fix(validate): support enum-based multi-exit and upgrade json-cas to 0.5.3

Two fixes for 'uwf thread start solve-issue' failures: 1. json-cas 0.5.2 (npm) was missing oneOf in ALLOWED_SCHEMA_KEYS. Published json-cas 0.5.3 with the fix, bumped all packages to ^0.5.3. 2. Semantic validator only recognized oneOf-based multi-exit schemas. Roles using $status with enum (e.g. enum: [approved, rejected]) were incorrectly treated as single-exit. Added isEnumMultiExit() support. Changes: - validate-semantic.ts: isEnumMultiExit(), getEnumStatuses(), checkSingleExitMustache() - All package.json: @uncaged/json-cas ^0.5.2 → ^0.5.3 - validate-semantic.test.ts: 5 new enum multi-exit tests (Suite 3b) - solve-issue-tea-worktree.test.ts: updated for current workflow structure 小橘 🍊
2026-05-25 13:06:44 +00:00
parent a40e1bb847
commit 54dc8fcb39
9 changed files with 336 additions and 78 deletions
@@ -1,92 +1,198 @@
 name: "solve-issue"
-description: "End-to-end issue resolution"
+description: "TDD-driven issue resolution for small, focused changes. Loop protection relies on engine maxRounds."
 roles:
  planner:
-    description: "Creates implementation plan"
-    goal: "You are a planning agent. You analyze issues and create implementation plans grounded in the actual codebase."
+    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
-      - file-read
-      - shell
    procedure: |
-      1. Locate the code repository:
-         - Check if the current working directory is the repo (look for package.json, .git, etc.)
-         - If the task mentions a repo URL, clone it first.
-         - If this is a new project, create the repo and note the path.
-      2. Explore the codebase — read the relevant source files mentioned in the issue. Understand the current architecture, types, and conventions (check CLAUDE.md, CONTRIBUTING.md, .cursor/rules/).
-      3. Identify which files need changes and what the changes should be, with specific code references.
-      4. Output the plan with:
-         - `repoPath`: absolute path to the repository root
-         - `plan`: detailed implementation plan with file paths and code references
-         - `steps`: concrete action items for the developer
-    output: |
-      Provide repoPath, plan summary, and steps in the frontmatter.
-      The plan MUST reference actual file paths and code structures you found by reading the source.
-      Do NOT guess — if you haven't read a file, read it before referencing it.
+      On first run (no previous steps):
+      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
+
+      On subsequent runs (bounced back by tester with 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
+
+      After producing the test spec:
+      1. Store it via `uwf cas put-text "<markdown content>"` and capture the returned hash
+      2. Put the hash in frontmatter.plan (required when $status=ready)
+      3. Set repoPath to the absolute path of the repository root
+    output: "Output a brief summary of the test spec. Set $status to ready (with plan hash and repoPath) or insufficient_info."
    frontmatter:
-      type: object
-      properties:
-        $status:
-          enum: ["_"]
-        repoPath:
-          type: string
-        plan:
-          type: string
-      required: [$status, repoPath, plan]
+      oneOf:
+        - properties:
+            $status: { const: "ready" }
+            plan: { type: string }
+            repoPath: { type: string }
+          required: [$status, plan, repoPath]
+        - properties:
+            $status: { const: "insufficient_info" }
+          required: [$status]
  developer:
-    description: "Implements code changes"
-    goal: "You are a developer agent. You implement code changes according to plans."
+    description: "TDD implementation per test spec"
+    goal: "You are a developer agent. You implement code changes following TDD — write tests first, then implementation."
    capabilities:
-      - file-edit
-      - shell
-      - testing
+      - coding
    procedure: |
-      1. Read the planner's output to get the repoPath and implementation plan.
-      2. cd to the repoPath before making any changes.
-      3. Create a feature branch from the default branch.
-      4. Implement the plan — write code, tests, and ensure existing tests pass.
-      5. Run the project's lint/check command (e.g. `bun run check`, `npm run lint`) and fix ALL errors before proceeding. Build and lint must pass cleanly.
-      6. Commit your changes with a descriptive message referencing the issue.
-    output: "List all files changed and provide a summary of the implementation."
