Skip to content

feat(agents): evaluate subscription routing policy explicitly - #210

Merged
devantler merged 4 commits into
mainfrom
codex/model-routing-209
Sep 12, 2026
Merged

feat(agents): evaluate subscription routing policy explicitly#210
devantler merged 4 commits into
mainfrom
codex/model-routing-209

Conversation

@devantler

@devantler devantler commented Sep 12, 2026

Copy link
Copy Markdown
Contributor

🤖 Generated by the Agentic Engineer

Why

Deployments need consistent model selection and escalation without treating uncertain quota or billing evidence as permission to run.

What

Adds routing-policy checks and bounded delegation procedures, together with the reviewed measurement skills. The 5.1.0 release keeps automatic execution dependent on verified native controls.

Fixes #209. Part of devantler-tech/monorepo#3314.

@devantler

Copy link
Copy Markdown
Contributor Author

🤖 Generated by the Agentic Engineer

@coderabbitai review

@coderabbitai

coderabbitai Bot commented Sep 12, 2026

Copy link
Copy Markdown

@devantler: I will review the changes.

✅ Action performed

Review finished.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

@coderabbitai

coderabbitai Bot commented Sep 12, 2026

Copy link
Copy Markdown

Review Change StackReview Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Advanced

Run ID: ca01de2c-c9bb-4107-b224-1c3637233c3e

📥 Commits

Reviewing files that changed from the base of the PR and between a657cd5 and c99a54b.

📒 Files selected for processing (12)
  • .claude-plugin/marketplace.json
  • .github/plugin/marketplace.json
  • plugins/agentic-engineering/.claude-plugin/plugin.json
  • plugins/agentic-engineering/README.md
  • plugins/agentic-engineering/agents/agent-improver.agent.md
  • plugins/agentic-engineering/agents/agentic-engineer.agent.md
  • plugins/agentic-engineering/plugin.json
  • plugins/agentic-engineering/resources/inference-routing.md
  • plugins/agentic-engineering/resources/provider-neutral.desired-state.json
  • plugins/agentic-engineering/scripts/classify-default-branch-ci-runs.test.sh
  • plugins/agentic-engineering/scripts/evaluate-inference-routing.sh
  • plugins/agentic-engineering/scripts/evaluate-inference-routing.test.sh

Included review availability: Your plan provides up to 1 included review per hour; 0 remain after this review.

📜 Recent review details
🧰 Additional context used
📓 Path-based instructions (3)
Any change to the plugin set updates both manifests in the same PR

📄 CodeRabbit inference engine (AGENTS.md)

Files:

  • .github/plugin/marketplace.json
  • .claude-plugin/marketplace.json
A plugin's version is its cache key — move it whenever its content changes.

📄 CodeRabbit inference engine (AGENTS.md)

Files:

  • plugins/agentic-engineering/.claude-plugin/plugin.json
  • plugins/agentic-engineering/plugin.json
keep manifests/README cross-tool

📄 CodeRabbit inference engine (AGENTS.md)

Files:

  • .github/plugin/marketplace.json
  • .claude-plugin/marketplace.json
  • plugins/agentic-engineering/README.md
🧠 Learnings (1)
📚 Learning: 2026-07-25T12:40:46.973Z
Learnt from: devantler
Repo: devantler-tech/agent-plugins PR: 89
File: plugins/agentic-engineering/skills/portfolio-maintenance/SKILL.md:0-0
Timestamp: 2026-07-25T12:40:46.973Z
Learning: During code review in this repo: (1) For `plugins/agentic-engineering/agents/*.agent.md` (local agent-entrypoints), do NOT require upstream provenance frontmatter—assume these are authored locally; renames/edits to agent-entrypoints should remain local and not be forced through the upstream sync process. (2) For bundled skill artifacts at `plugins/*/skills/*/SKILL.md`, expect upstream provenance frontmatter to be present; do not make direct “local” edits for skill content—skill changes must originate from the upstream source and be brought in via the repo’s sync workflow.

Applied to files:

  • plugins/agentic-engineering/agents/agent-improver.agent.md
🔇 Additional comments (12)
plugins/agentic-engineering/README.md (1)

217-220: LGTM!

plugins/agentic-engineering/agents/agentic-engineer.agent.md (1)

65-73: LGTM!

plugins/agentic-engineering/agents/agent-improver.agent.md (1)

95-102: LGTM!

plugins/agentic-engineering/resources/inference-routing.md (1)

1-115: LGTM!

plugins/agentic-engineering/.claude-plugin/plugin.json (1)

4-4: LGTM!

plugins/agentic-engineering/plugin.json (1)

4-4: LGTM!

plugins/agentic-engineering/scripts/evaluate-inference-routing.sh (1)

1-107: LGTM!

plugins/agentic-engineering/resources/provider-neutral.desired-state.json (1)

28-35: LGTM!

Also applies to: 74-74, 105-107, 124-124

plugins/agentic-engineering/scripts/classify-default-branch-ci-runs.test.sh (1)

209-216: LGTM!

Also applies to: 232-236

plugins/agentic-engineering/scripts/evaluate-inference-routing.test.sh (1)

1-91: LGTM!

