feat(custom-model): discover context length from /v1/models and add a default context length

Fixes #754

src/custom-model-hosts.ts

@@ -52,13 +52,16 @@ export interface CustomModelHost {
   defaultModelId?: string;
   /**
    * Discovered context-window size (tokens) per model id, keyed by the same strings as
-   * `models`. Populated opportunistically during discovery (`custom-model-routes.ts`) from
-   * llama.cpp/llama-swap's `GET /props?model=<id>` — the plain OpenAI-shaped `/v1/models`
-   * response has no such field. Only ever probed for a model the server already reports as
-   * loaded (llama-swap's `status.value === 'loaded'`); an unloaded one is deliberately never
-   * probed, since llama-swap treats `/props?model=` as a routing hint that can trigger an
-   * actual (slow, GPU-swapping) model load as a side effect of merely asking. A model this
-   * has no entry for simply gets no context-length env override applied — never a guess.
+   * `models`. Populated only by discovery (`custom-model-routes.ts`), from the strongest
+   * source the server offers: the llama-swap launch command reported by `GET /running`
+   * (the source of truth for a loaded model), then llama.cpp's `GET /props?model=<id>`
+   * `n_ctx` (only ever probed for a model the server already reports as loaded, since
+   * llama-swap treats `/props?model=` as a routing hint that can trigger an actual
+   * (slow, GPU-swapping) model load as a side effect of merely asking), then the model's
+   * own `GET /v1/models` entry (`context_length`, else `context_window`, which current
+   * llama-swap, Bifrost and OpenRouter-style servers each state to varying degrees). A
+   * model with no entry here falls back to the endpoint's `defaultContextLength`; with
+   * neither, it simply gets no context-length env override applied, never a guess.
    */
   modelContextLengths?: Record<string, number>;
   /**
@@ -88,6 +91,15 @@ export interface CustomModelHost {
    * server-side check relies on.
    */
   modelSizesGB?: Record<string, number>;
+  /**
+   * User-set fallback context length (tokens), applied by the read sites in
+   * `session-routes.ts` only when `modelContextLengths` has no entry for the selected
+   * model (a gateway that states no per-model figure, a model never loaded yet). Never
+   * written by discovery, so a value set in the endpoint editor survives every
+   * re-discovery sweep; unset keeps the long-standing behaviour of letting each CLI
+   * assume its own default.
+   */
+  defaultContextLength?: number;
 }
 
 export function customModelHostsPath(configDir: string): string {

src/web/public/i18n.js

@@ -615,6 +615,9 @@
     'API key': 'API 密钥',
     'Optional. Left blank on edit keeps the existing key.': '可选。编辑时留空将保留现有密钥。',
     'Auth header': '认证请求头',
+    'Default context length (tokens)': '默认上下文长度（token 数）',
+    'Used for models whose size cannot be discovered. Leave empty to let each CLI assume its own default.':
+      '用于无法自动发现上下文大小的模型。留空则让各个 CLI 使用其自身的默认值。',
     'Never send both — some servers hang indefinitely.': '切勿同时发送两者 — 部分服务器会因此无限期挂起。',
     'Authorization: Bearer (default)': 'Authorization: Bearer（默认）',
     'api-key header (Azure)': 'api-key 请求头（Azure）',

src/web/public/index.html

@@ -2799,6 +2799,10 @@
                         <div class="set-row-text"><span class="set-row-label">Base URL</span></div>
                         <input type="text" id="customModelHostBaseUrl" class="set-input" placeholder="http://192.168.1.50:8080">
                       </div>
+                      <div class="set-row has-field">
+                        <div class="set-row-text"><span class="set-row-label">Default context length (tokens)</span><span class="set-row-desc">Used for models whose size cannot be discovered. Leave empty to let each CLI assume its own default.</span></div>
+                        <input type="number" id="customModelHostDefaultContextLength" class="set-input" min="1" max="100000000" step="1" placeholder="131072">
+                      </div>
                       <div class="set-row has-field">
                         <div class="set-row-text"><span class="set-row-label">API key</span><span class="set-row-desc">Optional. Left blank on edit keeps the existing key.</span></div>
                         <input type="password" id="customModelHostApiKey" class="set-input" autocomplete="new-password">

