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/translator/request/openai-responses.js

@@ -177,6 +177,12 @@ export function openaiResponsesToOpenAIRequest(model, body, stream, credentials)
   }
 
   // Cleanup Responses API specific fields
+  // Map Responses-only max_output_tokens to Chat max_tokens (avoid leaking unknown field upstream)
+  if (result.max_output_tokens !== undefined) {
+    if (result.max_tokens === undefined) result.max_tokens = result.max_output_tokens;
+    delete result.max_output_tokens;
+  }
+
   delete result.input;
   delete result.instructions;
   delete result.include;