.claude-plugin/marketplace.json (1)

30-30: LGTM!

.github/plugin/marketplace.json (1)

30-30: LGTM!


📝 Walkthrough

Walkthrough

The plugin adds an optional consumer-owned inference-routing contract and documents its policy schema and runtime controls. A new offline evaluator returns RECOMMEND, HOLD, or INVALID decisions without launching inference or reserving quota. Desired-state metadata includes the evaluator and its checksum. Tests cover routing, escalation, quota, policy, and validation cases. Plugin metadata is updated to version 5.1.0.

Priority: ➖ Normal

Merge Risk: ⚪ Minimal · up to c99a5

The optional routing evaluator remains advisory and preserves existing behavior for consumers without the contract. No current merge-blocking risk was identified.


Important

Pre-merge checks failed

Please resolve all errors before merging. Addressing warnings is optional.

❌ Failed checks (1 error)

Check name Status Explanation Resolution
Docstring Coverage ❌ Error Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 2 functions across 3 files. (9 skipped: 9 … Write docstrings for the functions missing them to satisfy the coverage threshold.
✅ Passed checks (4 passed)
Check name Status Explanation
Linked Issues check ✅ Passed Issue #209 requires a portable deterministic evaluator with separate eligibility and readiness outcomes. The new evaluator reads one JSON request offline, validates the policy, task, snapshot, model t…
Out of Scope Changes check ✅ Passed The changes remain within issue #209. The version updates maintain manifest parity. The routing contract and role-entrypoint text document the evaluator's optional consumer behavior. The desired-state…
Title check ✅ Passed The title clearly and concisely describes the main change: explicit evaluation of inference subscription routing policy.
Description check ✅ Passed The description explains the routing-policy checks, bounded delegation, verified controls, and linked issue. It is directly related to the changeset.
Full details: Docstring Coverage

Explanation

Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 2 functions across 3 files. (9 skipped: 9 unsupported.)


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@devantler

Copy link
Copy Markdown
Contributor Author

🤖 Generated by the Agentic Engineer

@coderabbitai review

The helper-function documentation flagged by the pre-merge check is now present; the runtime-asset digest is refreshed. Behavior is unchanged and all evaluator cases still pass.

@coderabbitai

coderabbitai Bot commented Sep 12, 2026

Copy link
Copy Markdown

@devantler: I will review the updated changes.

⚠️ Action not completed

Review rate limited.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

@devantler

Copy link
Copy Markdown
Contributor Author

🤖 Generated by the Agentic Engineer

@codex review

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Sep 12, 2026

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review Completed 2026-09-12T11:09:35.238071Z 1ddcdbc Manual request
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" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. 🎉

Reviewed commit: e23fff0705

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".

@devantler

Copy link
Copy Markdown
Contributor Author

🤖 Generated by the Agentic Engineer

@coderabbitai review

@coderabbitai

coderabbitai Bot commented Sep 12, 2026

Copy link
Copy Markdown

@devantler: I will review the updated changes.

⚠️ Action not completed

Review rate limited.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

@devantler

Copy link
Copy Markdown
Contributor Author

🤖 Generated by the Agentic Engineer

@codex review

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 7e3c1521ef

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".

Comment thread plugins/agentic-engineering/agents/agent-improver.agent.md
Comment thread plugins/agentic-engineering/scripts/evaluate-inference-routing.test.sh Outdated
Comment thread plugins/agentic-engineering/scripts/evaluate-inference-routing.sh
@botantler-1 botantler-1 Bot closed this Sep 12, 2026
@botantler-1 botantler-1 Bot reopened this Sep 12, 2026
@github-project-automation github-project-automation Bot moved this from 🫴 Ready to ✅ Done in 🌊 Project Board Sep 12, 2026
@github-project-automation github-project-automation Bot moved this from ✅ Done to 🫴 Ready in 🌊 Project Board Sep 12, 2026
@devantler
devantler force-pushed the codex/model-routing-209 branch from 7e3c152 to 1ddcdbc Compare September 12, 2026 11:00
@devantler

Copy link
Copy Markdown
Contributor Author

🤖 Generated by the Agentic Engineer

@coderabbitai review

@coderabbitai

coderabbitai Bot commented Sep 12, 2026

Copy link
Copy Markdown

@devantler: I will review the updated changes.

⚠️ Action not completed

Review rate limited.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

@devantler

Copy link
Copy Markdown
Contributor Author

🤖 Generated by the Agentic Engineer

@codex review

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Breezy!

Reviewed commit: 1ddcdbc702

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".

@devantler
devantler marked this pull request as ready for review September 12, 2026 11:11
@devantler
devantler merged commit 314ca13 into main Sep 12, 2026
41 checks passed
@devantler
devantler deleted the codex/model-routing-209 branch September 12, 2026 11:11
@github-project-automation github-project-automation Bot moved this from 🫴 Ready to ✅ Done in 🌊 Project Board Sep 12, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Status: ✅ Done

Development

Successfully merging this pull request may close these issues.

feat(agents): evaluate consumer routing policy without implying runtime admission

1 participant