src/web/public/settings-ui.js

@@ -3809,6 +3809,9 @@ Object.assign(CodemanApp.prototype, {
     document.getElementById('customModelHostApiKey').value = ''; // the server never returns the real value (apiKeySet is a bool)
     document.getElementById('customModelHostApiKey').placeholder = host?.apiKeySet ? '•••••••• (unchanged if left blank)' : '';
     document.getElementById('customModelHostAuthStyle').value = host?.authStyle || 'bearer';
+    // User-set fallback, round-tripped verbatim (discovery never touches it, so the
+    // cached copy is authoritative); blank means "no default", cleared on save.
+    document.getElementById('customModelHostDefaultContextLength').value = host?.defaultContextLength ?? '';
     this._populateCustomModelDefaultSelect(host);
     document.getElementById('customModelHostEditor').style.display = '';
   },
@@ -3834,6 +3837,18 @@ Object.assign(CodemanApp.prototype, {
     const baseUrl = document.getElementById('customModelHostBaseUrl').value.trim();
     const apiKeyInput = document.getElementById('customModelHostApiKey').value;
     const authStyle = document.getElementById('customModelHostAuthStyle').value;
+    // Blank means "no default" (key omitted, so PUT clears it); a value must satisfy
+    // the same bound the server schema enforces, caught here for a friendlier message.
+    const defaultContextLengthInput = document.getElementById('customModelHostDefaultContextLength').value.trim();
+    let defaultContextLength;
+    if (defaultContextLengthInput !== '') {
+      const parsed = Number(defaultContextLengthInput);
+      if (!Number.isInteger(parsed) || parsed < 1 || parsed > 100000000) {
+        this.showToast('Default context length must be a whole number of tokens between 1 and 100,000,000', 'warning');
+        return;
+      }
+      defaultContextLength = parsed;
+    }
     const defaultModelId = document.getElementById('customModelHostDefaultModel').value || undefined;
     if (!id || !label || !baseUrl) {
       this.showToast('Id, label and base URL are all required', 'warning');
@@ -3854,6 +3869,7 @@ Object.assign(CodemanApp.prototype, {
       baseUrl,
       authStyle,
       defaultModelId,
+      defaultContextLength,
       apiKey: apiKeyInput || undefined,
       models: existing?.models,
       lastDiscoveredAt: existing?.lastDiscoveredAt,

src/web/routes/custom-model-routes.ts

@@ -158,7 +158,12 @@ function authHeaders(host: Pick<CustomModelHost, 'apiKey' | 'authStyle'>): Recor
 
 export interface DiscoveryResult {
   models: string[];
-  /** See `CustomModelHost.modelContextLengths` — only ever populated for models already loaded. */
+  /**
+   * See `CustomModelHost.modelContextLengths`: populated from a model's own `/v1/models`
+   * entry (`context_length`, else `context_window`) whenever the server states one, and
+   * from the launch command or `/props` for loaded models, which overwrite (and so win
+   * over) any listed figure for the same model.
+   */
   contextLengths: Record<string, number>;
   /** See `CustomModelHost.modelSlotCounts`; populated on the same loaded-models-only basis as `contextLengths`. */
   slotCounts: Record<string, number>;
@@ -182,6 +187,27 @@ function parseSizeGB(description: unknown): number | undefined {
   return Number.isFinite(size) && size > 0 ? size : undefined;
 }
 
+/**
+ * Ceiling shared with `schemas.ts`'s `CustomModelHostSchema` bound on context lengths:
+ * anything above it reads as nonsense and is ignored, because a bogus figure here
+ * overflows the smaller server, which is the exact failure this field exists to prevent.
+ */
+const MAX_DISCOVERED_CONTEXT_TOKENS = 100_000_000;
+
+/**
+ * Best-effort: reads a context length (tokens) stated by a model's OWN entry in
+ * `GET /v1/models`. OpenRouter-style servers call the field `context_length`; current
+ * llama-swap sends both `context_length` and `context_window` per model, and current
+ * Bifrost (a gateway in front of llama-swap) passes `context_window` through. Older
+ * servers send neither, and a server that states nothing gets no entry, never a guess.
+ * Non-numeric, zero, negative, fractional or over-the-ceiling values are ignored, the
+ * same rule the stored field's schema enforces: a wrong figure here is worse than none.
+ */
+function parseListedContextLength(value: unknown): number | undefined {
+  if (typeof value !== 'number' || !Number.isInteger(value) || value <= 0) return undefined;
+  return value <= MAX_DISCOVERED_CONTEXT_TOKENS ? value : undefined;
+}
+
 /**
  * Best-effort: fetches `GET /props?model=<id>` (llama.cpp-native, llama-swap-proxied) for
  * ONE already-loaded model and pulls its `n_ctx` and `total_slots` out. Never called for a model that
@@ -312,24 +338,38 @@ async function discoverModels(
   });
   if (!res.ok) throw new Error(`HTTP ${res.status}`);
   const body = (await res.json()) as {
-    data?: Array<{ id?: unknown; status?: { value?: unknown }; description?: unknown }>;
+    data?: Array<{
+      id?: unknown;
+      status?: { value?: unknown };
+      description?: unknown;
+      context_length?: unknown;
+      context_window?: unknown;
+    }>;
   };
   const entries = body.data ?? [];
   const models = entries.map((m) => m.id).filter((id): id is string => typeof id === 'string' && id.length > 0);
 
