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

Fixes #754

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(),
 });
 
 /**