Add support for Gemini's code_execution and url_context tools in the
request translators, enabling:
- Agentic Vision: Image analysis with Python code execution for
bounding boxes, annotations, and visual reasoning
- URL Context: Live web page content fetching and analysis
Tools are passed through using the same pattern as google_search:
- code_execution: {} -> codeExecution: {}
- url_context: {} -> urlContext: {}
Tested with Gemini 3 Flash Preview agentic vision successfully.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
feat(translator): improve system message handling and content indexing across translators
- Updated logic for processing system messages in `claude`, `gemini`, `gemini-cli`, and `antigravity` translators.
- Introduced indexing for `systemInstruction.parts` to ensure proper ordering and handling of multi-part content.
- Added safeguards for accurate content transformation and serialization.
This change removes the translation logic for several non-standard, proprietary extensions used to configure thinking/reasoning. Specifically, support for `extra_body.google.thinking_config` and the Anthropic-style `thinking` object has been dropped from the OpenAI request translators.
This simplification streamlines the translators, focusing them on the standard `reasoning_effort` parameter. It also removes the need to look up model information from the registry within these components.
BREAKING CHANGE: Support for non-standard thinking configurations via `extra_body.google.thinking_config` and the Anthropic-style `thinking` object has been removed. Clients should now use the standard `reasoning_effort` parameter to control reasoning.
When streaming responses with tool calls, the finish_reason was being
overwritten. The upstream sends functionCall in chunk 1, then
finishReason: STOP in chunk 2. The old code would set finish_reason
from every chunk, causing "tool_calls" to be overwritten by "stop".
This broke clients like Claude Code that rely on finish_reason to
detect when tool calls are complete.
Changes:
- Add SawToolCall bool to track tool calls across entire stream
- Add UpstreamFinishReason to cache the finish reason
- Only emit finish_reason on final chunk (has both finishReason + usage)
- Priority: tool_calls > max_tokens > stop
Includes 5 unit tests covering:
- Tool calls not overwritten by subsequent STOP
- Normal text gets "stop"
- MAX_TOKENS without tool calls gets "max_tokens"
- Tool calls take priority over MAX_TOKENS
- Intermediate chunks have no finish_reason
Fixes streaming tool call detection for Claude Code + Gemini models.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Enhanced node structure by including `thoughtSignature` for inline data parts in Gemini OpenAI, Gemini CLI, and Antigravity request handlers to improve traceability of thought processes.
fix(antigravity): validate function arguments before serialization
Ensure `function.arguments` is a valid JSON before setting raw bytes, fallback to setting as parameterized content if invalid.
feat: handle array input for system instructions in translators
Enhanced Gemini, Gemini-CLI, and Antigravity translators to process array content for system instructions. Adds support for assigning roles and handling multiple content parts dynamically.
Optimized the handling of JSON serialization and deserialization by replacing redundant `json.Marshal` and `json.Unmarshal` calls with `sjson` and `gjson`. Introduced a `marshalJSONValue` utility for compact JSON encoding, improving performance and code simplicity. Removed unused `encoding/json` imports.
Refactors the reasoning effort conversion logic for Gemini models.
The update specifically addresses how `reasoning_effort` is translated into Gemini 3 specific thinking configurations (`thinkingLevel`, `includeThoughts`) and ensures that numeric budgets are not incorrectly applied to level-based models.
Changes include:
- Differentiating conversion logic for Gemini 3 models versus other models.
- Handling `none`, `auto`, and validated thinking levels for Gemini 3.
- Maintaining existing conversion for models not using discrete thinking levels.
Move OpenAI `reasoning_effort` -> Gemini `thinkingConfig` budget logic into
shared helpers used by Gemini, Gemini CLI, and antigravity translators.
Normalize Claude thinking handling by preferring positive budgets, applying
budget token normalization, and gating by model support.
Always convert Gemini `thinkingBudget` back to OpenAI `reasoning_effort` to
support allowCompat models, and update tests for normalization behavior.
- Updated `antigravity_openai_request.go` to process non-JSON outputs gracefully by verifying and distinguishing between JSON and plain string formats.
- Ensured proper assignment of parsed or raw response to `functionResponse`.
- Updated handling of `thoughtSignature` across all translator modules to retain other content payloads if present.
- Adjusted logic for `thought_signature` and `inline_data` keys for consistent processing.
- Refactored response translation logic to support mixed content types (`input_text`, `output_text`, `input_image`) with better role assignments and part handling.
- Added image processing logic for embedding inline data with MIME type and base64 encoded content.
- Updated Antigravity request conversion to replace Gemini CLI references for consistency.
- Introduced request and response translation functions to enable compatibility between OpenAI Chat Completions API and Antigravity.
- Registered translation utilities for both streaming and non-streaming scenarios.
- Added support for reasoning content, tool calls, and metadata handling.
- Established request normalization and embedding for Antigravity-compatible payloads.
- Added new fields to `Params` struct for better tracking of finish reasons, usage metadata, and tool usage.
- Refactored handling of response transitions, final events, and state-driven logic in `ConvertAntigravityResponseToClaude`.
- Introduced `appendFinalEvents` and `resolveStopReason` helper functions for cleaner separation of concerns.
- Added `TotalTokenCount` field to `Params` struct for enhanced token tracking.
- Updated token count calculations to fallback on `TotalTokenCount` when specific counts are missing.
- Introduced `hasNonZeroUsageMetadata` function to validate presence of token data in `usage_metadata`.
