refactor(cli-workflow): reduce cmdStepRead cognitive complexity

Extract four helper functions from cmdStepRead to reduce cognitive
complexity from 27 to ≤15:
- loadStepDetail: Load and validate step detail node
- loadTurnData: Load all turn nodes and extract content
- selectTurnsForQuota: Select turns within quota (≥1 always shown)
- formatStepMarkdown: Assemble final markdown output

All 6 existing tests pass. Zero Biome warnings. CLAUDE.md compliant.

Fixes #487

.cursor/rules/sync-readme.mdc

@@ -0,0 +1,67 @@
+# Sync README
+
+When updating README.md files in this monorepo, follow these conventions.
+
+## Scope
+
+- Root `README.md` — project overview and navigation hub
+- Per-package `packages/*/README.md` — each package self-contained
+
+## Root README Structure
+
+The root README should have these sections in order:
+
+1. **Title and one-liner** — stateless workflow engine driven by single-step CLI
+2. **Overview** — 2-3 paragraphs explaining what it does and key concepts
+3. **Architecture** — dependency layer diagram (text-based)
+4. **Packages** — table with ALL packages from packages/ directory, columns: Package, Description, Type (cli/lib/agent/app)
+5. **Quick Start** — install, build, register workflow, start thread, run step
+6. **CLI Reference** — brief command list, detailed usage in cli-workflow README
+7. **Development** — bun install / build / check / test
+
+## Per-Package README Structure
+
+Each package README should have:
+
+1. **Title** — package name
+2. **One-line description** — matching package.json
+3. **Overview** — what it does, where it sits in the architecture, dependencies
+4. **Installation** — bun add (for libs) or "included as binary" (for cli/agents)
+5. **API** (lib packages) — all exports from src/index.ts with type signatures, grouped by category, minimal usage examples
+6. **CLI Usage** (cli/agent packages) — command reference with examples
+7. **Internal Structure** — brief src/ file organization
+8. **Configuration** (if applicable)
+
+## Execution Steps
+
+### Step 1: Gather current state
+For each package read:
+- package.json (name, version, description, dependencies, bin)
+- src/index.ts (public API exports)
+- Existing README.md (preserve hand-written content worth keeping)
+
+### Step 2: Update root README
+- Ensure ALL packages in packages/ directory are listed in the table
+- Update CLI command reference from uwf --help output
+- Keep Quick Start examples valid
+
+### Step 3: Write/update each package README
+- Follow the per-package structure
+- API section MUST match actual src/index.ts exports — never invent
+- For agent packages: document CLI binary name, how it is invoked
+- For lib packages: document exported types and functions
+- Internal structure: list actual files in src/
+
+### Step 4: Verify
+- All relative links work
+- Package names match package.json
+- No references to removed/renamed packages
+- bun run build still passes
+
+## Guidelines
+
+- Only document what src/index.ts actually exports
+- Root README summarizes, package READMEs go into detail
+- Verify CLI examples against actual commands
+- Preserve existing good prose when updating
+- English for all README content

.env.example

@@ -1,40 +0,0 @@
-# ──────────────────────────────────────────────
-# Workflow Engine — Environment Variables
-# ──────────────────────────────────────────────
-# Copy this file to .env and fill in the values.
-
-# ── Cursor Agent ──
-
-# CLI command to invoke the Cursor agent (required for develop workflow)
-WORKFLOW_CURSOR_COMMAND=
-
-# Model override for Cursor agent
-WORKFLOW_CURSOR_MODEL=
-
-# Timeout in milliseconds for Cursor agent operations
-WORKFLOW_CURSOR_TIMEOUT=
-
-# ── Hermes Agent (used by develop tester/committer + solve-issue) ──
-
-# CLI command to invoke the Hermes agent (absolute path required)
-WORKFLOW_HERMES_COMMAND=
-
-# Model override for Hermes agent
-WORKFLOW_HERMES_MODEL=
-
-# Timeout in milliseconds for Hermes agent operations
-WORKFLOW_HERMES_TIMEOUT=
-
-# ── Storage ──
-
-# Override the workflow storage root directory
-# Default: ~/.uncaged/workflow
-WORKFLOW_STORAGE_ROOT=
-
-# Gateway secret for the serve command
-WORKFLOW_DASHBOARD_SECRET=
-
-# ── Display ──
-
-# Set to any value to disable colored output
-# NO_COLOR=1

.gitignore

@@ -11,3 +11,5 @@ solve-issue-entry.ts
 packages/workflow-template-develop/develop.esm.js
 .DS_Store
 *.py
+.claude
+tmp

.plan/335-setup-validate.md

@@ -0,0 +1,83 @@
+# Test Spec: uwf setup model connectivity validation (#335)
+
+## Context
+
+File: `packages/cli-workflow/src/commands/setup.ts`
+Test file: `packages/cli-workflow/src/__tests__/setup-validate.test.ts`
+
+After `cmdSetup` writes config, it should send a test chat completion request to verify the configured model is reachable. If validation fails, warn the user (don't abort — config is already saved).
+
+## Implementation Notes
+
+- Add a `validateModel(baseUrl, apiKey, model)` function that sends a minimal chat completion request (`POST /chat/completions` with `messages: [{role:"user",content:"hi"}]`, `max_tokens: 1`)
+- Returns `Result<void, string>` — ok if 2xx response, error with reason string otherwise
+- Use `AbortSignal.timeout(15_000)` for the request
+- Both `cmdSetup` and `cmdSetupInteractive` should call it after saving config
+- `cmdSetup` returns validation result in its return object: `{ ...existing, validation: { ok: true } | { ok: false, error: string } }`
+- `cmdSetupInteractive` prints a warning to console if validation fails, success message if it passes
+- Use the project logger (`createLogger`) — no raw `console.log` except in interactive CLI output (per CLAUDE.md)
+
+## Test Cases (vitest)
+
+### 1. `validateModel` — success path
+- Mock `fetch` to return `{ status: 200, ok: true, json: () => ({}) }`
+- Call `validateModel(baseUrl, apiKey, model)`
+- Assert returns `{ ok: true, value: undefined }`
+- Assert fetch was called with correct URL (`${baseUrl}/chat/completions`), correct headers (`Authorization: Bearer ${apiKey}`), correct body (model, messages, max_tokens: 1)
+
+### 2. `validateModel` — HTTP error (401 unauthorized)
+- Mock `fetch` to return `{ status: 401, ok: false, statusText: "Unauthorized" }`
+- Call `validateModel(baseUrl, apiKey, model)`
+- Assert returns `{ ok: false, error: <string containing "401"> }`
+
+### 3. `validateModel` — HTTP error (404 model not found)
+- Mock `fetch` to return `{ status: 404, ok: false, statusText: "Not Found" }`
+- Assert returns `{ ok: false, error: <string containing "404"> }`
+
+### 4. `validateModel` — network timeout
+- Mock `fetch` to throw `DOMException` with name `AbortError`
+- Assert returns `{ ok: false, error: <string containing "timeout" or "unreachable"> }`
+
+### 5. `validateModel` — network error (DNS failure, connection refused)
+- Mock `fetch` to throw `TypeError("fetch failed")`
+- Assert returns `{ ok: false, error: <string mentioning connectivity> }`
+
+### 6. `cmdSetup` — includes validation result on success
+- Mock global `fetch` for `/chat/completions` to succeed
+- Call `cmdSetup({ provider, baseUrl, apiKey, model, storageRoot })`
+- Assert returned object has `validation: { ok: true, value: undefined }`
+- Assert config files are still written (existing behavior preserved)
+
+### 7. `cmdSetup` — includes validation result on failure (config still saved)
+- Mock global `fetch` for `/chat/completions` to return 401
+- Call `cmdSetup({ ... })`
+- Assert returned object has `validation: { ok: false, error: ... }`
+- Assert `config.yaml` and `.env` are still written (validation failure doesn't prevent saving)
+
+### 8. `cmdSetupInteractive` — prints success message on validation pass
+- Mock `fetch` for both `/models` and `/chat/completions` to succeed
+- Mock stdin to provide valid selections
+- Capture console output
+- Assert output contains a success message like "Model verified" or "✓"
+
+### 9. `cmdSetupInteractive` — prints warning on validation failure
+- Mock `fetch`: `/models` succeeds, `/chat/completions` returns 401
+- Mock stdin for valid selections
+- Capture console output
+- Assert output contains a warning about model not being reachable and suggests trying a different model
+
+### 10. `validateModel` — request body correctness
+- Mock `fetch` to capture the request body
+- Call `validateModel(baseUrl, apiKey, "test-model")`
+- Assert body is `{ model: "test-model", messages: [{role: "user", content: "hi"}], max_tokens: 1 }`
+
+## Export Requirements
+
+- `validateModel` must be exported (for direct unit testing)
+- Signature: `async function validateModel(baseUrl: string, apiKey: string, model: string): Promise<Result<void, string>>`
+- `Result` type: `{ ok: true; value: T } | { ok: false; error: E }` (project convention)
+
+## Files to Create/Modify
+
+- **New**: `packages/cli-workflow/src/__tests__/setup-validate.test.ts` — all test cases above
+- **Modify**: `packages/cli-workflow/src/commands/setup.ts` — add `validateModel`, integrate into `cmdSetup` and `cmdSetupInteractive`

.workflows/solve-issue.yaml

@@ -0,0 +1,216 @@
+name: "solve-issue"
+description: "TDD-driven issue resolution for small, focused changes. Loop protection relies on engine maxRounds."
+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: |
+      On first run (no previous steps):
+      1. Read the issue and all comments from Gitea using `tea issues <number> -r <owner/repo>`
+      2. Read CLAUDE.md (or equivalent project conventions file) to understand coding standards
+      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 and terminate
+      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)
+    output: "Output a brief summary of the test spec. Frontmatter must include: status (ready or insufficient_info) and plan (CAS hash of the test spec, required when status=ready)."
+    frontmatter:
+      type: object
+      properties:
+        status:
+          type: string
+          enum: [ready, insufficient_info]
+        plan:
+          type: string
+      required: [status]
+  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.
+
+      Before starting any work, set up an isolated worktree:
+      1. `cd ~/repos/workflow && git fetch origin` to get latest refs
+      2. First time (no existing branch):
+         - `git worktree add ~/repos/workflow-worktrees/fix/<issue-number>-<short-slug> -b fix/<issue-number>-<short-slug> origin/main`
+         - `cd ~/repos/workflow-worktrees/fix/<issue-number>-<short-slug> && bun install`
+      3. If bounced back from reviewer or tester (branch already exists):
+         - The worktree should already exist at `~/repos/workflow-worktrees/fix/<issue-number>-<short-slug>`
+         - `cd ~/repos/workflow-worktrees/fix/<issue-number>-<short-slug>`
+         - `git fetch origin && git rebase origin/main`
+      4. ALL subsequent work must happen inside the worktree directory.
+
+      Then implement TDD:
+      5. Read the test spec from CAS: `uwf cas get <plan hash>` (find the hash from the latest planner step's frontmatter.plan)
+      6. If bounced back from reviewer or tester: read the previous role's output to understand what needs fixing
+      7. Write tests first based on the spec
+      8. Implement the code to make tests pass
+      9. Ensure `bun run build` passes with no errors
+      10. Run `bun test` to verify all tests pass
+    output: "List all files changed and provide a summary. Frontmatter must include: status (done or failed)."
+    frontmatter:
+      type: object
+      properties:
+        status:
+          type: string
+          enum: [done, failed]
+      required: [status]
+  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: |
+      First, cd into the worktree: `cd ~/repos/workflow-worktrees/fix/<issue-number>-*` (find the exact directory)
+
+      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 CLAUDE.md conventions):
+      - Functional-first: `function` + `type`, not `class` + `interface`
+      - No optional properties (`?:`) — use `T | null`
+      - Naming conventions (kebab-case files, PascalCase types, camelCase functions)
+      - Module boundary discipline (folder exports via index.ts)
+      - No `console.log` (use structured logger)
+      - 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. Frontmatter must include: approved (true or false)."
+    frontmatter:
+      type: object
+      properties:
+        approved:
+          type: boolean
+      required: [approved]
+  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: |
+      First, cd into the worktree: `cd ~/repos/workflow-worktrees/fix/<issue-number>-*` (find the exact directory)
+
+      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 latest planner step's frontmatter.plan)
+      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. Frontmatter must include: status (passed, fix_code, or fix_spec)."
+    frontmatter:
+      type: object
+      properties:
+        status:
+          type: string
+          enum: [passed, fix_code, fix_spec]
+      required: [status]
+  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: |
+      First, cd into the worktree: `cd ~/repos/workflow-worktrees/fix/<issue-number>-*` (find the exact directory)
+
+      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 uncaged/workflow --title "..." --description "..."`
+         - The `--repo` flag is required to work in worktree directories (fixes #474 "path segment [0] is empty" error)
+         - If working on a different repo, extract owner/repo from: `git remote get-url origin | sed 's/.*[:/]\([^/]*\/[^.]*\).*/\1/'`
+         - PR description must follow the project template: What / Why / Changes / Ref sections, with `Fixes #N` in Ref
+         - On tea failure: capture stderr/stdout, log the error clearly, include PR details (title, description, branch) for manual creation, and mark success=false
+      5. After PR creation, clean up the worktree:
+         - `cd ~/repos/workflow`
+         - `git worktree remove ~/repos/workflow-worktrees/fix/<issue-number>-<slug>`
+    output: "Include PR URL on success or error log on failure. Frontmatter must include: success (true or false)."
+    frontmatter:
+      type: object
+      properties:
+        success:
+          type: boolean
+      required: [success]
+conditions:
+  insufficientInfo:
+    description: "Planner determined there's not enough info to proceed"
+    expression: "$last('planner').status = 'insufficient_info'"
+  devFailed:
+    description: "Developer failed to implement"
+    expression: "$last('developer').status = 'failed'"
+  rejected:
+    description: "Reviewer rejected the implementation"
+    expression: "$last('reviewer').approved = false"
+  fixCode:
+    description: "Tester found code issues"
+    expression: "$last('tester').status = 'fix_code'"
+  fixSpec:
+    description: "Tester found spec issues"
+    expression: "$last('tester').status = 'fix_spec'"
+  hookFailed:
+    description: "Push hook failed"
+    expression: "$last('committer').success = false"
+graph:
+  $START:
+    - role: "planner"
+      condition: null
+      prompt: "Analyze the issue and produce an implementation plan."
+  planner:
+    - role: "$END"
+      condition: "insufficientInfo"
+      prompt: "Insufficient information to proceed; end the workflow."
+    - role: "developer"
+      condition: null
+      prompt: "Implement the plan from the planner."
+  developer:
+    - role: "$END"
+      condition: "devFailed"
+      prompt: "Development failed; end the workflow."
+    - role: "reviewer"
+      condition: null
+      prompt: "Send the implementation to the reviewer."
+  reviewer:
+    - role: "developer"
+      condition: "rejected"
+      prompt: "Reviewer rejected the implementation; fix the issues."
+    - role: "tester"
+      condition: null
+      prompt: "Review passed; run tests on the implementation."
+  tester:
+    - role: "developer"
+      condition: "fixCode"
+      prompt: "Tests found code issues; return to developer."
+    - role: "planner"
+      condition: "fixSpec"
+      prompt: "Tests found spec issues; return to planner."
+    - role: "committer"
+      condition: null
+      prompt: "Tests passed; commit and push the changes."
+  committer:
+    - role: "developer"
+      condition: "hookFailed"
+      prompt: "Push hook failed; return to developer to fix."
+    - role: "$END"
+      condition: null
+      prompt: "Commit succeeded; complete the workflow."

