Add session summary to agent workflow

[opencode-agent]

I have updated the cogni-ai-agent.yml workflow to include a session summary step, following the pattern specified in the cogni-ai-agent-action repository.

Changes Made:

1. Added actions: read permission: Updated the cogni-ai-agent job permissions to allow the summary action to retrieve job logs.
2. Added Generate Session Summary step:
   • Invokes Cogni-AI-OU/cogni-ai-agent-action/ai-inference/summary@main.
   • Uses if: always() to ensure a summary (including failure analysis) is generated even if the agent execution fails.
   • Provides the necessary github_token.

Verification:

• Validated the modified workflow using actionlint via pre-commit.
• Verified YAML formatting using yamllint via pre-commit.

The summary action will now automatically generate a human-readable execution summary and visual audit report in the GitHub Actions job summary after each agent run.

Triggered by workflow_dispatch

opencode session  |  github run

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Updates the cogni-ai-agent GitHub Actions workflow to grant read access to Actions data and append a new, always-running session summary step that invokes the shared summary action with the appropriate GitHub token.

File-Level Changes

Change	Details	Files
Adjust job permissions so the workflow can read Actions data required for generating summaries.	Add actions: read to the cogni-ai-agent job permissions block while keeping existing write permissions intact	.github/workflows/cogni-ai-agent.yml
Add a post-run session summary step that always executes and calls the shared summary action with credentials.	Append a Generate Session Summary step after the agent execution step Configure the step with if: always() so it runs even when previous steps fail Invoke Cogni-AI-OU/cogni-ai-agent-action/ai-inference/summary@main Pass secrets.GITHUB_TOKEN to the action via the github_token input	.github/workflows/cogni-ai-agent.yml

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[kenorb]

/co Add as a separate job as per example.

[sourcery-ai]

Hey - I've left some high level feedback:

• Consider pinning Cogni-AI-OU/cogni-ai-agent-action/ai-inference/summary to a specific tag or commit SHA instead of @main to avoid unexpected behavior from upstream changes.
• You can use the built-in ${{ github.token }} instead of secrets.GITHUB_TOKEN for github_token to align with current GitHub Actions best practices and keep the config slightly clearer.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Consider pinning `Cogni-AI-OU/cogni-ai-agent-action/ai-inference/summary` to a specific tag or commit SHA instead of `@main` to avoid unexpected behavior from upstream changes.
- You can use the built-in `${{ github.token }}` instead of `secrets.GITHUB_TOKEN` for `github_token` to align with current GitHub Actions best practices and keep the config slightly clearer.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[opencode-agent]

I have updated the .github/workflows/cogni-ai-agent.yml workflow to move the session summary generation into a dedicated job, following the recommended pattern and addressing recent code review feedback.

Changes Summary:

1. Isolated Summary Job: Created a new summary job that runs after cogni-ai-agent finishes. This job is configured with if: always() && needs.cogni-ai-agent.result != 'skipped' to ensure summaries are generated even if the agent fails, while avoiding runs when the agent is skipped.
2. Reduced Agent Permissions: Removed the actions: read permission from the cogni-ai-agent job as it is no longer needed there, adhering to the principle of least privilege.
3. Best Practices & Security:
   • Switched from secrets.GITHUB_TOKEN to the built-in ${{ github.token }}.
   • Pinned the summary action to a specific commit SHA (d883c78527dba26908459dc3c86e2cdeddf42f0a) to ensure workflow stability and security.
4. Validation: Verified the modified workflow using actionlint and yamllint via pre-commit. The file was also automatically formatted using yamlfix.

The session summary will now be generated in a separate job, making the workflow more robust and easier to monitor.

opencode session  |  github run