tools.
`bashEnv` lives in its own `dsh-bash-env` row rather than inside
`tool-bash`, so a preset that isolates the realm must compose the provider
beside its consumer; the host row is disabled here like every other
model-facing one. Nothing outside the agent plane injects `bashEnv`, so it
stays per-session.
The Web overlay disables base's 32 agent-plane rows and mounts the preset
roster instead, so each session composes its own tools and prompt rather than
sharing one process-wide set. The TUI keeps base unchanged: it is single-session
and composing its agent process-wide is correct there.
`roots` is patched in by AppCLIEntry, like `distIndex`: the shipped presets sit
beside the composition that names them and the user's live under the Harness
home, neither of which a config author chooses.
A session's preset is fixed at creation. Naming a different one for an existing
identity is `agent-preset-conflict` rather than a switch, because that
session's history was produced under the first preset's tools. The guard sits
after `await creation`, beside the cwd check, so it covers every path that
yields a live agent — freshly created, adopted live, resumed, or recovered by
the concurrent-creation catch. A request naming no preset adopts the session as
it is, keeping reconnect and retry ordinary.
Two bugs the real-composition test caught, both invisible to unit tests:
`PresetTree` now refuses to write. The Loader persists a tree whose plugin
self-disposed, and tearing an agent down disposes its whole subtree — inherited,
that rewrote the shipped composition, truncating a 241-line preset to `[]` the
first time a session ended.
`dsh-tool-skill` compared against a lookup of its own name in the global layer,
so it threw inside any preset: `register()` files into the calling context's
scope. It now compares against the definition it registered, which is what the
identity check meant all along.
The `standard` catalog is asserted exactly, not spot-checked: a row that
registers into the wrong layer mounts cleanly and simply contributes nothing, so
an omission is this design's quietest failure. It matches the shipped TUI
catalog plus `glob`/`grep`, the pair that composition documents as
ripgrep-dependent.
Re-records `cordis-inspect-jsdoc`, whose rendered `SessionHeader` gains the
`agentPreset` field. `fs-glob-sampling` fails identically on pristine master
and is untouched here.
The browser e2e scaffold gains the roster fact AppCLIEntry supplies. `roots` is
resolved and patched in by the CLI entry, like `distIndex` on the webserver row,
and this lane boots the shipped tree without that entry — so it has to supply
the same fact or the roster resolves nothing and every session in the lane
composes an agent with no tools, no persona, and no token meter. Only the
shipped root: a developer's own `~/.dsh/.agent-presets` must not decide a golden. The
`cordis:group` builtin comes with it, exactly as `boot()` registers it, because
a preset resolving package names from its own directory cannot reach
`@cordisjs/plugin-group` by name.
The lane stays red through this layer and the next four for the reason stated
above — the api-proxy injects `subagents`, `workspace`, and `tools`, so
`api-gateway` cannot activate and the browser has no `/api` at all. It goes
green again in the layer that returns those registries to the host plane; this
change is what makes that layer's fix sufficient rather than partial.
`session.create` takes an optional `agentPreset`, and the host resolves it,
mounts it during pre-publication setup, and records the resolved id on the
session header so a later resume rebuilds the same agent.
Resolution happens BEFORE the session exists, not inside setup: the session
boundary snapshots `meta` before asynchronous setup begins, so an id discovered
during setup could never reach the header. Mounting still happens in setup,
where a failure rolls the whole creation back rather than publishing a session
whose capabilities are half-installed.
Resume ignores whatever the request names and rebuilds from the stored id. A
resumed session's history was produced under that composition; restoring a
different one would replay tool calls the model can no longer make.
`dsh-agent-presets` now throws `UnknownPresetError` / `PresetMountError` so
the host can tell a bad request from a broken preset — they become
`agent-preset-not-found` and `agent-preset-invalid`.
Ships the two built-in compositions (`standard`, `core-web`) and the persona
row that lets them differ in identity. Nothing mounts them yet: no roster is
configured, so `composeAgent` finds no service and every session keeps the host
composition. Wiring the roster and moving base's agent-plane rows behind it is
the next commit, so the switch happens atomically with a real-composition test.