CLAUDE.md

@@ -2,46 +2,41 @@
 
 ## Project Overview
 
-This monorepo implements a workflow engine that executes single-file ESM bundles. Each workflow is a self-contained `.esm.js` file with an XXH64 hash as its version identifier. Shared types live in `@uncaged/workflow-protocol`; bundle authors typically depend on `@uncaged/workflow-runtime`.
+This monorepo implements a stateless workflow engine driven by a single-step CLI (`uwf`). Workflows are **YAML definitions** stored as CAS nodes; threads are immutable chains of CAS-linked step nodes. No daemon — each `uwf thread step` invocation runs one moderator→agent→extract cycle and exits.
 
 ### Key Terms
 
 | Concept | What it is |
 |---------|-----------|
-| **Workflow** | A single-file ESM module that exports `run` (workflow function) and `descriptor` (metadata). Identified by its XXH64 hash (Crockford Base32). |
-| **Bundle** | The physical `.esm.js` file stored in `~/.uncaged/workflow/bundles/`. |
-| **Thread** | A single execution of a workflow, identified by a ULID. State lives in CAS (linked nodes); active threads indexed in `threads.json`; completed rows in `history/*.jsonl`. Debug logs use `.info.jsonl`. |
-| **Role** | A named actor within a workflow. Each role produces output with typed `meta`. |
-| **Registry** | `workflow.yaml` — maps workflow names to current/historical bundle hashes. |
+| **Workflow** | A YAML definition (`WorkflowPayload`) with roles, conditions, and a routing graph. Stored as a CAS node, identified by its XXH64 hash. |
+| **Thread** | A single execution of a workflow, identified by a ULID. State is an immutable CAS chain; active threads indexed in `threads.yaml`; completed threads in `history.jsonl`. |
+| **Role** | A named actor within a workflow. Each role has a system prompt and a JSON Schema `outputSchema`. |
+| **Moderator** | JSONata-based graph evaluator — determines the next role (or `$END`) with zero LLM cost. |
+| **Agent** | An external CLI command (`uwf-hermes`, etc.) spawned by `uwf thread step`. Produces frontmatter markdown output. |
+| **CAS** | Content-Addressed Storage via `@uncaged/json-cas` — all workflow definitions, thread nodes, and outputs are immutable CAS nodes. |
+| **Registry** | `~/.uncaged/workflow/registry.yaml` — maps workflow names to current CAS hashes. |
 
 ### Monorepo Structure
 
 ```
 workflow/
   packages/
-    workflow-protocol/              # @uncaged/workflow-protocol — shared types + Result
-    workflow-runtime/               # @uncaged/workflow-runtime — createWorkflow, type re-exports
-    workflow-util/                  # @uncaged/workflow-util — Base32, ULID, logger, storage paths, refs helpers
-    workflow-reactor/               # @uncaged/workflow-reactor — LLM fn + thread reactor (tool calls)
-    workflow-cas/                   # @uncaged/workflow-cas — CAS store, hash, Merkle
-    workflow-register/              # @uncaged/workflow-register — bundle validation, registry YAML, model resolution
-    workflow-execute/               # @uncaged/workflow-execute — engine, extract, fork, GC, workflowAsAgent
-    cli-workflow/                   # @uncaged/cli-workflow — uncaged-workflow CLI
-    workflow-agent-cursor/          # @uncaged/workflow-agent-cursor
-    workflow-agent-hermes/          # @uncaged/workflow-agent-hermes
-    workflow-agent-llm/             # @uncaged/workflow-agent-llm
-    workflow-agent-react/             # @uncaged/workflow-agent-react
-    workflow-util-agent/            # @uncaged/workflow-util-agent — buildAgentPrompt, spawnCli
-    workflow-template-develop/      # @uncaged/workflow-template-develop
-    workflow-template-solve-issue/  # @uncaged/workflow-template-solve-issue
-    workflow-dashboard/             # @uncaged/workflow-dashboard — React dashboard (private app)
-  docs/             # RFCs, conventions
-  biome.json        # root Biome config
-  tsconfig.json     # root TypeScript config
+    workflow-protocol/    # @uncaged/workflow-protocol — shared types (WorkflowPayload, StepNodePayload, WorkflowConfig, etc.)
+    workflow-util/        # @uncaged/workflow-util — Crockford Base32, ULID, logger, frontmatter parsing/validation
+    workflow-moderator/   # @uncaged/workflow-moderator — JSONata graph evaluator
+    workflow-agent-kit/   # @uncaged/workflow-agent-kit — createAgent factory, context builder, extract pipeline
+    workflow-agent-hermes/ # @uncaged/workflow-agent-hermes — uwf-hermes CLI binary (spawns hermes chat)
+    cli-workflow/         # @uncaged/cli-workflow — uwf CLI binary
+  legacy-packages/       # Archived packages (preserved for reference, not active)
+  examples/              # Workflow YAML examples (solve-issue.yaml)
+  docs/                  # Architecture docs
+  biome.json             # root Biome config
+  tsconfig.json          # root TypeScript config
 ```
 
-- Execution stack layers: `workflow-protocol` → (`workflow-runtime`, `workflow-util`, `workflow-reactor`) → (`workflow-cas`, `workflow-register`) → `workflow-execute` → `cli-workflow`
+- Dependency layers: `workflow-protocol` → (`workflow-util`, `workflow-moderator`) → `workflow-agent-kit` → `workflow-agent-hermes` / `cli-workflow`
 - Packages use `workspace:^` protocol (resolves to `^x.y.z` on publish)
+- External CAS: `@uncaged/json-cas` (store API, hashing, schema validation) + `@uncaged/json-cas-fs` (filesystem backend)
 
 ## Language & Paradigm
 
@@ -109,8 +104,6 @@ type WorkflowEntry = {
 - Always named exports, never default exports
 - One module = one responsibility, filename = purpose
 
-Workflow bundles (`.esm.js`) follow the same rule: export `const run` and `const descriptor`, not `export default`.
-
 ### Folder Module Discipline
 
 Every folder under `src/` is a **module boundary**. Four rules:
@@ -136,10 +129,10 @@ export { createCasStore } from "../cas/cas.js";
 
 // ❌ Bad — types defined in index.ts
 // in cas/index.ts:
-export type CasStore = { ... };  // should be in cas/types.ts
+export type CasStore = { ... }; // should be in cas/types.ts
 ```
 
-**Exception**: The package-level `src/index.ts` is the public API surface and re-exports from folder `index.ts` files. Files that remain at `src/` root (e.g. `types.ts`, `workflow-as-agent.ts`) are not inside a folder module and follow normal rules.
+**Exception**: The package-level `src/index.ts` is the public API surface and re-exports from folder `index.ts` files. Files that remain at `src/` root (e.g. `types.ts`) are not inside a folder module and follow normal rules.
 
 ## Naming
 
@@ -160,7 +153,7 @@ Workflow names use **verb-first** kebab-case:
 ### ID Encoding
 
 All IDs use **Crockford Base32**:
-- Bundle hash: XXH64 → 13-char Crockford Base32
+- CAS hash: XXH64 → 13-char Crockford Base32
 - Thread ID: ULID → 26-char Crockford Base32 (10 timestamp + 16 random)
 
 ## Error Handling
@@ -189,7 +182,7 @@ import { createLogger } from "@uncaged/workflow-util";
 const log = createLogger();
 
 // Each call site has a fixed 8-char Crockford Base32 tag
-log("4KNMR2PX", "Loading workflow bundle...");
+log("4KNMR2PX", "Loading workflow...");
 log("7BQST3VW", `Role ${role} started`);
 ```
 
@@ -204,7 +197,7 @@ log("7BQST3VW", `Role ${role} started`);
 
 ### Why fixed tags?
 
-- `grep "4KNMR2PX"` in `.info.jsonl` → instant code location
+- `grep "4KNMR2PX"` in logs → instant code location
 - No need for file/line info in the log — tag is the locator
 - Survives refactoring (tag stays the same when code moves)
 
@@ -221,74 +214,76 @@ console.log(result);
 
 Do NOT use `await import()` in production code. Always use static top-level `import`.
 
-**Exception**: The bundle loader and `extractBundleExports` dynamically import user workflow files at runtime.
-
-```ts
-// Dynamic import required: user bundle path resolved at runtime
-const mod = await import(bundlePath);
-```
-
 Test files (`__tests__/**`) are exempt.
 
 ## Toolchain
 
 | Tool | Purpose |
 |------|---------|
-| **bun** | Package manager + runtime + test runner |
+| **bun** | Package manager + runtime |
 | **TypeScript** | Type checking (strict mode) |
 | **Biome** | Lint + format (replaces ESLint + Prettier) |
+| **vitest** | Test runner (`cli-workflow` uses vitest; other packages use `bun test`) |
 
-### Commands
+### Development Workflow
 
 ```bash
-bun run check       # tsc --build + biome check
-bun run format      # biome format --write
-bun test            # run tests
+# ── Setup ──
+bun install                 # install all workspace dependencies
+
+# ── Daily development ──
+bun run build               # tsc --build (all packages, dependency order)
+bun run check               # tsc --build + biome check + lint-log-tags
+bun run format              # biome format --write
+bun test                    # run tests across all packages
+
+# ── Before committing ──
+bun run check               # must pass — typecheck + lint + log tag validation
+bun test                    # must pass — all package tests
 ```
 
-### Version Management & Publishing
+### Publishing
 
-All public `@uncaged/*` packages are published to **npmjs.org** via `@changesets/cli` with **fixed mode** (all packages share the same version number). `workflow-dashboard` is private and excluded.
+All public `@uncaged/*` packages are published to **npmjs.org** with **fixed mode** (all packages share the same version number).
 
 ```bash
-# 1. After making changes, add a changeset describing the change
+# 1. Add a changeset describing the change
 bun changeset
 
-# 2. Before release, bump all package versions + generate CHANGELOGs
+# 2. Bump all package versions + generate CHANGELOGs
 bun version
 
-# 3. Build, test, and publish to npmjs
+# 3. Build, test, and publish (runs scripts/publish-all.mjs)
 bun release
+
+# Or publish manually with a tag:
+node scripts/publish-all.mjs --tag alpha
+node scripts/publish-all.mjs --dry-run    # preview without publishing
 ```
 
 - `workspace:^` dependencies resolve to `^x.y.z` on publish
+- Publish order defined in `scripts/publish-all.mjs` (dependency order)
 - Changesets config: `.changeset/config.json` (fixed mode, public access)
-- Each package has auto-generated `CHANGELOG.md`
 
-### Consuming @uncaged/* Packages
-
-External workflow repos just `bun install` — packages come from npmjs like any other dependency. No special registry config needed.
-
-### End-to-end: Monorepo → Registry → Workspace → Bundle
+### End-to-end: Author → Register → Run
 
 ```
-workflow/ (monorepo)           — engine, runtime, templates, agents
-  │  bun release               — build + test + changeset publish
+examples/solve-issue.yaml       — write a workflow YAML definition
+  │  uwf workflow put
   ▼
-npmjs.org                      — @uncaged/* scoped packages (public)
-  │  bun install
+~/.uncaged/workflow/cas/        — Workflow stored as CAS node
+~/.uncaged/workflow/registry.yaml — name → hash mapping updated
+  │  uwf thread start <name> -p "..."
   ▼
-my-workflows/ (workspace)     — normal package.json
-  │  bun run build:develop     — bun build → single .esm.js
+~/.uncaged/workflow/threads.yaml — new thread head pointer
+  │  uwf thread step <thread-id>
   ▼
-uncaged-workflow workflow add  — register bundle locally
-uncaged-workflow run           — execute workflow
+moderator → agent → extract      — one step per invocation, repeat until $END
 ```
 
-1. **Monorepo changes** → `bun changeset` (describe change) → `bun version` (bump) → `bun release` (publish)
-2. **Workspace** → `bun install` fetches latest from npmjs
-3. **Build** → produces single-file ESM bundle with `@uncaged/*` as externals
-4. **Register & Run** → `uncaged-workflow workflow add <name> <bundle>` then `uncaged-workflow run <name>`
+1. **Author** — write a workflow YAML file with roles, conditions, and graph
+2. **Register** — `uwf workflow put <file.yaml>` parses YAML, registers output schemas, stores `WorkflowPayload` in CAS
+3. **Run** — `uwf thread start` creates a thread, `uwf thread step` executes one cycle per invocation
 
 ## Commit Convention
 
@@ -296,5 +291,5 @@ uncaged-workflow run           — execute workflow
 <type>(<scope>): <description>
 
 type: feat | fix | refactor | docs | chore | test
-scope: workflow | cli | rfc-001 | ...
+scope: workflow | cli | moderator | agent-kit | hermes | util | protocol | ...
 ```

README.md

@@ -1,71 +1,104 @@
 # @uncaged/workflow
 
-A workflow engine that executes single-file ESM bundles. Each workflow is a self-contained `.esm.js` file identified by its XXH64 hash (Crockford Base32).
+A stateless workflow engine driven by a single-step CLI. Workflows are YAML definitions with roles, JSONata routing conditions, and a directed graph. Threads are immutable CAS-linked chains — each `uwf thread step` runs one moderator→agent→extract cycle and exits.
 
-## Core Concepts
+## Overview
 
-| Concept | Description |
-|---------|-------------|
-| **Workflow** | A single-file ESM module exporting `run` (workflow function) and `descriptor` (metadata). Identified by its XXH64 hash. |
-| **Bundle** | The physical `.esm.js` file stored in `~/.uncaged/workflow/bundles/`. |
-| **Thread** | A single execution of a workflow, identified by a ULID. CAS-backed chain plus `threads.json` / `history/*.jsonl`; `.info.jsonl` for debug logs. |
-| **Role** | A named actor within a workflow. Each role produces output with typed `meta`. Roles live inside template packages (`src/roles/`). |
-| **Registry** | `workflow.yaml` — maps workflow names to current/historical bundle hashes. |
-| **CAS** | Content-Addressed Storage — bundles are immutable and addressed by hash. |
+This monorepo implements **uwf**, a workflow engine with no long-running daemon. You register YAML workflow definitions in a content-addressed store (CAS), start a thread with an initial prompt, then invoke `uwf thread step` repeatedly until the moderator routes to `$END`. Each step is a complete process: the moderator evaluates JSONata conditions to pick the next role, an external agent CLI produces frontmatter markdown output, and an extract pipeline validates or structures that output against the role's JSON Schema.
 
-## Monorepo Packages
+Workflow state lives entirely on disk under `~/.uncaged/workflow/`: CAS nodes for definitions and step payloads, `registry.yaml` for workflow name→hash mappings, and `threads.yaml` for active thread head pointers. Completed threads are archived to `history.jsonl`. Because there is no server process, workflows are easy to debug, fork, and inspect with ordinary CLI tools.
+
+Agents are pluggable CLI binaries (`uwf-hermes`, `uwf-builtin`, `uwf-claude-code`, or custom commands). The engine spawns the configured agent with `<thread-id>` and `<role>`, sets `UWF_EDGE_PROMPT` from the graph transition, and captures both the agent's markdown output and a detail CAS node for session replay.
+
+## Architecture
+
+Dependency layers (lower layers have no dependency on higher layers):
 
