feat(custom-model): launch directly on the endpoint, no restart, for 7 of 8 CLIs

Fixes the visible double-launch reported on Codex: picking a custom-model
Run-menu entry launched natively first, waited for it to settle, then
restarted it in place with the endpoint applied. Necessary for the design at
the time, but visibly a native boot immediately followed by a second one -
worst on a CLI whose TUI fully reinitializes on a restart, confirmed live on
Codex.

POST /api/quick-start gains an optional customModel field
({endpointId, modelId, confirmed?}). When present, the route mints the
session's id itself (crypto.randomUUID()) before constructing it, computes
the same injection the existing POST /api/sessions/:id/custom-model route
computes (including the llama-swap conflict check from the last commit -
same {requiresConfirmation, currentlyLoadedModel, affectedSessions} shape,
no session created until confirmed), and launches the session already
pointed at the endpoint: env vars via the constructor, and the launchModel
override merged onto piConfig/grokConfig/ompConfig using the registry's own
launch.legacyConfigField the same way session.ts's restart path already
does. No restart at all - setCustomModel() afterward is bookkeeping only.

Wired into 7 of 8 launch functions (session-ui.js): openCode, codex, gemini,
pi, grok, deepseek, omp. Claude stays on the original launch-then-restart
path for now: its own --resume-based restart is far less jarring than the
other seven's, and runClaude()'s multi-tab launch plus docker-config-drift
confirm/retry loop make folding it into the one-shot path separate,
higher-risk work than the other seven's each-a-single-simple-launch shape.

Also fixes a pre-existing 'mode === omp' branch flagged by the CLI-id
static guard (test/cli-registry-no-id-branching.test.ts) - the ompConfig
launchModel merge is the same 'legacy <Mode>Config plumbing' category as
the six sibling branches already allowlisted there, just newly literal
where it was previously only inside resolveOmpConfigForCreate's own check.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
This commit is contained in:
Devvyn
2026-09-16 15:04:10 +08:00
co-authored by Claude Sonnet 5
parent fbee1b2d82
commit f865f74a0f
9 changed files with 879 additions and 120 deletions
+152 -91
View File
@@ -694,7 +694,96 @@ Object.assign(CodemanApp.prototype, {
* default, which a one-off endpoint run must not do — and is restored in
* `finally` even if run() throws.
*/
/**
* Dispatches to the ONE-SHOT launch path (below) for every custom-model-eligible CLI
* except claude, which still goes through the restart-after-native-boot path
* (`_runCustomModelEntryViaRestart`): claude's own `runClaude()` carries multi-tab
* launch and a docker-config-drift confirm/retry loop neither of the other seven
* functions has, and folding those into the one-shot flow is unstarted, separate work.
* The other seven (opencode/codex/gemini/pi/grok/deepseek/omp) are each a single,
* simple launch, so they get the one-shot path — the one visibly worth it, since a
* native-boot-then-restart is far more jarring on a CLI whose TUI fully reinitializes
* (Codex, confirmed live) than on claude's own `--resume`-based restart.
*/
async runCustomModelEntry(mode, endpointId, modelId) {
if (mode === 'claude') {
return this._runCustomModelEntryViaRestart(mode, endpointId, modelId);
}
return this._runCustomModelEntryOneShot(mode, endpointId, modelId);
},
/**
* Launches directly on the endpoint — no restart, so no visible relaunch. Stashes the
* pick on `_pendingCustomModelForLaunch` for the targeted run<Mode>() function to read
* and fold into its own /api/quick-start body (see `_quickStartWithCustomModelConfirm`);
* cleared in `finally` the same way `_runMode`'s temporary swap is, even if run() throws.
*/
async _runCustomModelEntryOneShot(mode, endpointId, modelId) {
document.getElementById('runModeMenu')?.classList.remove('active');
const previousRunMode = this._runMode;
const tabCountEl = document.getElementById('tabCount');
const prevTabCount = tabCountEl?.value;
this._runMode = mode;
this._pendingCustomModelForLaunch = { endpointId, modelId };
if (tabCountEl) tabCountEl.value = '1';
try {
await this.run();
} finally {
this._runMode = previousRunMode;
this._pendingCustomModelForLaunch = undefined;
if (tabCountEl && prevTabCount !== undefined) tabCountEl.value = prevTabCount;
}
// run() (via _quickStartWithCustomModelConfirm) reports its own launch error or
// cancellation via toast and leaves this unset — nothing more to do here then.