   const sizesGB: Record<string, number> = {};
+  // The lowest-precedence context source, and the only one a gateway without /running or
+  // /props of its own (e.g. Bifrost) can offer: the figure a model's own listing states
+  // (`context_length`, else `context_window`). The loaded-model pass below OVERWRITES
+  // these for whatever it reads from the launch command or /props, so precedence per
+  // model stays: `/running` cmd, then `/props`, then this listed figure.
+  const contextLengths: Record<string, number> = {};
   for (const entry of entries) {
     if (typeof entry.id !== 'string' || !entry.id) continue;
     const size = parseSizeGB(entry.description);
     if (size !== undefined) sizesGB[entry.id] = size;
+    const listed = parseListedContextLength(entry.context_length) ?? parseListedContextLength(entry.context_window);
+    if (listed !== undefined) contextLengths[entry.id] = listed;
   }
 
   // llama-swap-specific, feature-detected: a server that never mentions `status` on ANY
-  // entry gets no context-length enrichment at all, rather than treating "no status field"
-  // as "assume unloaded" — either reading is a guess, and skipping is the safe one, since
-  // fetchContextLength must only ever run against a model this server itself calls loaded.
+  // entry gets no launch-command/props context enrichment at all, rather than treating
+  // "no status field" as "assume unloaded"; either reading is a guess, and skipping is
+  // the safe one, since fetchContextLength must only ever run against a model this server
+  // itself calls loaded. Listed figures above are unaffected: reading them triggers nothing.
   const hasStatusField = entries.some((m) => m && typeof m === 'object' && 'status' in m);
-  const contextLengths: Record<string, number> = {};
   const slotCounts: Record<string, number> = {};
   if (hasStatusField) {
     const loadedIds = entries
@@ -364,6 +404,9 @@ async function discoverModels(
           // merges onto what was learned before).
           if (cmdSlots !== undefined && ctxFromProps) slots = 1;
         }
+        // Assigning only when a probe answered keeps the listed figure (if any) when
+        // neither the launch command nor /props stated one, and replaces it with the
+        // stronger source whenever they did: cmd > /props > listed, never the reverse.
         if (ctx !== undefined) contextLengths[id] = ctx;
         if (slots !== undefined) slotCounts[id] = slots;
       }

src/web/routes/session-routes.ts

@@ -1541,7 +1541,10 @@ export function registerSessionRoutes(
     if (!endpoint) {
       return createErrorResponse(ApiErrorCode.NOT_FOUND, 'Model endpoint not found');
     }
-    const contextLength = endpoint.modelContextLengths?.[body.modelId];
+    // Discovery's per-model figure wins; the endpoint's user-set default covers models
+    // whose size discovery could not determine (a gateway that states none, say). With
+    // neither, the existing "no override, CLI assumes its own default" behaviour stands.
+    const contextLength = endpoint.modelContextLengths?.[body.modelId] ?? endpoint.defaultContextLength;
     const slotCount = endpoint.modelSlotCounts?.[body.modelId];
 
     // Some CLIs (today: only claude) carry enough of their own fixed system-prompt/tool-
@@ -4447,7 +4450,9 @@ export function registerSessionRoutes(
       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');
-      const cmContextLength = cmEndpoint.modelContextLengths?.[customModel.modelId];
+      // Per-model discovery figure first, user-set endpoint default second, nothing third
+      // (see the dedicated route's own comment above).
+      const cmContextLength = cmEndpoint.modelContextLengths?.[customModel.modelId] ?? cmEndpoint.defaultContextLength;
       const cmSlotCount = cmEndpoint.modelSlotCounts?.[customModel.modelId];
 