 ```
-packages/
-  workflow/                      # @uncaged/workflow — core lib (types, engine, hash, ULID, registry)
-  cli-workflow/                  # @uncaged/cli-workflow — CLI (`uncaged-workflow` command)
-  workflow-template-develop/     # @uncaged/workflow-template-develop — develop workflow template (includes roles)
-  workflow-template-solve-issue/ # @uncaged/workflow-template-solve-issue — solve-issue workflow template (includes roles)
-  workflow-agent-hermes/         # @uncaged/workflow-agent-hermes — Hermes agent adapter
-  workflow-agent-cursor/         # @uncaged/workflow-agent-cursor — Cursor agent adapter
-  workflow-agent-llm/            # @uncaged/workflow-agent-llm — LLM agent adapter
-  workflow-util-agent/           # @uncaged/workflow-util-agent — agent utilities (buildAgentPrompt, spawnCli)
+Layer 0 — Contract
+  workflow-protocol          Shared types and JSON Schema definitions
+
+Layer 1 — Shared infra
+  workflow-util              Encoding, IDs, logging, frontmatter, paths
+  workflow-moderator         JSONata graph evaluator
+
+Layer 2 — Agent framework
+  workflow-agent-kit         createAgent factory, context builder, extract pipeline
+
+Layer 3 — Agent implementations
+  workflow-agent-hermes      Hermes ACP agent (uwf-hermes)
+  workflow-agent-builtin     Built-in LLM + tools agent (uwf-builtin)
+  workflow-agent-claude-code Claude Code agent (uwf-claude-code)
+
+Layer 4 — CLI
+  cli-workflow               uwf binary — thread lifecycle, registry, CAS, setup
+
+App (uses protocol; not in the runtime engine stack)
+  workflow-dashboard         Web UI for visual workflow editing
 ```
 
-Managed with **bun workspace** using the `workspace:*` protocol.
+External CAS: [`@uncaged/json-cas`](https://www.npmjs.com/package/@uncaged/json-cas) (store API, hashing, schema validation) + `@uncaged/json-cas-fs` (filesystem backend).
+
+See [docs/architecture.md](docs/architecture.md) for the full design — three-phase engine loop, CAS node types, storage layout, agent CLI protocol, and design decisions.
+
+## Packages
+
+| Package | npm | Description | Type | README |
+|---------|-----|-------------|------|--------|
+| `cli-workflow` | `@uncaged/cli-workflow` | `uwf` CLI — thread lifecycle, workflow registry, CAS inspection, setup | cli | [README](packages/cli-workflow/README.md) |
+| `workflow-protocol` | `@uncaged/workflow-protocol` | Shared TypeScript types and JSON Schema constants | lib | [README](packages/workflow-protocol/README.md) |
+| `workflow-moderator` | `@uncaged/workflow-moderator` | JSONata graph evaluator — next role or `$END` | lib | [README](packages/workflow-moderator/README.md) |
+| `workflow-agent-kit` | `@uncaged/workflow-agent-kit` | `createAgent` factory, context builder, extract pipeline | lib | [README](packages/workflow-agent-kit/README.md) |
+| `workflow-util` | `@uncaged/workflow-util` | Crockford Base32, ULID, logger, frontmatter parsing, storage paths | lib | [README](packages/workflow-util/README.md) |
+| `workflow-agent-hermes` | `@uncaged/workflow-agent-hermes` | `uwf-hermes` — spawns Hermes chat via ACP | agent | [README](packages/workflow-agent-hermes/README.md) |
+| `workflow-agent-builtin` | `@uncaged/workflow-agent-builtin` | `uwf-builtin` — built-in LLM agent with file/shell tools | agent | [README](packages/workflow-agent-builtin/README.md) |
+| `workflow-agent-claude-code` | `@uncaged/workflow-agent-claude-code` | `uwf-claude-code` — spawns Claude Code CLI | agent | [README](packages/workflow-agent-claude-code/README.md) |
+| `workflow-dashboard` | `@uncaged/workflow-dashboard` | Web graph editor for workflow YAML (private, alpha) | app | [README](packages/workflow-dashboard/README.md) |
 
 ## Quick Start
 
 ```bash
-# Install dependencies
-bun install
+# 1. Configure provider, model, and default agent
+uwf setup
 
-# Build all packages
-bun run build
+# 2. Register a workflow from YAML
+uwf workflow add examples/solve-issue.yaml
 
-# Register a workflow bundle
-uncaged-workflow workflow add solve-issue dist/packages/workflow-template-solve-issue/solve-issue.esm.js
+# 3. Start a thread (creates head pointer; does not execute)
+uwf thread start solve-issue -p "Fix the login redirect bug"
 
-# Run a workflow
-uncaged-workflow run solve-issue --prompt "Fix bug #42"
+# 4. Execute steps (one at a time, until done)
+uwf thread exec <thread-id>
 ```
 
-## CLI Usage
+Use `-c, --count <number>` on `thread exec` to run multiple steps in one invocation. Override the agent with `--agent <cmd>`.
 
-```bash
-uncaged-workflow                   # Print full command usage (exits with status 1)
-uncaged-workflow workflow list     # List registered workflows
-uncaged-workflow run <name>        # Start a workflow thread
-uncaged-workflow thread list       # List all threads
-uncaged-workflow thread show <id>  # Inspect a thread
-uncaged-workflow skill             # Agent-consumable reference docs
-```
+## CLI Reference
 
-Run `uncaged-workflow` with no arguments to print usage, or `uncaged-workflow skill cli` for the full CLI skill reference.
+Global options: `-V, --version`, `--format <json|yaml>`, `-h, --help`.
+
+| Group | Commands |
+|-------|----------|
+| **thread** | `start`, `exec`, `show`, `list`, `stop`, `cancel`, `read` |
+| **step** | `list`, `show`, `read`, `fork` |
+| **workflow** | `add`, `show`, `list` |
+| **cas** | `get`, `put`, `put-text`, `has`, `refs`, `walk`, `reindex`, `schema list`, `schema get` |
+| **setup** | Interactive or `--provider`, `--base-url`, `--api-key`, `--model`, `--agent` |
+| **skill** | `cli` — print markdown reference of all uwf commands |
+| **log** | `list`, `show`, `clean` — process-level debug logs |
+
+Config is stored in `~/.uncaged/workflow/config.yaml`. API keys go in `~/.uncaged/workflow/.env`.
+
+Detailed command usage, options, and examples: [packages/cli-workflow/README.md](packages/cli-workflow/README.md).
 
 ## Development
 
 ```bash
-bun run check    # Biome lint + format check
-bun run format   # Auto-format with Biome
-bun test         # Run tests
+bun install --no-cache     # Install dependencies
+bun run build              # tsc --build (all packages)
+bun run check              # tsc + biome + lint-log-tags
+bun run format             # Auto-format with Biome
+bun test                   # Run all tests
 ```
 
-## Architecture
-
-See [docs/architecture.md](docs/architecture.md) for the full design — three-phase engine loop, bundle contract, storage layout, and design decisions.
+Managed with **bun workspace**. See [CLAUDE.md](CLAUDE.md) for coding conventions.

biome.json

@@ -5,6 +5,8 @@
       "**",
       "!**/dist",
       "!**/node_modules",
+      "!**/legacy-packages",
+      "!scripts",
       "!packages/workflow/workflow",
       "!xiaoju/scripts/bundle.ts"
     ]
@@ -15,6 +17,15 @@
     "indentWidth": 2,
     "lineWidth": 100
   },
+  "css": {
+    "parser": {
+      "cssModules": true,
+      "tailwindDirectives": true
+    },
+    "linter": {
+      "enabled": false
+    }
+  },
   "javascript": {
     "formatter": {
       "quoteStyle": "double",
@@ -36,7 +47,7 @@
       }
     },
     {
-      "includes": ["**/*.d.ts"],
+      "includes": ["**/*.d.ts", "**/vitest.config.*"],
       "linter": {
         "rules": {
           "style": {
@@ -44,6 +55,16 @@
           }
         }
       }
+    },
+    {
+      "includes": ["**/cli.ts", "**/setup.ts"],
+      "linter": {
+        "rules": {
+          "suspicious": {
+            "noConsole": "off"
+          }
+        }
+      }
     }
   ],
   "linter": {

docs/architecture.md

@@ -1,4 +1,4 @@
-# uwf — Architecture
+# Workflow Engine — Architecture
 
 **Last updated:** 2026-05-19
 
@@ -14,12 +14,12 @@ The implementation lives in **6** active packages under `packages/`, plus two ex
 
 | Layer | Package | One-line role |
 |-------|---------|---------------|
-| Contract | `@uncaged/uwf-protocol` → `uwf-protocol` | Shared TypeScript types (`WorkflowPayload`, `StepNodePayload`, `ModeratorContext`, `WorkflowConfig`, etc.). No runtime deps beyond `@uncaged/json-cas-fs`. |
+| Contract | `@uncaged/workflow-protocol` → `workflow-protocol` | Shared TypeScript types (`WorkflowPayload`, `StepNodePayload`, `ModeratorContext`, `WorkflowConfig`, etc.). No runtime deps beyond `@uncaged/json-cas-fs`. |
 | Shared infra | `@uncaged/workflow-util` → `workflow-util` | Crockford Base32, ULID generation, `createLogger`, frontmatter parsing/validation. |
-| Moderator | `@uncaged/uwf-moderator` → `uwf-moderator` | JSONata-based graph evaluator: given a `WorkflowPayload` and `ModeratorContext`, returns the next role or `$END`. |
-| Agent framework | `@uncaged/uwf-agent-kit` → `uwf-agent-kit` | `createAgent` entrypoint factory, context builder, frontmatter fast-path extractor, LLM extract fallback, output format instruction builder. |
-| Agent: Hermes | `@uncaged/uwf-agent-hermes` → `uwf-agent-hermes` | `uwf-hermes` CLI binary — spawns `hermes chat`, pipes prompt, captures session detail. |
-| CLI | `@uncaged/cli-uwf` → `cli-uwf` | `uwf` binary — thread lifecycle, workflow registry, CAS inspection, setup. |
+| Moderator | `@uncaged/workflow-moderator` → `workflow-moderator` | JSONata-based graph evaluator: given a `WorkflowPayload` and `ModeratorContext`, returns the next role or `$END`. |
+| Agent framework | `@uncaged/workflow-agent-kit` → `workflow-agent-kit` | `createAgent` entrypoint factory, context builder, frontmatter fast-path extractor, LLM extract fallback, output format instruction builder. |
+| Agent: Hermes | `@uncaged/workflow-agent-hermes` → `workflow-agent-hermes` | `uwf-hermes` CLI binary — spawns `hermes chat`, pipes prompt, captures session detail. |
+| CLI | `@uncaged/cli-workflow` → `cli-workflow` | `uwf` binary — thread lifecycle, workflow registry, CAS inspection, setup. |
 
 ### External dependencies
 
@@ -27,8 +27,8 @@ The implementation lives in **6** active packages under `packages/`, plus two ex
 |---------|------|
 | `@uncaged/json-cas` | Content-addressed store API, XXH64 hashing, JSON Schema registration and validation. |
 | `@uncaged/json-cas-fs` | Filesystem backend for `json-cas`. |
-| `jsonata` | JSONata expression evaluator (used by `uwf-moderator`). |
-| `commander` | CLI argument parsing (used by `cli-uwf`). |
+| `jsonata` | JSONata expression evaluator (used by `workflow-moderator`). |
+| `commander` | CLI argument parsing (used by `cli-workflow`). |
 | `dotenv` | Loads `.env` files for API keys. |
 | `yaml` | YAML parse/stringify. |
 
@@ -41,20 +41,20 @@ flowchart BT
     jcasfs["@uncaged/json-cas-fs"]
   end
   subgraph L0["Layer 0 — contract"]
-    protocol["@uncaged/uwf-protocol"]
+    protocol["@uncaged/workflow-protocol"]
   end
   subgraph L1["Layer 1 — shared"]
     util["@uncaged/workflow-util"]
-    moderator["@uncaged/uwf-moderator"]
+    moderator["@uncaged/workflow-moderator"]
   end
   subgraph L2["Layer 2 — agent framework"]
-    kit["@uncaged/uwf-agent-kit"]
+    kit["@uncaged/workflow-agent-kit"]
   end
   subgraph L3["Layer 3 — agent implementations"]
-    hermes["@uncaged/uwf-agent-hermes"]
+    hermes["@uncaged/workflow-agent-hermes"]
   end
   subgraph L4["Layer 4 — CLI"]
-    cli["@uncaged/cli-uwf"]
+    cli["@uncaged/cli-workflow"]
   end
   protocol --> jcasfs
   util --> protocol
@@ -85,8 +85,13 @@ description: "End-to-end issue resolution"
 roles:
   planner:
     description: "Creates implementation plan"
-    systemPrompt: "You are a planning agent. Analyze the issue and create a step-by-step plan."
-    outputSchema:
+    goal: "You are a planning agent. Analyze the issue and create a step-by-step plan."
+    capabilities:
+      - issue-analysis
+      - planning
+    procedure: "Analyze the issue and create a detailed, actionable implementation plan."
+    output: "Output the plan summary and list of concrete steps."
+    meta:
       type: object
       properties:
         plan: { type: string }
@@ -94,8 +99,13 @@ roles:
       required: [plan, steps]
   developer:
     description: "Implements code changes"
-    systemPrompt: "You are a developer agent. Implement the plan."
-    outputSchema:
+    goal: "You are a developer agent. Implement the plan."
+    capabilities:
+      - file-edit
+      - shell
+    procedure: "Implement the plan. Write code, tests, and ensure existing tests pass."
+    output: "List all files changed and provide a summary of the implementation."
+    meta:
       type: object
       properties:
         filesChanged: { type: array, items: { type: string } }
@@ -103,8 +113,12 @@ roles:
       required: [filesChanged, summary]
   reviewer:
     description: "Reviews code changes"
-    systemPrompt: "You are a code reviewer. Review the implementation."
-    outputSchema:
+    goal: "You are a code reviewer. Review the implementation."
+    capabilities:
+      - code-review
+    procedure: "Review the implementation against the plan."
+    output: "Approve or reject with detailed comments."
+    meta:
       type: object
       properties:
         approved: { type: boolean }
@@ -133,7 +147,7 @@ graph:
 
 Key properties:
 
-- **`roles`** — inline role definitions; each `outputSchema` is a JSON Schema (stored as its own CAS node on registration)
+- **`roles`** — inline role definitions; each `meta` is a JSON Schema (stored as its own CAS node on registration)
 - **`conditions`** — named JSONata expressions evaluated against the `ModeratorContext`
 - **`graph`** — `Record<Role | "$START", Transition[]>` — first matching transition wins; `condition: null` = fallback
 - **No agent binding** — agent selection is a deployment concern, configured in `config.yaml`
@@ -141,7 +155,7 @@ Key properties:
 
 ## Three-phase engine loop
 
-Each `uwf thread step` runs exactly one cycle: moderator → agent → extract. The CLI orchestrates this in `packages/cli-uwf/src/commands/thread.ts` (`cmdThreadStep`).
+Each `uwf thread step` runs exactly one cycle: moderator → agent → extract. The CLI orchestrates this in `packages/cli-workflow/src/commands/thread.ts` (`cmdThreadStep`).
 
 ```
 ┌─→ Phase 1: MODERATOR
@@ -156,7 +170,7 @@ Each `uwf thread step` runs exactly one cycle: moderator → agent → extract.
 │   Output: raw string (frontmatter markdown)
 │
 │   Phase 3: EXTRACT
-│   Input:  raw agent output + role's outputSchema
+│   Input:  raw agent output + role's meta schema
 │   Engine: two-layer extract (frontmatter fast path → LLM fallback)
 │   Output: CasRef to structured output node
 │
@@ -167,7 +181,7 @@ Each `uwf thread step` runs exactly one cycle: moderator → agent → extract.
 
