fix: clear remaining release validation blockers#104555
Conversation
openclaw-barnacle
Bot
added
commands
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7cc55c31ec
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| supportsPromptCacheKey: z.boolean().optional(), | ||
| supportsDeveloperRole: z.boolean().optional(), | ||
| supportsReasoningEffort: z.boolean().optional(), | ||
| supportsTemperature: z.boolean().optional(), |
There was a problem hiding this comment.
When a GPT-5.6 openai-responses model from a generated catalog carries compat.supportsTemperature: false and an agent extra param supplies temperature, validation now succeeds and ModelRegistry preserves the flag, but the core Responses transport still unconditionally copies options.temperature in buildOpenAIResponsesParams (src/agents/openai-transport-stream.ts:2666-2668). That sends the API-rejected temperature field this compat flag is meant to suppress on the managed OpenAI/Azure Responses path; gate that assignment with the same temperature-support check used by the package Responses builders.
Useful? React with 👍 / 👎.
|
Codex review: stale review; fresh review needed. Summary Next step |
|
Merged via squash.
|
* test: align provider tool call lifecycles * test: isolate plugin install repair migrations * fix: accept catalog temperature compatibility * fix: disable GPT-5.6 tool reasoning on completions * style: avoid shadowed stream model (cherry picked from commit 57af2bb)
…faults for the stable cut (#104656) * feat(openai): default new setups to GPT-5.6 (#103581) * feat(openai): default fresh setup to GPT-5.6 * test(crestodian): expect GPT-5.6 Codex defaults * test(crestodian): expect GPT-5.6 bootstrap default (cherry picked from commit ab5d143) * fix(infra): converge legacy state migrations on archive collisions (cherry picked from commit 474d660) * fix(codex): prevent startup hangs after binding migration (#103281) * fix(codex): archive imported orphan binding sidecars * fix(codex): harden binding sidecar migration Co-authored-by: Benjamin Badejo <[email protected]> * chore: keep release notes out of contributor PRs --------- Co-authored-by: Benjamin Badejo <[email protected]> Co-authored-by: Peter Steinberger <[email protected]> (cherry picked from commit 1f3ea6f) * fix(migrations): converge recoverable legacy state (#104529) Signed-off-by: sallyom <[email protected]> (cherry picked from commit cdb58ca) * test(openai): align auth contract with provider default (#103760) (cherry picked from commit 9b4c7c0) * fix: clear remaining release validation blockers (#104555) * test: align provider tool call lifecycles * test: isolate plugin install repair migrations * fix: accept catalog temperature compatibility * fix: disable GPT-5.6 tool reasoning on completions * style: avoid shadowed stream model (cherry picked from commit 57af2bb) * test(release): keep GPT-5.6 backport scoped * test(release): restore doctor config type import --------- Signed-off-by: sallyom <[email protected]> Co-authored-by: Ayaan Zaidi <[email protected]> Co-authored-by: Ben Badejo <[email protected]> Co-authored-by: Benjamin Badejo <[email protected]> Co-authored-by: Sally O'Malley <[email protected]>
* test: align provider tool call lifecycles * test: isolate plugin install repair migrations * fix: accept catalog temperature compatibility * fix: disable GPT-5.6 tool reasoning on completions * style: avoid shadowed stream model
1 participant
What Problem This Solves
Full Release Validation exposed four additional deterministic blockers after the initial Plugin Prerelease repair:
toolcall_endevent lifecycle.supportsTemperature, but strict runtime config rejected it.reasoning_effort: low.Why This Change Was Made
reasoning_effort: noneonly for GPT-5.6 function-tool requests on known OpenAI/Azure Chat Completions paths, including the Anthropic-to-OpenAI payload adapter.User Impact
Release validation reflects the current runtime contracts, doctor CI no longer stalls on unrelated disk discovery, generated GPT-5.6 catalogs load successfully, and GPT-5.6 function tools no longer receive an API-rejected reasoning mode.
Evidence
check:test-types: https://github.com/openclaw/openclaw/actions/runs/29159518425git diff --checkThe stable package gate remains intentionally blocked until the
2026.7.2changelog section is finalized; this PR does not bypass that release contract.