- Moved `parallel_tool_calls` and `tool_choice` logic inside conditional handling for `chatCompletionsTools`.
- Eliminated redundant field updates to streamline payload processing.
Closes: #4491
- Added tests to ensure no-copy payload reuse for various translators (Codex, Gemini, OpenAI, Claude, etc.).
- Covered scenarios for field normalization, tool parameter cleaning, and thought signature sanitization.
- Included a benchmark for SanitizeGeminiRequestThoughtSignatures with large normalized payloads.
- Introduced field normalization functions (`setCodexRequiredBool`, `setCodexRequiredInclude`) to ensure correct Codex input structure.
- Added tests for normalized payload reuse and field validation in `ConvertOpenAIResponsesRequestToCodex`.
- Implemented `deleteCodexRequestFields` utility to remove unsupported fields dynamically.
- Added benchmarks for normalized payload processing to measure performance across different payload sizes.
Closes: #4362
- Added `NormalizeOpenAIFileData` utility to parse and validate file content, ensuring proper MIME type handling and base64 extraction.
- Refactored translation logic to use normalized file data for Gemini, Antigravity, and Interactions processors.
- Introduced comprehensive unit tests for both valid and invalid file data scenarios across all translators.
Fixed: #4416
- Updated `ConvertOpenAIResponsesRequestToOpenAIChatCompletions` to include namespaces when generating function names for tool calls.
- Added test case to validate namespace qualification logic for function call histories.
Fixed: #4423
- Added conditional logic to append `content_block_start` for empty responses, ensuring correct event flow.
- Updated default `responseJSON` structure to use an empty array (`[]`) for the `content` field instead of `null`.
Fixed: #4431
- Refactored state management to introduce deterministic output indexing for reasoning, messages, and function calls.
- Added new structures `MessageItems` and `ReasoningItems` to aggregate responses with consistent indices.
- Updated OpenAI response generation to include `output_index` for all outputs, ensuring correct order and no gaps.
- Enhanced tests to validate contiguous output indices and response event lifecycle.
Fixed: #4429
- Updated `codex_claude_request` to set the service tier as "priority" when `speed` is "fast".
- Enhanced request template generation logic to reflect dynamic service tier evaluation.
Closes: #4349
- Enhanced response handling to support `response.incomplete` events across translator components and executors.
- Refactored `resultErrorFromError` to centralize error conversion and consolidate repeated logic for constructing custom errors.
- Updated handling of `max_output_tokens` and similar terminal reasons in OpenAI and Gemini translator workflows.
- Introduced `IsRequestScoped` and `IsRequestScopedError` to differentiate between request-scoped and non-request-scoped errors.
- Added comprehensive test cases for incomplete responses, terminal failures, and error propagation in both streaming and non-streaming conditions.
Closes: #3055
- Replaced per-item `sjson.SetRawBytes(out, "system.-1"/"messages.-1", ...)` appends, which reparsed and rewrote the growing output document on every conversation item, causing O(n^2) work on long histories.
- Collected system and message blocks into slices and wrote each array once via `common.JoinRawArray`, moving the cache_control post-processing and system-only fallback turn onto the collected slices.
- Replaced per-item `sjson.SetRawBytes(out, "input.-1"/"messages.-1", ...)` appends, which reparsed and rewrote the growing output document on every conversation item, causing O(n^2) work on long histories.
- Applied the same approach to both interactions translation directions and the OpenAI Responses to Chat Completions path.
- Introduced `SanitizedFunctionNameMap` and `DisambiguatedToolNameMap` for consistent mapping between sanitized and original tool names.
- Added collision handling with deterministic hash suffixes for name disambiguation within character limits.
- Implemented logic to deduplicate and map tool and function names across translator components, including Interactions, Claude, and Gemini.
- Updated test cases to validate name restoration, deduplication, disambiguation, and mapping behaviors.