 ### Context types
 
-Defined in `packages/uwf-protocol/src/types.ts`:
+Defined in `packages/workflow-protocol/src/types.ts`:
 
 ```typescript
 type StepContext = {
@@ -209,11 +223,11 @@ Each agent is an external command invoked by `uwf thread step`:
 Contract:
 1. `uwf thread step` determines the next role via the moderator
 2. Agent CLI is spawned with `(thread-id, role)` as positional args
-3. `uwf-agent-kit` (`createAgent`) handles the boilerplate:
+3. `workflow-agent-kit` (`createAgent`) handles the boilerplate:
    - Parses argv
    - Loads `.env` from storage root
    - Builds `AgentContext` by walking the CAS chain from `threads.yaml` head
-   - Resolves the role's `outputSchema` and builds `outputFormatInstruction`
+   - Resolves the role's `meta` schema and builds `outputFormatInstruction`
    - Calls the agent's `run` function
    - Runs two-layer extract on the raw output
    - Writes `StepNode` to CAS (output + detail + prev link)
@@ -242,18 +256,18 @@ scope: role
 Fixed the login redirect by updating the auth middleware...
 ```
 
-The `outputFormatInstruction` (built by `buildOutputFormatInstruction` in `uwf-agent-kit`) is prepended to the role's system prompt, so the deliverable format is the first thing the agent sees. It lists the expected frontmatter fields derived from the role's JSON Schema.
+The `outputFormatInstruction` (built by `buildOutputFormatInstruction` in `workflow-agent-kit`) is prepended to the role's system prompt, so the deliverable format is the first thing the agent sees. It lists the expected frontmatter fields derived from the role's `meta` JSON Schema.
 
 ## Two-layer extract
 
-Structured output extraction uses a two-layer strategy (`uwf-agent-kit`):
+Structured output extraction uses a two-layer strategy (`workflow-agent-kit`):
 
 ### Layer 1: frontmatter fast path (`frontmatter.ts`)
 
 1. Parse YAML frontmatter from raw agent output (`parseFrontmatterMarkdown`)
 2. Validate required fields (`validateFrontmatter`)
 3. Build a candidate object from frontmatter fields (`status`, `next`, `confidence`, `artifacts`, `scope`)
-4. `store.put()` the candidate against the role's `outputSchema`
+4. `store.put()` the candidate against the role's `meta` schema
 5. Validate with `json-cas` schema validation
 6. If valid → return `outputHash` (zero LLM cost)
 
@@ -270,9 +284,9 @@ If the fast path returns `null` (no frontmatter, invalid, or doesn't satisfy sch
 
 ## Prompt injection
 
-`uwf-agent-kit` prepends two pieces of context to the agent's system prompt:
+`workflow-agent-kit` prepends two pieces of context to the agent's system prompt:
 
-1. **Deliverable format instruction** — generated from the role's `outputSchema`, tells the agent exactly what frontmatter fields to produce and the expected format
+1. **Deliverable format instruction** — generated from the role's `meta` schema, tells the agent exactly what frontmatter fields to produce and the expected format
 2. **Scope constraint** — "Focus exclusively on YOUR role's deliverable. Do not perform actions outside your role's scope."
 
