Commit graph

4102 commits

Author SHA1 Message Date
H Lohaus
3597c48d4f
Merge branch 'main' into master 2026-02-21 12:36:32 +01:00
H Lohaus
2c6bc306cb
Update GeminiCLI.py 2026-02-21 12:31:19 +01:00
H Lohaus
a435f74971
Update Antigravity.py 2026-02-21 12:29:58 +01:00
H Lohaus
f3d8a7b31e
Update GeminiCLI.py 2026-02-21 12:27:46 +01:00
H Lohaus
3d0d969b1a
Update GithubCopilot.py 2026-02-21 12:25:29 +01:00
hlohaus
a9395404ff feat: implement quota retrieval for providers and update related methods 2026-02-20 20:58:09 +01:00
hlohaus
86203e2746 fix: correct method name for usage retrieval in Backend_Api 2026-02-20 14:01:10 +01:00
hlohaus
3f5eca67da feat: add usage retrieval methods for GitHub Copilot and Antigravity providers, update Flask dependency to async version 2026-02-20 13:55:04 +01:00
hlohaus
7461d049c9 chore: remove subproject references for g4f.dev and g4f.exe 2026-02-20 10:02:30 +01:00
H Lohaus
3810e9a7e5 Updates 2026-02-20 09:16:39 +01:00
hlohaus
0dec7d2ad6 fix: update parent class name in SharedTokenManager for consistency 2026-02-19 20:32:05 +01:00
hlohaus
54eb2bd41e feat: integrate AppConfig for API key management and environment loading across providers 2026-02-19 20:30:59 +01:00
hlohaus
d6dcb36c50 feat: add GitHub Copilot provider with conversation handling and token management 2026-02-12 16:22:00 +01:00
hlohaus
8db86ad78b feat: implement GitHub Copilot provider with OAuth authentication and token management 2026-02-12 16:21:40 +01:00
hlohaus
9cdbd36038 fix: update STATIC_URL path replacements in render function for consistency 2026-02-12 01:09:26 +01:00
hlohaus
c651a7ca52 fix: correct STATIC_URL path replacements in render function 2026-02-12 00:19:55 +01:00
hlohaus
b0a2e7bec2 fix: update HTML paths to use STATIC_URL in render function 2026-02-11 23:36:23 +01:00
hlohaus
1e39bf569e fix: update path replacements in render function for static files 2026-02-11 22:53:50 +01:00
hlohaus
2cc9404719 fix: reorder parameters in YuppAPIClient and YuppModelManager constructors 2026-02-11 22:33:31 +01:00
hlohaus
1ed7450927 fix: reorder parameters in YuppModelManager constructor and update scraper session handling 2026-02-11 22:26:21 +01:00
Tekky
19e390ae18
. 2026-02-11 14:00:38 +01:00
Marcos Vinícius Claudiano
405868c576
feat: add tool_call emulation for OpenAI API (#3352)
* feat: add tool_call emulation for OpenAI API

Avoid forcing PollinationsAI when tools are present, and add an opt-in tool_emulation mode (or G4F_TOOL_EMULATION=1) to emit OpenAI-compatible tool_calls for providers that ignore tools.

* fix: avoid duplicate stream kwarg in tool emulation

Tool emulation calls the upstream provider with stream=False; remove stream/stream_timeout from forwarded kwargs to prevent conflicts.

* fix: prefer non-auth providers when api_key missing

When routing via AnyProvider without an api_key, try providers with needs_auth=false first to reduce MissingAuthError for tool-enabled clients like MarksCode.

* test: cover tool call emulation

Route tool_emulation through ToolSupportProvider (avoid circular imports) and add unittest coverage for multi-tool JSON plans and run_tools integration.
2026-02-09 12:01:52 +01:00
H Lohaus
00966737bc
Update LMArena.py 2026-02-08 03:17:54 +01:00
hlohaus
19f4ce47d8 fix: handle TimeoutError when selecting grid element in LMArena class 2026-02-08 03:05:50 +01:00
hlohaus
0563c0c1d3 fix: await stop_browser call in GoogleSearch to ensure proper asynchronous execution 2026-02-08 02:49:04 +01:00
hlohaus
0943d16eef fix: update stop_browser calls to be asynchronous across multiple provider files 2026-02-08 02:48:54 +01:00
hlohaus
0035bc473d fix: update nodriver import to use zendriver and correct executable finder 2026-02-08 02:34:09 +01:00
hlohaus
3e3f9269cb fix: update nodriver import to use zendriver in You.py 2026-02-08 02:28:06 +01:00
hlohaus
a954617540 refactor: replace nodriver imports with zendriver across multiple provider files 2026-02-08 02:27:53 +01:00
hlohaus
3c0126b868 fix: update LMArena URLs to point to arena.ai 2026-02-08 02:17:26 +01:00
H Lohaus
19a576bdcd
Update Antigravity.py 2026-02-06 17:16:05 +01:00
hlohaus
6472b47739 feat: add CLI entry points for GeminiCLI and QwenCode providers 2026-02-06 11:25:35 +01:00
hlohaus
e4125ecae4 Add Antigravity provider and update API response handling
- Imported Antigravity provider in the needs_auth module.
- Removed login response handling from the API to streamline output.
- Added console script entry for Antigravity in setup.py.
2026-02-06 10:30:18 +01:00
Max Luecke
80edb02bf8
Implement automatic NextAction token swapping for Yupp provider (#3345)
* WIP: Implement automatic NextAction token swapping for Yupp provider

