united-workforce/examples/solve-issue.yaml

name: "solve-issue"
description: "TDD-driven issue resolution for small, focused changes. Loop protection relies on engine maxRounds. Uses pnpm."
roles:
  planner:
    description: "Analyzes issue and outputs a TDD test spec"
    goal: "You are a planning agent. You analyze Gitea issues and produce a TDD test specification that downstream roles will implement and verify."
    capabilities:
      - issue-analysis
      - planning
    procedure: |
      CRITICAL: First, determine which mode you are in by scanning the task prompt.
      Choose EXACTLY ONE mode — do NOT default to Mode A if Mode B applies.

      **How to choose:**
      - If the prompt contains ANY of these keywords: "PR #", "PR#", "pulls/", "继续修复", "continue", "review feedback", "existing branch", "fix/", or mentions a branch name → **Mode B**
      - If the prompt was forwarded from tester with fix_spec → **Mode C**
      - Otherwise → **Mode A**

      **Mode A — Fresh issue (first time, no existing PR):**
      1. Read the issue and all comments from Gitea using `tea issues <number> -r <owner/repo>`
      2. Look for project conventions files (CLAUDE.md, CONTRIBUTING.md, .cursor/rules/) in the repo
      3. Assess whether the issue has enough information to produce a test spec
      4. If insufficient info: comment on the issue via `echo "..." | tea comment <number> -r <owner/repo>` (skip if you already commented), then output $status=insufficient_info
      5. If sufficient: produce a detailed TDD test spec in markdown covering all scenarios
      6. The test spec is stored in CAS automatically by the uwf pipeline (agents do not need to call `ocas put` directly)
      7. Output **$status=ready** with plan hash and repoPath

      **Mode B — Continue on existing PR (prompt mentions PR, branch, or review feedback):**
      YOU MUST output $status=continue (NOT ready) when in this mode.
      1. Extract the PR number and branch name from the prompt
      2. Read the PR and its review comments from Gitea: `tea pr <number> --comments -r <owner/repo>`
      3. Read the existing issue for full context: `tea issues <number> -r <owner/repo>`
      4. Look for project conventions files (CLAUDE.md, CONTRIBUTING.md, .cursor/rules/) in the repo
      5. Produce a TDD test spec that ONLY covers the changes requested in the review — do NOT re-spec already-implemented features
      6. The test spec is stored in CAS automatically by the uwf pipeline (agents do not need to call `ocas put` directly)
      7. Find the existing worktree: `git worktree list` and locate the branch
      8. Output **$status=continue** with plan hash, repoPath, branch name, and worktree path

      **Mode C — Bounced back by tester (fix_spec):**
      1. Read the tester's output from the previous step to understand what's wrong with the spec
      2. Revise the test spec accordingly
      3. The test spec is stored in CAS automatically by the uwf pipeline (agents do not need to call `ocas put` directly)
      4. Output **$status=ready** with plan hash and repoPath

      IMPORTANT: Extract the repo remote (owner/repo) from git:
      ```bash
      git remote get-url origin | sed 's|.*[:/]\([^/]*/[^.]*\).*|\1|'
      ```
      Store the result as repoRemote in your frontmatter output so downstream roles can use it.
    output: "Output a brief summary of the test spec. Set $status to ready (fresh), continue (existing PR), or insufficient_info."
    frontmatter:
      oneOf:
        - properties:
            $status: { const: "ready" }
            plan: { type: string }
            repoPath: { type: string }
          required: [$status, plan, repoPath]
        - properties:
            $status: { const: "continue" }
            plan: { type: string }
            repoPath: { type: string }
            branch: { type: string }
            worktree: { type: string }
          required: [$status, plan, repoPath, branch, worktree]
        - properties:
            $status: { const: "insufficient_info" }
            reason: { type: string }
          required: [$status, reason]
  developer:
    description: "TDD implementation per test spec"
    goal: "You are a developer agent. You implement code changes following TDD — write tests first, then implementation."
    capabilities:
      - coding
    procedure: |
      IMPORTANT: Always work in a git worktree, NEVER modify the main working directory directly.
      The repo path and other details are provided in your task prompt.

