Commit Graph

76 Commits

Author SHA1 Message Date
hkfires
199cf480b0 refactor(thinking): remove support for non-standard thinking configurations
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.
2026-01-15 19:32:12 +08:00
hkfires
ed8b0f25ee fix(thinking): use LookupModelInfo for model data 2026-01-15 13:06:41 +08:00
hkfires
6e4a602c60 fix(thinking): map reasoning_effort to thinkingConfig 2026-01-15 13:06:40 +08:00
hkfires
0b06d637e7 refactor: improve thinking logic 2026-01-15 13:06:39 +08:00
Luis Pater
8f8dfd081b Merge pull request #850 from can1357/main
feat(translator): add developer role support for Gemini translators
2026-01-05 11:27:24 +08:00
Luis Pater
8edbda57cf feat(translator): add thoughtSignature to node parts for Gemini and Antigravity requests
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.
2026-01-05 09:25:17 +08:00
can1357
6762e081f3 feat(translator): add developer role support for Gemini translators
Treat OpenAI's "developer" role the same as "system" role in request
translation for gemini, gemini-cli, and antigravity backends.
2026-01-03 21:01:01 +01:00
Luis Pater
33e53a2a56 fix(translators): ensure correct handling and output of multimodal assistant content across request handlers 2025-12-26 05:08:04 +08:00
TinyCoder
a7fc2ee4cf refactor(image): avoid using json.Marshal 2025-12-25 14:21:01 +07:00
TinyCoder
671558a822 fix(openai): add index field to image response for LiteLLM compatibility
LiteLLM's Pydantic model requires an index field in each image object.
Without it, responses fail validation with "images.0.index Field required".
2025-12-24 17:43:31 +07:00
Luis Pater
66769ec657 fix(translators): update role from tool to user in Gemini and Gemini-CLI requests 2025-12-24 04:24:07 +08:00
Luis Pater
4e572ec8b9 fix(translators): handle string system instructions in Claude translators
Updated Antigravity, Gemini, and Gemini-CLI translators to process `systemResult` of type `string` for system instructions. Ensures properly formatted JSON with dynamic content assignment.
2025-12-23 08:44:36 +08:00
Luis Pater
5106caf641 Fixed: #654
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.
2025-12-23 02:24:26 +08:00
Luis Pater
a86d501dc2 refactor: replace json.Marshal and json.Unmarshal with sjson and gjson
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.
2025-12-22 11:44:06 +08:00
Luis Pater
453e744abf Fixed: #642
fix: remove unsupported fields `type` and `cache_control` across translators
2025-12-21 03:38:38 +08:00
Luis Pater
ffdfad8482 Fixed: #551
fix(translator): standardize content node handling across translators for assistant and tool calls
2025-12-17 13:16:07 +08:00
hkfires
716aa71f6e fix(thinking): centralize reasoning_effort mapping
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.
2025-12-15 09:16:14 +08:00
hkfires
e8976f9898 fix(thinking): map budgets to effort for level models 2025-12-15 09:16:14 +08:00
hkfires
a89514951f fix(claude): prevent final events when no content streamed 2025-12-10 22:19:55 +08:00
Luis Pater
1249b07eb8 feat(responses): add unique identifiers for responses, function calls, and tool uses 2025-12-10 16:02:54 +08:00
hkfires
9b202b6c1c fix(executor): centralize default thinking config 2025-12-09 21:05:06 +08:00
hkfires
5b6d201408 refactor(translator): remove thinking budget normalization across all translators 2025-12-09 21:05:06 +08:00
Luis Pater
7a628426dc Fixed: #433
refactor(translator): normalize finish reason casing across all OpenAI response handlers
2025-12-07 01:48:24 +08:00
Luis Pater
c8cee547fd **fix(translator): ensure partial content is retained while skipping encrypted thoughtSignature**
- 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.
2025-11-27 00:52:17 +08:00
Luis Pater
ddb0c0ec1c **fix(translator): reintroduce thoughtSignature bypass logic for model parts**
- Restored `thoughtSignature` validator bypass for model-specific parts in Gemini content processing.
- Removed redundant logic from the `executor` for cleaner handling.
2025-11-23 20:52:23 +08:00
hkfires
1061354b2f fix: handle empty and non-JSON SSE chunks safely 2025-11-22 13:49:23 +08:00
hkfires
c29931e093 fix(translator): ignore empty JSON chunks in OpenAI responses 2025-11-22 13:09:16 +08:00
hkfires
b05cfd9f84 fix(translator): include empty text chunks in responses 2025-11-22 13:03:50 +08:00
hkfires
dc8d3201e1 feat(translator): support image size and googleSearch tools 2025-11-22 10:36:52 +08:00
hkfires
abc2465b29 fix(gemini-cli): ignore thoughtSignature and empty parts 2025-11-21 17:12:56 +08:00
Luis Pater
2d84d2fb6a **feat(auth, executor, cmd): add Antigravity provider integration**
- Implemented OAuth login flow for the Antigravity provider in `auth/antigravity.go`.
- Added `AntigravityExecutor` for handling requests and streaming via Antigravity APIs.
- Created `antigravity_login.go` command for triggering Antigravity authentication.
- Introduced OpenAI-to-Antigravity translation logic in `translator/antigravity/openai/chat-completions`.