+      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> && bun install`
+      4. If bounced back from reviewer or tester (branch already exists):
+         - cd into the existing worktree under `.worktrees/fix/<issue-number>-<short-slug>`
+         - `git fetch origin && git rebase origin/main`
+      5. ALL subsequent work must happen inside the worktree directory.
+
+      Then implement TDD:
+      6. Read the test spec from CAS: `uwf cas 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 `bun run build` passes with no errors
+      11. Run `bun 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:
-      type: object
-      properties:
-        $status:
-          enum: ["_"]
-        filesChanged:
-          type: array
-          items:
-            type: string
-        summary:
-          type: string
-      required: [$status, filesChanged, summary]
+      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: "Reviews code changes"
-    goal: "You are a code reviewer. You review implementations for correctness and quality."
+    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: |
-      1. Run hard checks first — build (`bun run build` or equivalent) and lint (`bunx biome check .` or equivalent) MUST pass with zero errors. If they fail, reject immediately.
-      2. Then review code quality: correctness, edge cases, naming, project conventions (CLAUDE.md), and test coverage.
-      3. Only reject for hard check failures or genuine correctness/security issues. Style suggestions alone should not block approval.
-    output: "Approve or reject with detailed comments explaining your decision."
+      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. `bun run build` — no build errors
+      4. `bunx biome 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:
-      type: object
-      properties:
-        $status:
-          enum: ["approved", "rejected"]
-        comments:
-          type: string
-      required: [$status, comments]
+      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 `bun test` for automated test verification
+      2. Read the test spec from CAS: `uwf cas 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:
  $START:
-    _: { role: "planner", prompt: "Analyze the issue described in the task and produce a detailed implementation plan." }
+    _: { role: "planner", prompt: "Analyze the issue and produce an implementation plan." }
  planner:
-    _: { role: "developer", prompt: "Implement the plan from the planner. Write code, tests, and ensure existing tests pass." }
+    insufficient_info: { role: "$END", prompt: "Insufficient information to proceed; end the workflow." }
+    ready: { role: "developer", prompt: "Implement the TDD test spec (CAS hash: {{{plan}}}) in repo {{{repoPath}}}." }
  developer:
-    _: { role: "reviewer", prompt: "Review the developer's implementation against the plan for correctness and quality." }
+    done: { role: "reviewer", prompt: "Review branch {{{branch}}} at {{{worktree}}} for code standards compliance." }
+    failed: { role: "$END", prompt: "Developer failed: {{{reason}}}. Ending workflow." }
  reviewer:
-    approved: { role: "$END", prompt: "The review passed. Complete the workflow." }
-    rejected: { role: "developer", prompt: "The reviewer rejected your implementation. Read their feedback and fix the issues: {{{comments}}}" }
+    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." }
@@ -11,8 +11,8 @@
    "uwf": "./src/cli.ts"
  },
  "dependencies": {
-    "@uncaged/json-cas": "^0.5.2",
-    "@uncaged/json-cas-fs": "^0.5.2",
+    "@uncaged/json-cas": "^0.5.3",
+    "@uncaged/json-cas-fs": "^0.5.3",
    "@uncaged/workflow-protocol": "workspace:^",
    "@uncaged/workflow-util": "workspace:^",
    "@uncaged/workflow-util-agent": "workspace:^",
@@ -250,6 +250,110 @@ describe("Suite 3: Status-Edge Consistency", () => {
  });
 });

+describe("Suite 3b: Enum-Based Multi-Exit", () => {
