Commit Graph

530 Commits

Author SHA1 Message Date
Lucas Alvares Gomes 501dde5570 Replace deprecated Claude ACP package links (#8625)
Signed-off-by: Lucas Alvares Gomes <lucasagomes@gmail.com>
2026-04-22 12:35:12 +00:00
g.sunilkumar 03f4bfaa99 fix(providers): handle missing delta field in streaming chunks (#8700)
Signed-off-by: sunilkumarvalmiki <g.sunilkumarvalmiki@gmail.com>
Co-authored-by: Lifei Zhou <lifei@squareup.com>
2026-04-22 09:06:45 +00:00
이대희 d18bb6e512 refactor(providers): extract http_status module and rename handle_status_openai_compat (#8620)
Signed-off-by: DaeHee Lee <lee111dae11@proton.me>
2026-04-22 08:33:26 +00:00
Sam Osborn 015b0d92d3 fix(providers/openai): accept streaming chunks with both reasoning fields (#8715)
Signed-off-by: Sam Osborn <samosborn88@gmail.com>
2026-04-22 07:35:48 +00:00
Bradley Axen ab0c40d26a fix: add strict:false to Responses API tools and gpt-5.4 to known models (#8636)
Signed-off-by: Bradley Axen <baxen@squareup.com>
2026-04-21 22:32:24 +00:00
Bradley Axen dfc5b0b803 consolidate provider ACP methods onto inventory (#8710)
Signed-off-by: Bradley Axen <baxen@squareup.com>
2026-04-21 16:19:20 +00:00
Spike Wang aa731a9596 Stop load openai fast model for openapi compatible custom endpoint (#8644) 2026-04-21 13:10:00 +00:00
Bradley Axen 8eda6fdabc overhaul provider inventory and agent/model selection (#8652)
Signed-off-by: Bradley Axen <baxen@squareup.com>
2026-04-20 15:00:17 -07:00
이대희 e74438bc8b refactor(providers): extract shared OAuth device-flow helper (#8619)
Signed-off-by: DaeHee Lee <lee111dae11@proton.me>
2026-04-20 14:41:16 +00:00
Aravind Kumar Dhodda 5205540311 fix: append /chat/completions for prefixed v1 base URLs (#8521) 2026-04-20 11:45:31 +00:00
Vincenzo Palazzo f2350f8d68 Reset ChatGPT Codex auth during OAuth setup (#8569)
Signed-off-by: Vincenzo Palazzo <vincenzopalazzodev@gmail.com>
Co-authored-by: goose <goose@aaif.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-20 11:36:20 +00:00
Michael Neale 4656d1a706 chore: adding opus 4.7 (#8614) 2026-04-18 03:20:48 +00:00
Will Pfleger 7fa662bcac feat(extensions): support Unix domain socket transport for StreamableHttp MCP (#7860) 2026-04-17 19:16:37 +00:00
이대희 afcdf2cab3 fix(kimicode): align model metadata with live Kimi Code API (#8588)
Signed-off-by: DaeHee Lee <lee111dae11@proton.me>
2026-04-17 09:53:39 +00:00
Alex fd93865951 feat: add Novita AI as declarative provider (#8432)
Signed-off-by: Alex-wuhu <yanglongwei06@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-16 12:54:31 +00:00
이대희 93e6f8d521 feat: add Kimi Code provider with OAuth device flow authentication (#8466)
Signed-off-by: DaeHee Lee <lee111dae11@proton.me>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-16 10:13:50 +00:00
Juan Palomino aa8ea99584 fix: create logs dir before writing llm request log (#8522)
Signed-off-by: Juan Palomino <jpalomino09@gmail.com>
2026-04-16 07:50:34 +00:00
Kasper Jensen a6e5d70df0 fix: enable token usage tracking and configurable stream timeout for Ollama provider (#8493) 2026-04-16 07:49:39 +00:00
Lifei Zhou a5a497b341 pass globally unique conversation identifier as sessionId in databricks api call (#8576) 2026-04-16 04:32:19 +00:00
github-actions[bot] 8e04d7c8be chore(release): bump version to 1.31.0 (minor) (#8527)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-14 14:48:16 +00:00
jh-block 65e5d97cac Improve local inference settings and model downloader (#8467)
Signed-off-by: jh-block <jhugo@block.xyz>
2026-04-14 08:50:50 +00:00
Can H. Tartanoglu d2b473f8ee feat(providers): add llama-swap declarative provider (#8462) 2026-04-13 16:45:25 +00:00
jh-block de317d5445 Add vision/image support for local inference models (#8442)
Signed-off-by: jh-block <jhugo@block.xyz>
2026-04-13 08:17:04 +00:00
Steffen Kram 501c3e8a24 fix: use api. subdomain for enterprise GitHub Copilot token URL (#8494) 2026-04-12 23:32:20 +00:00
Vincenzo Palazzo 8c3b5eb56a feat: add Ollama Cloud as a declarative provider (#8189) 2026-04-09 20:19:27 +00:00
jh-block e8cbfc55da fix: local inference provider loses thinking and fragments tool calls across turns (#8415)
Signed-off-by: jh-block <jhugo@block.xyz>
2026-04-09 09:27:31 +00:00
Bradley Axen 9d7de43eec feat(acp): introduce threads (#8344)
Signed-off-by: Bradley Axen <baxen@squareup.com>
2026-04-08 22:14:28 -07:00
jh-block 8b1007eee0 fix: correctly parse thinking content from gemma4 (#8407)
Signed-off-by: jh-block <jhugo@block.xyz>
2026-04-08 19:22:35 +00:00
Pete Gonzalez 4de4d475a4 fix: add skip_canonical_filtering to Anthropic and Ollama providers (#8349)
Signed-off-by: Pete Gonzalez <4673363+octogonz@users.noreply.github.com>
2026-04-08 15:17:45 +00:00
juanxincai 71b59805b3 fix: apply declarative provider context_limit via canonical create path (#8364)
Signed-off-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: juanxincai <zarttic@users.noreply.github.com>
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-04-08 15:10:22 +00:00
Lifei Zhou fe0adf17b7 fix: return raw text when chatparseError (#8402) 2026-04-08 11:00:56 +00:00
Lifei Zhou 0450aaa39f enable gemma 4 local model (#8366)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 09:51:57 +00:00
Lifei Zhou c4aa7f56df added x-client header in the nanogpt api call (#8368) 2026-04-07 12:51:03 +00:00
Jack Amadeo 583acd4335 chore(aaif): rename a bunch of repository references (#8152)
Signed-off-by: Michael Neale <michael.neale@gmail.com>
Co-authored-by: Michael Neale <michael.neale@gmail.com>

