Commit Graph

73 Commits

Author SHA1 Message Date
dongjiang 78044d0df3 fall back to static model list only for non-models payloads (#10189)
Signed-off-by: dongjiang <dongjiang1989@126.com>
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
2026-08-03 14:36:09 +00:00
Wolfe-James 10df80e409 fix(anthropic): add claude-sonnet-5 and claude-fable-5 to known models list (#10865)
Co-authored-by: Wolfe-Jam <wolfejam77@gmail.com>
2026-08-03 09:39:33 -04:00
dependabot[bot] 058d5e9e3f chore(deps): bump pem from 3.0.6 to 4.0.0 (#10853)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-31 16:53:26 -04:00
Lee-Si-Yoon 6a6d56fc0e feat(provider): add Friendli as declarative provider (#10762) 2026-07-31 11:57:01 -04:00
Jared Manfredi d982860222 fix: honor timeout_seconds on the Anthropic declarative provider (#10440) 2026-07-31 11:21:56 +00:00
Aaron Alaniz ee5e5f17b2 fix(cerebras): preserve thinking inline for models that reject reasoning_content (#10774) 2026-07-30 21:39:44 +00:00
jonathan MERCIER a6420ea34b Add Azure AI Foundry multi-LLM provider (#10622)
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com>
2026-07-30 15:14:26 +00:00
Michael Neale 866d3e4e47 fix(together): parse model list response (#10576) 2026-07-30 10:37:58 -04:00
Vincenzo Palazzo 4a3e70c4dc fix(providers): refresh Moonshot model list with current Kimi lineup (#10696)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-07-29 09:54:52 -04:00
github-actions[bot] 404cd28d15 chore(release): bump version to 1.45.0 (minor) (#10750)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com>
2026-07-29 13:03:40 +00:00
Abhijay Jain 4db6f25a4d fix(providers): update DeepSeek model names to v4 API (#10729) 2026-07-27 16:30:23 -04:00
Michael Neale 305849b717 chore: opus5 support (including adaptive thinking) (#10686)
Co-authored-by: Michael Neale <14976+michaelneale@users.noreply.github.com>
2026-07-27 00:37:18 +00:00
Douwe Osinga d17d65f2f3 feat: support latest Gemini models (#10630)
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
2026-07-23 16:10:45 +00:00
Jack Amadeo e43ed3a6fd enhance the uniffi API layer (#10427) 2026-07-22 18:48:30 +00:00
Alex Hancock 248999c55f Add declarative Sakana AI provider for the OpenAI-compatible Fugu API (#10357) 2026-07-17 17:57:43 +00:00
Lifei Zhou dae512010a chore: remove unused utoipa ToSchema derives (#10505) 2026-07-16 08:58:17 +00:00
Sheikh Limon 3d893a3850 fix(provider): add MiniMax-M3 and missing M2.7 variants to minimax provider (#10431)
Signed-off-by: sheikhlimon <sheikhlimon404@gmail.com>
2026-07-15 11:38:28 -04:00
Ben Godfrey f47cebf855 feat(metamodels): Add support for Muse Spark 1.1 via the Meta Models API (#10432) 2026-07-14 12:55:42 -04:00
Angie Jones 6e8f7108d5 Add GPT-5.6 support (#10384)
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com>
2026-07-14 12:10:36 +00:00
Aaron Alaniz 7e95db9c0c chore: remove unavailable models from cerebras catalog (#10407) 2026-07-13 02:33:13 +00:00
elbatoony b7eb1e9735 feat(ovhcloud): add Qwen3.6-27B model (262K context, \$0.47/\$3.19 pe… (#10339)
Co-authored-by: Anthony LEBAS <alebas@cram.fr>
2026-07-10 00:53:09 +00:00
Michael Neale 0eabb6ecc1 Add GPT-5.6 family support (#10349) 2026-07-09 18:35:46 +00:00
Rob Gray 12f80edee6 feat(providers): add OllamaCloudProvider with dynamic model discovery and context limits (#10264)
Co-authored-by: Angie Jones <jones.angie@gmail.com>
2026-07-08 03:48:55 +00:00
Angie Jones 65eed51555 Disable thinking preservation for Groq (#10284) 2026-07-06 03:44:59 +00:00
Jack Amadeo 8e18f07487 move google provider into goose-providers (#10216) 2026-07-06 01:51:36 +00:00
Jack Amadeo 140158c756 add provider bindings MVP to goose-sdk, and add python wheel publishing (#10208) 2026-07-06 01:15:54 +00:00