+  test("3b.1 enum multi-exit passes with matching graph keys", () => {
+    const wf = makeWorkflow();
+    wf.roles.reviewer = {
+      ...wf.roles.reviewer,
+      frontmatter: {
+        type: "object",
+        properties: {
+          $status: { enum: ["approved", "rejected"] },
+          comments: { type: "string" },
+        },
+        required: ["$status", "comments"],
+      } as unknown as string,
+    };
+    wf.graph.reviewer = {
+      approved: { role: "$END", prompt: "Done" },
+      rejected: { role: "writer", prompt: "Fix: {{{comments}}}" },
+    };
+    const errors = validateWorkflow(wf);
+    expect(errors).toEqual([]);
+  });
+
+  test("3b.2 enum multi-exit with extra graph key", () => {
+    const wf = makeWorkflow();
+    wf.roles.reviewer = {
+      ...wf.roles.reviewer,
+      frontmatter: {
+        type: "object",
+        properties: {
+          $status: { enum: ["approved", "rejected"] },
+          comments: { type: "string" },
+        },
+        required: ["$status", "comments"],
+      } as unknown as string,
+    };
+    wf.graph.reviewer = {
+      approved: { role: "$END", prompt: "Done" },
+      rejected: { role: "writer", prompt: "Fix" },
+      timeout: { role: "$END", prompt: "Timed out" },
+    };
+    const errors = validateWorkflow(wf);
+    expect(errors.some((e) => e.includes("extra status keys: timeout"))).toBe(true);
+  });
+
+  test("3b.3 enum multi-exit with missing graph key", () => {
+    const wf = makeWorkflow();
+    wf.roles.reviewer = {
+      ...wf.roles.reviewer,
+      frontmatter: {
+        type: "object",
+        properties: {
+          $status: { enum: ["approved", "rejected"] },
+          comments: { type: "string" },
+        },
+        required: ["$status", "comments"],
+      } as unknown as string,
+    };
+    wf.graph.reviewer = {
+      approved: { role: "$END", prompt: "Done" },
+    };
+    const errors = validateWorkflow(wf);
+    expect(errors.some((e) => e.includes("missing status keys: rejected"))).toBe(true);
+  });
+
+  test("3b.4 enum with single value (not multi-exit) treated as single-exit", () => {
+    const wf = makeWorkflow();
+    wf.roles.writer = {
+      ...wf.roles.writer,
+      frontmatter: {
+        type: "object",
+        properties: {
+          $status: { enum: ["_"] },
+          plan: { type: "string" },
+        },
+        required: ["$status", "plan"],
+      } as unknown as string,
+    };
+    wf.graph.writer = { _: { role: "reviewer", prompt: "Review: {{{plan}}}" } };
+    const errors = validateWorkflow(wf);
+    expect(errors).toEqual([]);
+  });
+
+  test("3b.5 enum multi-exit mustache var not in frontmatter", () => {
+    const wf = makeWorkflow();
+    wf.roles.reviewer = {
+      ...wf.roles.reviewer,
+      frontmatter: {
+        type: "object",
+        properties: {
+          $status: { enum: ["approved", "rejected"] },
+          comments: { type: "string" },
+        },
+        required: ["$status", "comments"],
+      } as unknown as string,
+    };
+    wf.graph.reviewer = {
+      approved: { role: "$END", prompt: "Done: {{{nonexistent}}}" },
+      rejected: { role: "writer", prompt: "Fix: {{{comments}}}" },
+    };
+    const errors = validateWorkflow(wf);
+    expect(errors.some((e) => e.includes("nonexistent") && e.includes("not found"))).toBe(true);
+  });
+});
+
 describe("Suite 4: Mustache Template Variable Existence", () => {
  test("4.1 prompt references nonexistent variable (single-exit)", () => {
    const wf = makeWorkflow();
@@ -23,6 +23,28 @@ function isOneOfSchema(fm: unknown): fm is SchemaObj & { oneOf: SchemaObj[] } {
  return Array.isArray(obj.oneOf);
 }

+/** Check if a frontmatter schema uses enum-based multi-exit ($status with multiple enum values). */
+function isEnumMultiExit(fm: unknown): boolean {
+  if (typeof fm !== "object" || fm === null) return false;
+  const obj = fm as SchemaObj;
