Files
orca/src/shared/native-chat-session-option-defaults.ts
T
JinjingandOrca 094d6821ef feat(native-chat): add model and effort pickers for grok (#12780)
* feat(native-chat): add model and effort pickers for grok

Grok had no session-option catalog, so the native chat composer showed no
pills and every launch ran the CLI's own defaults with no way to change them.

Adds a `GROK_SESSION_OPTION_CATALOG` (model via `-m`/`/model`, reasoning
effort via `--reasoning-effort`/`/effort`) and the discovery plumbing behind
it. Grok's selectable ids depend on the signed-in account and on `[model.*]`
config, so the seed carries only `grok-4.5` and a runtime `grok models` probe
supplies the rest as authoritative — a retired id must be droppable, since
launching one is a fatal exit rather than a warning.

Because `grok models` publishes `Default model:` and marks the row
`(default)`, the picker can name the model a fresh session is actually
running: `defaultModelIsCliDefault` plus an untracked record means no `-m`
was ever emitted, so the CLI is on its own default. That default scopes the
effort row but is never written to persisted settings — that field is what
authorizes `-m` on every later launch, and adopting a model the user never
picked would pin today's default forever, fatally so on an account without
it. `grok --help` publishes no default for `--reasoning-effort`, so the
effort value stays unnamed until something sets it.

Known gap: that refusal to persist is also a limit. An option set while on
the CLI default is dispatched and honored in-session, but reaches no later
launch — it persists under the default's id with `model` left unset, and
both `resolveNativeChatSessionOptionDefaults` and
`resolveAgentSessionOptionLaunch` bail without that key. Picking a model
explicitly persists normally. Closing this means teaching both to resolve
options from the default model while still refusing to emit `-m`, which is
the launch-args path and wants its own review.

Known gap: the picker infers "no `-m` was emitted" from its own in-memory
record, so a model reaching argv from outside it — the user's own
`agentDefaultArgs`, or a renderer reload that drops the record while the
flagged PTY lives on — leaves the pill claiming the CLI default while
another model runs. No wrong model is persisted.

Extracts `hasFlag` and `labelFromModelId`, and splits the model-probe spec
out of the commit-message registry so discovery no longer implies an agent
can write commit messages.

Co-authored-by: Orca <help@stably.ai>

* docs(native-chat): note the invariant keeping modelIsCliDefault agent-safe

The flag is computed without checking the catalog, so it reads as unsafe for
the four agents with no CLI default. It is safe only because `persist` bails
unless `modelId` is truthy, which for those agents implies a tracked model.
Widening that guard would silently change persistence for every agent.

Co-authored-by: Orca <help@stably.ai>

* fix: retire persisted models on mount and handle -- terminator

- When a pane mounts after model discovery has already settled, it now checks
  the cache and retires persisted models that are no longer available.
- CLI flag detection now respects the `--` option terminator, treating
  everything after it as positional arguments rather than flags.

* Fix: persist grok session options under probe-confirmed defaults

Options set under the CLI default were silently lost on restart.
Distinguish seed guesses from probe-confirmed defaults by renaming
`modelIsCliDefault` to `modelIsUnverifiedDefault`. Once confirmed,
adopt the default as a persisted flag so options survive restarts.

* fix(native-chat): close the retired-model fatal-launch paths from counsel review

Counsel report C1/C2 (High), C3, P1, C4:
- Untrack a session model an authoritative discovery dropped and gate every
  persist path, so option writes can never re-adopt a retired id (C1).
- Resolve launch defaults through the enrichment cache: a persisted model
  missing from every settled probe no longer becomes a fatal `-m` (C2).
- Serialize retirement and picks on one settings write queue that re-reads
  live state at apply time (C3).
- Stabilize onSwitchToTerminal so the session-option surface is not rebuilt
  every TerminalPane render (P1), and cap the enrichment host map (C4).