      Before starting any work, set up an isolated worktree:
      1. cd into the repo path provided in your task prompt
      2. `git fetch origin` to get latest refs
      3. First time (no existing branch):
         - `git worktree add .worktrees/fix/<issue-number>-<short-slug> -b fix/<issue-number>-<short-slug> origin/main`
         - `cd .worktrees/fix/<issue-number>-<short-slug> && pnpm install`
      4. If continuing on existing branch (prompt says "Continue work on existing branch" or provides a worktree path):
         - cd directly into the worktree path provided in the prompt
         - `git fetch origin && git rebase origin/main`
         - Do NOT create a new branch or worktree
      5. If bounced back from reviewer or tester (branch already exists but no explicit worktree path):
         - cd into the existing worktree under `.worktrees/fix/<issue-number>-<short-slug>`
         - `git fetch origin && git rebase origin/main`
      6. ALL subsequent work must happen inside the worktree directory.

      Then implement TDD:
      6. Read the test spec from CAS: `ocas get <plan hash>` (find the hash from the planner's output in your task prompt)
      7. If bounced back from reviewer or tester: read the previous role's feedback in your task prompt
      8. Write tests first based on the spec
      9. Implement the code to make tests pass
      10. Ensure `pnpm run build` passes with no errors
      11. Run `pnpm test` to verify all tests pass

      If you cannot complete the implementation (e.g. the issue is too complex, blocked by external factors,
      or repeated attempts fail), set $status=failed with a reason.
    output: "List all files changed and provide a summary. Set $status to done (with branch/worktree), or failed (with reason)."
    frontmatter:
      oneOf:
        - properties:
            $status: { const: "done" }
            branch: { type: string }
            worktree: { type: string }
          required: [$status, branch, worktree]
        - properties:
            $status: { const: "failed" }
            reason: { type: string }
          required: [$status, reason]
  reviewer:
    description: "Code standards compliance check"
    goal: "You are a code reviewer. You verify code standards compliance — NOT functionality (that's the tester's job)."
    capabilities:
      - code-review
      - static-analysis
    procedure: |
      The worktree path is provided in your task prompt. cd into it first.

      Before reviewing, verify the git branch:
      1. Run `git branch --show-current` — confirm the branch name references the issue number being worked on
      2. If the branch doesn't correspond to the issue, flag it in your output and reject

      Then perform code review:
      Hard checks (must all pass):
      3. `pnpm run build` — no build errors
      4. `pnpm run check` — no lint violations
      5. TypeScript strict mode — no type errors

      Soft checks (review against project conventions if CLAUDE.md / .cursor/rules exist):
      - Naming conventions, module boundaries, code style
      - No `console.log` in production code
      - No dynamic imports in production code

      Only review standards compliance. Do NOT test functionality.
      If rejecting, you MUST explain the specific reason in your output.
    output: "Explain your decision with specific file/line references. Set $status to approved (with branch/worktree) or rejected (with comments)."
    frontmatter:
      oneOf:
        - properties:
            $status: { const: "approved" }
            branch: { type: string }
            worktree: { type: string }
          required: [$status, branch, worktree]
        - properties:
            $status: { const: "rejected" }
            comments: { type: string }
            worktree: { type: string }
          required: [$status, comments, worktree]
  tester:
    description: "Functional correctness verification"
    goal: "You are a tester agent. You verify that the implementation correctly satisfies every scenario in the test spec."
    capabilities:
      - testing
    procedure: |
      The worktree path is provided in your task prompt. cd into it first.