This PR adds automatic token extraction and swapping when NextAction tokens expire.

- Add token_extractor.py with multi-strategy extraction

- Add constants.py with configuration

- Integrate into Yupp.py with automatic failure detection

- Tested and verified working

* fix: Add 404 detection to token failure handlers

- Detect token failures in generic exception handler

- Improves extraction triggering for invalid/expired tokens

- Verified working with invalid token test

* refactor: Address code review feedback

- Remove unused EXTRACTION_COOLDOWN constant

- Add MIN_REQUIRED_TOKENS constant

- Fix race condition in mark_token_failed()

- Remove unused hashlib import

- Add type hints for scraper parameter

- Add debug stack trace logging for exceptions

- Fix line length issues

- Reorder imports to PEP 8

- Update docstring for get_token()

- Standardize error logging format

* style: Remove duplicate docstring and unused import

- Remove duplicate module docstring

- Remove unused 'time' import

* fix: Remove gpt-oss-120b from DeepInfra

DeepInfra no longer lists openai/gpt-oss-120b in their featured models API.

This fixes the failing test test_provider_has_model.

- Removed from DeepInfra.vision_models

- Removed from gpt_oss_120b best_provider list
2026-02-03 14:44:44 +01:00
H Lohaus
3b6bf11254
Merge pull request #3343 from aannoo/fix/openai-chat-conversation-id
fix: include conversation_id in prepare request for conversation continuity
2026-02-03 14:08:58 +01:00
aannoo
2b3a2ea70c fix: include conversation_id in prepare request for conversation continuity
The prepare request to /backend-api/f/conversation/prepare was missing
conversation_id, causing ChatGPT to always create a new conversation
even when continuing an existing one. This adds conversation_id to the
prepare payload when available, matching the main request behavior.

Fixes #2897, #3102
2026-01-30 02:18:09 +10:30
H Lohaus
20637d6004
Merge pull request #3342 from xtekky/3.14
fix: Simplify API key check and ensure conversation messages are adde…
2026-01-28 16:33:24 +01:00
hlohaus
287d89a13e fix: Simplify API key check and ensure conversation messages are added only for text responses 2026-01-28 14:27:58 +01:00
H Lohaus
fb1857240e
Merge pull request #3339 from xtekky/3.14
fix: Update Python version in CI workflow from 3.12 to 3.14
2026-01-28 14:09:40 +01:00
hlohaus
e1b7471f9f fix: Update references from 'nest_asyncio' to 'nest-asyncio2' across the codebase 2026-01-27 11:29:43 +01:00
hlohaus
f03c08d66f fix: Update Python version in CI workflow from 3.12 to 3.14 2026-01-27 11:20:56 +01:00
H Lohaus
20f0ef8575
Merge pull request #3337 from GamerReady/main
Refactor reward handling, add feedback recording, deleting yupp chats…
2026-01-27 10:39:14 +01:00
GamerReady
7f78c93f37
Only delete chats when "conversation" is not present on kwargs 2026-01-26 03:41:53 -04:00
GamerReady
f3a36e87a8
Refactor reward handling, add feedback recording, deleting yupp chats after response. 2026-01-25 23:56:20 -04:00
hlohaus
a0e20efaa5 feat: Add synthesize endpoint for text-to-speech in MCPServer 2026-01-24 09:35:26 +01:00
hlohaus
000516c357 fix: Update API key validation logic and enhance chunk handling in Backend_Api 2026-01-24 09:17:06 +01:00
hlohaus
8e52133e7f fix: Add media file handling to MCPServer with caching and conditional requests 2026-01-24 09:10:38 +01:00
hlohaus
b324f4070d fix: Load API key in PollinationsAI and Yupp providers if not provided 2026-01-24 08:40:58 +01:00
hlohaus
136cb3159d fix: Remove unused response_format parameter in ImageGenerationTool 2026-01-24 07:58:29 +01:00
hlohaus
ac1221aa76 fix: Import read_cookie_files to enable cookie handling in MCPServer 2026-01-24 07:41:32 +01:00