       // See the dedicated route's own comment for the full reasoning: some CLIs' own fixed

src/web/schemas.ts

@@ -2380,6 +2380,9 @@ export const CustomModelHostSchema = z.object({
   modelSlotCounts: z.record(z.string().max(200), z.number().int().positive().max(4096)).optional(),
   // Same reasoning as modelContextLengths above.
   modelSizesGB: z.record(z.string().max(200), z.number().positive().max(100_000)).optional(),
+  // User-set fallback for models discovery has no context length for (session-routes.ts);
+  // discovery never writes it. Same bound as the modelContextLengths values above.
+  defaultContextLength: z.number().int().positive().max(100_000_000).optional(),
 });
 
 /**

test/routes/custom-model-routes.test.ts

@@ -11,7 +11,7 @@
 import { describe, it, expect, vi, afterEach } from 'vitest';
 import { registerCustomModelRoutes } from '../../src/web/routes/custom-model-routes.js';
 import { webviewFetch } from '../../src/web/webview-egress.js';
-import { createRouteTestHarness } from './_route-test-utils.js';
+import { createRouteTestHarness, type RouteTestHarness } from './_route-test-utils.js';
 
 vi.mock('../../src/web/webview-egress.js', async () => {
   const actual = await vi.importActual<typeof import('../../src/web/webview-egress.js')>(
@@ -417,3 +417,166 @@ describe('apiKey is never handed back to the browser', () => {
     expect(fetchMock).toHaveBeenCalledTimes(1);
   });
 });
+
+describe('context-length discovery from the /v1/models listing', () => {
+  // The gateway path (a Bifrost in front of llama-swap, an OpenRouter-style server):
+  // no /running, no /props, just a per-model `context_length` or `context_window` in the
+  // model listing. Distinct ports per test keep the file's shared data dir unambiguous.
+  afterEach(() => {
+    fetchMock.mockReset();
+  });
+
+  type StoredHost = { id: string; modelContextLengths?: Record<string, number>; defaultContextLength?: number };
+
+  type HarnessApp = RouteTestHarness['app'];
+
+  async function endpointWith(id: string, port: number, extra: Record<string, unknown> = {}): Promise<HarnessApp> {
+    const { app } = await setup();
+    const res = await app.inject({
+      method: 'POST',
+      url: '/api/model-endpoints',
+      payload: { id, label: 'A', baseUrl: `http://localhost:${port}`, ...extra },
+    });
+    expect(res.statusCode).toBe(200);
+    return app;
+  }
+
+  async function storedHost(app: HarnessApp, id: string): Promise<StoredHost | undefined> {
+    const list = await app.inject({ method: 'GET', url: '/api/model-endpoints' });
+    return (list.json() as StoredHost[]).find((h) => h.id === id);
+  }
+
+  it('reads context_length (preferred) then context_window from each entry into modelContextLengths', async () => {
+    const app = await endpointWith('ep-ctx-listed', 8101);
+    fetchMock.mockResolvedValue(
+      new Response(
+        JSON.stringify({
+          data: [
+            { id: 'both', context_length: 131072, context_window: 32768 },
+            { id: 'window-only', context_window: 8192 },
+            { id: 'no-figure' },
+          ],
+        }),
+        { status: 200 }
+      )
+    );
+
+    const discover = await app.inject({ method: 'POST', url: '/api/model-endpoints/ep-ctx-listed/discover-models' });
+    expect(discover.json().success).toBe(true);
+
+    const stored = await storedHost(app, 'ep-ctx-listed');
+    expect(stored?.modelContextLengths).toEqual({ both: 131072, 'window-only': 8192 });
+  });
+
+  it('ignores non-numeric, zero, negative and absurd listed values; the schema bound itself is still accepted', async () => {
+    const app = await endpointWith('ep-ctx-bad', 8102);
+    fetchMock.mockResolvedValue(
+      new Response(
+        JSON.stringify({
+          data: [
+            { id: 'string', context_length: '131072' },
+            { id: 'zero', context_window: 0 },
+            { id: 'negative', context_length: -10 },
+            { id: 'over-bound', context_length: 100_000_001 },
+            { id: 'fractional', context_window: 16384.5 },