const result = this._lastCustomModelLaunchResult;
this._lastCustomModelLaunchResult = undefined;
if (result?.modelSwapInProgress) {
void this._watchLlamaSwapLoading(endpointId, modelId);
}
},
/**
* POSTs a /api/quick-start body already carrying `customModel` (see the run<Mode>()
* call sites below), showing the same llama-swap "this will unload it for session X"
* warning the restart path's `_applyCustomModelToSession` shows when the route asks
* for confirmation, and retrying with `confirmed: true` on accept. Stashes the final
* response's payload on `_lastCustomModelLaunchResult` for
* `_runCustomModelEntryOneShot` to read `modelSwapInProgress` off afterward — run()'s
* eleven per-mode dispatch targets have no shared return-value contract of their own,
* so a side channel here is simpler than threading one through every one of them.
*/
async _quickStartWithCustomModelConfirm(bodyObj) {
const post = async (body) => {
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(body),
});
return res.json();
};
let data = await post(bodyObj);
if (data?.data?.requiresConfirmation) {
const { currentlyLoadedModel, affectedSessions } = data.data;
const names = affectedSessions.map((s) => s.name || s.id).join(', ');
const proceed = confirm(
`${names} ${affectedSessions.length === 1 ? 'is' : 'are'} currently using ` +
`${currentlyLoadedModel} on this endpoint. Switching will unload it for ` +
`${affectedSessions.length === 1 ? 'that session' : 'those sessions'} too. Continue?`
);
if (!proceed) {
this._lastCustomModelLaunchResult = undefined;
return { success: false, error: 'Model switch cancelled' };
}
data = await post({ ...bodyObj, customModel: { ...bodyObj.customModel, confirmed: true } });
}
this._lastCustomModelLaunchResult = data?.success !== false ? data?.data : undefined;
return data;
},
/** The restart-after-native-boot path — see `runCustomModelEntry`'s own comment for
* which CLIs still use this one. */
async _runCustomModelEntryViaRestart(mode, endpointId, modelId) {
document.getElementById('runModeMenu')?.classList.remove('active');
const previousRunMode = this._runMode;
@@ -1583,20 +1672,16 @@ Object.assign(CodemanApp.prototype, {
// Quick-start with opencode mode (auto-allow tools by default).
// No `effort` field — it's Claude-specific (OpenCode has no /effort).
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), this.loadAppSettingsFromStorage());
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'opencode',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
openCodeConfig: { autoAllowTools: true },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
}),
})
const data = await this._quickStartWithCustomModelConfirm({
caseName,
mode: 'opencode',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
openCodeConfig: { autoAllowTools: true },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
...(this._pendingCustomModelForLaunch ? { customModel: this._pendingCustomModelForLaunch } : {}),
}),
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start OpenCode');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
@@ -1637,24 +1722,20 @@ Object.assign(CodemanApp.prototype, {
const globalSettings = this.loadAppSettingsFromStorage();
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), globalSettings);
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'codex',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
codexConfig: {
dangerouslyBypassApprovals: globalSettings.codexDangerouslyBypassApprovals ?? false,
animations: globalSettings.codexAnimationsEnabled ?? false,
renderMode: 'hybrid',
},
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
}),
})
const data = await this._quickStartWithCustomModelConfirm({
caseName,
mode: 'codex',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
codexConfig: {
dangerouslyBypassApprovals: globalSettings.codexDangerouslyBypassApprovals ?? false,
animations: globalSettings.codexAnimationsEnabled ?? false,
renderMode: 'hybrid',
},
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
...(this._pendingCustomModelForLaunch ? { customModel: this._pendingCustomModelForLaunch } : {}),
}),
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start Codex');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
@@ -1694,20 +1775,16 @@ Object.assign(CodemanApp.prototype, {
}
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), this.loadAppSettingsFromStorage());
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'gemini',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
geminiConfig: { approvalMode: 'yolo' },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
}),
})
const data = await this._quickStartWithCustomModelConfirm({
caseName,
mode: 'gemini',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
geminiConfig: { approvalMode: 'yolo' },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
...(this._pendingCustomModelForLaunch ? { customModel: this._pendingCustomModelForLaunch } : {}),
}),
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start Gemini');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
@@ -1805,17 +1882,13 @@ Object.assign(CodemanApp.prototype, {