The Models page could name a provider's key and little else. Adding an
OpenAI-compatible gateway meant opening $DSH_HOME/settings.yaml and
knowing the profile shape; correcting a stale context window meant the
same. This layer puts both on the page: a card that declares a route
pi-ai does not ship — id, endpoint, protocol, key, models — and a model
list on the pi-ai editor that can ask the provider what it serves and
adopt the answer.
It follows the DeepSeek catalog editor that landed in #1050 rather than
inventing a second look for the same job. Both editors now share the
section shell and heading, the danger-tinted delete, the add-model
button, the empty state, the per-row validator that names a bad row by
its position, and one K/M capacity vocabulary — 256K and 1M are read and
spelled back, while settings.yaml still stores plain token counts. The
row type is structurally open like that editor's, so a profile field
this card does not edit survives an edit here.
Three of that editor's decisions replaced weaker ones this branch had
made. Inheritance now reads the composition base rather than the
effective value, which would echo an override back the moment a reset
dropped it. Validation names the offending row instead of stating a
blanket problem. And emptying the list is no longer conflated with
handing the catalog back to the adapter — those are separate acts, with
separate affordances.
The create write carries the revision the card opened at, so a route
another tab declared meanwhile is a conflict rather than a silent
overwrite of its profile.
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).
Update every doc referencing base.cordis.yml/web.cordis.yml, --config, -p, or
$DSH_HOME/config.yaml to the profile vocabulary with bilingual counterparts
re-recorded; regenerate the catalogs and graphs; add the
profile-plugin-bundles Agent Note recording the design and its rejected
alternatives.
dsh --profile <name> replaces the fixed entry modes: --config and -p are
removed, --patch adds overlays over the composed profile, a positional task
selects one-shot mode (requires the headless-runner row), and dsh web stays as
the alias for --profile web carrying the Web flag family as patches. dsh
plugin --profile <name> forwards verbatim to pnpm in the profile directory,
initializes on first use, and reconciles the dsh.plugins layer list after
add/remove (patch-less packages warn and stay plain dependencies). Config
dumps and the keyless web e2e scaffold compose the same bundle layers over the
same empty root as the boot.
The webserver's built-in static dist serving becomes a single-owner fallback
seat (registerFallback/applyIndexTaps); the SPA server moves to the new
@deepseek-ai/dsh-frontend-static plugin so the composing application owns its
dist as composition, not carrier config. distIndex leaves the webserver
schema; unclaimed fallback answers 404.
Move the claimed-message notification loop out of the loop's pre-step
into Inbox.claim(target, turn), so the step-boundary operation publishes
its own claimed notifications like insertions and discards do.
Master polished two Chinese sentences this branch also edits — an
expectation is now 陈旧 rather than 过期, and the package-root sentence
spells out 包（package）. Taking master's wording alongside this branch's
own additions leaves the recorded pair fingerprints stale, so they are
re-recorded against the merged text.
llm.discoverModels was reachable from any declared trusted host. The
method takes a caller-supplied baseURL and makes the host issue a GET to
it, then reports the status or the parsed body — so on a LAN deployment
an anonymous caller had a probe for whatever the host can reach and the
browser cannot, plus a path that carries a draft credential. The
PRIVILEGED_METHODS doc already states the rule this broke: trustedHosts
is a DNS-rebinding fence, not authentication, so the configuration plane
stays loopback-same-origin. It is in that set now, asserted both against
the hand-built fence and over real HTTP beside the catalog reads that
deliberately stay reachable.
supportsDiscovery and listModelDiscoveryNamespaces are gone. The field
was required on the wire and read by nobody: its own contract said a
surface should offer the action "instead of naming an adapter family it
would have to hardcode", while the surface hardcodes llm-pi-ai in two
places and gates the button on whether there is anything to probe. Its
shape did not fit the second caller either — the create card has no row
to read a per-row field from. Keeping a required field alive for a
consumer that may never arrive costs every producer and fixture a value
nobody consults, which is exactly how the fixtures drifted. The registry
that fed it had no other production consumer, so registration and
disposal are now observed through the offer itself.
