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/elevenlabs.js

@@ -0,0 +1,35 @@
+export default {
+  id: "elevenlabs",
+  alias: "el",
+  display: {
+    name: "ElevenLabs",
+    icon: "record_voice_over",
+    color: "#6C47FF",
+    textIcon: "EL",
+    website: "https://elevenlabs.io",
+    notice: {
+      apiKeyUrl: "https://elevenlabs.io/app/settings/api-keys"
+    }
+  },
+  category: "apikey",
+  authType: "apikey",
+  serviceKinds: [
+    "tts"
+  ],
+  ttsConfig: {
+    baseUrl: "https://api.elevenlabs.io/v1/text-to-speech",
+    authType: "apikey",
+    authHeader: "xi-api-key",
+    format: "elevenlabs",
+    models: [
+      {
+        id: "eleven_multilingual_v2",
+        name: "Eleven Multilingual v2"
+      },
+      {
+        id: "eleven_turbo_v2_5",
+        name: "Eleven Turbo v2.5"
+      }
+    ]
+  }
+};