Review PR Fix — Autonomous Agents Agentic Workflow

schema_version: 1
id: agent_qa_validate
title: "Review PR Fix"
description: "Review PR code against ticket acceptance criteria — does NOT test live site"
overview: |
  A code-level QA review that checks whether a PR's changes actually satisfy the acceptance criteria on the linked ticket. The agent reads the ticket, then reads the PR diff line-by-line, mapping each requirement to the code that implements it. If something in the criteria has no backing code, that is called out explicitly.

  This workflow never touches a running site — it is a gating step before deploy, not a validation of deployed behaviour. Output is an approval, a request-changes with specific line references, or a block decision with rationale, all posted to the ticket and the PR.

category:
  level: pipeline
  domain: engineering

metadata:
  agent: true
  role: qa
  # Gate-verdict vocabulary for portal playbook steps (PLAYBOOKS.md §5) — matched from the
  # step's ticket comment; declaring it here is what makes this workflow content-routable.
  verdicts: [PASS, FAIL]

params:
  agentic_app:
    type: string
    default: "cc"
    description: "Agent-app slug selecting the per-run env file ~/.agent-env.d/<slug> (AAP-C); 'cc'/subscription clears provider vars"
  ticket_url:
    type: string
    description: "Jira ticket URL"
  hint:
    type: string
    default: ""
    description: "Optional extra instructions for the agent"
  entry_path:
    type: string
    default: "~/workspace"
    description: "Working directory for the agent"

steps:
  - type: terminal.open
    title: "Agent: QA Review PR Fix"
    cwd: "{{entry_path}}"
  - type: terminal.run
    cmd: |
      source ~/.agent-env
      # AAP-C (SCRUM-1506) + AAP-17 (SCRUM-1653): clear EVERY provider var an agent-app can deliver so
      # none hijacks/poisons a subscription run. A stray global ANTHROPIC_MODEL / ANTHROPIC_SMALL_FAST_MODEL
      # needs no CLAUDE_CODE_USE_* flag, so the old ${!CLAUDE_CODE_USE_@} glob never caught it — it survived
      # into the run and 404-ed aux/small-fast calls against api.anthropic.com. This explicit list mirrors
      # AGENT_APP_ENV_KEYS 1:1 (the-assistant website/src/lib/cloud/agent-app-env.ts — the single source of
      # truth; a parity test in each repo guards the two from drifting). Explicit over a glob: the union has
      # non-ANTHROPIC_ members (AWS_REGION, AWS_PROFILE, CLOUD_ML_REGION, CLAUDE_CODE_MAX_OUTPUT_TOKENS) and
      # a ${!AWS_@} glob would over-clear unrelated creds. Then source the per-run app env by slug when it
      # exists; no file => subscription/default. base/19-secrets stages ~/.agent-env.d/<slug>.
      unset \
        ANTHROPIC_API_KEY ANTHROPIC_BASE_URL ANTHROPIC_AUTH_TOKEN CCR_CONFIG_B64 \
        CLAUDE_CODE_USE_BEDROCK AWS_REGION AWS_PROFILE ANTHROPIC_MODEL \
        ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION ANTHROPIC_SMALL_FAST_MODEL CLAUDE_CODE_MAX_OUTPUT_TOKENS \
        CLAUDE_CODE_USE_VERTEX CLOUD_ML_REGION ANTHROPIC_VERTEX_PROJECT_ID ANTHROPIC_VERTEX_BASE_URL \
        CLAUDE_CODE_USE_FOUNDRY ANTHROPIC_FOUNDRY_RESOURCE ANTHROPIC_FOUNDRY_BASE_URL \
        ANTHROPIC_DEFAULT_OPUS_MODEL ANTHROPIC_DEFAULT_SONNET_MODEL ANTHROPIC_DEFAULT_HAIKU_MODEL
      if [ -f "$HOME/.agent-env.d/{{agentic_app}}" ]; then
        source "$HOME/.agent-env.d/{{agentic_app}}"
      fi
      claude --dangerously-skip-permissions "$(cat <<'SB_PROMPT'
      read ticket with attachments and all comments - {{ticket_url}}. if it fails, stop and report the error.
      learn how to QA relevant parts.
      IMPORTANT — the fix is in a PR branch, NOT deployed to production. do NOT test the live site to verify the fix.
      1. find the PR link in ticket comments.
      2. review the PR diff for correctness against acceptance criteria.
      3. check out the branch locally and build/test if possible.
      4. if not buildable, do a thorough diff review against the ticket requirements.
      5. check edge cases by reviewing code paths changed in the PR.
      you MAY confirm the bug exists on the live site as a baseline, but do NOT expect the fix to be live.
      {{hint}}
      save each evidence file, publish it via the publish_artifact tool, and cite the returned download link inline in your single ticket comment; if publish_artifact is unavailable, save under ~/workspace/artifacts/ for post-run collection.
      write one comment to the ticket with: pre-fix baseline (optional), PR fix verification, edge case analysis, and verdict (PASS or FAIL).
      UNATTENDED RUN — this is a dispatched job: nobody is watching this terminal and nobody will answer, so never call AskUserQuestion and never end your turn by putting a question to the operator. Apply the policy stated above and carry it out as written, including where carrying it out is destructive — the call to run this job was made when it was dispatched, and it is not yours to re-take. Where that policy leaves a genuine choice, make it yourself and keep going; only where it is genuinely SILENT, prefer the option that does not destroy work nobody can recreate. Say what you decided and what you skipped and why — but INSIDE the report this prompt already specifies: wherever a report shape, a token vocabulary or a last-line verdict is stated above, that format still binds exactly as written, and this clause adds no section, no token and nothing after the last line. Questions the deliverable is MEANT to contain are content, not an unanswered prompt. Asking does not pause the job either: an unanswered prompt is auto-answered from the option ordering once the unattended wait budget lapses (KAN-204), so asking only burns ~15 minutes of the run and hands a real decision to a default.
      SB_PROMPT
      )"