Commit Graph

83 Commits

Author SHA1 Message Date
Dax Raad 91fa6a804d core: fix message caching for Anthropic models to improve response consistency 2025-12-15 14:33:14 -05:00
René e9e1f3302e Provider fix, anthropic Errorhandling if empty image file is read (#5521) 2025-12-14 23:56:47 -06:00
Aiden Cline e3bd8cd9ed tweak: fallback to provider default for temperature 2025-12-14 11:57:12 -06:00
Aiden Cline 627534a90b add topK function to transform, add temp defaults for glm and minimax 2025-12-13 23:27:11 -06:00
Aiden Cline c753868778 chore: reduce duplication of field in transform 2025-12-13 18:07:22 -06:00
Aiden Cline 3801c02db8 tweak: 5.1 -> 5. in transform 2025-12-12 15:17:11 -06:00
Aiden Cline 0474f3bba4 tweak: 5.1 -> 5. reasoning effort match 2025-12-12 13:21:57 -06:00
Aiden Cline ce4aad9b5c tweak: setting chat_template_args in transform 2025-12-11 16:22:10 -06:00
Aiden Cline 79d682c1f9 ignore: tmp transform exclusion 2025-12-10 21:18:19 -06:00
Aiden Cline 96397dc1ef tweak: correct thinkingLevel 2025-12-10 21:13:10 -06:00
Aiden Cline d9f443d333 more interleaved thinking fixes (#5334) 2025-12-10 13:29:26 -06:00
Aiden Cline 1cb69581b4 tweak: set gemini thinkingLevel to high by default 2025-12-10 13:09:27 -06:00
Tom Aylott 15b0da75e1 fix: upgrade OpenRouter sdk pkg (#5302)
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-12-10 13:02:26 -06:00
Aiden Cline b9ad1b09cb better interleaved thinking support (#5298) 2025-12-09 16:32:12 -06:00
Aiden Cline 14183f06c6 core: refactor providerOptions function to accept Provider.Model for cleaner API 2025-12-09 01:25:36 -06:00
Aiden Cline d38bb05c69 pdf support in read tool (#5222)
Co-authored-by: ammi1378 <ammi1378@users.noreply.github.com>
2025-12-07 21:54:00 -06:00
Jakub Matjanowski 73c6b95c7d feat: Enhance DeepSeek reasoning content handling (#4975)
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-12-03 21:31:36 -06:00
Aiden Cline 8d83815413 fix: dax typo 2025-12-03 20:39:11 -06:00
Dax 85d8825cb1 core: refactor provider and model system (#5033)
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: thdxr <thdxr@users.noreply.github.com>
2025-12-03 21:09:03 -05:00
Aiden Cline f5cdf14820 fix: sanitize more invalid schema cases for gemini models 2025-12-01 16:19:10 -06:00
Aiden Cline 0399ec2808 fix case where opencode wasn't retrying 2025-12-01 13:02:33 -06:00
Aiden Cline 2788fac2ac tweak: better err msgs 2025-12-01 01:33:32 -06:00
Dmitry Halushka 0e7c91e29e fix: transform MCP tool schemas for Google/Gemini compatibility (#4538)
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
Co-authored-by: Github Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2025-11-26 00:58:20 -06:00
Shantur Rathore e80e5b1974 config: add setCacheKey in provider options (#4738)
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2025-11-25 17:53:56 -06:00
Aiden Cline 90d38a69dc Revert "config: add setCacheKey in provider options (#4654)"
This reverts commit 3617f90c73.
2025-11-24 22:30:56 -06:00
Shantur Rathore 3617f90c73 config: add setCacheKey in provider options (#4654)
Co-authored-by: GitHub Action <action@github.com>
2025-11-24 22:20:52 -06:00
Aiden Cline 37fa3dd61b bump copilot plugin, give better error message for copilot (#4678) 2025-11-24 00:40:15 -06:00
Dax Raad 7747652bf6 summary optimizaitons 2025-11-22 11:32:49 -05:00
Frank f0de3764c0 update logic for local and dev providers 2025-11-21 13:31:33 -05:00
Dax e9141bf5cd Tui onboarding (#4569)
Co-authored-by: GitHub Action <action@github.com>
2025-11-21 00:21:06 -05:00
Aiden Cline db2353a33b tweak: make /export go to cwd 2025-11-19 22:45:40 -06:00
Aiden Cline d2c4bc5b50 fix: openrouter ai sdk package support 2025-11-19 14:22:51 -06:00
Tommy D. Rossi ad2963bb30 fix: show reasoning summaries for gemini models (#4491)
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-19 11:25:18 -06:00
Aiden Cline 15ca13204b tweak: use temperature 1 for gemini 3 pro 2025-11-18 11:49:39 -06:00
Aiden Cline 0d31818c43 fix: vercel gateway options 2025-11-16 18:39:31 -06:00
Aiden Cline f4ee72f295 fix: promptCacheKey set unnecessarily 2025-11-16 14:32:57 -06:00
Aiden Cline 6ef0b7201f fix: add azure exclusion 2025-11-14 11:54:00 -06:00
Aiden Cline e569a81396 set verbosity to low for gpt-5.1 (match codex) 2025-11-14 11:52:29 -06:00
Shantur Rathore 6ee3cd1a17 set promptCacheKey for openai compatible providers (#4203)
Co-authored-by: GitHub Action <action@github.com>
2025-11-14 11:41:01 -06:00
Aiden Cline 840f332700 fix: max tokens when using models like opus with providers other than anthropic (#4307) 2025-11-13 16:39:09 -06:00
GitHub Action 9855771157 chore: format code 2025-11-08 01:59:02 +00:00
Nicolai van der Smagt 0fd59de486 fix: resolve Mistral API compatibility issues (#2440)
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-06 20:05:59 -05:00
Dax Raad 5be6405521 codex tweaks 2025-11-06 19:14:01 -05:00
Nicolai van der Smagt e189c90cc0 fix: resolve Mistral API compatibility issues (#2440)
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-06 16:53:02 -06:00
Dax Raad ed8913324e big format 2025-11-06 13:03:12 -05:00
Dax Raad 5d8d65bedc do not set temperature for claude models 2025-10-28 01:14:25 -04:00
Aurelien Ribon e6c7aeb3c1 fix: dont set reasoning effort to medium for gpt-5-pro (#3474) 2025-10-27 10:50:57 -05:00
Aiden Cline d11ed02f1e fix: bedrock reasoning 2025-10-24 17:35:08 -05:00
Dax Raad 69128ae829 codex does not have reasoning effort set 2025-10-24 00:29:34 -04:00
Aiden Cline e25a4ed732 fix: provider option transforms (#3331) 2025-10-21 11:08:21 -05:00