The Agent Note claimed the key is never logged, which the wire schema
beside it already contradicts, and predated both the provider field and
the catalog-answer path. The two new public types pointed at core.md
without a type-equiv block or manifest entry, so the generated service
catalog named documentation that did not exist.
Clicking "fetch available models" on a built-in provider went to the
network. That is the wrong source: pi-ai's registry is the authoritative
list for its own providers, and it carries the context windows and output
caps a `GET /models` listing does not disclose. Asking api.deepseek.com
what DeepSeek serves is both slower and worse, and against an endpoint
that answers a different shape it failed outright.
Interrogation is still keyed by settings namespace — the provider being
added has no route — but the request may now name the route it is
editing. An adapter that already describes that route answers from what
it knows, needs no endpoint at all, and never touches the network; only a
route the catalog does not describe reaches the wire, and one naming no
endpoint is told to set one or enter its models by hand.
`ConfigurableProviderView` gained `supportsDiscovery` so a surface offers
the action where a namespace can answer instead of hardcoding an adapter
family.
Three narrower corrections ride along. Discovery no longer claims Azure
or Codex: Azure authenticates with an `api-key` header and an
`api-version` query despite its OpenAI lineage, and Codex uses OAuth, so
both reported an authentication failure as a provider with no models.
Cancellation during the body read escaped as the raw abort reason rather
than a coded ABORTED. And the schema comment claiming the probe key is
never logged overstated it: the host neither stores nor returns it, but
it rides the client's outgoing envelope like every other secret-bearing
payload, and redacting that tap is a configuration-plane-wide change.
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.
The mocked process.send consumed vitest's own fork-pool IPC messages and immediately ran the post callback, whose disconnect() severed the test worker's channel (process.connected is true under forks) — the whole spec's results vanished and win32-dialog-bindings.ts/win32-dialog-worker.ts fell to near-zero coverage on CI. The mock now records without invoking the callback or disconnecting; the real close lifecycle stays with built-worker.e2e.ts. Verified under both the threads and forks pools.
The win32 tier is exactly the koffi IFileOpenDialog child process; any failure surfaces as-is. The pwsh -> Windows PowerShell 5.1 cascade, the shared WinForms script, and the triple-miss AggregateError are deleted: koffi is a packaged dependency whose availability the install guarantees, so no mechanism fallback exists (the browse backend remains the fallback at the composition level). The pwsh-first DPI picker-fix note is consolidated into a new simplification note recording the reversal.
The koffi IFileOpenDialog conversation runs in a spawned child process instead of a worker thread: the dialog is the child's first window, so Windows activates it without a foreground call, and a native fault stays contained to the child. The driver maps the child's message protocol onto a promise and services aborts by posting WM_CLOSE to the dialog thread's windows, killing the child when the close budget is exhausted. The built worker ships as lib/worker.cjs (the ./worker export) under plain node, and win32-dialog.spec.ts returns to the thread-safe pool.
The koffi redesign moved the dialog from a spawned child process (which
inherits a foreground-activation right from the spawning app) onto a worker
thread of the same process, so Windows shows the dialog without activating
it — it opens behind the app with a taskbar flash. The app has no native
HWND to hand the seam, so raise from the driver: on the 'showing' notice
(the worker posts it right before Show, before the dialog window exists),
attach this thread's input queue to the dialog thread's, call
SetForegroundWindow on its top-level window, and detach — retried on the
close cadence until the window appears, stopped on settle/abort/success,
never blocking the pick. Injectable seam mirrors closeThreadWindows; driver
tests pin the raise and its retry; the in-process note records the
mechanism (both languages, pairing re-recorded).
The driver's switch over Win32DialogWorkerMessage handled all three current
kinds but had no default, so a fourth kind added to the worker protocol
would compile cleanly and silently no-op — settle() never called and the
pick dangles until worker exit. Add the local assertNever backstop (the
command-compact shape; this package does not depend on dsh-llm for the
helper) and the return the error case needs to avoid falling into it.
Round-five review finding.