 This ensures agents produce parseable frontmatter output without requiring per-agent format knowledge.
@@ -289,8 +303,11 @@ payload:
   roles:
     planner:
       description: "Creates implementation plan"
-      systemPrompt: "You are a planning agent..."
-      outputSchema: "5GWKR8TN1V3JA"    # cas_ref → JSON Schema node
+      goal: "You are a planning agent..."
+      capabilities: [planning, issue-analysis]
+      procedure: "Analyze the issue and create a plan."
+      output: "Output the plan summary."
+      meta: "5GWKR8TN1V3JA"    # cas_ref → JSON Schema node
   conditions:
     notApproved:
       description: "Reviewer rejected"
@@ -318,7 +335,7 @@ payload:
   start: "4TNVW8KR2B3MA"      # cas_ref → StartNode
   prev: "2MXBG6PN4A8JR"       # cas_ref → previous StepNode (null for first step)
   role: "developer"
-  output: "9KRVW3TN5F1QA"     # cas_ref → structured output (validated against outputSchema)
+  output: "9KRVW3TN5F1QA"     # cas_ref → structured output (validated against meta schema)
   detail: "7BQST3VW9F2MA"     # cas_ref → execution detail (raw turns, session data)
   agent: "uwf-hermes"         # agent command used (plain string)
 ```

docs/builtin-agent-research.md

@@ -0,0 +1,779 @@
+# Built-in Role Agent 调研
+
+## 目标
+
+实现一个内置的 role agent（暂称 `uwf-builtin`），不依赖 hermes/openclaw 等外部 agent 进程。
+直接使用 workflow config 中配置的 model，自己实现 agent run loop 和关键 toolkit。
+
+---
+
+## 关键问题
+
+### Q1: Agent 接口协议
+
+现有 agent 是怎么被 CLI 调用的？输入（argv、环境变量）和输出（stdout、CAS）格式是什么？
+
+**调研要点：**
+- `cli-workflow` 里 `spawnAgent` 的完整实现
+- AgentConfig 类型定义
+- agent 进程的 exit code 约定
+- 环境变量传递（UWF_STORAGE_ROOT 等）
+
+**答案：**
+
+#### 调用链
+
+`uwf thread step` → `cmdThreadStepOnce` → moderator 求值下一 role → `resolveAgentConfig` → `spawnAgent`。
+
+#### AgentConfig 类型
+
+```146:149:packages/workflow-protocol/src/types.ts
+export type AgentConfig = {
+  command: string;
+  args: string[];
+};
+```
+
+在 `config.yaml` 的 `agents` 段注册，例如 `hermes: { command: "uwf-hermes", args: [] }`。
+
+#### spawnAgent 行为
+
+```627:653:packages/cli-workflow/src/commands/thread.ts
+function spawnAgent(agent: AgentConfig, threadId: ThreadId, role: string): CasRef {
+  const argv = [...agent.args, threadId, role];
+  let stdout: string;
+  try {
+    stdout = execFileSync(agent.command, argv, {
+      encoding: "utf8",
+      env: process.env,
+      stdio: ["ignore", "pipe", "pipe"],
+    });
+  } catch (e) {
+  // ... stderr 拼进 fail 消息
+  }
+
+  const line = stdout.trim().split("\n").pop()?.trim() ?? "";
+  if (!isCasRef(line)) {
+    fail(`agent stdout is not a valid CAS hash: ${line || "(empty)"}`);
+  }
+  return line;
+}
+```
+
+| 项目 | 约定 |
+|------|------|
+| **argv** | `[...agent.args, <thread-id>, <role>]`，即 `process.argv[2]`=threadId，`process.argv[3]`=role（与 `createAgent` 的 `parseArgv` 一致） |
+| **stdin** | 忽略 |
+| **stdout** | 纯文本，**最后一行**必须是新 `StepNode` 的 CAS hash（13 字符 Crockford Base32） |
+| **stderr** | 失败时 CLI 会附带 stderr；成功时无约定 |
+| **exit code** | `0` = 成功；非 0 时 `execFileSync` 抛错，step 失败 |
+| **环境变量** | 继承父进程 `process.env`（含 storage root、API key 等） |
+| **链头更新** | **不由 agent 负责**；agent 只写 CAS StepNode，CLI 在拿到 stdout hash 后更新 `threads.yaml` |
+
+Agent 解析优先级（`resolveAgentConfig`）：
+
+1. CLI `--agent` override（整段 command + args 字符串）
+2. `config.agentOverrides[workflow.name][role]`
+3. `config.defaultAgent`
+
+#### 环境变量：Storage Root
+
+文档中写的 `UWF_STORAGE_ROOT` **在当前代码中不存在**。实际优先级（`workflow-agent-kit` / `cli-workflow` 一致）：
+
+```33:43:packages/workflow-agent-kit/src/storage.ts
+export function resolveStorageRoot(): string {
+  const internal = process.env.UNCAGED_WORKFLOW_STORAGE_ROOT;
+  if (internal !== undefined && internal !== "") {
+    return internal;
+  }
+  const userOverride = process.env.WORKFLOW_STORAGE_ROOT;
+  if (userOverride !== undefined && userOverride !== "") {
+    return userOverride;
+  }
+  return getDefaultStorageRoot();
+}
+```
+
+Agent 子进程通过继承的 `process.env` 与父 CLI 共享同一 storage root；`createAgent` 内还会 `loadDotenv({ path: getEnvPath(storageRoot) })` 加载 `~/.uncaged/workflow/.env`。
+
+#### Agent 侧职责（设计文档 + 实现）
+
+- 读 `threads.yaml` 链头，构建 context，执行 role
+- 将 `StepNode` 写入 CAS（`output` / `detail` / `agent` / `prev` / `start`）
+- stdout 打印 step hash
+- **不**更新 `threads.yaml`
+
+---
+
+### Q2: createAgent 工厂
+
+workflow-agent-kit 的 `createAgent` 做了什么？它的完整生命周期是什么？
+
+**调研要点：**
+- `AgentOptions` 类型的 `run` 和 `continue` 回调签名
+- `AgentRunResult` 的完整定义
+- retry 逻辑（frontmatter 校验失败后的重试机制）
+- `persistStep` 写入 CAS 的 StepNode 结构
+
+**答案：**
+
+#### 类型定义
+
+```4:35:packages/workflow-agent-kit/src/types.ts
+export type AgentContext = ModeratorContext & {
+  threadId: ThreadId;
+  role: string;
+  store: Store;
+  workflow: WorkflowPayload;
+  outputFormatInstruction: string;
+};
+
+export type AgentRunResult = {
+  output: string;
+  detailHash: CasRef;
+  sessionId: string;
+};
+
+export type AgentContinueFn = (
+  sessionId: string,
+  message: string,
+  store: AgentContext["store"],
+) => Promise<AgentRunResult>;
+
+export type AgentRunFn = (ctx: AgentContext) => Promise<AgentRunResult>;
+
+export type AgentOptions = {
+  name: string;
+  run: AgentRunFn;
+  continue: AgentContinueFn;
+};
+```
+
+- **`run(ctx)`**：首次执行，返回原始 agent 文本 `output`、审计用 `detailHash`、用于续聊的 `sessionId`。
+- **`continue(sessionId, message, store)`**：在同一 session 上追加用户消息（用于 frontmatter 纠错），再次返回 `AgentRunResult`。
+
+`createAgent(options)` 返回 `() => Promise<void>`，作为 agent CLI 的 `main`（见 `uwf-hermes` 的 `cli.ts`）。
+
+#### 生命周期（按执行顺序）
+
+```101:152:packages/workflow-agent-kit/src/run.ts
+export function createAgent(options: AgentOptions): () => Promise<void> {
+  return async function main(): Promise<void> {
+    const { threadId, role } = parseArgv(process.argv);
+    const storageRoot = resolveStorageRoot();
+    loadDotenv({ path: getEnvPath(storageRoot) });
+
+    const ctx = await buildContextWithMeta(threadId, role);
+    // 1. 校验 role 存在
+    // 2. 从 CAS 取 frontmatter JSON Schema → buildOutputFormatInstruction → ctx.outputFormatInstruction
+
+    let agentResult = await options.run(ctx);
+
+    let outputHash = await tryExtractOutput(agentResult.output, roleDef.frontmatter, ctx);
+
+    for (let retry = 0; retry < MAX_FRONTMATTER_RETRIES && outputHash === null; retry++) {
+      const correctionMessage = "Your previous response did not contain valid YAML frontmatter...";
+      agentResult = await options.continue(agentResult.sessionId, correctionMessage, ctx.meta.store);
+      outputHash = await tryExtractOutput(agentResult.output, roleDef.frontmatter, ctx);
+    }
+
+    if (outputHash === null) { fail(...); }
+
+    const stepHash = await persistStep({ ctx, outputHash, detailHash: agentResult.detailHash, agentName });
+    process.stdout.write(`${stepHash}\n`);
+  };
+}
+```
+
+| 阶段 | 行为 |
+|------|------|
+| 解析 argv | `argv[2]=threadId`, `argv[3]=role`，缺失则 `stderr` + `exit(1)` |
+| Context | `buildContextWithMeta` + 可选 `outputFormatInstruction` |
+| Run | `options.run(ctx)` |
+| Extract | **仅** `tryFrontmatterFastPath`（见 Q4）；**不**调用 `extract()` LLM fallback |
+| Retry | 最多 `MAX_FRONTMATTER_RETRIES = 2` 次 `continue` + 再试 fast-path |
+| Persist | `persistStep` → `writeStepNode` |
+| 输出 | stdout 一行 step CAS hash |
+
+#### StepNode 写入结构
+
+```44:68:packages/workflow-agent-kit/src/run.ts
+async function writeStepNode(options: {
+  store: AgentStore["store"];
+  schemas: AgentStore["schemas"];
+  startHash: CasRef;
+  prevHash: CasRef | null;
+  role: string;
+  outputHash: CasRef;
+  detailHash: CasRef;
+  agentName: string;
+}): Promise<CasRef> {
+  const payload: StepNodePayload = {
+    start: options.startHash,
+    prev: options.prevHash,
+    role: options.role,
+    output: options.outputHash,
+    detail: options.detailHash,
+    agent: options.agentName,
+  };
+  // store.put(stepNode schema) + validate
+}
+```
+
+`agentName` 经 `agentLabel(name)` 规范化：已有 `uwf-` 前缀则原样，否则加 `uwf-`（如 `hermes` → `uwf-hermes`）。
+
+`prevHash`：若链头仍是 `StartNode` 则为 `null`，否则为当前 head step hash。
+
+---
+
+### Q3: Context Builder
+
+`buildContextWithMeta` 构建了什么上下文给 agent？
+
+**调研要点：**
+- `AgentContext` 完整类型定义（所有字段）
+- context 构建过程（CAS chain walk）
+- `outputFormatInstruction` 怎么生成的
+- role definition 怎么获取（从 workflow YAML）
+
+**答案：**
+
+#### AgentContext 字段
+
+继承 `ModeratorContext`：
+
+```60:68:packages/workflow-protocol/src/types.ts
+export type ModeratorContext = {
+  start: StartNodePayload;
+  steps: StepContext[];
+};
+```
+
+```48:51:packages/workflow-protocol/src/types.ts
+export type StartNodePayload = {
+  workflow: CasRef;
+  prompt: string;
+};
+```
+
+```61:63:packages/workflow-protocol/src/types.ts
+export type StepContext = Omit<StepRecord, "output"> & {
+  output: unknown;
+};
+```
+
+`AgentContext` 额外字段：
+
+| 字段 | 类型 | 含义 |
+|------|------|------|
+| `threadId` | `ThreadId` | 当前线程 |
+| `role` | `string` | 本步要执行的角色名 |
+| `store` | `Store` | CAS store（读写节点） |
+| `workflow` | `WorkflowPayload` | 已从 CAS 加载的 workflow 定义 |
+| `outputFormatInstruction` | `string` | 由 `createAgent` 根据 role 的 frontmatter schema 生成；`buildContext*` 初始为 `""` |
+
+`buildContextWithMeta` 还返回 `meta`：
+
+```148:154:packages/workflow-agent-kit/src/context.ts
+export type BuildContextMeta = {
+  storageRoot: string;
+  store: Store;
+  schemas: AgentStore["schemas"];
+  headHash: CasRef;
+  chain: ChainState;
+};
+```
+
+#### CAS chain walk
+
+1. 从 `threads.yaml[threadId]` 取 `headHash`
+2. `walkChain`：若 head 是 `StartNode`，`stepsNewestFirst=[]`；否则沿 `prev` 收集所有 `StepNode`， newest-first
+3. `buildHistory`：反转为时间序，`expandOutput` 把每步 `output` CasRef 展开为 JSON payload（供 prompt / JSONata 使用）
+4. `loadWorkflow`：从 `start.workflow` CasRef 加载 `WorkflowPayload`
+
+#### Role definition 来源
+
+- 作者写在 workflow YAML 的 `roles.<name>`（`goal`, `capabilities`, `procedure`, `output`, `frontmatter` 等）
+- `uwf workflow put` 时 `frontmatter` 内联 JSON Schema 经 `putSchema` 存入 CAS，workflow 里存的是 **CasRef**
+- Agent 运行时：`ctx.workflow.roles[ctx.role]` → `RoleDefinition`
+
+#### outputFormatInstruction
+
+在 `createAgent` 中，若 `getSchema(store, roleDef.frontmatter)` 非空，则：
+
+```typescript
+ctx.outputFormatInstruction = buildOutputFormatInstruction(frontmatterSchema);
+```
+
+`buildOutputFormatInstruction` 根据 JSON Schema 的 `properties` 生成「必须以 `---` YAML frontmatter 开头」的说明和示例字段列表（见 `build-output-format-instruction.ts`）。
+
+各 agent 实现（Hermes / Claude Code）在组装 prompt 时把该块放在最前，再接 `buildRolePrompt(roleDef)`。
+
+---
+
+### Q4: Extract Pipeline
+
+agent 输出怎么被处理成结构化数据？
+
+**调研要点：**
+- frontmatter fast-path 的完整逻辑
+- LLM extract fallback 的实现（`extract.ts`）
+- frontmatter schema 从哪里来（role 定义里的 `frontmatter` 字段）
+- 校验失败时的 correction prompt 是什么
+
+**答案：**
+
+#### Schema 来源
+
+Workflow YAML 中每个 role 的 `frontmatter:` 段是 JSON Schema 对象；注册时：
+
+```66:76:packages/cli-workflow/src/commands/workflow.ts
+async function resolveFrontmatterRef(..., frontmatter: unknown): Promise<CasRef> {
+  // 校验为 JSON Schema → putSchema → 返回 CasRef
+}
+```
+
+运行时 `roleDef.frontmatter` 即该 schema 的 CAS hash；structured `output` 节点用**同一 schema** 写入 CAS。
+
+#### Frontmatter fast-path（createAgent 实际使用的路径）
+
+```148:195:packages/workflow-agent-kit/src/frontmatter.ts
+export async function tryFrontmatterFastPath(
+  raw: string,
+  outputSchema: CasRef,
+  store: Store,
+): Promise<FrontmatterFastPathResult | null>
+```
+
+流程：
+
+1. `parseFrontmatterMarkdown(raw)` → 标准 agent 字段（`status`, `next`, `confidence`, `artifacts`, `scope`）+ body
+2. `validateFrontmatter` 失败 → `null`
+3. `getSchema(store, outputSchema)` + `extractSchemaFields` 得到 role 需要的属性名
+4. `buildCandidate`：从标准 frontmatter + YAML 原始字段拼出符合 schema 的对象
+5. `store.put(outputSchema, candidate)` + `validate` → 成功则 `{ body, outputHash }`
+
+**永不抛错**，失败返回 `null`。
+
+#### LLM extract fallback（已实现但未接入 createAgent）
+
+```135:181:packages/workflow-agent-kit/src/extract.ts
+export async function extract(
+  rawOutput: string,
+  outputSchema: CasRef,
+  config: WorkflowConfig,
+): Promise<ExtractResult>
+```
+
+- 模型：`resolveExtractModelAlias(config)` → `modelOverrides.extract` → `models.extract` → `models.default` → `defaultModel`
+- HTTP：`POST {baseUrl}/chat/completions`，`response_format: { type: "json_object" }`
+- System：要求按 JSON Schema 从 agent 输出提取单个 JSON 对象
+- 校验通过后 `store.put(outputSchema, structured)`
+
+**重要：`createAgent` 当前未调用 `extract()`**。fast-path 失败且 2 次 `continue` 仍失败则直接 `fail()`。builtin agent 若希望无 frontmatter 也能跑，需在 kit 或 builtin 层显式接入 `extract()`。
+
+#### Correction prompt（retry）
+
+```125:128:packages/workflow-agent-kit/src/run.ts
+const correctionMessage =
+  "Your previous response did not contain valid YAML frontmatter matching the role schema.\n" +
+  "You MUST begin your response with a YAML frontmatter block (--- delimited).\n" +
+  "Please output ONLY the corrected frontmatter block followed by your work.";
+```
+
+通过 `options.continue(sessionId, correctionMessage, store)` 发给外部 agent；builtin 需在自有 message 历史里 append 同等语义的 user 消息。
+
+---
+
+### Q5: Model 配置与 LLM 调用
+
+workflow 怎么配置和使用 model？
+
+**调研要点：**
+- `WorkflowConfig` 中 providers/models/defaultModel/modelOverrides 的完整定义
+- `resolveModel` 函数的实现
+- `chatCompletionText` 的实现（OpenAI 兼容 HTTP 客户端）
+- 有没有 streaming 支持？tool calling 支持？
+
+**答案：**
+
+#### WorkflowConfig
+
+```136:160:packages/workflow-protocol/src/types.ts
+export type ProviderConfig = {
+  baseUrl: string;
+  apiKeyEnv: string;
+};
+
+export type ModelConfig = {
+  provider: ProviderAlias;
+  name: string;
+};
+
+export type WorkflowConfig = {
+  providers: Record<ProviderAlias, ProviderConfig>;
+  models: Record<ModelAlias, ModelConfig>;
+  agents: Record<AgentAlias, AgentConfig>;
+  defaultAgent: AgentAlias;
+  agentOverrides: Record<WorkflowName, Record<RoleName, AgentAlias>> | null;
+  defaultModel: ModelAlias;
+  modelOverrides: Record<Scenario, ModelAlias> | null;
+};
+```
+
+示例见 `docs/architecture.md`（`providers` / `models` / `defaultModel` / `modelOverrides.extract`）。
+
+#### resolveModel
+
+```32:50:packages/workflow-agent-kit/src/extract.ts
+export function resolveModel(config: WorkflowConfig, alias: ModelAlias): ResolvedLlmProvider {