}
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), this.loadAppSettingsFromStorage());
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'pi',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote || Object.keys(envOverrides).length === 0 ? {} : { envOverrides }),
})
const data = await this._quickStartWithCustomModelConfirm({
caseName,
mode: 'pi',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote || Object.keys(envOverrides).length === 0 ? {} : { envOverrides }),
...(!isRemote && this._pendingCustomModelForLaunch ? { customModel: this._pendingCustomModelForLaunch } : {}),
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start Pi');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
@@ -1853,19 +1926,15 @@ Object.assign(CodemanApp.prototype, {
}
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), this.loadAppSettingsFromStorage());
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'omp',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
}),
})
const data = await this._quickStartWithCustomModelConfirm({
caseName,
mode: 'omp',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
...(this._pendingCustomModelForLaunch ? { customModel: this._pendingCustomModelForLaunch } : {}),
}),
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start OMP');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
@@ -1912,20 +1981,16 @@ Object.assign(CodemanApp.prototype, {
}
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), this.loadAppSettingsFromStorage());
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'grok',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
grokConfig: { alwaysApprove: true },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
}),
})
const data = await this._quickStartWithCustomModelConfirm({
caseName,
mode: 'grok',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
grokConfig: { alwaysApprove: true },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
...(this._pendingCustomModelForLaunch ? { customModel: this._pendingCustomModelForLaunch } : {}),
}),
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start Grok');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
@@ -1990,20 +2055,16 @@ Object.assign(CodemanApp.prototype, {
}
const envOverrides = this.buildEnvOverrides(this.getCaseSettings(caseName), this.loadAppSettingsFromStorage());
const res = await fetch('/api/quick-start', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
caseName,
mode: 'deepseek',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
deepSeekConfig: { permissionMode: 'danger-full-access' },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
}),
})
const data = await this._quickStartWithCustomModelConfirm({
caseName,
mode: 'deepseek',
sessionName: `w${this._nextCaseSessionStartNumber(caseName)}-${caseName}`,
...(isRemote ? {} : {
deepSeekConfig: { permissionMode: 'danger-full-access' },
...(Object.keys(envOverrides).length > 0 ? { envOverrides } : {}),
...(this._pendingCustomModelForLaunch ? { customModel: this._pendingCustomModelForLaunch } : {}),
}),
});
const data = await res.json();
if (!data.success) throw new Error(data.error || 'Failed to start DeepSeek');
await this._ensureCreatedSessionVisible(data.data.sessionId, data.data.session);
+133 -9
View File
@@ -11,7 +11,7 @@ import { homedir } from 'node:os';
import { existsSync, statSync, mkdirSync, writeFileSync } from 'node:fs';
import { execFile } from 'node:child_process';
import fs from 'node:fs/promises';
import { randomBytes } from 'node:crypto';
import { randomBytes, randomUUID } from 'node:crypto';
import { performance } from 'node:perf_hooks';
import {
ApiErrorCode,
@@ -3136,6 +3136,7 @@ export function registerSessionRoutes(
effort,
parentSessionId,
agentOrigin,
customModel,
} = parseBody(QuickStartSchema, req.body);
// Resolved ONCE here: the same value labels a case directory this request creates
@@ -3188,11 +3189,12 @@ export function registerSessionRoutes(
grokConfig ||
deepSeekConfig ||
ompConfig ||
openCodeConfig
openCodeConfig ||
customModel
) {
return createErrorResponse(
ApiErrorCode.INVALID_INPUT,
'envOverrides, effort, modelOverride, and per-CLI config are not supported for remote cases (they do not cross ssh). Configure the remote command via the host command override instead.'
'envOverrides, effort, modelOverride, per-CLI config, and custom model endpoints are not supported for remote cases (they do not cross ssh). Configure the remote command via the host command override instead.'
);
}
@@ -3223,11 +3225,12 @@ export function registerSessionRoutes(
grokConfig ||
deepSeekConfig ||
ompConfig ||
openCodeConfig
openCodeConfig ||
customModel
) {
return createErrorResponse(
ApiErrorCode.INVALID_INPUT,
'envOverrides, effort, and per-CLI config are not supported for docker cases (they do not cross into the container). Configure the container via the docker host command override instead.'
'envOverrides, effort, per-CLI config, and custom model endpoints are not supported for docker cases (they do not cross into the container). Configure the container via the docker host command override instead.'
