feat(openai): capture reasoning summaries from responses API#7375
Merged
DOsinga merged 2 commits intoblock:mainfrom Mar 10, 2026
Merged
feat(openai): capture reasoning summaries from responses API#7375DOsinga merged 2 commits intoblock:mainfrom
DOsinga merged 2 commits intoblock:mainfrom
Conversation
rabi
force-pushed
the
responses_reasoning
branch
from
5d01e2f to
3ea1527
Compare
Avoid emitting empty assistant message chunks when providers send empty text deltas during streaming, reducing noisy no-op stream events. Change-Id: I955d92569dc04d4b8231255491dd88a539eee1b0 Signed-off-by: rabi <[email protected]>
Send reasoning.effort and reasoning.summary in the Responses API request so OpenAI returns reasoning summaries. Parse the structured summary objects (Vec<SummaryText> instead of Vec<String>) and convert them to MessageContent::Reasoning instead of skipping them. Extract extract_reasoning_effort into a shared util so both openai.rs and openai_responses.rs use the same logic. Change-Id: I009b6ce3ffb4d3cd73ebaef8a39cb075a329c61a Signed-off-by: rabi <[email protected]>
rabi
force-pushed
the
responses_reasoning
branch
from
3ea1527 to
181eb51
Compare
DOsinga
approved these changes
Mar 10, 2026
lifeizhou-ap
added a commit
that referenced
this pull request
Mar 11, 2026
* main: (45 commits)
fix: resolve {{ recipe_dir }} in nested sub-recipe paths during secret discovery (#7797)
Add @DOsinga as CODEOWNER for documentation (#7799)
feat: Add summarize tool for deterministic reads (#7054)
fix(api): use camelCase in CallToolResponse and add type discriminators to ContentBlock (#7487)
feat: ACP providers for claude code and codex (#6605)
chore(deps): bump express-rate-limit from 8.2.1 to 8.3.0 in /evals/open-model-gym/mcp-harness (#7703)
feat(openai): capture reasoning summaries from responses API (#7375)
Fix some dependencies (#7794)
fix: improve keyring availability error detection (#7766)
feat: add MiniMax provider with Anthropic-compatible API (#7640)
feat: add Tensorix as a declarative provider (#7712)
fix(security): remove insecure default secret from GOOSE_EXTERNAL_BACKEND (#7783)
refactor: Convert Tanzu provider to declarative JSON config (#7124)
replaces https://github.com/block/goose/pull/7340/changes (#7786)
feat(summon): make skill supporting files individually loadable via load() (#7583)
Keep toast open on failed extension (#7771)
fix(ui-desktop): unify path resolution around GOOSE_PATH_ROOT (#7335)
fix: pass OAuth scopes to DCR and extract granted_scopes from token response (#7571)
fix: write to real file if config.yaml is symlink (#7669)
fix: preserve pairings when stopping gateway (#7733)
...
lifeizhou-ap
added a commit
that referenced
this pull request
Mar 11, 2026
* main: (69 commits)
fix: resolve {{ recipe_dir }} in nested sub-recipe paths during secret discovery (#7797)
Add @DOsinga as CODEOWNER for documentation (#7799)
feat: Add summarize tool for deterministic reads (#7054)
fix(api): use camelCase in CallToolResponse and add type discriminators to ContentBlock (#7487)
feat: ACP providers for claude code and codex (#6605)
chore(deps): bump express-rate-limit from 8.2.1 to 8.3.0 in /evals/open-model-gym/mcp-harness (#7703)
feat(openai): capture reasoning summaries from responses API (#7375)
Fix some dependencies (#7794)
fix: improve keyring availability error detection (#7766)
feat: add MiniMax provider with Anthropic-compatible API (#7640)
feat: add Tensorix as a declarative provider (#7712)
fix(security): remove insecure default secret from GOOSE_EXTERNAL_BACKEND (#7783)
refactor: Convert Tanzu provider to declarative JSON config (#7124)
replaces https://github.com/block/goose/pull/7340/changes (#7786)
feat(summon): make skill supporting files individually loadable via load() (#7583)
Keep toast open on failed extension (#7771)
fix(ui-desktop): unify path resolution around GOOSE_PATH_ROOT (#7335)
fix: pass OAuth scopes to DCR and extract granted_scopes from token response (#7571)
fix: write to real file if config.yaml is symlink (#7669)
fix: preserve pairings when stopping gateway (#7733)
...
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Send reasoning.effort and reasoning.summary in the Responses API request so OpenAI returns reasoning summaries. Parse the structured summary objects (
Vec<SummaryText> instead of Vec<String>) and convert them to MessageContent::Reasoning instead of skipping them.Extract extract_reasoning_effort into a shared util so both openai.rs and openai_responses.rs use the same logic.
Note: The content field with reasoning_text which is optional, is not deserialized. So before this PR even with
GOOSE_CLI_SHOW_THINKINGyou see no thinking for models using responses API.Type of Change
AI Assistance
Testing
Unit and Locally tested.