fix(qoder): report usage to all clients and stop inlining large attachments

- Coalesce Qoder's empty finish-in-delta frame with the later choices:[] usage
  frame so OpenAI and Claude clients receive prompt_tokens, completion_tokens
  and cache-hit tokens (the dashboard already saw them)
- Upload inlined images through /api/v2/image/upload like qodercli, and stub
  oversized non-image files instead of stuffing 30MB+ data URIs into
  agent_chat_generation
- Emit response.completed -> response.usage for chat-native upstreams so
  /v1/responses clients (Codex CLI, sub2api) no longer log 0/0/0
- Keep Claude message_delta.usage working when usage arrives without choices[0]
- Escalate to the smallest advertised Qoder context tier (200K/400K/1M) when
  the estimated prompt no longer fits max_input_tokens
- Pass apiKey for PAT connections and list hidden enable:false catalog keys
  from /v1/models

src/app/api/v1/models/route.js

@@ -9,7 +9,7 @@ import { getProviderConnections, getCombos, getCustomModels, getModelAliases } f
 import { getDisabledModels } from "@/lib/disabledModelsDb";
 import { resolveKiroModels } from "open-sse/services/kiroModels.js";
 import { resolveKimchiModels } from "open-sse/services/kimchiModels.js";
-import { resolveQoderModels } from "open-sse/services/qoderModels.js";
+import { resolveQoderModels, routableQoderModels } from "open-sse/services/qoderModels.js";
 import { resolveCopilotModels } from "open-sse/services/copilotModels.js";
 import { resolveClinepassModels } from "open-sse/services/clinepassModels.js";
 import { resolveGrokCliModels } from "open-sse/services/grokCliModels.js";
@@ -34,15 +34,18 @@ const LIVE_MODEL_RESOLVERS = {
   qoder: async (conn) => {
     const result = await resolveQoderModels({
       accessToken: conn.accessToken,
+      // PAT (pt-...) connections keep the token in apiKey; without it the live
+      // catalog silently fails and /v1/models falls back to the static list.
+      apiKey: conn.apiKey,
       refreshToken: conn.refreshToken,
       email: conn.email,
       displayName: conn.displayName,
       providerSpecificData: conn.providerSpecificData || {}
     });
-    if (!result?.models?.length) return null;
-    return {
-      models: result.models.map((m) => ({ id: m.id, name: m.name })),
-    };
+    // Visible + hidden (enable:false) catalog keys — chat routes all of them.
+    const models = routableQoderModels(result);
+    if (!models.length) return null;
+    return { models: models.map((m) => ({ id: m.id, name: m.name })) };
   },
   kimchi: async (conn) => {
     const result = await resolveKimchiModels({