Skip to content

Make OpenAI Responses API store param configurable - #10040

Merged
jamadeo merged 1 commit into
aaif-goose:mainfrom
umago:store-openai
Jun 30, 2026
Merged

Make OpenAI Responses API store param configurable#10040
jamadeo merged 1 commit into
aaif-goose:mainfrom
umago:store-openai

Conversation

@umago

@umago umago commented Jun 26, 2026

Copy link
Copy Markdown
Contributor

Summary

The "store" field in create_responses_request() was hardcoded to false. It is now read from ModelConfig::request_params, following the same targeted pattern as thinking_effort.

A new Config::get_openai_store() method reads OPENAI_STORE (env var or config file) and injects it into request_params during OpenAI model config materialization, so it flows through to the Responses API payload.

This is useful when connecting Goose to inference servers that implement the OpenAI Responses API (e.g. vLLM, OGX https://ogx-ai.github.io/) and require store=true to retain conversation state on the server side.

Testing

With goose CLI, set OPENAI_STORE=true to ~/.config/goose/config.yaml.

Related Issues

Relates to #ISSUE_ID
Discussion: LINK (if any)

Screenshots/Demos (for UX changes)

Before: N/A
After: N/A

@umago
Make OpenAI Responses API store param configurable
2aee274 
The "store" field in create_responses_request() was hardcoded to false.
It is now read from ModelConfig::request_params, following the same
targeted pattern as thinking_effort.

A new Config::get_openai_store() method reads OPENAI_STORE (env var or
config file) and injects it into request_params during OpenAI model
config materialization, so it flows through to the Responses API payload.

This is useful when connecting Goose to inference servers that implement
the OpenAI Responses API (e.g. vLLM, OGX <https://ogx-ai.github.io/>)
and require store=true to retain conversation state on the server side.

Signed-off-by: Lucas Alvares Gomes <lucasagomes@gmail.com>
jamadeo
jamadeo approved these changes Jun 30, 2026
View reviewed changes

@jamadeo jamadeo left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We probably need a better way of threading these through than using ModelConfig's request_params, but that is how we pass these in general today, so this seems reasonable.

@jamadeo
jamadeo added this pull request to the merge queue Jun 30, 2026
Merged via the queue into aaif-goose:main with commit a90430e Jun 30, 2026
25 checks passed
DOsinga
DOsinga approved these changes Jun 30, 2026
View reviewed changes

@DOsinga DOsinga left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM — small, well-scoped change that follows the existing thinking_effort materialization pattern and reuses with_merged_request_params/request_param::<bool>. Correct default (false), a meaningful test that asserts the param flows through to the payload, and docs updated. CI is green. Thanks!