+  const props = obj.properties as Record<string, SchemaObj> | undefined;
+  if (!props?.$status) return false;
+  const statusDef = props.$status;
+  if (!Array.isArray(statusDef.enum)) return false;
+  // Filter out "_" (wildcard) — if remaining values > 1, it's multi-exit
+  const statuses = (statusDef.enum as string[]).filter((s) => s !== "_");
+  return statuses.length > 1;
+}
+
+/** Extract status values from an enum-based $status field. */
+function getEnumStatuses(fm: SchemaObj): string[] {
+  const props = fm.properties as Record<string, SchemaObj> | undefined;
+  if (!props?.$status) return [];
+  const statusDef = props.$status;
+  if (!Array.isArray(statusDef.enum)) return [];
+  return (statusDef.enum as string[]).filter((s) => s !== "_");
+}
+
 /** Get property names from a schema object. */
 function getPropertyNames(schema: SchemaObj): Set<string> {
  const props = schema.properties;
@@ -230,6 +252,11 @@ function checkRoleConsistency(payload: WorkflowPayload, errors: string[]): void
      checkOneOfDiscriminant(roleName, variants, statuses, errors);
      checkMultiExitEdges(roleName, graphKeys, new Set(statuses), errors);
      checkMultiExitMustache(roleName, graphEntry, variants, errors);
+    } else if (isEnumMultiExit(fm)) {
+      const statuses = getEnumStatuses(fm as SchemaObj);
+      checkMultiExitEdges(roleName, graphKeys, new Set(statuses), errors);
+      // For enum-based schemas, mustache vars come from the flat properties
+      checkSingleExitMustache(roleName, graphEntry, fm as SchemaObj, errors);
    } else {
      checkSingleExitRole(roleName, graphKeys, graphEntry, fm as SchemaObj | null, errors);
    }
@@ -265,6 +292,27 @@ function checkSingleExitRole(
  }
 }

+/** Check mustache vars in all edge prompts against flat schema properties. */
+function checkSingleExitMustache(
+  roleName: string,
+  graphEntry: Record<string, { role: string; prompt: string }>,
+  fm: SchemaObj,
+  errors: string[],
+): void {
+  const propNames = getPropertyNames(fm);
+  for (const [status, target] of Object.entries(graphEntry)) {
+    const vars = extractMustacheVars(target.prompt);
+    for (const v of vars) {
+      if (v === "$status") continue;
+      if (!propNames.has(v)) {
+        errors.push(
+          `prompt variable "${v}" in graph[${roleName}][${status}] not found in role "${roleName}" frontmatter`,
+        );
+      }
+    }
+  }
+}
+
 /**
 * Validate a parsed WorkflowPayload for semantic correctness.
 * Returns an array of error messages. Empty array = valid.
@@ -22,7 +22,7 @@
    "test:ci": "bun test"
  },
  "dependencies": {
-    "@uncaged/json-cas": "^0.5.2",
+    "@uncaged/json-cas": "^0.5.3",
    "@uncaged/workflow-util-agent": "workspace:^",
    "@uncaged/workflow-util": "workspace:^"
  },
@@ -22,7 +22,7 @@
    "test:ci": "bun test"
  },
  "dependencies": {
-    "@uncaged/json-cas": "^0.5.2",
+    "@uncaged/json-cas": "^0.5.3",
    "@uncaged/workflow-util-agent": "workspace:^",
    "@uncaged/workflow-util": "workspace:^"
  },
@@ -22,7 +22,7 @@
    "test:ci": "bun test __tests__/*.test.ts"
  },
  "dependencies": {
-    "@uncaged/json-cas": "^0.5.2",
+    "@uncaged/json-cas": "^0.5.3",
    "@uncaged/workflow-util-agent": "workspace:^",
    "@uncaged/workflow-protocol": "workspace:^",
    "@uncaged/workflow-util": "workspace:^"
@@ -15,8 +15,8 @@
    }
  },
  "dependencies": {
-    "@uncaged/json-cas": "^0.5.2",
-    "@uncaged/json-cas-fs": "^0.5.2"
+    "@uncaged/json-cas": "^0.5.3",
+    "@uncaged/json-cas-fs": "^0.5.3"
  },
  "devDependencies": {
    "typescript": "^5.8.3"
@@ -19,8 +19,8 @@
    "test:ci": "bun test"
  },
  "dependencies": {
-    "@uncaged/json-cas": "^0.5.2",
-    "@uncaged/json-cas-fs": "^0.5.2",
+    "@uncaged/json-cas": "^0.5.3",
+    "@uncaged/json-cas-fs": "^0.5.3",
    "@uncaged/workflow-protocol": "workspace:^",
    "@uncaged/workflow-util": "workspace:^",
    "dotenv": "^16.6.1",