[PR #354] [MERGED] ci: request medium reasoning effort in OpenCodeReview

## 📋 Pull Request Information **Original PR:** https://github.com/kvcache-ai/AgentENV/pull/354 **Author:** [@yingdi-shan](https://github.com/yingdi-shan) **Created:** 10/10/2026 **Status:** ✅ Merged **Merged:** 10/10/2026 **Merged by:** [@yingdi-shan](https://github.com/yingdi-shan) **Base:** `main` ← **Head:** `ci/ocr-reasoning-effort` --- ### 📝 Commits (1) - [`5693cde`](https://github.com/kvcache-ai/AgentENV/commit/5693cde9fe6438368e5df3feda97dc368e330a0a) ci: request medium reasoning effort in OpenCodeReview ### 📊 Changes **1 file changed** (+6 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/open-code-review.yml` (+6 -0) </details> ### 📄 Description ## What On the `alibaba/open-code-review` step, set `llm_extra_body: '{}'` so that the action stops sending its default `{"thinking": {"type": "disabled"}}` body, and set `llm_reasoning_effort: medium`. ## Why The OpenCodeReview job fails with: ```text gpt-6.1-sol does not support reasoning effort "none"; use low, medium, high, xhigh or max ``` The OpenAI-compatible endpoint maps the action's default "thinking disabled" `extra_body` to `reasoning_effort: "none"`, and the configured model rejects that value. With an empty `extra_body` and `llm_reasoning_effort: medium`, the request carries `reasoning_effort: "medium"`, a value the model accepts. The `effort` input does not help here: it only sets the number of review rounds. ## Related issue N/A ## Scope and non-goals Only the workflow inputs change. The review-round `effort` input is left at its default. ## Design and behavior changes LLM review requests no longer disable thinking and instead ask for medium reasoning effort. Reviews may use more tokens and take somewhat longer. ## Compatibility and operations - Public API or generated protocol: N/A - Configuration or defaults: OCR requests send `reasoning_effort: "medium"` instead of `thinking: disabled`. `llm_reasoning_effort` applies to OpenAI-compatible protocols only; the action fails fast if `OCR_LLM_USE_ANTHROPIC` is enabled while it is set, so switching to Anthropic also requires removing it. - Snapshot manifest, artifact layout, or storage format: N/A - Upgrade and rollback: Revert this commit - Host requirements, permissions, ports, or dependencies: N/A ## Validation - [ ] `make fmt` - [ ] `make clippy` - [ ] `make test-unit` - [ ] Relevant Rust integration tests - [ ] `make -C services test` (required when `services/` changes) - [ ] Generated clients/server regenerated with the documented `make` target - [ ] Documentation updated - [ ] Benchmarks or performance comparison completed Commands and results: ```text python3 -c "import yaml; yaml.safe_load(open('.github/workflows/open-code-review.yml'))" # ok ``` Skipped checks and reasons: CI workflow-only change; no Rust or Go code changed. The real validation is the OpenCodeReview run, which only runs from the base repository's `pull_request_target` workflow after this merges. ## Risks and reviewer notes Because the workflow is `pull_request_target`, this PR's own OCR run still uses the workflow from `main`, so it is expected to fail with the same error until this merges. ## Checklist - [x] The PR contains one coherent change and no unrelated formatting or refactoring. - [x] New behavior is covered by tests, or I explained why testing is impractical. - [x] Logs and examples contain no credentials, tokens, or private registry information. - [x] I did not manually edit generated code without updating its source and regenerating it. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi commented

2026-10-29 14:22:44 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/AgentENV/pull/354
Author: @yingdi-shan
Created: 10/10/2026
Status: ✅ Merged
Merged: 10/10/2026
Merged by: @yingdi-shan

Base: main ← Head: ci/ocr-reasoning-effort

📝 Commits (1)

5693cde ci: request medium reasoning effort in OpenCodeReview

📊 Changes

1 file changed (+6 additions, -0 deletions)

View changed files

📝 .github/workflows/open-code-review.yml (+6 -0)

📄 Description

What

On the alibaba/open-code-review step, set llm_extra_body: '{}' so that the action stops sending its default {"thinking": {"type": "disabled"}} body, and set llm_reasoning_effort: medium.

Why

The OpenCodeReview job fails with:

gpt-6.1-sol does not support reasoning effort "none"; use low, medium, high, xhigh or max

The OpenAI-compatible endpoint maps the action's default "thinking disabled" extra_body to reasoning_effort: "none", and the configured model rejects that value. With an empty extra_body and llm_reasoning_effort: medium, the request carries reasoning_effort: "medium", a value the model accepts. The effort input does not help here: it only sets the number of review rounds.

N/A

Scope and non-goals

Only the workflow inputs change. The review-round effort input is left at its default.

Design and behavior changes

LLM review requests no longer disable thinking and instead ask for medium reasoning effort. Reviews may use more tokens and take somewhat longer.

Compatibility and operations

Public API or generated protocol: N/A
Configuration or defaults: OCR requests send reasoning_effort: "medium" instead of thinking: disabled. llm_reasoning_effort applies to OpenAI-compatible protocols only; the action fails fast if OCR_LLM_USE_ANTHROPIC is enabled while it is set, so switching to Anthropic also requires removing it.
Snapshot manifest, artifact layout, or storage format: N/A
Upgrade and rollback: Revert this commit
Host requirements, permissions, ports, or dependencies: N/A

Validation

make fmt
make clippy
make test-unit
Relevant Rust integration tests
make -C services test (required when services/ changes)
Generated clients/server regenerated with the documented make target
Documentation updated
Benchmarks or performance comparison completed

Commands and results:

python3 -c "import yaml; yaml.safe_load(open('.github/workflows/open-code-review.yml'))"  # ok

Skipped checks and reasons: CI workflow-only change; no Rust or Go code changed. The real validation is the OpenCodeReview run, which only runs from the base repository's pull_request_target workflow after this merges.

Risks and reviewer notes

Because the workflow is pull_request_target, this PR's own OCR run still uses the workflow from main, so it is expected to fail with the same error until this merges.

Checklist

The PR contains one coherent change and no unrelated formatting or refactoring.
New behavior is covered by tests, or I explained why testing is impractical.
Logs and examples contain no credentials, tokens, or private registry information.
I did not manually edit generated code without updating its source and regenerating it.

🤖 Generated with Claude Code

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

bsakaguchi

closed this issue
added the
pull-request
label

bsakaguchi referenced this issue

2026-10-29 14:22:51 +00:00

[PR #373] [MERGED] test(config): fail when the reference or bundled config drifts from cfg.rs #383

Rows
Columns

[PR #354] [MERGED] ci: request medium reasoning effort in OpenCodeReview #373