continuing migration to aaif
2026-04-07 15:34:48 +10:00
Bradley Axen 2c4129af56 feat(acp): add reusable ACP provider controls (#8314)
Signed-off-by: Bradley Axen <baxen@squareup.com>
2026-04-06 01:15:37 +00:00
Andrew Grigorev e94f304780 fix: use v1beta1 API version for Google/MaaS models on GCP Vertex AI (#8278)
Signed-off-by: Andrew Grigorev <andrew@ei-grad.ru>
Co-authored-by: Claude <noreply@anthropic.com>
2026-04-03 17:39:39 +00:00
Dale Lakes d18555ca62 fix: reconsolidate split tool-call messages to follow OpenAI format (#7921)
Signed-off-by: Dale Lakes <6843636+spitfire55@users.noreply.github.com>
Signed-off-by: Dale Lakes <dale.lakes55@gmail.com>
Signed-off-by: Clyde <clyde@users.noreply.github.com>
Co-authored-by: Dale Lakes <6843636+spitfire55@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Clyde <clyde@Clydes-Mac-Studio.local>
2026-04-02 14:01:38 +00:00
Ravitez Dondeti 8d4835f070 feat: add configurable fast_model for declarative providers (#8194)
Signed-off-by: rdondeti <ravitez.dondeti@gmail.com>
Signed-off-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-04-02 13:54:11 +00:00
github-actions[bot] 5a8686bb83 chore(release): bump version to 1.30.0 (minor) (#8217)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-02 10:29:55 -04:00
Lifei Zhou 03afcf1ffc add customised github copilot configuration (#8251) 2026-04-02 13:51:50 +00:00
fre$h 8c542843cd feat: add zhipu declarative provider with ZHIPU_BASE_URL override (#8204)
Signed-off-by: fre <anonwurcod@proton.me>
2026-04-02 10:40:56 +00:00
Ravitez Dondeti 26d3d3ace3 fix: use build_host_url for GCP Vertex AI location fallback (#8185)
Signed-off-by: rdondeti <ravitez.dondeti@gmail.com>
2026-03-30 15:11:36 +00:00
Douwe Osinga a7f5c6c112 fix(openai): use safely_parse_json for streaming tool arguments (#8208)
Signed-off-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-03-30 15:09:03 +00:00
Adrian Cole 764760edfb feat: add copilot-acp provider (#8154)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2026-03-30 14:15:11 +00:00
Michael Neale 38f11d84db feat: Gemini OAuth provider (#8129)
Signed-off-by: Michael Neale <michael.neale@gmail.com>
2026-03-26 21:08:51 +00:00
Extra Small 65376e011b fix: strip message wrapper in CLI session title generation (#7996)
Signed-off-by: Extra Small <littleshuai.bot@gmail.com>
2026-03-26 19:56:36 +00:00
Pete Gonzalez 27e197e467 fix(providers): fall back to configured models when models endpoint fetch fails (#7530)
Signed-off-by: Pete Gonzalez <4673363+octogonz@users.noreply.github.com>
Signed-off-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Pete Gonzalez <octogonz@users.noreply.github.com>
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-03-26 19:49:37 +00:00
fre$h 7ec07f2c79 fix: prevent Ollama provider from hanging on tool-calling requests (#7723)
Signed-off-by: fre <anonwurcod@proton.me>
Signed-off-by: fresh3nough <nicholasanthony742@gmail.com>
Signed-off-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-03-26 18:43:59 +00:00
Nick Kuhn c936514014 fix: VMware Tanzu Platform provider - bug fixes, streaming, UI improvements (#8126)
Signed-off-by: Nick Kuhn <nick.kuhn@broadcom.com>
Signed-off-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-03-26 18:16:01 +00:00
jh-block 11f46dc0e0 fix: GitHub Copilot auth fails to open browser in Desktop app (#6957) (#8019)
Signed-off-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-03-26 18:03:44 +00:00