Commit Graph

327 Commits

Author SHA1 Message Date
Adrian Cole f5b402bbdf fix(goose): only send agent-session-id when a session exists (#6657)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2026-01-27 13:43:05 +09:00
jh-block 82ba07ff1d Speed up Databricks provider init by removing fetch of supported models (#6616) 2026-01-26 16:51:49 +01:00
Alex Hancock 8233f0afac chore: upgrade to rmcp 0.14.0 (#6674) 2026-01-23 14:52:43 -05:00
Hugues Clouâtre 346ff7ab84 Fix GCP Vertex AI global endpoint support for Gemini 3 models (#6187)
Signed-off-by: Hugues Clouâtre <hugues@linux.com>
2026-01-23 11:18:54 -05:00
Michael Neale e78a1e7d4e feat: codex subscription support (#6600)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
Co-authored-by: Adrian Cole <adrian@tetrate.io>
2026-01-23 17:11:58 +11:00
Douwe Osinga c57c2562a1 Strip the audience for compacting (#6646)
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-01-22 16:13:35 -05:00
github-actions[bot] 86b38c6a4f chore(release): release version 1.21.0 (minor) (#6634)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Zane Staggs <zane@squareup.com>
2026-01-22 12:59:51 -08:00
Adrian Cole 67de49abbb fix(goose): propagate session_id across providers and MCP (#6584)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2026-01-22 08:28:56 +08:00
Lifei Zhou f26ffed587 Lifei/fixed accumulated token count (#6587) 2026-01-22 03:27:16 +11:00
Rabi Mishra fbe46d0b22 feat(gcp-vertex): add model list with org policy filtering (#6393)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-20 11:49:10 -05:00
Zane 080a0e04ba added optional request params and context limit from GOOSE_PREDEFINED_MODELS (#6489) 2026-01-16 08:12:14 -10:00
Alex Hancock 4191826569 chore: upgrade rmcp (#6516) 2026-01-16 12:09:51 -05:00
github-actions[bot] f5753759bb Release 1.20.0
Auto-merged release PR after tag v1.20.0 was pushed
2026-01-16 15:57:28 +00:00
Lifei Zhou 9a96b84372 fixed 0 token in openrouter steaming (#6493) 2026-01-15 13:43:13 +11:00
Rabi Mishra 7b59f554d7 perf(google): avoid accumulating thoughtSignatures across conversation history (#6462)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-14 08:36:41 -05:00
Rabi Mishra a66e5d306a fix(openai): make tool_call arguments optional and fix silent stream termination (#6309)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-14 08:36:27 -05:00
Rabi Mishra bb209498d6 fix(openrouter): Handle Gemini thoughtSignature for tool calls (#6370)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-13 19:02:47 -05:00
Abhijay Jain 115bbd5491 fix: inconsistent API url requirement between desktop and CLI versions (#6419)
Signed-off-by: Abhijay007 <Abhijay007j@gmail.com>
2026-01-12 14:15:33 -05:00
Rabi Mishra b357460013 feat(vertexai): Add streaming support (#6409)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-12 14:09:18 -05:00
Douwe Osinga ba702d820f More 3.7 removal (#6414)
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-01-12 10:28:42 -05:00
Rabi Mishra a153c06aaf fix(google): treat signed text as regular content in streaming (#6400)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-09 09:41:28 -05:00
Jack Amadeo 4a60f026d5 Sort keys in canonical models (#6403) 2026-01-08 19:42:02 -05:00
Lifei Zhou 9aee76391c Handling special claude model response in github copilot provider (#6369) 2026-01-08 08:22:59 +11:00
Rabi Mishra a4c7a746a0 feat(providers): add streaming support for Google Gemini provider (#6191)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-07 14:17:12 -05:00
Douwe Osinga 463eee3f76 Claude 3.7 is out. we had some harcoded stuff (#6197)
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2026-01-06 15:50:39 -05:00