Closes: #4244
- Introduced support for custom tool calls in request serialization, including preservation of call IDs, input, and output.
- Enhanced tool call batching logic to handle ambiguous, missing, and reused call IDs across assistant messages.
- Updated processing of tool call outputs to ensure proper matching with pending calls and introduced synthesized IDs when necessary.
- Added extensive test cases to validate behavior for custom tool call histories, mixed call types, and edge cases with ambiguous or orphaned IDs.
Closes: #4256
- Added support for reasoning content in assistant messages with proper serialization of `thought`, `thoughtSignature`, and content parts.
- Ensured empty assistant messages and invalid function calls are skipped during request generation.
- Enhanced compatibility by adding test cases for preserving reasoning content, tool calls, and visible assistant content in `ConvertOpenAIRequestToGemini` and `ConvertOpenAIRequestToAntigravity`.
Closes: #4304
Preserve include=reasoning.encrypted_content, cache reasoning+assistant message
for store:false multi-turn, and accept Grok thinking signatures on Claude→Codex
for grok targets.
Harden replay cache: blob-level reasoning filter, never double-inject assistant
when history has a last message, isolate session keys by downstream API key,
clear cache on non-replayable completed turns, and normalize refusal parts.
- Enhanced `convertResponsesCustomToolToOpenAIChat` to handle custom tool overrides with qualified names.
- Added namespace child consolidation logic for tools.
- Updated `responsesCustomToolNames` to include namespace-aware tool extraction.
- Introduced new test cases to validate namespace and custom tool transformations in both streaming and non-streaming responses.
- Introduced handling for `cache_write_tokens` in `input_tokens_details` and mapped to `cached_creation_tokens` in output.
- Added comprehensive tests to validate correct parsing, preservation, and omission of `cache_write_tokens` in both streaming and non-streaming responses.
Closes: #4197
- Added logic to convert OpenAI `max_tokens` and `max_completion_tokens` to `generationConfig.maxOutputTokens`.
- Implemented unit tests to validate proper mapping behavior, including precedence of `max_tokens` over `max_completion_tokens`.
Closes: #4108
- Introduced `AttachCacheControl` and `AttachMessageCacheControl` utilities for consistent cache control injection in content parts and messages.
- Updated Claude translator modules to preserve and apply cache control metadata for responses, messages, tools, and parts.
- Added unit tests to validate proper cache control behavior across multiple scenarios.
Closes: #4146
- Consolidated thinking content block handling for improved clarity and efficiency.
- Unified `generationConfig` handling, including normalization of `thinkingConfig` settings.
- Added `applyOpenAIThinkingCompatibilityToAntigravity` for consistent reasoning and thought configuration compatibility.
Closes: #4067
- Added `applyResponsesToolResultContent` to process and structure tool response content.
- Introduced conversion logic for text, image, and file parts in tool responses.
- Updated tests to validate correct handling of data URL images in tool response outputs.
Closes: #4116
- Introduced API handlers and executor logic for Google Interactions
- Added request and response transformations for OpenAI and Claude Interactions.
- Integrated Gemini API with Interactions support.
- Updated tests to validate Interactions request parsing and error handling.
- Refactored translator logic for Interactions data flows.
Enhance reasoning content retrieval by falling back to 'reasoning' if 'reasoning_content' is absent or empty.
In some selfhosted openai-like server serving deepseek, the response.delta may contains reasoning rather than reasoning_content. So the client like codex does not recognize the thinking process.
Recognize model-visible output_text even when message.role is user, accept
assistant string content, and preserve raw merged text without trimming.
Always merge the adjacent visible item into native Gemini reasoning turns so
trailing output is not dropped by prefill stripping.
Build Gemini-native model contents for reasoning items when the routed model
uses the Gemini signature provider: thought summary on a thought part and the
replay signature on the adjacent visible part. Merge following assistant
visible text when it is not trailing prefill, and keep reasoning history when
stripping trailing model-authored prefill.
