Matt Toohey
4889539ebb
feat(observability): trace provider/model at every reply hand-off
...
- Always populate Message.metadata.inference in reply_internal so the
client has a per-message ground truth even when fetch_model_info()
cannot resolve a canonical model (resolved_model: None is now a
legitimate carried value).
- Add gen_ai.provider and gen_ai.request.model fields to the existing
tracing::instrument on stream_response_from_provider, which wraps
every Provider::stream call. (Instrumenting the trait method
directly is not possible: it has no body for tracing-attributes to
wrap and the in-tree comment at base.rs explicitly forbids it.)
- Add structured tracing::info! at the four reply hand-off points,
tagged with session.id for end-to-end correlation:
* /reply entry, after the session is loaded
(goose-server/src/routes/reply.rs)
* restore_provider_from_session, with provider_source and
model_source = "session" | "config_default"
(goose/src/agents/agent.rs)
* update_provider, with source = "explicit_update"
(goose/src/agents/agent.rs)
* just before provider.stream(...)
(goose/src/agents/reply_parts.rs)
* MessageEvent::Message emit, with the message's inference metadata
(goose-server/src/routes/reply.rs)
- ACP path: add symmetric entry and emit logs in
GooseAcpAgent::on_prompt (goose/src/acp/server.rs). The actual LLM
call site is shared via Agent::reply, so the agent-level changes
cover both /reply and ACP.
Together these allow correlating one log chain per session and
locating where the requested model and the actually-used model
diverge.
Verified: cargo build -p goose -p goose-server, cargo clippy
--all-targets -p goose -p goose-server -- -D warnings, and
cargo test -p goose --lib conversation:: all pass. Pre-existing
sqlx-runtime-feature test failures under cargo test -p goose --lib
are unrelated to this change (confirmed via git stash).
Signed-off-by: Matt Toohey <contact@matttoohey.com >
2026-06-01 10:33:02 +10:00
Kalvin C
13f7be2ed5
feat: replay acp images on session load ( #9496 )
...
Signed-off-by: Kalvin Chau <kalvin@block.xyz >
2026-05-29 19:34:25 +00:00
Bradley Axen
25ff547487
Expose raw provider supported models over ACP ( #9475 )
...
Signed-off-by: Bradley Axen <baxen@squareup.com >
Signed-off-by: Matt Toohey <contact@matttoohey.com >
Co-authored-by: Matt Toohey <contact@matttoohey.com >
2026-05-29 02:18:42 +00:00
Matt Toohey
a3bdb918e7
fix(acp): forward ACP server context window size to clients ( #9455 )
...
Signed-off-by: Matt Toohey <contact@matttoohey.com >
2026-05-29 01:05:45 +00:00
Bradley Axen
104cc17758
Add ACP session system prompt setter ( #9478 )
...
Signed-off-by: Bradley Axen <baxen@squareup.com >
2026-05-29 00:35:12 +00:00
Rodolfo Olivieri
2116f88908
feat: add tui feature flag to gate the tui command ( #9428 )
...
Signed-off-by: Rodolfo Olivieri <rolivier@redhat.com >
2026-05-28 14:12:31 +00:00
Jack Amadeo
d10d009b97
CLI to list skills with token counts ( #9326 )
2026-05-28 14:09:11 +00:00
Alex Hancock
9c403b1560
refactor: convert desktop v1 and goose-server extensions to ACP+ ( #9448 )
2026-05-27 20:59:48 +00:00
dependabot[bot]
c9945bca5d
chore(deps): bump sha2 from 0.10.9 to 0.11.0 ( #8963 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com >
2026-05-27 19:08:54 +00:00
James Liounis
e9b0d9247b
feat(providers): add Perplexity as a declarative OpenAI-compatible provider ( #9324 )
2026-05-27 19:07:03 +00:00
Jeremy Dawes
4c88f4b91c
feat(providers): add Alibaba (Qwen via DashScope) declarative provider ( #9443 )
...