github-actions[bot] 635131d7bf Release 1.19.0
Auto-merged release PR after tag v1.19.0 was pushed
2026-01-06 20:32:50 +00:00
Jack Amadeo fb1d3dfd3d Bump rust toolchain to 1.92 (current stable) (#6356) 2026-01-06 14:13:20 -05:00
Rabi Mishra 0788f88929 feat(providers): add retry for model fetching (#6347)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-06 12:14:56 -05:00
Lifei Zhou a842c99d11 make sure the models are using streaming properly (#6331) 2026-01-06 15:28:15 +11:00
albina-popova 4a08ad5c43 fix: Make Azure OpenAI API key optional to match documentation (#6215)
Signed-off-by: albina-popova <97168987+albina-popova@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-05 13:31:28 -05:00
github-actions[bot] cabbda3dbc Release 1.18.0
Auto-merged release PR after tag v1.18.0 was pushed
2026-01-05 18:28:22 +00:00
Rabi Mishra 4aa6a176ea fix(openai): handle interleaved streaming chunks in tool call (#6312)
Signed-off-by: rabi <ramishra@redhat.com>
2026-01-05 12:13:41 +11:00
Bradley Axen f19ee33e60 feat: add caching support for Anthropic models via Databricks (#6320) 2026-01-03 17:56:37 -08:00
Bradley Axen 4e1384887c chore: refactor format_messages in databricks.rs to reduce line count (#6275) 2025-12-31 10:56:31 +11:00
Adrian Cole d1f95757cf feat(code-mode): use server names for MCP extensions (#6284)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2025-12-30 13:08:38 +08:00
Ramiro Salas 31eaa47209 feat: add OpenAI Codex CLI provider (#6263)
Signed-off-by: RamXX <ramxx@ramirosalas.com>
Co-authored-by: Michael Neale <michael.neale@gmail.com>
2025-12-29 17:01:21 +11:00
Adrian Cole 2f876725d3 test: fix recipe and audio tests to avoid side effects (#6231)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2025-12-23 10:26:34 +08:00
Alex Hancock 7134e89c4b feat: improved UX for tool calls via execute_code (#6205) 2025-12-22 10:42:20 -05:00
Adrian Cole 5942e9c4b2 fix: prevent keychain requests during cargo test (#6219)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2025-12-22 10:37:30 +08:00
David Katz 6a0b8c25d5 Integrate pricing with canonical model (#6130) 2025-12-18 11:44:36 -05:00
David Katz 473f269daa Regenerate canonical models when release branch is created. (#6127) 2025-12-18 11:44:01 -05:00
Rabi Mishra fc8a4b4adf fix(google): Fix 400 Bad Request error with Gemini 3 thought signatures (#6035)
Signed-off-by: rabi <ramishra@redhat.com>
2025-12-17 08:38:46 -05:00
tko39 34b20ae0fe fix(providers): fix for gemini-cli on windows to work around cmd's multiline prompt limitations #5911 (#5966)
Signed-off-by: tko39 <kramer.tal@gmail.com>
2025-12-17 11:31:12 +11:00
Douwe Osinga 1c820addeb OpenRouter & Xai streaming (#5873)
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2025-12-16 13:24:53 -05:00
Rizel Scarlett 8b80d8b354 fix: filter tools in Ollama streaming when chat mode is enabled (#6118) 2025-12-15 20:10:24 -06:00
Bradley Axen 4e649c56ec fix: use system not developer role in db (#6098) 2025-12-12 17:33:09 -08:00
David Katz 239f4ec8aa OpenAI responses streaming (#5837)
Co-authored-by: Michael Neale <michael.neale@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-12 17:25:36 -05:00
David Katz 5c964d2691 Canonical models for Providers (#5694) 2025-12-12 17:25:10 -05:00
Kenan Hasanaliyev 8d183e3615 feat: add Inception provider for Mercury models (#6029)
Signed-off-by: Kenan Hasanaliyev <kenan@kenans-mbp.local.meter>
Co-authored-by: Kenan Hasanaliyev <kenan@kenans-mbp.local.meter>
2025-12-12 16:55:05 -05:00
Douwe Osinga cdab2fc3a6 Tool reply meta (#6074)
Co-authored-by: Douwe Osinga <douwe@squareup.com>
2025-12-11 19:43:36 -05:00