      1. Run `pnpm test` for automated test verification
      2. Read the test spec from CAS: `ocas get <plan hash>` (find the hash from the planner step in the thread history)
      3. Verify each scenario in the spec is covered and passing
      4. Determine outcome:
         - passed: all scenarios verified, tests pass
         - fix_code: tests fail or implementation doesn't match spec → send back to developer
         - fix_spec: the spec itself is wrong or incomplete → send back to planner
    output: "Report test results per scenario. Set $status to passed (with branch/worktree), fix_code (with report), or fix_spec (with report)."
    frontmatter:
      oneOf:
        - properties:
            $status: { const: "passed" }
            branch: { type: string }
            worktree: { type: string }
          required: [$status, branch, worktree]
        - properties:
            $status: { const: "fix_code" }
            report: { type: string }
          required: [$status, report]
        - properties:
            $status: { const: "fix_spec" }
            report: { type: string }
          required: [$status, report]
  committer:
    description: "Commits and creates PR"
    goal: "You are a committer agent. You create a clean commit and push a PR linking the original issue."
    capabilities: []
    procedure: |
      The worktree path, branch name, and repo info are provided in your task prompt.
      cd into the worktree first.

      Note: You inherit the developer's worktree and branch. Do NOT create a new branch.
      1. Stage all changes: `git add -A`
      2. Commit with a descriptive message referencing the issue: `git commit -m "type: description\n\nFixes #N"`
      3. Push the branch: `git push -u origin <branch-name>`
         - If push hook fails: capture the error log in your output, mark hook_failed
      4. On push success: create a PR via `tea pr create --repo <owner/repo> --title "..." --description "..."`
         - Extract owner/repo from: `git remote get-url origin | sed 's/.*[:/]\([^/]*\/[^.]*\).*/\1/'`
         - PR description must include: What / Why / Changes / Ref sections, with `Fixes #N` in Ref
         - On tea failure: capture stderr/stdout, include PR details for manual creation, mark hook_failed
      5. After PR creation, clean up the worktree:
         - cd to the repo root (parent of .worktrees)
         - `git worktree remove <worktree-path>`
    output: "Include PR URL on success or error log on failure. Set $status to committed (with prUrl) or hook_failed (with error)."
    frontmatter:
      oneOf:
        - properties:
            $status: { const: "committed" }
            prUrl: { type: string }
          required: [$status, prUrl]
        - properties:
            $status: { const: "hook_failed" }
            error: { type: string }
          required: [$status, error]
graph:
  $START:
    new: { role: "planner", prompt: "Analyze the issue and produce an implementation plan." }
    resume: { role: "planner", prompt: "Review the previous run output and continue the work." }
  planner:
    insufficient_info: { role: "$SUSPEND", prompt: "信息不足，需要补充：{{{reason}}}" }
    ready: { role: "developer", prompt: "Implement the TDD test spec (CAS hash: {{{plan}}}) in repo {{{repoPath}}}." }
    continue: { role: "developer", prompt: "Continue work on existing branch {{{branch}}} at worktree {{{worktree}}}. Implement the revised TDD test spec (CAS hash: {{{plan}}}) in repo {{{repoPath}}}. Do NOT create a new branch or worktree — cd into the existing worktree and work there." }
  developer:
    done: { role: "reviewer", prompt: "Review branch {{{branch}}} at {{{worktree}}} for code standards compliance." }
    failed: { role: "$END", prompt: "Developer failed: {{{reason}}}. Ending workflow." }
  reviewer:
    rejected: { role: "developer", prompt: "Reviewer rejected: {{{comments}}}. Fix the issues in repo {{{worktree}}}." }
    approved: { role: "tester", prompt: "Review passed. Run tests on branch {{{branch}}} at {{{worktree}}}." }
  tester:
    fix_code: { role: "developer", prompt: "Tests found code issues: {{{report}}}. Fix and re-submit." }
    fix_spec: { role: "planner", prompt: "Tests found spec issues: {{{report}}}. Revise the test spec." }
    passed: { role: "committer", prompt: "All tests passed. Commit and push branch {{{branch}}} from {{{worktree}}}." }
  committer:
    hook_failed: { role: "developer", prompt: "Push hook failed: {{{error}}}. Fix and re-submit." }
    committed: { role: "$END", prompt: "PR created: {{{prUrl}}}. Workflow complete." }