Signed-off-by: Jeremy Dawes <jeremy@jezweb.net >
2026-05-27 18:45:48 +00:00
Douwe Osinga
1125e8dd54
fix: make azure api-version query param optional ( #9221 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-27 18:32:19 +00:00
Douwe Osinga
10ac6b18c9
feat: make tool output size limit configurable via GOOSE_MAX_TOOL_RESPONSE_SIZE ( #9256 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-27 18:31:22 +00:00
Angie Jones
d017295f32
fix: tolerate missing responses output ( #9449 )
...
Signed-off-by: Angie Jones <jones.angie@gmail.com >
2026-05-27 18:05:00 +00:00
jh-block
27b41d93f5
local inference: stricter GGUF requirements, auto detection of tool calling support, fixed thinking output parsing ( #9442 )
...
Signed-off-by: jh-block <jhugo@block.xyz >
2026-05-27 18:00:30 +00:00
Bradley Axen
d90b349a69
feat: add /model slash command to CLI for session model switching ( #8747 )
...
Signed-off-by: Bradley Axen <baxen@squareup.com >
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-27 13:38:59 +00:00
Bradley Axen
17493540e1
Prefer goose aliases for Databricks v2 inventory ( #9430 )
...
Signed-off-by: Bradley Axen <baxen@squareup.com >
2026-05-27 01:32:32 +00:00
Bradley Axen
7dc904e1e2
add databricks ai gateway provider ( #9274 )
...
Signed-off-by: Bradley Axen <baxen@squareup.com >
2026-05-26 22:45:01 +00:00
github-actions[bot]
b0cd61aa42
chore(release): bump version to 1.36.0 (minor) ( #9417 )
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-05-26 18:02:17 +00:00
jh-block
27dc0d5f83
Improve dependency hygiene ( #9360 )
...
Signed-off-by: jh-block <jhugo@block.xyz >
2026-05-26 16:09:03 +00:00
Douwe Osinga
e1cc44f7ec
Build summon instructions per turn ( #9329 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-25 00:55:58 +00:00
Angie Jones
c4d64d1a83
Fix desktop chat search session limiting ( #9366 )
...
Signed-off-by: Angie Jones <jones.angie@gmail.com >
2026-05-24 23:33:44 +00:00
fre$h
ce004f7475
fix(agents): serialize per-session agent creation to stop duplicate MCP init ( #9357 )
...
Signed-off-by: fresh3nough <anonwurcod@proton.me >
2026-05-23 18:42:32 +00:00
dependabot[bot]
8689fdf33f
chore(deps): bump image from 0.24.9 to 0.25.10 ( #9383 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-23 18:40:20 +00:00
dependabot[bot]
728d72a79f
chore(deps): bump ctor from 0.2.9 to 1.0.6 ( #9380 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com >
2026-05-22 22:13:15 +00:00
dependabot[bot]
656ae04d97
chore(deps): bump shlex from 1.3.0 to 2.0.1 ( #9379 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-22 21:11:59 +00:00
dependabot[bot]
a7d46251a0
chore(deps): bump sigstore-verify from 0.6.6 to 0.8.0 ( #9378 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-22 21:11:10 +00:00
dependabot[bot]
9185be5f94
chore(deps): bump clap_mangen from 0.2.33 to 0.3.0 ( #9377 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-22 21:10:58 +00:00
dependabot[bot]
61252fc4fd
chore(deps): bump the cargo-minor-and-patch group with 12 updates ( #9376 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-22 21:09:13 +00:00
Jack Amadeo
0a958213db
protocol cleanup ( #9147 )
2026-05-22 21:04:46 +00:00
Alex Hancock
48d20e72d3
feat: tui command on goose-cli ( #9385 )
2026-05-22 20:32:40 +00:00
spendletonliveaction
f3260f4e2f
feat(cli): make MAX_CODE_BLOCK_LINES configurable via env vars ( #9301 )
...
