refactor(custom-model): one exported MAX_DISCOVERED_CONTEXT_TOKENS for routes and schema

Round-four review smaller item: the discovery comment claimed a shared ceiling while schemas.ts restated the literal twice; the constant now lives in schemas.ts (routes already import from it, no cycle) and both bounds reference it.

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

@@ -21,7 +21,7 @@ import { isMultiUserMode } from '../../config/multiuser.js';
 import { getDataDir } from '../../config/instance.js';
 import { isBlockedWebviewUrl } from '../webview-egress-policy.js';
 import { egressBlockedReason, webviewFetch } from '../webview-egress.js';
-import { CustomModelHostSchema } from '../schemas.js';
+import { CustomModelHostSchema, MAX_DISCOVERED_CONTEXT_TOKENS } from '../schemas.js';
 import { readCustomModelHosts, writeCustomModelHosts, type CustomModelHost } from '../../custom-model-hosts.js';
 import type { CliEntry } from '../../config/cli-registry/types.js';
 
@@ -187,13 +187,6 @@ 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

src/web/schemas.ts

@@ -2352,6 +2352,14 @@ export const WebviewUpdateSchema = WebviewBaseSchema.partial();
 /** POST /api/webviews/probe: reachability + framing check for the editor's Test button. */
 export const WebviewProbeSchema = z.object({ url: webviewUrlSchema });
 
+/**
+ * Ceiling on a stated context length (tokens), shared between the bounds below and
+ * discovery (`custom-model-routes.ts`): anything above it reads as nonsense and is
+ * ignored, because a bogus figure here overflows the smaller server, which is the exact
+ * failure the discovery field exists to prevent.
+ */
+export const MAX_DISCOVERED_CONTEXT_TOKENS = 100_000_000;
+
 // Custom Model Endpoint Profiles (docs/custom-model-endpoints-plan.md) — a
 // user-configured custom OpenAI-compatible endpoint, local (llama.cpp) or cloud
 // (Azure AI Foundry, etc.). Lives below `webviewUrlSchema` because `baseUrl` IS that
@@ -2375,14 +2383,16 @@ export const CustomModelHostSchema = z.object({
   defaultModelId: z.string().max(200).optional(),
   // Server-populated by discovery (custom-model-routes.ts); accepted here only so a client
   // round-tripping the GET response back through PUT (edit-save) doesn't drop it.
-  modelContextLengths: z.record(z.string().max(200), z.number().int().positive().max(100_000_000)).optional(),
+  modelContextLengths: z
+    .record(z.string().max(200), z.number().int().positive().max(MAX_DISCOVERED_CONTEXT_TOKENS))
+    .optional(),
   // Same reasoning as modelContextLengths above.
   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(),
+  defaultContextLength: z.number().int().positive().max(MAX_DISCOVERED_CONTEXT_TOKENS).optional(),
 });
 
 /**