);
}
@@ -3515,7 +3518,106 @@ export function registerSessionRoutes(
);
const qsTerminalHistoryConfig = await ctx.getTerminalHistoryConfig();
const qsGatedEnvOverrides = await clampEnvOverridesForOwner(owner, envOverrides);
const qsResolvedOmpConfig = resolveOmpConfigForCreate(mode, resolvedCasePath, ompConfig);
// Custom Model Endpoint Profiles, applied AT CREATE TIME (docs/custom-model-endpoints-plan.md)
// rather than via the dedicated restart-in-place route (POST /api/sessions/:id/custom-
// model, still what an ALREADY-RUNNING session uses to switch later): computing the
// injection before the process exists and launching directly on it avoids the visible
// native-boot-then-restart the restart-after-launch design otherwise shows on every
// custom-model run — most jarring on a CLI like Codex whose TUI fully reinitializes.
// Mirrors the dedicated route's own checks (llama-swap conflict, unsupported CLI,
// unknown endpoint, a model id the CLI's argv pattern can't carry) rather than trusting
// a lighter version of them, since this is the same server-side authority reached a
// different way, not a separate, less-checked path.
let qsCustomModelEnvOverrides = qsGatedEnvOverrides;
let qsCustomModelLaunchModel: string | undefined;
let qsCustomModelSessionId: string | undefined;
let qsCustomModelBookkeeping:
| {
endpointId: string;
modelId: string;
label?: string;
envKeys: string[];
configDir?: string;
launchModel?: string;
}
| undefined;
if (customModel) {
const cmEntry = getCli(mode);
if (!cmEntry) return createErrorResponse(ApiErrorCode.INVALID_INPUT, `No CLI registry entry for mode ${mode}`);
if (cmEntry.capabilities.customModelInjection.kind === 'unsupported') {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, `${mode} has no known custom-model mechanism`);
}
const cmHosts = await readCustomModelHosts(CODEMAN_CONFIG_DIR);
const cmEndpoint = cmHosts.find((h) => h.id === customModel.endpointId);
if (!cmEndpoint) return createErrorResponse(ApiErrorCode.NOT_FOUND, 'Model endpoint not found');
// See the dedicated route's own comment for the full reasoning: llama.cpp runs one
// model at a time, llama-swap swaps on demand, and switching away from what another
// live session is actively using deserves a warning, not a silent switch. There is no
// "self" to exclude from the affected-sessions scan here — this session doesn't exist
// yet.
const cmSwapStatus = await getLlamaSwapStatus(cmEndpoint);
const cmCurrentlyLoaded =
cmSwapStatus.running.find((r) => r.state === 'ready')?.model ?? cmSwapStatus.running[0]?.model;
const cmSwapNeeded = cmSwapStatus.isLlamaSwap && !!cmCurrentlyLoaded && cmCurrentlyLoaded !== customModel.modelId;
if (cmSwapNeeded && !customModel.confirmed) {
const cmAffectedSessions = [...ctx.sessions.values()]
.filter((s) => s.customModel?.endpointId === cmEndpoint.id && s.customModel?.modelId === cmCurrentlyLoaded)
.map((s) => ({ id: s.id, name: s.name }));
if (cmAffectedSessions.length > 0) {
return {
requiresConfirmation: true,
currentlyLoadedModel: cmCurrentlyLoaded,
affectedSessions: cmAffectedSessions,
};
}
}
// Minted ourselves (rather than left to Session's own default) so the injection
// below — and any configDir it writes — can target the REAL id the session launches
// with, not a placeholder: `new Session({ id: ... })` accepts an explicit id for
// exactly this reason.