**refactor(translator, executor): update Gemini CLI response translation and add Antigravity payload customization**

- Renamed Gemini CLI translation methods to align with response handling (`ConvertGeminiCliResponseToGemini` and `ConvertGeminiCliResponseToGeminiNonStream`).
- Updated `init.go` to reflect these method changes.
- Introduced `geminiToAntigravity` function to embed metadata (`model`, `userAgent`, `project`, etc.) into Antigravity payloads.
- Added random project, request, and session ID generators for enhanced tracking.
- Streamlined `buildRequest` to use `geminiToAntigravity` transformation before request execution.
2025-11-21 12:43:16 +08:00
Ben Vargas
ede4471b84 feat(translator): add default thinkingConfig for gemini-3-pro-preview
Match official Gemini CLI behavior by always sending default
thinkingConfig when client doesn't specify reasoning parameters.

- Set thinkingBudget=-1 (dynamic) for gemini-3-pro-preview
- Set include_thoughts=true to return thinking process
- Apply to both /v1/chat/completions and /v1/responses endpoints
- See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
2025-11-19 12:47:39 -07:00
Luis Pater
7a8e00fcea **fix(translator): handle missing parameters in Gemini tool schema gracefully** 2025-11-19 13:19:46 +08:00
Luis Pater
89771216a1 **feat(translator): add ThoughtSignature handling in Gemini request transformations** 2025-11-19 11:34:13 +08:00
Luis Pater
e5e985978d Fixed: #263
**fix(translator): remove input_examples from tool schema in Gemini-Claude requests**
2025-11-18 11:27:48 +08:00
hkfires
d60040b222 fix(translator): accept camelCase thinking config in OpenAI→Gemini 2025-11-07 16:45:31 +08:00
Luis Pater
2a73d8c4a3 fix(translator): simplify tool response handling and adjust JSON schema updates in Gemini modules 2025-11-05 22:48:50 +08:00
hkfires
a53c84d0d1 feat(gemini): apply default safety settings across request translators 2025-10-31 08:22:16 +08:00
Luis Pater
af3fbd134d fix(translator): remove strict key from function declaration to prevent errors during schema transformation 2025-10-30 13:14:26 +08:00
hkfires
5cb378256b feat(gemini-translators): set include_thoughts when mapping thinking 2025-10-29 19:19:18 +08:00
hkfires
3ac5f05e8c feat(gemini): prefer official reasoning fields, add extra_body(cherry studio) fallback 2025-10-29 19:19:18 +08:00
hkfires
2a3ee8d0e3 fix(translators): normalize thinking budgets 2025-10-29 19:19:17 +08:00
hkfires
41577bce07 feat(claude): map Anthropic 'thinking' to Gemini thinkingBudget 2025-10-29 19:19:17 +08:00
hkfires
680b3f5010 fix(translator): avoid default thinkingConfig in Gemini requests 2025-10-29 19:19:17 +08:00
Luis Pater
0defb68c6c fix(translator): improve error handling for function parameters schema transformation
- Added fallback to set default `parametersJsonSchema` when `parameters` key is absent.
- Enhanced logging to capture detailed errors during schema transformation.
- Refined tool declaration appending logic for robustness.
2025-10-28 22:57:26 +08:00
hkfires
7061cd6058 fix(gemini): map responseModalities to uppercase IMAGE/TEXT 2025-10-26 19:35:22 +08:00
Luis Pater
4477c729a4 Fixed: #129 #123 #102 #97
feat: add all protocols request and response translation for Gemini and Gemini CLI compatibility
2025-10-17 02:11:29 +08:00
Luis Pater
0d89a22aa0 feat: add handling for function call finish reasons in OpenAI response conversion 2025-10-17 00:19:32 +08:00
Luis Pater
11f090c223 Fixed #102
feat(translator): add support for removing `strict` in Gemini request transformation

- Updated API and CLI translators to remove the `strict` path during request transformation, in addition to existing predefined JSON paths.
2025-10-10 02:59:21 +08:00
hkfires
01be94a0de feat(translator): Map OpenAI modalities to Gemini responseModalities 2025-10-09 19:38:07 +08:00