cc @jamadeo

lifeizhou-ap added a commit that referenced this pull request Jul 1, 2026
@lifeizhou-ap
Merge branch 'main' into codex/acp-remote-server-tls
4ee3b0d 
* main: (26 commits)
  Fix MCP app sandbox bridge lifecycle (#10064)
  fix(bedrock): send inference config (max_tokens, temperature) on Converse (#9889)
  feat(providers): support OpenRouter request parameters (#9276)
  Migrate local inference model management to ACP (#10124)
  (attempt to) fix disk space errors in linux release builds (#10024)
  feat: add --edit session flag to edit conversation before forking (#9799)
  feat: add iFlytek Spark and Astron MaaS providers (#9837)
  fix(desktop): dedupe Nostr session deep link imports (#9918)
  [codex] Add SessionStart hook parity outside CLI (#9970)
  feat(providers): add Fireworks AI declarative provider (#9990)
  fix(providers): don't retry deterministically-permanent 400s (thinking-block immutability) (#10005)
  fix(deps): downgrade pkcs8 to v0.10 to match sec1/pkcs1 v0.7 (#10119)
  chore(deps): bump actions/cache from 5.0.2 to 6.0.0 (#10051)
  Make OpenAI Responses API store param configurable (#10040)
  remove unsupported model (#10121)
  chore(release): bump version to 1.40.0 (minor) (#10099)
  move ollama provider into goose-providers (#9986)
  UI acp migratoin: Decouple desktop UI types from generated OpenAPI types (#10109)
  fix(otel): use async reqwest client so OTLP export works in `goose serve` mode (#10100)
  feat (acp): exposed available tools in acp schema (#10097)
  ...
lifeizhou-ap added a commit that referenced this pull request Jul 1, 2026
@lifeizhou-ap
Merge branch 'main' into codex/remove-mcp-sampling
7347b8f 
* main: (42 commits)
  Fix MCP app sandbox bridge lifecycle (#10064)
  fix(bedrock): send inference config (max_tokens, temperature) on Converse (#9889)
  feat(providers): support OpenRouter request parameters (#9276)
  Migrate local inference model management to ACP (#10124)
  (attempt to) fix disk space errors in linux release builds (#10024)
  feat: add --edit session flag to edit conversation before forking (#9799)
  feat: add iFlytek Spark and Astron MaaS providers (#9837)
  fix(desktop): dedupe Nostr session deep link imports (#9918)
  [codex] Add SessionStart hook parity outside CLI (#9970)
  feat(providers): add Fireworks AI declarative provider (#9990)
  fix(providers): don't retry deterministically-permanent 400s (thinking-block immutability) (#10005)
  fix(deps): downgrade pkcs8 to v0.10 to match sec1/pkcs1 v0.7 (#10119)
  chore(deps): bump actions/cache from 5.0.2 to 6.0.0 (#10051)
  Make OpenAI Responses API store param configurable (#10040)
  remove unsupported model (#10121)
  chore(release): bump version to 1.40.0 (minor) (#10099)
  move ollama provider into goose-providers (#9986)
  UI acp migratoin: Decouple desktop UI types from generated OpenAPI types (#10109)
  fix(otel): use async reqwest client so OTLP export works in `goose serve` mode (#10100)
  feat (acp): exposed available tools in acp schema (#10097)
  ...
lifeizhou-ap added a commit that referenced this pull request Jul 1, 2026
@lifeizhou-ap
Merge branch 'main' into lifei/ui-acp-direct-spike
a773905 
* main: (31 commits)
  test: generic validator for declarative providers (#10010)
  UI acp migratoin: Decouple desktop UI types from generated OpenAPI types (Part 2) (#10149)
  Remove MCP sampling support (#10087)
  Support TLS for ACP serve (#10088)
  feat (ui): Migrate dictation local model manager to ACP (#10131)
  Fix MCP app sandbox bridge lifecycle (#10064)
  fix(bedrock): send inference config (max_tokens, temperature) on Converse (#9889)
  feat(providers): support OpenRouter request parameters (#9276)
  Migrate local inference model management to ACP (#10124)
  (attempt to) fix disk space errors in linux release builds (#10024)
  feat: add --edit session flag to edit conversation before forking (#9799)
  feat: add iFlytek Spark and Astron MaaS providers (#9837)
  fix(desktop): dedupe Nostr session deep link imports (#9918)
  [codex] Add SessionStart hook parity outside CLI (#9970)
  feat(providers): add Fireworks AI declarative provider (#9990)
  fix(providers): don't retry deterministically-permanent 400s (thinking-block immutability) (#10005)
  fix(deps): downgrade pkcs8 to v0.10 to match sec1/pkcs1 v0.7 (#10119)
  chore(deps): bump actions/cache from 5.0.2 to 6.0.0 (#10051)
  Make OpenAI Responses API store param configurable (#10040)
  remove unsupported model (#10121)
  ...
@github-actions github-actions Bot mentioned this pull request Jul 2, 2026
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@DOsinga DOsinga DOsinga approved these changes
@jamadeo jamadeo jamadeo approved these changes

Assignees

@jamadeo jamadeo

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@umago @DOsinga @jamadeo