Jack Amadeo 3eb9f50ae5 move snowflake (#10218) 2026-07-05 21:51:01 +00:00
filip 9b837f1a46 feat: per-message usage/cost tracking with derived session totals (#10172)
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
2026-07-05 16:39:10 -04:00
Jack Amadeo c82c431c70 move databricks providers into goose-providers crate (#10162) 2026-07-02 16:18:57 +00:00
Jack Amadeo 3254eed181 Move declarative definitions (#10167) 2026-07-02 16:09:20 +00:00
Jasper ba6fb2b56d Refactor local inference provider crates (#10169) 2026-07-02 08:51:53 +00:00
石岳峰 dbc1f88ca7 fix(providers): add claude-sonnet-5 to canonical model registry (#10183)
Co-authored-by: syf2211 <syf2211@users.noreply.github.com>
2026-07-02 06:10:35 +00:00
yyy33 9165e2738f fix: tolerate partial Responses output items (#10108) 2026-07-01 19:56:57 +00:00
Osraka 2d47d1feea fix(providers): unescape shell-escaped image paths (#10098) 2026-07-01 19:56:52 +00:00
Jack Amadeo b6349b5125 add declarative provider support to goose-providers crate (#9992) 2026-07-01 16:40:49 +00:00
Lucas Kim e8891b7bb0 fix(bedrock): send inference config (max_tokens, temperature) on Converse (#9889)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
2026-06-30 22:59:40 +00:00
Kyle E DeFreitas c45f757c9d fix(providers): don't retry deterministically-permanent 400s (thinking-block immutability) (#10005)
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
2026-06-30 21:15:41 +00:00
Rodolfo Olivieri d056c72a2c fix(deps): downgrade pkcs8 to v0.10 to match sec1/pkcs1 v0.7 (#10119)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-30 21:15:38 +00:00
Lucas Alvares Gomes a90430e8e5 Make OpenAI Responses API store param configurable (#10040)
Signed-off-by: Lucas Alvares Gomes <lucasagomes@gmail.com>
2026-06-30 20:00:12 +00:00
github-actions[bot] f1a97fde83 chore(release): bump version to 1.40.0 (minor) (#10099)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com>
2026-06-30 18:15:28 +00:00
Jack Amadeo b806204887 move ollama provider into goose-providers (#9986) 2026-06-30 17:28:45 +00:00
filip d43c692127 perf(providers): keep turn-context out of the Anthropic prefix cache (#10030) 2026-06-30 05:09:37 +00:00
Jack Amadeo fe7f16b727 Remove session_id from provider streaming trait methods (#9984) 2026-06-29 22:04:58 +00:00
lunchboxfortwo a1711e75e2 fix(providers): reject non-object tool-call arguments instead of panicking (#9832)
Signed-off-by: Lunchbox <lunchboxfortwo@gmail.com>
Signed-off-by: Douwe M Osinga <douwe@sidewalklabs.com>
Signed-off-by: Goose <goose@aaif.dev>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
Co-authored-by: Goose <goose@aaif.dev>
Co-authored-by: Michael Neale <michael.neale@gmail.com>
2026-06-29 04:08:19 +00:00
Bradley Axen d1d2166190 Support streamed tool calls without indexes (#10023) 2026-06-26 16:09:11 +00:00
Jack Amadeo 854fed5e5d move anthropic provider into goose-providers (#9985) 2026-06-25 23:00:08 +00:00
Theofanis Petkos 0c9acc33c9 fix(providers): Buffer thinking across stream chunks for DeepSeek/Kimi tool calls (#9704)
Signed-off-by: thepetk <thepetk@gmail.com>
2026-06-24 18:46:02 +00:00
Vincenzo Palazzo 63d1456b3b Fix: surface actionable errors for truncated tool-call arguments (#9946)
Co-authored-by: goose <noreply@aaif.ai>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
2026-06-24 14:53:58 -04:00
Jack Amadeo 35711b8691 provider refactor: don't require a model config to create a provider (#9953)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-06-23 23:18:07 +00:00
Jude Edwards a25f9e94d3 fix(cost): resolve databricks_v2 pricing and surface cost in standard usage update (#9925)
Co-authored-by: Douwe M Osinga <douwe@sidewalklabs.com>
2026-06-23 20:19:14 +00:00