fix(translator): ESM-safe registry + tool-id pairing + responses max_tokens; add real-creds tests

- translator/index.js: replace require() with static side-effect imports (ESM-safe),
  lazy-init registry maps to survive circular import order
- openai-responses->openai: map max_output_tokens -> max_tokens (avoid leaking field upstream)
- gemini/antigravity -> openai: derive deterministic tool_call id from name so
  functionCall/functionResponse pair correctly (fixes provider tool-pairing 400s)
- add offline unit tests (finish-reason, usage, session-manager, ollama malformed args, const guard)
- add real-creds integration tests (provider-cases + all-formats matrix: 6 inbound formats x 4 scenarios)

Includes co-located provider registry refactor (pricing/capabilities/media providers) and sessionManager updates.

Co-authored-by: Cursor <cursoragent@cursor.com>

open-sse/providers/registry/local-device.js

@@ -0,0 +1,24 @@
+export default {
+  id: "local-device",
+  alias: "local-device",
+  display: {
+    name: "Local Device",
+    icon: "speaker",
+    color: "#64748B",
+    textIcon: "LD"
+  },
+  category: "freeTier",
+  authType: "none",
+  serviceKinds: [
+    "tts"
+  ],
+  mediaPriority: 5,
+  noAuth: true,
+  ttsConfig: {
+    baseUrl: "local-device",
+    authType: "none",
+    authHeader: "none",
+    format: "local-device",
+    models: []
+  }
+};