Signed-off-by: Stephen Pendleton <spendleton@bluecatnetworks.com >
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Stephen Pendleton <spendleton@bluecatnetworks.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-22 18:12:55 +00:00
Douwe Osinga
612cd89d51
fix(litellm): use context limit from /model/info for custom models ( #9303 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-22 18:10:31 +00:00
Pierre LE GUEN
c434c84d23
feat(providers): add NEAR AI Cloud provider ( #9352 )
...
Signed-off-by: Pierre LE GUEN <26087574+PierreLeGuen@users.noreply.github.com >
2026-05-22 17:56:31 +00:00
asim48-ctrl
ee65a39d68
fix: preserve thinking content for provider context ( #9314 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com >
2026-05-22 17:42:37 +00:00
Quentin Champenois
cd68f068f3
Add Scaleway provider ( #9254 )
...
Co-authored-by: Quentin Champenois <qchampenois@scaleway.com >
2026-05-22 16:54:01 +00:00
Douwe Osinga
552154af71
fix: mention configurable timeout env vars in Ollama stream stall error ( #9246 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Jack Amadeo <jackamadeo@squareup.com >
2026-05-22 16:33:21 +00:00
Douwe Osinga
394abea75f
fix: include full recipe parameter details in load/discovery output ( #9233 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-22 16:23:27 +00:00
Rodolfo Olivieri
7a88d75fc9
Add feature codemode to tests ( #9344 )
2026-05-22 15:01:45 +00:00
fre$h
c1d50e234b
fix(gateway): respect GOOSE_MAX_TURNS in gateway sessions ( #9354 )
...
Signed-off-by: fresh3nough <anonwurcod@proton.me >
2026-05-22 14:57:28 +00:00
fre$h
f2e661a7e2
fix(anthropic): send empty object instead of null for tool_use input ( #9355 )
...
Signed-off-by: fresh3nough <anonwurcod@proton.me >
2026-05-22 14:55:56 +00:00
Vladislav
2045e63d8d
feat(goose): honor GOOSE_FAST_MODEL env var in ModelConfig::with_fast ( #9296 )
...
Signed-off-by: Vladislav Dobromyslov <vladik.dobrik@gmail.com >
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-22 13:47:50 +00:00
dependabot[bot]
603deb88bb
chore(deps): bump mockall from 0.13.1 to 0.14.0 ( #8962 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-22 13:44:46 +00:00
dependabot[bot]
db0c3c4b30
chore(deps): bump nanoid from 0.4.0 to 0.5.0 ( #8965 )
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-22 13:44:36 +00:00
dorien-koelemeijer
ca26f01d3a
[Prompt injection mitigation] Update pattern-based detection to reduce FPs ( #9350 )
2026-05-21 00:56:17 +00:00
Douwe Osinga
5f93990f36
Include request URL in provider error messages ( #9232 )
...
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-20 11:46:34 +00:00
Steve Marshall
955288db36
fix(databricks): ensure parallel tool image responses don't interleave tool results ( #9241 )
...
Signed-off-by: Steve Marshall <steve.marshall@fasthosts.com >
Signed-off-by: Douwe Osinga <douwe@squareup.com >
Co-authored-by: Douwe Osinga <douwe@squareup.com >
2026-05-20 11:44:10 +00:00
jh-block
8f9270e295
Surface resolved Databricks model metadata ( #9206 )
...
Signed-off-by: jh-block <jhugo@block.xyz >
2026-05-20 10:50:44 +00:00
jh-block
98a54e9ec6
Add unified thinking effort control across all providers ( #9242 )
...
Signed-off-by: jh-block <jhugo@block.xyz >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-05-20 08:42:42 +00:00
Bradley Axen
7a53017f44
chore: update canonical model registry ( #9331 )
...
Signed-off-by: Bradley Axen <baxen@squareup.com >
2026-05-20 06:39:57 +00:00