Co-authored-by: Orca <help@stably.ai>

* Store agent in enrichment entry and extract token utilities

Refactor enrichment to store the agent field directly instead of
parsing it from a composite key, and extract CLI flag token filtering
into a shared utility. Use a dedicated function for tracked model ID
lookup. Improves code reuse and reduces parsing overhead.

* Rename modelIsUnverifiedDefault to adoptModelAsLaunchDefault

Move the model adoption gate into the core session-options module, where probe confirmation and discovered-model status are known. This ensures adoption decisions are gate-checked before persisting to avoid fatal launch flags, and simplifies the picker surface by moving the logic to where it belongs.

* Keep model probe evidence by agent, not host

Store probed model IDs in agent-keyed cache independent of host cache, so
evidence persists across host eviction. Prevents retired models from being
treated as valid when host cache entries are evicted.

* Store agent in enrichment entries instead of separate proof-evidence map

Model probe evidence is now tied to enrichment entries rather than maintained in a separate per-agent map, eliminating the need for eviction logic that could disconnect proof from entries.

---------

Co-authored-by: Orca <help@stably.ai>
2026-08-07 17:48:27 -07:00

79 lines
2.9 KiB
TypeScript

import type { AgentType } from './agent-status-types'
import { sessionOptionValueIsValid } from './agent-session-option-catalog'
import type {
PersistedNativeChatSessionOptions,
SessionOptionValue
} from './native-chat-session-options'
export function resolveNativeChatSessionOptionDefaults(
persisted: PersistedNativeChatSessionOptions | null | undefined,
agent: AgentType
): Record<string, SessionOptionValue> | undefined {
const entry = persisted?.[agent]
// Why: untouched settings must preserve the agent CLI's configured defaults;
// only a model explicitly selected by the user authorizes launch flags.
const modelId = typeof entry?.model === 'string' && entry.model.trim() ? entry.model : undefined
if (!modelId) {
return undefined
}
const values: Record<string, SessionOptionValue> = { model: modelId }
const storedValues = entry?.valuesByModel?.[modelId]
if (storedValues && typeof storedValues === 'object') {
for (const [id, value] of Object.entries(storedValues)) {
if (sessionOptionValueIsValid(value)) {
values[id] = value
}
}
}
return values
}
/** Why: an authoritative probe proved this id gone, and a stale `model` is emitted
* verbatim as a launch flag — grok exits fatally on an unknown one. Dropping only
* `model` keeps the per-model option values for a later reselect. */
export function clearNativeChatSessionOptionModel(
persisted: PersistedNativeChatSessionOptions | null | undefined,
agent: AgentType
): PersistedNativeChatSessionOptions {
const currentAgent = persisted?.[agent]
if (!currentAgent?.model) {
return { ...persisted }
}
const { model: _dropped, ...rest } = currentAgent
return { ...persisted, [agent]: rest }
}
export function updateNativeChatSessionOptionDefaults(args: {
persisted: PersistedNativeChatSessionOptions | null | undefined
agent: AgentType
modelId: string
optionId: string
value: SessionOptionValue
/** Defaults to adopting, since without a `model` no launch resolves the value at all.
* Only the picker surface, which can tell a probe-confirmed id from the seed's guess
* at the CLI default, withholds it: adopting a guess would emit `-m <guess>` on every
* later launch, fatal on an account without that model. */
adoptModelAsLaunchDefault?: boolean
}): PersistedNativeChatSessionOptions {
const currentAgent = args.persisted?.[args.agent]
const currentModelValues = currentAgent?.valuesByModel?.[args.modelId] ?? {}
const valuesByModel = {
...currentAgent?.valuesByModel,
...(args.optionId === 'model'
? {}
: {
[args.modelId]: { ...currentModelValues, [args.optionId]: args.value }
})
}
return {
...args.persisted,
[args.agent]: {
...currentAgent,
...(args.adoptModelAsLaunchDefault === false
? {}
: { model: args.optionId === 'model' ? String(args.value) : args.modelId }),
valuesByModel
}
}
}