+            { id: 'at-bound', context_length: 100_000_000 },
+          ],
+        }),
+        { status: 200 }
+      )
+    );
+
+    await app.inject({ method: 'POST', url: '/api/model-endpoints/ep-ctx-bad/discover-models' });
+
+    const stored = await storedHost(app, 'ep-ctx-bad');
+    expect(stored?.modelContextLengths).toEqual({ 'at-bound': 100_000_000 });
+  });
+
+  it('prefers the /running launch command over the listed figure for a loaded model', async () => {
+    const app = await endpointWith('ep-ctx-cmd', 8103);
+    fetchMock.mockImplementation(async (url: URL) => {
+      if (url.pathname === '/v1/models') {
+        return new Response(
+          JSON.stringify({ data: [{ id: 'cmd-wins', status: { value: 'loaded' }, context_length: 131072 }] }),
+          { status: 200 }
+        );
+      }
+      if (url.pathname === '/running') {
+        return new Response(
+          JSON.stringify({ running: [{ model: 'cmd-wins', state: 'ready', cmd: 'llama-server --ctx-size 16384' }] }),
+          { status: 200 }
+        );
+      }
+      if (url.pathname === '/props') return new Response('nope', { status: 404 });
+      throw new Error(`unexpected request in this test: ${url.href}`);
+    });
+
+    await app.inject({ method: 'POST', url: '/api/model-endpoints/ep-ctx-cmd/discover-models' });
+
+    const stored = await storedHost(app, 'ep-ctx-cmd');
+    expect(stored?.modelContextLengths).toEqual({ 'cmd-wins': 16384 });
+  });
+
+  it('keeps a previously learned value the fresh listing says nothing about, and discovery never touches defaultContextLength', async () => {
+    const app = await endpointWith('ep-ctx-keep', 8104, {
+      models: ['re-listed', 'untouched'],
+      modelContextLengths: { 're-listed': 16384, untouched: 4096 },
+      defaultContextLength: 65536,
+    });
+    fetchMock.mockResolvedValue(
+      new Response(
+        JSON.stringify({ data: [{ id: 're-listed', context_length: 32768 }, { id: 'untouched' }] }),
+        { status: 200 }
+      )
+    );
+
+    await app.inject({ method: 'POST', url: '/api/model-endpoints/ep-ctx-keep/discover-models' });
+
+    const stored = await storedHost(app, 'ep-ctx-keep');
+    expect(stored?.modelContextLengths).toEqual({ 're-listed': 32768, untouched: 4096 });
+    expect(stored?.defaultContextLength).toBe(65536);
+  });
+});
+
+describe('defaultContextLength (the user-set fallback discovery never overwrites)', () => {
+  afterEach(() => {
+    fetchMock.mockReset();
+  });
+
+  it('stores it on create, updates it on PUT, and a PUT without it clears it', async () => {
+    const { app } = await setup();
+    const create = await app.inject({
+      method: 'POST',
+      url: '/api/model-endpoints',
+      payload: { id: 'ep-defctx', label: 'A', baseUrl: 'http://localhost:8105', defaultContextLength: 131072 },
+    });
+    expect(create.json().data.host.defaultContextLength).toBe(131072);
+
+    const update = await app.inject({
+      method: 'PUT',
+      url: '/api/model-endpoints/ep-defctx',
+      payload: { label: 'A', baseUrl: 'http://localhost:8105', defaultContextLength: 32768 },
+    });
+    expect(update.json().data.host.defaultContextLength).toBe(32768);
+
+    const cleared = await app.inject({
+      method: 'PUT',
+      url: '/api/model-endpoints/ep-defctx',
+      payload: { label: 'A', baseUrl: 'http://localhost:8105' },
+    });
+    expect(cleared.json().data.host.defaultContextLength).toBeUndefined();
+  });
+
+  it('rejects zero, negative, fractional, over-the-bound and non-numeric values', async () => {
+    const { app } = await setup();
+    for (const defaultContextLength of [0, -1, 1.5, 100_000_001, '131072']) {
+      const res = await app.inject({
+        method: 'POST',
+        url: '/api/model-endpoints',
+        payload: { id: 'ep-defctx-bad', label: 'A', baseUrl: 'http://localhost:8106', defaultContextLength },
+      });
+      expect(res.json().success, String(defaultContextLength)).toBe(false);
+      expect(res.json().errorCode, String(defaultContextLength)).toBe('INVALID_INPUT');
+    }
+  });
+});

