Revert Fire Pass model id to the router path

The previous pass "aligned" model-resolver.ts to
accounts/fireworks/models/kimi-k2.5-turbo — the per-token model path —
to match the connector catalog's default. That was the wrong direction:
Fire Pass subscription traffic routes exclusively through
accounts/fireworks/routers/kimi-k2p5-turbo (see docs.fireworks.ai/firepass),
and the entitlement does not attach to the per-token id. Existing agent
rows already pointed at the router id, so validateConnectorModelSelection
rejected every dispatch with "does not allow model
'accounts/fireworks/routers/kimi-k2p5-turbo'" and the CEO stopped running
entirely.

Put the router id back in model-resolver.ts (the enabled-pool source of
truth), and bring the two catalog defaults in line so a freshly-seeded
Fire Pass connector also ends up on the router id. The per-token
`fireworks` connector keeps the `models/...` default since that path
bills per token and genuinely targets the per-model endpoint.

src/main/connector-definitions-data-apikey.ts

@@ -169,9 +169,9 @@ export const API_KEY_CONNECTORS: ConnectorDefinition[] = [
     label: "Fireworks Fire Pass",
     description:
       "Fireworks Fire Pass — $7/week subscription for unlimited Kimi K2.5 Turbo. Uses the same FIREWORKS_API_KEY; the Fire Pass entitlement is attached to the account.",
-    defaultModel: "accounts/fireworks/models/kimi-k2.5-turbo",
+    defaultModel: "accounts/fireworks/routers/kimi-k2p5-turbo",
     auth: { type: "api_key", envKey: "FIREWORKS_API_KEY" },
     notes:
-      "Covers Kimi K2.5 Turbo only; other Fireworks models still bill per-token. See https://docs.fireworks.ai/firepass.",
+      "Fire Pass routes through the dedicated router id accounts/fireworks/routers/kimi-k2p5-turbo on both the OpenAI- and Anthropic-compat endpoints. See https://docs.fireworks.ai/firepass.",
   },
 ];

src/main/model-resolver.ts

@@ -25,7 +25,15 @@ const FIREWORKS_OPENAI_BASE_URL = "https://api.fireworks.ai/inference/v1";
 const FIREWORKS_DEFAULT_CONTEXT = 128_000;
 const FIREWORKS_DEFAULT_MAX_TOKENS = 8192;
 
-export const FIREWORKS_FIREPASS_MODEL_ID = "accounts/fireworks/models/kimi-k2.5-turbo";
+// Fire Pass routes subscription traffic through a dedicated router id,
+// not the per-token model path. The canonical identifier is documented
+// at https://docs.fireworks.ai/firepass and applies to both the
+// OpenAI-compatible (`/inference/v1`) and Anthropic-compatible
+// (`/inference`) endpoints. Do not "align" this to the
+// `accounts/fireworks/models/...` id — the subscription entitlement
+// only attaches to the router route, and switching to the model path
+// makes Fireworks bill per-token and reject Fire-Pass-only callers.
+export const FIREWORKS_FIREPASS_MODEL_ID = "accounts/fireworks/routers/kimi-k2p5-turbo";
 export const FIREWORKS_FIREPASS_MODEL_NAME = "Kimi K2.5 Turbo (Fire Pass)";
 
 const FIREWORKS_CURATED_MODELS: Array<{ id: string; name: string; contextWindow?: number }> = [

src/shared/connector-catalog.ts

@@ -236,9 +236,9 @@ const API_KEY_ENTRIES: ConnectorCatalogEntry[] = [
     provider: "fireworks-firepass",
     label: "Fireworks Fire Pass",
     description: "Fireworks Fire Pass — subscription bundle. Same FIREWORKS_API_KEY.",
-    defaultModel: "accounts/fireworks/models/kimi-k2.5-turbo",
+    defaultModel: "accounts/fireworks/routers/kimi-k2p5-turbo",
     auth: { type: "api_key", envKey: "FIREWORKS_API_KEY" },
-    notes: "Covers Kimi K2.5 Turbo only; other Fireworks models still bill per-token.",
+    notes: "Fire Pass uses the dedicated router id accounts/fireworks/routers/kimi-k2p5-turbo documented at docs.fireworks.ai/firepass.",
   },
 ];