+  const modelEntry = config.models[alias];
+  const providerEntry = config.providers[modelEntry.provider];
+  const apiKey = process.env[providerEntry.apiKeyEnv];
+  return { baseUrl: providerEntry.baseUrl, apiKey, model: modelEntry.name };
+}
+```
+
+`ResolvedLlmProvider = { baseUrl, apiKey, model }`。
+
+Extract 专用别名解析：
+
+```18:30:packages/workflow-agent-kit/src/extract.ts
+export function resolveExtractModelAlias(config: WorkflowConfig): ModelAlias {
+  return config.modelOverrides?.extract ?? (config.models.extract ? "extract" : config.models.default ? "default" : config.defaultModel);
+}
+```
+
+**尚无** `modelOverrides` 按 role/workflow 解析 agent 主模型的函数；builtin 首版可用 `config.defaultModel`，扩展时可加 `modelOverrides.agent` 或与 `agentOverrides` 对称的表。
+
+#### chatCompletionText
+
+```87:124:packages/workflow-agent-kit/src/extract.ts
+async function chatCompletionText(
+  provider: ResolvedLlmProvider,
+  messages: Array<{ role: "system" | "user"; content: string }>,
+): Promise<string>
+```
+
+| 能力 | 现状 |
+|------|------|
+| 协议 | OpenAI 兼容 `POST /chat/completions` |
+| Streaming | **无**（一次性 `response.text()`） |
+| Tool calling | **无**（无 `tools` / `tool_calls` 字段） |
+| 多模态 | **无**（仅 text `content`） |
+| Extract 专用 | `response_format: { type: "json_object" }` |
+
+builtin agent 的 run loop 需要**新写**带 `tools` 的 completion 客户端（可放在 `workflow-agent-builtin` 或扩展 `workflow-agent-kit` 的 `llm/` 模块），不能复用当前 `chatCompletionText` 而不改。
+
+---
+
+### Q6: Hermes Agent 参考实现
+
+`uwf-hermes` 是怎么实现 `run` 和 `continue` 的？
+
+**调研要点：**
+- prompt 怎么组装的（outputFormatInstruction + rolePrompt + task + history）
+- hermes CLI 的调用参数
+- session management（resume）
+- 输出怎么捕获
+
+**答案：**
+
+#### Prompt 组装
+
+```40:53:packages/workflow-agent-hermes/src/hermes.ts
+export function buildHermesPrompt(ctx: AgentContext): string {
+  const roleDef = ctx.workflow.roles[ctx.role];
+  const rolePrompt = roleDef !== undefined ? buildRolePrompt(roleDef) : "";
+  const parts: string[] = [];
+  if (ctx.outputFormatInstruction !== "") {
+    parts.push(ctx.outputFormatInstruction, "");
+  }
+  parts.push(rolePrompt, "", "## Task", ctx.start.prompt);
+  const historyBlock = buildHistorySummary(ctx.steps);
+  if (historyBlock !== "") {
+    parts.push("", historyBlock);
+  }
+  return parts.join("\n");
+}
+```
+
+`buildRolePrompt` 生成 `## Goal` / `## Capabilities` / `## Prepare`（含 `generateCliReference()`）/ `## Procedure` / `## Output`。
+
+`buildHistorySummary`：每步 `role`、`JSON.stringify(step.output)`、`agent`。
+
+Hermes 把**整段 prompt 作为单条 user 消息**传给 `hermes chat -q`（无独立 system channel）。
+
+#### Hermes CLI 参数
+
+首次：
+
+```88:97:packages/workflow-agent-hermes/src/hermes.ts
+spawnHermes(["chat", "-q", prompt, "--yolo", "--max-turns", "90", "--quiet"]);
+```
+
+续聊：
+
+```100:114:packages/workflow-agent-hermes/src/hermes.ts
+spawnHermes(["chat", "--resume", sessionId, "-q", message, "--yolo", "--max-turns", "90", "--quiet"]);
+```
+
+#### Session
+
+- stdout/stderr 中解析 `session_id: <id>`（`parseSessionIdFromStdout`）
+- 会话文件：`~/.hermes/sessions/session_<id>.json`
+- `loadHermesSession` → `storeHermesSessionDetail`：每 assistant/tool 消息写成 CAS turn 节点，汇总为 `detail`；**output 文本** = 最后一条非空 `assistant` 的 `content`
+
+#### 与 createAgent 的衔接
+
+```157:164:packages/workflow-agent-hermes/src/hermes.ts
+export function createHermesAgent(): () => Promise<void> {
+  return createAgent({ name: "hermes", run: runHermes, continue: continueHermes });
+}
+```
+
+`uwf-hermes` 入口：`createHermesAgent()` 即 main。
+
+Claude Code 包（`workflow-agent-claude-code`）结构相同：`buildClaudeCodePrompt` 同构，`claude -p` + `--resume` + JSON stdout 解析。
+
+---
+
+### Q7: Toolkit 需求分析
+
+要实现一个自给自足的 agent，最少需要哪些 tool？
+
+**调研要点：**
+- 现有 workflow example（solve-issue.yaml）里 role 都做什么任务
+- hermes agent 在 workflow 场景下常用哪些 tool
+- 哪些 tool 是 agent loop 必须的（如 file read/write、shell exec、web fetch）
+
+**答案：**
+
+#### solve-issue.yaml 角色能力
+
+| Role | capabilities | 隐含需求 |
+|------|----------------|----------|
+| planner | issue-analysis, planning | 读上下文/仓库、总结，通常不需写代码 |
+| developer | file-edit, shell, testing | **读文件、写文件、执行命令** |
+| reviewer | code-review, static-analysis | 读 diff/文件、静态分析（可读+可选 shell） |
+
+#### Hermes 侧
+
+Hermes 自带完整 agent runtime（`--yolo`、max-turns），tool 集由 Hermes 项目定义，workflow 不配置。从 session JSON 可见 `tool_calls` 被记入 detail，常见包括文件与 shell 类工具。
+
+#### Builtin 最小 toolkit 建议
+
+| 优先级 | Tool | 用途 |
+|--------|------|------|
+| P0 | `read_file` | 读仓库/配置/issue 上下文 |
+| P0 | `write_file` / `edit_file` | developer 改代码 |
+| P0 | `run_command` | 测试、构建、git（需 cwd + timeout + 输出截断） |
+| P1 | `list_dir` / `glob` | 导航代码库 |
+| P1 | `grep` | 搜索符号/引用 |
+| P2 | `fetch_url` | 查文档（planner 偶尔需要） |
+
+**不需要**在 builtin 里实现 moderator / workflow 路由工具——仍由 `uwf thread step` + JSONata 负责。
+
+#### Agent loop 必须能力
+
+1. 多轮 LLM 调用 + **OpenAI-style tool_calls** 解析与执行
+2. 将 tool 结果 append 回 messages
+3. 终止条件：模型不再请求 tool，或达到 `maxTurns`
+4. 最终响应须含合法 YAML frontmatter（满足 Q4），供 `createAgent` fast-path
+
+---
+
+## 方案草案
+
+（调研完成后基于以上答案撰写）
+
+### 架构设计
+
+```mermaid
+flowchart TB
+  subgraph cli ["cli-workflow"]
+    Step["uwf thread step"]
+    Spawn["spawnAgent(uwf-builtin, threadId, role)"]
+    Step --> Spawn
+  end
+
+  subgraph builtin_pkg ["@uncaged/workflow-agent-builtin"]
+    Main["createBuiltinAgent() = createAgent({...})"]
+    Prompt["buildBuiltinPrompt(ctx)"]
+    Loop["runBuiltinLoop(provider, messages, tools)"]
+    Tools["Toolkit: read/write/exec/..."]
+    Detail["storeBuiltinDetail(turns)"]
+    Main --> Prompt
+    Main --> Loop
+    Loop --> Tools
+    Loop --> Detail
+  end
+
+  subgraph kit ["workflow-agent-kit"]
+    Ctx["buildContextWithMeta"]
+    FM["tryFrontmatterFastPath"]
+    Persist["persistStep"]
+    Ctx --> Main
+    Main --> FM
+    FM --> Persist
+  end
+
+  subgraph cas ["CAS / config"]
+    Config["config.yaml models/providers"]
+    CAS["cas/ + threads.yaml"]
+  end
+
+  Spawn --> Main
+  Config --> Loop
+  CAS --> Ctx
+  Persist --> CAS
+  Spawn -->|"stdout: step hash"| Step
+```
+
+**新包**：`packages/workflow-agent-builtin`，bin `uwf-builtin`，仅依赖 `workflow-agent-kit`、`workflow-protocol`、`workflow-util`（可选 `@uncaged/json-cas` 写 detail schema）。
+
+**分层**：
+
+| 层 | 职责 |
+|----|------|
+| `createAgent`（kit） | argv、context、frontmatter extract、StepNode、stdout 协议 — **不变** |
+| `builtin/agent.ts` | `run` / `continue` 实现 |
+| `builtin/llm.ts` | OpenAI 兼容 chat + tools（可后续抽到 kit） |
+| `builtin/tools/*.ts` | 各 tool 的 JSON Schema + handler |
+| `builtin/prompt.ts` | 复用 Hermes 的 prompt 拼接逻辑（或抽到 kit 的 `buildAgentPrompt`） |
+| `builtin/detail.ts` | 类似 Hermes：每轮 assistant/tool 写入 CAS detail |
+
+**配置集成**：
+
+```yaml
+agents:
+  builtin:
+    command: "uwf-builtin"
+    args: []
+defaultAgent: "builtin"   # 或 agentOverrides 按 role 指定
+```
+
+模型：首版 `resolveModel(config, config.defaultModel)`；后续可增加 `modelOverrides.agent` 或 per-role 映射。
+
+---
+
+### Agent Run Loop
+
+伪代码（单次 `run(ctx)`）：
+
+```
+1. provider ← resolveModel(loadWorkflowConfig(), defaultModel)
+2. system ← buildBuiltinPrompt(ctx)   // outputFormatInstruction + buildRolePrompt + Task + History
+3. messages ← [{ role: "system", content: system }]
+4. sessionId ← newULID()              // 内存或临时目录，供 continue 使用
+5. turns ← []
+
+6. for turn in 1..MAX_TURNS:
+     response ← chatCompletionWithTools(provider, messages, TOOL_DEFINITIONS)
+     record assistant message + tool_calls in turns
+
+     if response has no tool_calls:
+       finalText ← response.content
+       break
+
+     for each tool_call:
+       result ← executeTool(tool_call, { cwd: process.cwd() })
+       messages.push tool result
+       record in turns
+
+7. if no finalText with valid frontmatter after loop:
+     optionally one-shot "finalize" message without tools
+
+8. detailHash ← storeBuiltinDetail(store, sessionId, turns, metadata)
+9. return { output: finalText, detailHash, sessionId }
+```
+
+**`continue(sessionId, message, store)`**：
+
+- 从内存/磁盘恢复 `messages` + `turns`
+- `messages.push({ role: "user", content: message })`（correction 或续聊）
+- 从步骤 6 继续，步数上限可单独设小一点（如 3）
+- 返回新的 `AgentRunResult`
+
+**与 frontmatter 的配合**：
+
+- system prompt 已含 `outputFormatInstruction`；最后一轮可强制 user：`Now output your final answer with YAML frontmatter only if you have not yet.`
+- 仍依赖 `createAgent` 的 fast-path + 最多 2 次 continue
+
+**安全**：
+
+- `run_command`：白名单或需 `UWF_BUILTIN_ALLOW_SHELL=1`，默认工作区限定在 `process.cwd()` 或 `start` 中将来扩展的 `workspace` 字段
+- 路径：禁止 `..` 逃逸出 workspace root
+
+---
+
+### Toolkit 设计
+
+统一注册表：
+
+```typescript
+type BuiltinTool = {
+  name: string;
+  description: string;
+  parameters: JSONSchema; // object type
+  execute: (args: unknown, ctx: ToolContext) => Promise<string>;
+};
+
+type ToolContext = {
+  cwd: string;
+  storageRoot: string;
+};
+```
+
+| Tool name | OpenAI function | 行为摘要 |
+|-----------|-----------------|----------|
+| `read_file` | `read_file` | `{ path }` → UTF-8 文本，大小上限 |
+| `write_file` | `write_file` | `{ path, content }` → 写盘，返回确认 |
+| `edit_file` | 可选 | search/replace 块，减少 token |
+| `run_command` | `run_command` | `{ command, cwd? }` → stdout/stderr 截断 |
+| `list_dir` | `list_dir` | `{ path }` → 条目列表 |
+| `grep` | `grep` | `{ pattern, path? }` → 匹配行 |
+
+**LLM 请求形状**（扩展 extract 客户端）：
+
+```json
+{
+  "model": "...",
+  "messages": [...],
+  "tools": [{ "type": "function", "function": { "name", "description", "parameters" } }],
+  "tool_choice": "auto"
+}
+```
+
+解析 `choices[0].message.tool_calls`，执行后以 `{ role: "tool", tool_call_id, content }` 回传。
+
+**不提供** streaming 首版；detail CAS 记录每轮 tool 名/参数/结果摘要供 `uwf thread step-details` 调试。
+
+---
+
+### 与现有架构的集成
+
+| 集成点 | 方式 |
+|--------|------|
+| CLI 协议 | 实现标准 agent CLI：`uwf-builtin <thread-id> <role>`，stdout 一行 step hash，exit 0/1 |
+| 工厂 | `export function createBuiltinAgent()` → `createAgent({ name: "builtin", run, continue })` |
+| Context / Prompt | 复用 `buildContextWithMeta`、`buildRolePrompt`、`buildOutputFormatInstruction`；prompt 布局对齐 `buildHermesPrompt` |
+| 结构化输出 | 优先 YAML frontmatter fast-path；可选后续在 `createAgent` 增加 `extract()` fallback 开关 |
+| 配置 | `config.yaml` 增加 `agents.builtin`；`uwf setup` 可选默认 agent |
+| 存储 | `resolveStorageRoot()` + `loadWorkflowConfig` + `getEnvPath`；与 Hermes 相同，**不**改 `threads.yaml` 写入方 |
+| 测试 | 单元测试：tool handlers、prompt 组装、mock LLM tool loop；集成测试：临时 storage root + fake provider |
+| 发布 | 新包 `@uncaged/workflow-agent-builtin`，bin `uwf-builtin`，加入 `scripts/publish-all.mjs` |
+
+**明确不做**：
+
+- 不替代 moderator / 不在 agent 内调用 `uwf thread step`
+- 不依赖 Hermes/OpenClaw/Claude Code 二进制
+- 首版不实现 streaming、不实现 MCP
+
+**建议实现顺序**：
+
+1. `llm.ts`：tool calling HTTP 客户端 + 单测
+2. P0 tools + `runBuiltinLoop`
+3. `createBuiltinAgent` + detail CAS
+4. `config` / docs / `examples` 可选 `agentOverrides` 演示
+5. （可选）`createAgent` 接入 `extract()` fallback

docs/investigations/issue-418-acp-resume.md

@@ -0,0 +1,73 @@
+# Issue #418: ACP session/resume 返回空文本
+
+## 调研日期: 2026-05-23
+
+## 根因
+
+`session/resume` 在 restore 路径下 `_make_agent()` 失败，异常被静默吞掉。
+
+### 完整调用链
+
+```
+resume_session(sid)
+  → update_cwd(sid)
+    → get_session(sid) → _restore(sid)
+      → _make_agent()
+        → resolve_runtime_provider("custom") 失败（line 548-561）
+        → AIAgent() 抛出 "No LLM provider configured"（line 564）
+      → except Exception 静默吞掉（line 482-484）→ return None
+    → return None
+  → state is None → fallback: create_session()（新 sid，无历史）
+```
+
+### 关键代码位置（acp_adapter/session.py）
+
+- `_restore()` line 426-498: 从 DB 恢复 session，但 except 太宽泛
+- `_make_agent()` line 520-568: provider 解析在 restore 路径下不完整
+- Line 548-561: `resolve_runtime_provider("custom")` 失败后，`base_url` 虽然从 DB 取到了但没传给 AIAgent
+
+### 实测行为
+
+1. Phase 1: `session/new` + `prompt` → 正常，有 `agent_message_chunk`
+2. Phase 2: `session/resume` + `prompt`
+   - resume 返回成功，但 `available_commands_update` 里 sessionId 是新的（create_session fallback）
+   - 用原始 sid 发 prompt → `stopReason: "refusal"`（session 不在内存中）
+   - 用新 sid 发 prompt → 能跑但无历史（agent 回答"不知道 secret code"）
+
+### 验证脚本
+
+```python
+# 直接调用 _restore 验证
+cd ~/.hermes/hermes-agent
+python3 -c "
+import sys; sys.path.insert(0, '.')
+from acp_adapter.session import SessionManager
+sm = SessionManager()
+result = sm._restore('SESSION_ID_HERE')
+print(result)  # None — _make_agent 抛异常被吞掉
+"
+```
+
+### 两个 bug
+
+1. **`_make_agent` provider fallback 不完整**: restore 时 DB 里有 `base_url` 和 `api_mode`，但 `resolve_runtime_provider` 失败后这些值没被正确传递给 AIAgent
+2. **`_restore` 的 except 太宽泛**: 静默吞掉所有异常，连 warning 都只在 debug 级别，导致 resume 失败完全无感知
+
+### Hermes 版本
+
+- v0.10.0 (2026.4.16) — 初始测试
+- v0.14.0 (2026.5.16) — 更新后重新测试，bug 仍在
+- 代码路径: ~/.hermes/hermes-agent/acp_adapter/session.py
+
+### v0.14.0 测试结果 (2026-05-23)
+
+- `_restore` 仍因 `custom` provider 解析失败返回 None
+- 日志更清晰了：`WARNING: Failed to recreate agent for ACP session ...`
+- resume fallback 创建新 session（新 sid），但 agent 居然能回答之前的问题（可能通过 memory/session search）
+- 核心问题不变：sessionId 变了，client 用旧 sid 发 prompt → refusal
+
+### 上游 Issue
+
+- https://github.com/NousResearch/hermes-agent/issues/13489 — 已评论根因分析
+- https://github.com/NousResearch/hermes-agent/issues/8083 — resume 静默创建新 session
+- https://github.com/NousResearch/hermes-agent/issues/18452 — _make_agent fallback 不完整

docs/wf-stateless-design.md

@@ -112,8 +112,8 @@ uwf-hermes <thread-id> <role>
 
 **约定：**
 - `uwf step` 负责 moderator 决策，将 role 传给 agent CLI
-- agent-kit 根据 thread + role 从 CAS 读 systemPrompt / outputSchema
-- agent-kit 组装完整 prompt（role systemPrompt + thread context + user prompt from StartNode）
+- agent-kit 根据 thread + role 从 CAS 读 goal / capabilities / procedure / output / meta
+- agent-kit 组装完整 prompt（role goal/capabilities/procedure/output + thread context + user prompt from StartNode）
 - agent 执行实际逻辑，agent-kit 负责 extract
 - agent 将 StepNode 写入 CAS（含 output、detail、agent、prev），但**不挪链头指针**
 - stdout 输出新 StepNode 的 CAS hash（纯文本，一行）
@@ -143,7 +143,7 @@ uwf-hermes <thread-id> <role>
 
 #### `Workflow`
 
-Roles 和 moderator 内联在 Workflow 中，只有 outputSchema 独立为 CAS 节点（方便 json-cas 校验）。
+Roles 和 moderator 内联在 Workflow 中，只有 meta 独立为 CAS 节点（方便 json-cas 校验）。
 