qsCustomModelSessionId = randomUUID();
const cmContextLength = cmEndpoint.modelContextLengths?.[customModel.modelId];
const cmApplied = applyCustomModelInjection(
cmEntry,
cmEndpoint,
customModel.modelId,
qsCustomModelSessionId,
cmContextLength
);
if (!cmApplied) {
return createErrorResponse(ApiErrorCode.OPERATION_FAILED, `${mode} has no known custom-model mechanism`);
}
const cmModelSpec = cmEntry.launch.params.model;
if (
cmApplied.launchModel !== undefined &&
cmModelSpec?.type === 'token' &&
!matchesPattern(cmModelSpec.pattern, cmApplied.launchModel)
) {
removeConfigDir(cmApplied.configDir);
return createErrorResponse(
ApiErrorCode.INVALID_INPUT,
`Model id ${JSON.stringify(customModel.modelId)} cannot be passed to ${mode} on its command line`
);
}
qsCustomModelEnvOverrides = { ...qsGatedEnvOverrides, ...cmApplied.envOverrides };
qsCustomModelLaunchModel = cmApplied.launchModel;
qsCustomModelBookkeeping = {
endpointId: cmEndpoint.id,
modelId: customModel.modelId,
label: cmEndpoint.label,
envKeys: cmApplied.envKeys,
configDir: cmApplied.configDir,
launchModel: cmApplied.launchModel,
};
}
const session = new Session({
id: qsCustomModelSessionId,
workingDir: resolvedCasePath,
name: sessionName ? sessionName.slice(0, MAX_SESSION_NAME_LENGTH) : '',
mux: ctx.mux,
@@ -3530,11 +3632,24 @@ export function registerSessionRoutes(
codexConfig: mode === 'codex' ? qsGatedCodexConfig : undefined,
geminiConfig: mode === 'gemini' ? qsGatedGeminiConfig : undefined,
antigravityConfig: mode === 'antigravity' ? qsGatedAntigravityConfig : undefined,
piConfig: mode === 'pi' ? qsGatedPiConfig : undefined,
grokConfig: mode === 'grok' ? qsGatedGrokConfig : undefined,
piConfig:
mode === 'pi'
? qsCustomModelLaunchModel !== undefined
? { ...(qsGatedPiConfig ?? {}), model: qsCustomModelLaunchModel }
: qsGatedPiConfig
: undefined,
grokConfig:
mode === 'grok'
? qsCustomModelLaunchModel !== undefined
? { ...(qsGatedGrokConfig ?? {}), model: qsCustomModelLaunchModel }
: qsGatedGrokConfig
: undefined,
deepSeekConfig: mode === 'deepseek' ? qsGatedDeepSeekConfig : undefined,
ompConfig: resolveOmpConfigForCreate(mode, resolvedCasePath, ompConfig),
envOverrides: qsGatedEnvOverrides,
ompConfig:
mode === 'omp' && qsCustomModelLaunchModel !== undefined
? { ...(qsResolvedOmpConfig ?? {}), model: qsCustomModelLaunchModel }
: qsResolvedOmpConfig,
envOverrides: qsCustomModelEnvOverrides,
effort,
remote,
docker,
@@ -3543,6 +3658,15 @@ export function registerSessionRoutes(
parentSessionId: qsParentSessionId,
});
// Records the selection for session.customModel/getCustomModelForPersist() and future
// clear/switch calls — the actual env vars and launch-model config are already part of
// the launch above (constructor envOverrides, piConfig/grokConfig/ompConfig.model), so
// this is bookkeeping only, never a restart: setCustomModel() is synchronous state, no
// tmux IO of its own (see its own doc comment in session.ts).
if (qsCustomModelBookkeeping) {
session.setCustomModel(qsCustomModelBookkeeping, qsCustomModelEnvOverrides);
}
// Auto-detect completion phrase from CLAUDE.md BEFORE broadcasting
// so the initial state already has the phrase configured (only if globally enabled)
if (getCli(mode)?.capabilities.ralph && !remote && !docker && ctx.store.getConfig().ralphEnabled) {
+19
View File
@@ -1033,6 +1033,25 @@ export const QuickStartSchema = z.object({
* because it takes an existing `workingDir` and so never creates a directory to label.
*/
agentOrigin: z.string().max(64).optional(),
/**
* Custom Model Endpoint Profiles (docs/custom-model-endpoints-plan.md): launches directly
* on this saved endpoint/model instead of the mode's native backend, computed server-side
* from the admin-configured endpoint store the same way `POST /api/sessions/:id/custom-
* model` does — never trusting raw env values from the client. One-shot, launch-time
* equivalent of that route: no restart, so no visible relaunch (that route's restart-in-
* place is still what an ALREADY-RUNNING session uses to switch later). Rejected for
* remote/docker cases, same reasoning as `envOverrides` above. `confirmed` mirrors that
* route's field: skips the llama-swap "this will unload it for another session" check on
* a deliberate retry.
*/
customModel: z
.object({
endpointId: z.string().regex(/^[a-zA-Z0-9_-]+$/, 'Invalid endpoint id'),
modelId: z.string().min(1).max(200),
confirmed: z.boolean().optional(),
})
.strict()
.optional(),
});
// ========== Hook Events ==========