Track when executor calls cross an upstream transport boundary and use that
signal to keep model/provider errors from being replaced by later local
preparation, selection, or internal failures.
Mark HTTP, websocket, relay, and usage-tracked transports as upstream
attempts, while avoiding marks for local validation, logging, missing
sessions, and successful websocket handshakes before request send.
Parse relative auth expiry metadata and adjust Antigravity refresh timing.
* fix(executor): prepend empty user turn for model-first requests targeting Gemini/Antigravity (#4959)
When forwarding sliced conversation histories or tool calls across OpenAI Responses,
OpenAI Chat Completions, Claude Messages, and native Gemini, native Gemini and Antigravity
Gemini endpoints require that conversation contents begin with a user turn.
Normalize leading turns at the executor boundary rather than the translator layer:
- Prepend an empty user turn ({"role":"user","parts":[{"text":""}]}) for Gemini, Gemini Vertex,
AI Studio, and Antigravity Gemini generation and CountTokens requests if the first turn is 'model'.
- Keep Antigravity Claude requests untouched to avoid adapter 400 errors.
- Ensure normalization runs after payload rules so payload index overrides target the original turns.
- Use no-copy GJSON inspection to keep overhead zero on valid user-first requests.
* fix(executor): inject Antigravity leading user after reasoning replay (#4959)
Replay can insert a model functionCall at contents[0] for sliced
tool-result history. Run the empty-user prepend on the final
requestPayload, after sanitize and prepareAntigravityGeminiReasoningReplayPayload.
- Removed deprecated interceptor and executor-related methods, including `callRequestInterceptor`, `callResponseInterceptor`, and `callStreamChunkInterceptor`.
- Consolidated unused logic and pruned redundant imports to streamline `adapters.go`.
- No functional changes.