 ```yaml
 type: <workflow-schema-hash>
@@ -153,16 +153,25 @@ payload:
   roles:
     planner:
       description: "Creates implementation plan"
-      systemPrompt: "You are a planning agent..."
-      outputSchema: "5GWKR8TN1V3JA"    # cas_ref → JSON Schema 节点（json-cas 内置）
+      goal: "You are a planning agent..."
+      capabilities: [planning, issue-analysis]
+      procedure: "Analyze the issue and create a plan."
+      output: "Output the plan summary."
+      meta: "5GWKR8TN1V3JA"    # cas_ref → JSON Schema 节点（json-cas 内置）
     developer:
       description: "Implements code changes"
-      systemPrompt: "You are a developer agent..."
-      outputSchema: "8CNWT4KR6D1HV"    # cas_ref → JSON Schema 节点
+      goal: "You are a developer agent..."
+      capabilities: [file-edit, shell]
+      procedure: "Implement the plan."
+      output: "List all files changed."
+      meta: "8CNWT4KR6D1HV"    # cas_ref → JSON Schema 节点
     reviewer:
       description: "Reviews code changes"
-      systemPrompt: "You are a code reviewer..."
-      outputSchema: "1VPBG9SM5E7WK"    # cas_ref → JSON Schema 节点
+      goal: "You are a code reviewer..."
+      capabilities: [code-review]
+      procedure: "Review the implementation."
+      output: "Approve or reject with comments."
+      meta: "1VPBG9SM5E7WK"    # cas_ref → JSON Schema 节点
   conditions:
     needsClarification:
       description: "Planner requests clarification from user"
@@ -189,7 +198,7 @@ payload:
         condition: null
 ```
 
-- `roles` — 内联定义，每个 role 的 `outputSchema` 是独立的 cas_ref（指向 json-cas 内置 JSON Schema 节点）
+- `roles` — 内联定义，每个 role 的 `meta` 是独立的 cas_ref（指向 json-cas 内置 JSON Schema 节点）
 - `conditions` — `Record<Name, JSONata>`，命名条件，方便画图描述
 - `graph` — `Record<Role | "$START", Transition[]>`，每个 Transition = `{ role, condition }`
 - `condition` 引用 conditions 中的 key，`null` = fallback
@@ -234,14 +243,14 @@ payload:
   start: "4TNVW8KR2B3MA"          # cas_ref → StartNode（每个 step 都引用）
   prev: "2MXBG6PN4A8JR"           # cas_ref → 前一个 StepNode，第一步为 null
   role: "developer"
-  output: "9KRVW3TN5F1QA"         # cas_ref → 结构化输出节点（符合 role 的 outputSchema）
+  output: "9KRVW3TN5F1QA"         # cas_ref → 结构化输出节点（符合 role 的 meta schema）
   detail: "7BQST3VW9F2MA"         # cas_ref → 执行详情（content node / 子 workflow terminal StepNode / ...）
   agent: "uwf-cursor"              # 实际使用的 agent 命令（纯字符串）
 ```
 
 - `start` — 每个 StepNode 都直接引用 StartNode，方便随机访问
 - `prev` — 前一个 StepNode 的 cas_ref，第一步为 `null`（不指向 StartNode）
-- `output` — cas_ref，指向符合 role outputSchema 的 CAS 节点，可用 json-cas 校验
+- `output` — cas_ref，指向符合 role meta schema 的 CAS 节点，可用 json-cas 校验
 - `detail` — cas_ref，指向执行详情。可以是原始 agent 输出（content node），也可以是子 workflow thread 的 terminal StepNode（workflowAsAgent 场景）
 - `agent` — 纯字符串，不是 CAS 节点
 
@@ -340,12 +349,12 @@ OPENROUTER_API_KEY=sk-or-...
 
 ```
 packages/
-├── cli-uwf/              # @uncaged/cli-uwf — uwf CLI（thread/workflow 命令）
-├── uwf-moderator/        # @uncaged/uwf-moderator — JSONata moderator 引擎
-├── uwf-agent-kit/        # @uncaged/uwf-agent-kit — Agent CLI 框架（含 extractor）
-├── uwf-agent-hermes/     # @uncaged/uwf-agent-hermes — uwf-hermes CLI
-├── uwf-agent-cursor/     # @uncaged/uwf-agent-cursor — uwf-cursor CLI
-└── uwf-protocol/         # @uncaged/uwf-protocol — 共享类型定义
+├── cli-workflow/              # @uncaged/cli-workflow — uwf CLI（thread/workflow 命令）
+├── workflow-moderator/        # @uncaged/workflow-moderator — JSONata moderator 引擎
+├── workflow-agent-kit/        # @uncaged/workflow-agent-kit — Agent CLI 框架（含 extractor）
+├── workflow-agent-hermes/     # @uncaged/workflow-agent-hermes — uwf-hermes CLI
+├── workflow-agent-cursor/ # @uncaged/workflow-agent-cursor — uwf-cursor CLI
+└── workflow-protocol/         # @uncaged/workflow-protocol — 共享类型定义
 ```
 