test/routes/quick-start-custom-model.test.ts

@@ -367,6 +367,50 @@ describe('POST /api/quick-start: customModel (one-shot custom-model launch)', ()
       expect(res.statusCode).toBe(200);
       expect(res.json().requiresContextWarning).toBeUndefined();
     });
+
+    it('warns using the endpoint defaultContextLength when discovery recorded no per-model figure', async () => {
+      const endpoint: CustomModelHost = {
+        id: 'ep-default',
+        label: 'silent gateway',
+        baseUrl: 'http://192.168.1.53:8080',
+        apiKey: 'k',
+        defaultContextLength: 16384,
+      };
+      await writeCustomModelHosts(getDataDir(), [ENDPOINT, endpoint]);
+
+      const res = await quickStart({
+        caseName: 'cm-default-ctx',
+        mode: 'claude',
+        customModel: { endpointId: 'ep-default', modelId: 'some-unknown-model' },
+      });
+
+      const body = res.json();
+      expect(body.requiresContextWarning).toBe(true);
+      expect(body.contextLength).toBe(16384);
+      expect(ctx.sessions.size).toBe(1); // nothing was created
+    });
+
+    it('a discovered per-model figure wins over the endpoint defaultContextLength', async () => {
+      const endpoint: CustomModelHost = {
+        id: 'ep-precedence',
+        label: 'mixed box',
+        baseUrl: 'http://192.168.1.54:8080',
+        apiKey: 'k',
+        modelContextLengths: { m: 131072 },
+        defaultContextLength: 16384,
+      };
+      await writeCustomModelHosts(getDataDir(), [ENDPOINT, endpoint]);
+
+      const res = await quickStart({
+        caseName: 'cm-precedence',
+        mode: 'claude',
+        customModel: { endpointId: 'ep-precedence', modelId: 'm' },
+      });
+
+      expect(res.statusCode).toBe(200);
+      expect(res.json().requiresContextWarning).toBeUndefined();
+      expect(ctx.sessions.size).toBe(2);
+    });
   });
 
   describe('triggering the actual llama-swap load (not just watching for it)', () => {

test/routes/session-custom-model.test.ts

@@ -449,6 +449,58 @@ describe('POST /api/sessions/:id/custom-model', () => {
       expect(session.restartCli).not.toHaveBeenCalled();
     });
 
+    it('the endpoint defaultContextLength stands in when discovery recorded no per-model figure', async () => {
+      const { app, ctx } = await setup();
+      // A gateway that states nothing per model: only the user's default is known.
+      const endpoint: CustomModelHost = {
+        id: 'ep-default',
+        label: 'silent gateway',
+        baseUrl: 'http://192.168.1.53:8080',
+        apiKey: 'k',
+        defaultContextLength: 16384,
+      };
+      await writeCustomModelHosts(getDataDir(), [CLAUDE_ENDPOINT, endpoint]);
+      const session = ctx.sessions.get('test-session-1')!;
+      session.mode = 'claude';
+
+      const res = await app.inject({
+        method: 'POST',
+        url: '/api/sessions/test-session-1/custom-model',
+        payload: { endpointId: 'ep-default', modelId: 'some-unknown-model' },
+      });
+
+      const body = res.json();
+      expect(body.requiresContextWarning).toBe(true);
+      expect(body.contextLength).toBe(16384);
+      expect(session.setCustomModel).not.toHaveBeenCalled();
+    });
+
+    it('a discovered per-model figure wins over the endpoint defaultContextLength', async () => {
+      const { app, ctx } = await setup();
+      // The default is small enough to warn on; the discovered figure for THIS model is
+      // not, so the fallback must not leak into the per-model path.
+      const endpoint: CustomModelHost = {
+        id: 'ep-precedence',
+        label: 'mixed box',
+        baseUrl: 'http://192.168.1.54:8080',
+        apiKey: 'k',
+        modelContextLengths: { 'qwen3.8-27b-ud-q4_k_xl': 131072 },
+        defaultContextLength: 16384,
+      };
+      await writeCustomModelHosts(getDataDir(), [CLAUDE_ENDPOINT, endpoint]);
+      const session = ctx.sessions.get('test-session-1')!;
+      session.mode = 'claude';
+
+      const res = await app.inject({
+        method: 'POST',
+        url: '/api/sessions/test-session-1/custom-model',
+        payload: { endpointId: 'ep-precedence', modelId: 'qwen3.8-27b-ud-q4_k_xl' },
+      });
+
+      expect(res.json().requiresContextWarning).toBeUndefined();
+      expect(session.setCustomModel).toHaveBeenCalledTimes(1);
+    });
+
     // llama-server splits its context across --parallel slots, and Claude Code sends several
     // requests at once, so a context that clears the floor as a whole can still fail per slot.
     describe('parallel slots share the context', () => {