Extend Responses translator tests for signature compatibility and Antigravity
wrapper coverage; clarify stale replay signature expectations in executor tests.
- Added `ClaudeMessageSystemReminderText` to convert system content into user-readable reminder text.
- Updated translators (Antigravity, Gemini, Codex, OpenAI) to wrap `system` roles as reminders with `<system-reminder>` tags.
- Adjusted related test cases to validate reminder wrapping logic.
- Added tests for `ConvertOpenAIRequestToAntigravity` and `ConvertOpenAIRequestToGemini` to verify skipping of empty text parts while maintaining non-null structure.
- Refactored part index logic to correctly handle placement of replay parts in `antigravity_reasoning_replay`.
- Introduced helper functions `antigravityExistingReplayPartPath` and `antigravityReplayPartWritePath` for consistent replay part path management.
- Updated `ConvertOpenAIRequestToGemini` to process `video_url` message types, extracting and embedding video metadata (MIME type and base64 data) into Gemini request parts.
- Added corresponding unit tests to validate `video_url` handling, ensuring proper extraction and data preservation.
Closes: #3920
- Updated `ConvertGeminiRequestToClaude`, `ConvertGeminiRequestToCodex`, and their respective response counterparts to include logic for retaining and using tool/call IDs when present from gateway-provided inputs.
- Enhanced pairing logic between function calls and responses to handle custom and auto-generated IDs consistently.
- Introduced tests validating ID preservation and proper behavior in both streaming and non-streaming flows.
Closes: #3878
- Updated `ConvertGeminiRequestToOpenAI` to consume `tool_call_id`s in FIFO order, ensuring consistent mapping between calls and responses.
- Added fallback logic for unmatched or extra function responses to generate unique `tool_call_id`s with a `call_` prefix.
- Introduced comprehensive unit tests to validate order enforcement, distinct ID assignment, and fallback behavior.
Closes: #3874
- Applied `CleanJSONSchemaForGemini` to ensure compatibility by removing unsupported fields and cleaning schema requirements.
- Added test cases to validate schema transformation, ensuring only necessary `required` fields are retained.
- Enhanced both request and response flows to consistently clean and sanitize tool parameter schemas.
Closes: #3863
- Introduced `BenchmarkConvertSystemRoleToDeveloperLargeInput` to evaluate performance on various input sizes and configurations.
- Improved `convertSystemRoleToDeveloper` logic to optimize JSON rebuilding and reduce unnecessary operations.
- Created helper `makeLargeResponsesInputForBenchmark` to generate test data for performance scenarios.
Closes: #3751
- Implemented `applyOpenAIResponsesTextFormatToGemini` to handle `json_object` and `json_schema` formats.
- Updated generation config to set appropriate `responseMimeType` and optional `responseJsonSchema`.
- Introduced unit tests to validate correct handling of `text.format` conversion scenarios.
Closes: #3721
- Updated `ConvertCodexResponseToClaude` to delay emitting `function_call` start events until the `name` field is resolved.
- Introduced `pendingCodexFunctionCall` for buffering incomplete function calls.
- Added tests to ensure proper behavior for deferred starts, including argument buffering and finalization.
Closes: #3471
- Updated `ConvertOpenAIRequestToGemini` and `ConvertOpenAIRequestToCodex` to handle `input_audio`, retaining `data` and `format` fields.
- Added helper `openAIInputAudioMimeType` for determining MIME types from audio formats.
- Introduced unit tests to validate correct preservation of `input_audio` data and format.
Closes: #3447
- Enhanced `ConvertOpenAIResponsesRequestToOpenAIChatCompletions` to include `reasoning_content` in assistant and tool call messages.
- Introduced `collectOpenAIResponsesReasoningContent` for aggregating reasoning summaries.
- Added tests to validate reasoning attachment in various scenarios, including empty reasoning, tool calls, and reasoning followed by user messages.
Closes: #3397
Luis Pater