chore(ci): add OpenCode PR review workflow

[spike-rabbit]

What kind of change does this PR introduce? (check one with "x")

• Bugfix
• Feature
• Code style update (formatting, local variables)
• Refactoring (no functional changes, no api changes)
• Build related changes
• CI related changes
• Other... Please describe:

What is the current behavior? (You can also link to an open issue here)

What is the new behavior?

Added codereviews based on opencode + Siemens qwen instance.

Does this PR introduce a breaking change? (check one with "x")

• Yes
• No

If this PR contains a breaking change, please describe the impact and migration path for existing applications: ...

Other information:

[gemini-code-assist]

Code Review

This pull request introduces a new configuration file opencode.json to define the Siemens provider and its qwen-3.6-27b model. The review feedback correctly points out that the output token limit is set excessively high at 262144 and suggests reducing it to 4096 to avoid potential API errors.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

The output token limit is set to 262144, which matches the context limit. LLMs (including Qwen models) typically have a much smaller maximum output token limit, usually 4096 or 8192. Setting this value excessively high can lead to API errors or client-side issues when requesting generation.

Suggested change

	"output": 262144
	"output": 4096

[github-actions]

Author identity unknown

*** Please tell me who you are.

Run

git config --global user.email "you@example.com"
git config --global user.name "Your Name"

to set your account's default identity.
Omit --global to set the identity only in this repository.

fatal: empty ident name (for runner@runnervm1li68.z3jxgq5ehwnebfxq4u2nylwtgb.dx.internal.cloudapp.net) not allowed

opencode session  |  github run

[Copilot]

Pull request overview

Adds an OpenCode-based automated PR review workflow wired to Siemens’ Qwen model, enabling CI to post review feedback on pull requests.

Changes:

• Introduces opencode.json configuring a Siemens OpenAI-compatible provider and the qwen-3.6-27b model.
• Adds a GitHub Actions workflow to run OpenCode on pull_request events and post results to the PR.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.

File	Description
opencode.json	Defines the OpenCode provider/model configuration (Siemens LLM endpoint + Qwen model).
.github/workflows/opencode-review.yml	New PR-triggered workflow that checks out the repo and runs OpenCode to create PR review feedback.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

Here's my review of the PR:

---

opencode.json line 15 — The output token limit of 262144 is excessively high. Most LLM APIs enforce a max output of 4096–8192 tokens. Setting this to the context window size can cause API errors. Consider reducing to 4096 or 8192.

.github/workflows/opencode-review.yml line 10 — id-token: write is requested but not needed. The job authenticates via SIEMENS_API_KEY (a long-lived secret), not GitHub OIDC. Follow least-privilege and remove this permission.

.github/workflows/opencode-review.yml line 14 — actions/checkout@v6 uses a moving tag. Per repo convention (see test_and_deploy.yml:20), pin to an immutable commit SHA: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.

.github/workflows/opencode-review.yml line 18 — anomalyco/opencode/github@latest is a floating reference. Pin to a specific version tag or commit SHA to prevent unreviewed changes from being pulled into CI unexpectedly.

.github/workflows/opencode-review.yml line 4 — This workflow triggers on all pull_request events, including fork PRs. Fork PRs don't have access to repository secrets, so the job will fail for external contributors. Consider using pull_request_target with caution, or adding a condition to skip fork PRs.

opencode session  |  github run

[github-actions]

The PR has already incorporated fixes from prior reviews (pinned action SHAs, removed id-token: write, added fork filter). One remaining issue:

opencode.json line 15 — The output token limit of 262144 remains excessively high. Qwen models typically cap output at 4096–8192 tokens. Requesting 262144 output tokens will likely cause API errors. Reduce to "output": 4096.

opencode session  |  github run

[github-actions]

APIError: The model qwen-3.6-27b does not exist.

opencode session  |  github run