 **外部依赖：**
@@ -372,7 +381,7 @@ type ThreadId = string;
 /** 一个 step 的核心数据，被 StepNode payload 和 JSONata 上下文共享 */
 type StepRecord = {
   role: string;
-  output: CasRef;                    // cas_ref → 结构化输出节点（符合 role outputSchema）
+  output: CasRef;                    // cas_ref → 结构化输出节点（符合 role meta schema）
   detail: CasRef;                    // cas_ref → 执行详情（content node / 子 workflow terminal StepNode）
   agent: string;                     // 实际使用的 agent 命令（纯字符串）
 };
@@ -383,8 +392,11 @@ type StepRecord = {
 ```typescript
 type RoleDefinition = {
   description: string;
-  systemPrompt: string;
-  outputSchema: CasRef;              // cas_ref → json-cas 内置 JSON Schema 节点
+  goal: string;
+  capabilities: string[];
+  procedure: string;
+  output: string;
+  meta: CasRef;                      // cas_ref → json-cas 内置 JSON Schema 节点
 };
 
 type Transition = {

examples/analyze-topic.yaml

@@ -0,0 +1,43 @@
+name: "analyze-topic"
+description: "Single-role topic analysis using four-phase role description"
+roles:
+  analyst:
+    description: "Analyzes a given topic and produces a structured summary"
+    goal: |
+      You are a research analyst with expertise in breaking down complex topics
+      into clear, structured summaries. You think critically and cite key points.
+    capabilities:
+      - research
+      - critical-thinking
+      - structured-writing
+    procedure: |
+      Analyze the topic by:
+      1. Identifying the main thesis or question
+      2. Listing 3-5 key points with brief explanations
+      3. Noting any counterarguments or caveats
+      Keep your analysis concise (under 500 words).
+    output: |
+      Provide your analysis as markdown under the frontmatter.
+      The frontmatter must include your structured findings.
+    frontmatter:
+      type: object
+      properties:
+        thesis:
+          type: string
+        keyPoints:
+          type: array
+          items:
+            type: string
+        caveats:
+          type: string
+      required: [thesis, keyPoints]
+conditions: {}
+graph:
+  $START:
+    - role: "analyst"
+      condition: null
+      prompt: "Analyze the topic in the task and produce a structured summary with key points."
+  analyst:
+    - role: "$END"
+      condition: null
+      prompt: "Analysis complete. Finish the workflow."

examples/debate.yaml

@@ -0,0 +1,77 @@
+name: "debate"
+description: "Structured debate between two sides. Tests cross-process session resume."
+roles:
+  against:
+    description: "Argues against the proposition"
+    goal: |
+      You are a skilled debater arguing AGAINST the proposition.
+      Be logical, cite evidence, and directly address your opponent's points.
+      Keep each argument concise (under 200 words).
+    capabilities:
+      - argumentation
+      - critical-thinking
+    procedure: |
+      1. If this is the opening, present your strongest argument against the proposition.
+      2. If responding to the other side, directly counter their points with evidence and logic.
+      3. If you find yourself genuinely convinced by the other side, you may concede.
+    output: |
+      Provide your argument in the frontmatter.
+      Set conceded to true ONLY if you are genuinely convinced and wish to stop debating.
+    frontmatter:
+      type: object
+      properties:
+        argument:
+          type: string
+        conceded:
+          type: boolean
+      required: [argument, conceded]
+  for:
+    description: "Argues for the proposition"
+    goal: |
+      You are a skilled debater arguing FOR the proposition.
+      Be logical, cite evidence, and directly address your opponent's points.
+      Keep each argument concise (under 200 words).
+    capabilities:
+      - argumentation
+      - critical-thinking
+    procedure: |
+      1. Read the opposing side's latest argument carefully.
+      2. Counter their points with evidence and logic.
+      3. If you find yourself genuinely convinced by the other side, you may concede.
+    output: |
+      Provide your argument in the frontmatter.
+      Set conceded to true ONLY if you are genuinely convinced and wish to stop debating.
+    frontmatter:
+      type: object
+      properties:
+        argument:
+          type: string
+        conceded:
+          type: boolean
+      required: [argument, conceded]
+conditions:
+  againstConceded:
+    description: "The against side conceded"
+    expression: "$last('against').conceded = true"
+  forConceded:
+    description: "The for side conceded"
+    expression: "$last('for').conceded = true"
+graph:
+  $START:
+    - role: "against"
+      condition: null
+      prompt: "Present your opening argument against the proposition."
+  against:
+    - role: "$END"
+      condition: "againstConceded"
+      prompt: "The against side conceded. Debate over."
+    - role: "for"
+      condition: null
+      prompt: "Counter the opposing argument. Address their points directly."
+  for:
+    - role: "$END"
+      condition: "forConceded"
+      prompt: "The for side conceded. Debate over."
+    - role: "against"
+      condition: null
+      prompt: "Counter the opposing argument. Address their points directly."

examples/solve-issue.yaml

@@ -3,21 +3,51 @@ description: "End-to-end issue resolution"
 roles:
   planner:
     description: "Creates implementation plan"
-    systemPrompt: "You are a planning agent. Analyze the issue and create a step-by-step plan."
-    outputSchema:
+    goal: "You are a planning agent. You analyze issues and create implementation plans grounded in the actual codebase."
+    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.
+    frontmatter:
       type: object
       properties:
+        repoPath:
+          type: string
         plan:
           type: string
-        steps:
-          type: array
-          items:
-            type: string
-      required: [plan, steps]
+      required: [repoPath, plan]
   developer:
     description: "Implements code changes"
-    systemPrompt: "You are a developer agent. Implement the plan."
-    outputSchema:
+    goal: "You are a developer agent. You implement code changes according to plans."
+    capabilities:
+      - file-edit
+      - shell
+      - testing
+    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."
+    frontmatter:
       type: object
       properties:
         filesChanged:
@@ -29,8 +59,16 @@ roles:
       required: [filesChanged, summary]
   reviewer:
     description: "Reviews code changes"
-    systemPrompt: "You are a code reviewer. Review the implementation."
-    outputSchema:
+    goal: "You are a code reviewer. You review implementations for correctness and quality."
+    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."
+    frontmatter:
       type: object
       properties:
         approved:
@@ -41,19 +79,24 @@ roles:
 conditions:
   notApproved:
     description: "Reviewer rejected the implementation"
-    expression: "steps[-1].output.approved = false"
+    expression: "$last('reviewer').approved = false"
 graph:
   $START:
     - role: "planner"
       condition: null
+      prompt: "Analyze the issue described in the task and produce a detailed implementation plan."
   planner:
     - role: "developer"
       condition: null
+      prompt: "Implement the plan from the planner. Write code, tests, and ensure existing tests pass."
   developer:
     - role: "reviewer"
       condition: null
+      prompt: "Review the developer's implementation against the plan for correctness and quality."
   reviewer:
     - role: "developer"
       condition: "notApproved"
+      prompt: "The reviewer rejected your implementation. Read their feedback and fix the issues."
     - role: "$END"
       condition: null
+      prompt: "The review passed. Complete the workflow."

legacy-packages/workflow-agent-docx-diff/__tests__/agent.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test";
-import { packageDescriptor } from "../src/package-descriptor.js";
 import { createDocxDiffAgent } from "../src/agent.js";
+import { packageDescriptor } from "../src/package-descriptor.js";
 
 describe("createDocxDiffAgent", () => {
   test("returns an AdapterFn (function)", () => {

legacy-packages/workflow-agent-docx-diff/__tests__/runner.test.ts

@@ -1,8 +1,8 @@
-import { mkdirSync, writeFileSync } from "node:fs";
-import { join } from "node:path";
-import { tmpdir } from "node:os";
 import { describe, expect, mock, test } from "bun:test";
-import { ok, err } from "@uncaged/workflow-util";
+import { mkdirSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { err, ok } from "@uncaged/workflow-util";
 import type { SpawnCliConfig } from "@uncaged/workflow-util-agent";
 import { runDocxDiff } from "../src/runner.js";
 
@@ -74,7 +74,12 @@ describe("runDocxDiff", () => {
   test("exit 2: throws error", async () => {
     const dir = tempDir();
     const spawnFn = makeSpawn(
-      err({ kind: "non_zero_exit", exitCode: 2, stdout: "", stderr: "fatal error" }) as MockSpawnResult,
+      err({
+        kind: "non_zero_exit",
+        exitCode: 2,
+        stdout: "",
+        stderr: "fatal error",
+      }) as MockSpawnResult,
     );
 
     await expect(

legacy-packages/workflow-agent-docx-diff/package.json

@@ -1,7 +1,11 @@
 {
   "name": "@uncaged/workflow-agent-docx-diff",
   "version": "0.1.0",
-  "files": ["src", "dist", "package.json"],
+  "files": [
+    "src",
+    "dist",
+    "package.json"
+  ],
   "type": "module",
   "types": "src/index.ts",
   "exports": {

legacy-packages/workflow-agent-docx-diff/src/agent.ts

@@ -1,7 +1,12 @@
-import * as z from "zod/v4";
 import { dirname, join } from "node:path";
-import type { AdapterFn, RoleResult, ThreadContext, WorkflowRuntime } from "@uncaged/workflow-runtime";
+import type {
+  AdapterFn,
+  RoleResult,
+  ThreadContext,
+  WorkflowRuntime,
+} from "@uncaged/workflow-runtime";
 import type { WriterMeta } from "@uncaged/workflow-template-document";
+import type * as z from "zod/v4";
 import { runDocxDiff } from "./runner.js";
 import type { DocxDiffAgentConfig } from "./types.js";
 
@@ -12,16 +17,10 @@ export function createDocxDiffAgent(config: DocxDiffAgentConfig): AdapterFn {
       if (writerStep === undefined) throw new Error("differ: no writer step found");
 
       const writerMeta = writerStep.meta as WriterMeta;
-      if (writerMeta.mode !== "edit")
-        throw new Error("differ: writer did not run in edit mode");
+      if (writerMeta.mode !== "edit") throw new Error("differ: writer did not run in edit mode");
 
       const diffDocx = join(dirname(writerMeta.outputDocx), "diff.docx");
-      const raw = await runDocxDiff(
-        config,
-        writerMeta.sourceDocx,
-        writerMeta.outputDocx,
-        diffDocx,
-      );
+      const raw = await runDocxDiff(config, writerMeta.sourceDocx, writerMeta.outputDocx, diffDocx);
 
       const meta = schema.parse(JSON.parse(raw)) as T;
       return { meta, childThread: null };

legacy-packages/workflow-agent-docx-diff/src/runner.ts

@@ -1,6 +1,6 @@
 import { stat } from "node:fs/promises";
-import { spawnCli } from "@uncaged/workflow-util-agent";
 import type { SpawnCliError } from "@uncaged/workflow-util-agent";
+import { spawnCli } from "@uncaged/workflow-util-agent";
 import type { DocxDiffAgentConfig } from "./types.js";
 
 type SpawnCliFn = typeof spawnCli;
@@ -8,8 +8,7 @@ type SpawnCliFn = typeof spawnCli;
 function throwSpawnError(e: SpawnCliError): never {
   if (e.kind === "non_zero_exit")
     throw new Error(`docx-diff failed (exit ${e.exitCode}): ${e.stderr}`);
-  if (e.kind === "timeout")
-    throw new Error("docx-diff: timed out");
+  if (e.kind === "timeout") throw new Error("docx-diff: timed out");
   throw new Error(`docx-diff: spawn failed: ${e.message}`);
 }
 

legacy-packages/workflow-agent-office/__tests__/agent.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test";
-import { packageDescriptor } from "../src/package-descriptor.js";
 import { createOfficeAgent } from "../src/agent.js";
+import { packageDescriptor } from "../src/package-descriptor.js";
 
 describe("createOfficeAgent", () => {
   test("returns an AdapterFn (function)", () => {

legacy-packages/workflow-agent-office/__tests__/runner.test.ts

@@ -1,8 +1,8 @@
-import { mkdirSync, writeFileSync } from "node:fs";
-import { join } from "node:path";
-import { tmpdir } from "node:os";
 import { describe, expect, mock, test } from "bun:test";
-import { ok, err } from "@uncaged/workflow-util";
+import { mkdirSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { err, ok } from "@uncaged/workflow-util";
 import type { SpawnCliConfig } from "@uncaged/workflow-util-agent";
 import { editDocument, generateDocument } from "../src/runner.js";
 
@@ -123,7 +123,13 @@ describe("editDocument", () => {
     );
 
     await expect(
-      editDocument({ outputDir: base, command: null, timeout: null }, "te2", "edit", inputFile, spawnFn),
+      editDocument(
+        { outputDir: base, command: null, timeout: null },
+        "te2",
+        "edit",
+        inputFile,
+        spawnFn,
+      ),
     ).rejects.toThrow("spawn failed");
   });
 });

legacy-packages/workflow-agent-office/package.json

@@ -1,7 +1,11 @@
 {
   "name": "@uncaged/workflow-agent-office",
   "version": "0.1.0",
-  "files": ["src", "dist", "package.json"],
+  "files": [
+    "src",
+    "dist",
+    "package.json"
+  ],
   "type": "module",
   "types": "src/index.ts",
   "exports": {

legacy-packages/workflow-agent-office/src/agent.ts

@@ -1,6 +1,11 @@
-import * as z from "zod/v4";
-import type { AdapterFn, RoleResult, ThreadContext, WorkflowRuntime } from "@uncaged/workflow-runtime";
+import type {
+  AdapterFn,
+  RoleResult,
+  ThreadContext,
+  WorkflowRuntime,
+} from "@uncaged/workflow-runtime";
 import { createLogger } from "@uncaged/workflow-util";
+import type * as z from "zod/v4";
 import { editDocument, generateDocument } from "./runner.js";
 import type { OfficeAgentConfig } from "./types.js";
 
@@ -27,7 +32,10 @@ export function createOfficeAgent(config: OfficeAgentConfig): AdapterFn {
   return <T>(_systemPrompt: string, schema: z.ZodType<T>) =>
     async (ctx: ThreadContext, _runtime: WorkflowRuntime): Promise<RoleResult<T>> => {
       const { prompt, inputDocx } = parseStartInput(ctx.start.content);
-      log("8FQKP3NV", `office-agent: mode=${inputDocx === null ? "generate" : "edit"} thread=${ctx.threadId}`);
+      log(
+        "8FQKP3NV",
+        `office-agent: mode=${inputDocx === null ? "generate" : "edit"} thread=${ctx.threadId}`,
+      );
 
       let raw: string;
       if (inputDocx === null) {
@@ -35,7 +43,11 @@ export function createOfficeAgent(config: OfficeAgentConfig): AdapterFn {
         raw = JSON.stringify({ mode: "generate", outputDocx: result.outputDocx, sourceDocx: null });
       } else {
         const result = await editDocument(config, ctx.threadId, prompt, inputDocx);
-        raw = JSON.stringify({ mode: "edit", outputDocx: result.outputDocx, sourceDocx: result.sourceDocx });
+        raw = JSON.stringify({
+          mode: "edit",
+          outputDocx: result.outputDocx,
+          sourceDocx: result.sourceDocx,
+        });
       }
 
       const meta = schema.parse(JSON.parse(raw)) as T;

legacy-packages/workflow-agent-office/src/runner.ts

@@ -1,7 +1,7 @@
 import { copyFile, mkdir, stat } from "node:fs/promises";
 import { join } from "node:path";
-import { spawnCli } from "@uncaged/workflow-util-agent";
 import type { SpawnCliError } from "@uncaged/workflow-util-agent";
+import { spawnCli } from "@uncaged/workflow-util-agent";
 import type { OfficeAgentConfig } from "./types.js";
 
 type SpawnCliFn = typeof spawnCli;
@@ -9,8 +9,7 @@ type SpawnCliFn = typeof spawnCli;
 function throwSpawnError(e: SpawnCliError): never {
   if (e.kind === "non_zero_exit")
     throw new Error(`office-agent failed (exit ${e.exitCode}): ${e.stderr}`);
-  if (e.kind === "timeout")
-    throw new Error("office-agent: timed out");
+  if (e.kind === "timeout") throw new Error("office-agent: timed out");
   throw new Error(`office-agent: spawn failed: ${e.message}`);
 }
 

legacy-packages/workflow-dashboard/index.html

@@ -5,7 +5,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>Workflow Dashboard</title>
     <script>
-      (function () {
+      (() => {
         var t = localStorage.getItem("theme");
         if (t === "dark" || (!t && matchMedia("(prefers-color-scheme: dark)").matches)) {
           document.documentElement.classList.add("dark");

legacy-packages/workflow-dashboard/plugins/vite-limit-line-plugin.ts

@@ -54,10 +54,14 @@ type CallExpression = {
   arguments: Array<AstExpression>;
 };
 
-type AstExpression = Identifier | MemberExpression | CallExpression | {
-  type: string;
-  [key: string]: unknown;
-};
+type AstExpression =
+  | Identifier
+  | MemberExpression
+  | CallExpression
+  | {
+      type: string;
+      [key: string]: unknown;
+    };
 
 type VariableDeclarator = {
   id: Identifier | null;
@@ -258,15 +262,21 @@ function createLimitResolver(options: LimitLineOptions): (id: string) => Resolve
 }
 
 function shouldProcess(id: string, options: LimitLineOptions): boolean {
-  return options.include.test(id) && !id.includes("node_modules") && (options.exclude === null || !options.exclude.test(id));
+  return (
+    options.include.test(id) &&
+    !id.includes("node_modules") &&
+    (options.exclude === null || !options.exclude.test(id))
+  );
 }
 
 // --- Plugin ---
 
-function viteLimitLinePlugin(
-  userOptions: Partial<LimitLineOptions> = {},
-): Array<Plugin> {
-  const options: LimitLineOptions = { ...DEFAULT_OPTIONS, ...userOptions, overrides: userOptions.overrides ?? [] };
+function viteLimitLinePlugin(userOptions: Partial<LimitLineOptions> = {}): Array<Plugin> {
+  const options: LimitLineOptions = {
+    ...DEFAULT_OPTIONS,
+    ...userOptions,
+    overrides: userOptions.overrides ?? [],
+  };
   const resolve = createLimitResolver(options);
 
   const rawCodeCache = new Map<string, string>();
@@ -358,5 +368,5 @@ function viteLimitLinePlugin(
   ];
 }
 
-export { viteLimitLinePlugin };
 export type { LimitLineOptions, LimitLineOverride };
+export { viteLimitLinePlugin };

legacy-packages/workflow-dashboard/src/components/ui/resizable-panel.tsx

@@ -55,10 +55,7 @@ export function ResizablePanel({
   }, []);
 
   return (
-    <div
-      className={cn("relative shrink-0", className)}
-      style={{ ...style, width }}
-    >
+    <div className={cn("relative shrink-0", className)} style={{ ...style, width }}>
       {children}
       <div
         className="absolute top-0 -right-1 w-2 h-full cursor-col-resize z-10 group"

legacy-packages/workflow-execute/src/engine/engine.ts

@@ -531,13 +531,25 @@ export async function executeThread(
       timestamp: nowMs,
       parentState: options.parentStateHash,
     },
-    steps: input.steps.map((out, i) => ({
-      role: out.role,
-      contentHash: out.contentHash,
-      meta: out.meta,
-      refs: out.refs,
-      timestamp: replayTs?.[i] ?? prefilled?.[i]?.timestamp ?? nowMs + i,
-    })),
+    steps: await Promise.all(
+      input.steps.map(async (out, i) => {
+        // Resolve content for the last step (most relevant for the next agent).
+        // Earlier steps only carry meta summaries to avoid bloating the prompt.
+        const isLast = i === input.steps.length - 1;
+        let content: string | null = null;
+        if (isLast) {
+          content = await getContentMerklePayload(io.cas, out.contentHash);
+        }
+        return {
+          role: out.role,
+          contentHash: out.contentHash,
+          content,
+          meta: out.meta,
+          refs: out.refs,
+          timestamp: replayTs?.[i] ?? prefilled?.[i]?.timestamp ?? nowMs + i,
+        };
+      }),
+    ),
   };
 
   const runtime: WorkflowRuntime = {

legacy-packages/workflow-protocol/src/types.ts

@@ -71,6 +71,7 @@ export type RoleStep<M extends RoleMeta> = {
     role: K;
     meta: M[K];
     contentHash: string;
+    content: string | null;
     refs: string[];
     timestamp: number;
   };

legacy-packages/workflow-runtime/src/build-context.ts

@@ -71,7 +71,8 @@ async function buildRoleStepsFromStates<M extends RoleMeta>(
   cas: CasStore,
 ): Promise<RoleStep<M>[]> {
   const steps: RoleStep<M>[] = [];
-  for (const st of chronologicalStates) {
+  for (let idx = 0; idx < chronologicalStates.length; idx++) {
+    const st = chronologicalStates[idx];
     if (st.payload.role === END) {
       continue;
     }
@@ -79,10 +80,13 @@ async function buildRoleStepsFromStates<M extends RoleMeta>(
     if (contentParsed === null || contentParsed.kind !== "content") {
       throw new Error(`buildThreadContext: expected content node at ${st.payload.content}`);
     }
+    // Resolve full text content for the last step only
+    const isLast = idx === chronologicalStates.length - 1;
     steps.push({
       role: st.payload.role,
       meta: st.payload.meta,
       contentHash: st.payload.content,
+      content: isLast ? contentParsed.node.payload : null,
       refs: [...contentParsed.node.refs],
       timestamp: st.payload.timestamp,
     } as RoleStep<M>);

legacy-packages/workflow-runtime/src/create-workflow.ts

@@ -88,6 +88,7 @@ async function advanceOneRound<M extends RoleMeta>(
   const step = {
     role: next,
     contentHash,
+    content: contentPayload,
     meta,
     refs,
     timestamp: Date.now(),

legacy-packages/workflow-template-document/__tests__/document-template.test.ts

@@ -9,9 +9,7 @@ import type { DocumentMeta } from "../src/roles.js";
 
 const documentModerator = tableToModerator(documentTable);
 
-function makeCtx(
-  steps: ModeratorContext<DocumentMeta>["steps"],
-): ModeratorContext<DocumentMeta> {
+function makeCtx(steps: ModeratorContext<DocumentMeta>["steps"]): ModeratorContext<DocumentMeta> {
   return {
     threadId: "01TEST000000000000000000TR",
     depth: 0,
@@ -25,7 +23,11 @@ function writerGenerateStep(): RoleStep<DocumentMeta> {
   return {
     role: "writer",
     contentHash: "STUBHASHWRITER001",
-    meta: { mode: "generate", outputDocx: "/out/output.docx", sourceDocx: null } satisfies WriterMeta,
+    meta: {
+      mode: "generate",
+      outputDocx: "/out/output.docx",
+      sourceDocx: null,
+    } satisfies WriterMeta,
     refs: [],
     timestamp: 1,
   };
@@ -35,7 +37,11 @@ function writerEditStep(): RoleStep<DocumentMeta> {
   return {
     role: "writer",
     contentHash: "STUBHASHWRITER002",
-    meta: { mode: "edit", outputDocx: "/out/modified.docx", sourceDocx: "/out/original.docx" } satisfies WriterMeta,
+    meta: {
+      mode: "edit",
+      outputDocx: "/out/modified.docx",
+      sourceDocx: "/out/original.docx",
+    } satisfies WriterMeta,
     refs: [],
     timestamp: 1,
   };

legacy-packages/workflow-template-document/package.json

@@ -1,7 +1,11 @@
 {
   "name": "@uncaged/workflow-template-document",
   "version": "0.1.0",
-  "files": ["src", "dist", "package.json"],
+  "files": [
+    "src",
+    "dist",
+    "package.json"
+  ],
   "type": "module",
   "types": "src/index.ts",
   "exports": {

legacy-packages/workflow-util-agent/__tests__/build-agent-prompt.test.ts

@@ -30,7 +30,7 @@ describe("buildAgentPrompt", () => {
     expect(text).not.toContain("## Tools");
   });
 
-  test("single step shows hash and meta, and includes tools", async () => {
+  test("single step shows meta and content, and includes tools", async () => {
     const onlyHash = "01HASHSINGLESTEP0000000001";
     const ctx: AgentContext = {
       start: startTask("user task"),
@@ -42,6 +42,7 @@ describe("buildAgentPrompt", () => {
         {
           role: "coder",
           contentHash: onlyHash,
+          content: "Here is my implementation of the feature.",
           meta: { files: ["a.ts"] },
           refs: [onlyHash],
           timestamp: 2,
@@ -52,13 +53,39 @@ describe("buildAgentPrompt", () => {
     expect(text).toContain("## Task");
     expect(text).toContain("user task");
     expect(text).toContain("## Step: coder");
-    expect(text).toContain(`ContentHash: ${onlyHash}`);
     expect(text).toContain('Meta: {"files":["a.ts"]}');
+    expect(text).toContain("<output>");
+    expect(text).toContain("Here is my implementation of the feature.");
+    expect(text).toContain("</output>");
     expect(text).toContain("## Tools");
     expect(text).toContain("uncaged-workflow thread 01TEST000000000000000000TR");
   });
 
-  test("two or more steps: previous steps are meta-only; latest step includes hash", async () => {
+  test("single step with null content omits output tag", async () => {
+    const onlyHash = "01HASHSINGLESTEP0000000001";
+    const ctx: AgentContext = {
+      start: startTask("user task"),
+      depth: 0,
+      bundleHash: "TESTHASH00001",
+      threadId: "01TEST000000000000000000TR",
+      currentRole: { name: "coder", systemPrompt: "Be helpful." },
+      steps: [
+        {
+          role: "coder",
+          contentHash: onlyHash,
+          content: null,
+          meta: { files: ["a.ts"] },
+          refs: [onlyHash],
+          timestamp: 2,
+        },
+      ],
+    };
+    const text = await buildAgentPrompt(ctx);
+    expect(text).not.toContain("<output>");
+    expect(text).toContain('Meta: {"files":["a.ts"]}');
+  });
+
+  test("two or more steps: previous steps are meta-only; latest step includes content", async () => {
     const plannerHash = "01HASHPLANNER0000000000001";
     const coderHash = "01HASHCODER0000000000000001";
     const ctx: AgentContext = {
@@ -71,6 +98,7 @@ describe("buildAgentPrompt", () => {
         {
           role: "planner",
           contentHash: plannerHash,
+          content: null,
           meta: { plan: "short" },
           refs: [plannerHash],
           timestamp: 2,
@@ -78,6 +106,7 @@ describe("buildAgentPrompt", () => {
         {
           role: "coder",
           contentHash: coderHash,
+          content: "I reviewed the code and found 4 lint issues:\n1. Missing semicolon on line 42\n2. Unused import on line 3",
           meta: { done: true },
           refs: [coderHash],
           timestamp: 3,
@@ -90,10 +119,11 @@ describe("buildAgentPrompt", () => {
     expect(text).toContain("### Step 1: planner");
     expect(text).toContain('Summary: {"plan":"short"}');
     expect(text).toContain("## Latest Step: coder");
-    expect(text).toContain(`ContentHash: ${coderHash}`);
     expect(text).toContain('Meta: {"done":true}');
+    expect(text).toContain("<output>");
+    expect(text).toContain("I reviewed the code and found 4 lint issues:");
+    expect(text).toContain("</output>");
     expect(text).toContain("## Tools");
-    expect(text).toContain("uncaged-workflow thread 01TEST000000000000000000TR");
   });
 
   test("parentState null omits Parent Context section", async () => {
@@ -125,7 +155,7 @@ describe("buildAgentPrompt", () => {
     expect(text).toContain(`uncaged-workflow cas get ${parentHash}`);
   });
 
-  test("middle steps show meta summary only and latest shows hash", async () => {
+  test("middle steps show meta summary only and latest shows content", async () => {
     const ha = "01HASHA00000000000000000001";
     const hb = "01HASHB00000000000000000001";
     const hc = "01HASHC00000000000000000001";
@@ -139,6 +169,7 @@ describe("buildAgentPrompt", () => {
         {
           role: "a",
           contentHash: ha,
+          content: null,
           meta: { n: 1 },
           refs: [ha],
           timestamp: 2,
@@ -146,6 +177,7 @@ describe("buildAgentPrompt", () => {
         {
           role: "b",
           contentHash: hb,
+          content: null,
           meta: { n: 2 },
           refs: [hb],
           timestamp: 3,
@@ -153,6 +185,7 @@ describe("buildAgentPrompt", () => {
         {
           role: "c",
           contentHash: hc,
+          content: "Final output from role c",
           meta: { n: 3 },
           refs: [hc],
           timestamp: 4,
@@ -162,7 +195,35 @@ describe("buildAgentPrompt", () => {
     const text = await buildAgentPrompt(ctx);
     expect(text).toContain('Summary: {"n":1}');
     expect(text).toContain('Summary: {"n":2}');
-    expect(text).toContain(`ContentHash: ${hc}`);
     expect(text).toContain("## Latest Step: c");
+    expect(text).toContain("<output>");
+    expect(text).toContain("Final output from role c");
+    expect(text).toContain("</output>");
+  });
+
+  test("content is truncated when exceeding quota", async () => {
+    const longContent = "x".repeat(20_000);
+    const hash = "01HASHLONG000000000000000001";
+    const ctx: AgentContext = {
+      start: startTask("task"),
+      depth: 0,
+      bundleHash: "TESTHASH00001",
+      threadId: "01TEST000000000000000000TR",
+      currentRole: { name: "r", systemPrompt: "S" },
+      steps: [
+        {
+          role: "r",
+          contentHash: hash,
+          content: longContent,
+          meta: {},
+          refs: [],
+          timestamp: 2,
+        },
+      ],
+    };
+    const text = await buildAgentPrompt(ctx);
+    expect(text).toContain("<output>");
+    expect(text).toContain("... (truncated)");
+    expect(text.length).toBeLessThan(20_000);
   });
 });

package.json

@@ -5,20 +5,23 @@
     "packages/*"
   ],
   "scripts": {
+    "uwf": "bun packages/cli-workflow/src/cli.ts",
     "build": "bunx tsc --build",
     "check": "bunx tsc --build && biome check . && bash scripts/lint-log-tags.sh",
     "typecheck": "bunx tsc --build",
     "format": "biome format --write .",
-    "test": "bun run --filter '*' test",
+    "test": "bun run --filter './packages/*' test",
     "changeset": "bunx changeset",
     "version": "bunx changeset version",
-    "release": "bun run build && bun test && npx changeset publish --no-git-tag"
+    "release": "bun run build && bun test && node scripts/publish-all.mjs"
   },
   "devDependencies": {
+    "@agentclientprotocol/sdk": "^0.22.1",
     "@biomejs/biome": "^2.4.14",
     "@changesets/cli": "^2.31.0",
     "@types/node": "^25.7.0",
     "@types/xxhashjs": "^0.2.4",
+    "@uncaged/workflow-agent-hermes": "workspace:*",
     "bun-types": "^1.3.13"
   }
 }

packages/cli-uwf/src/__tests__/thread.test.ts

@@ -1,391 +0,0 @@
-import { mkdir, mkdtemp, rm } from "node:fs/promises";
-import { tmpdir } from "node:os";
-import { join } from "node:path";
-import { bootstrap, putSchema } from "@uncaged/json-cas";
-import { createFsStore } from "@uncaged/json-cas-fs";
-import type { CasRef, ThreadId } from "@uncaged/uwf-protocol";
-import { afterEach, beforeEach, describe, expect, test } from "vitest";
-import {
-  cmdThreadRead,
-  cmdThreadStepDetails,
-  extractLastAssistantContent,
-  THREAD_READ_DEFAULT_QUOTA,
-} from "../commands/thread.js";
-import { registerUwfSchemas } from "../schemas.js";
-import type { UwfStore } from "../store.js";
-import { saveThreadsIndex } from "../store.js";
-
-// ── schemas used in tests ────────────────────────────────────────────────────
-
-const TURN_SCHEMA = {
-  title: "hermes-turn",
-  type: "object" as const,
-  required: ["index", "role", "content"],
-  properties: {
-    index: { type: "integer" as const },
-    role: { type: "string" as const },
-    content: { type: "string" as const },
-    toolCalls: {
-      anyOf: [
-        { type: "array" as const, items: { type: "object" as const } },
-        { type: "null" as const },
-      ],
-    },
-    reasoning: { anyOf: [{ type: "string" as const }, { type: "null" as const }] },
-  },
-  additionalProperties: false,
-};
-
-const DETAIL_SCHEMA = {
-  title: "hermes-detail",
-  type: "object" as const,
-  required: ["sessionId", "model", "duration", "turnCount", "turns"],
-  properties: {
-    sessionId: { type: "string" as const },
-    model: { type: "string" as const },
-    duration: { type: "integer" as const },
-    turnCount: { type: "integer" as const },
-    turns: {
-      type: "array" as const,
-      items: { type: "string" as const, format: "cas_ref" },
-    },
-  },
-  additionalProperties: false,
-};
-
-// ── helpers ───────────────────────────────────────────────────────────────────
-
-async function makeUwfStore(storageRoot: string): Promise<UwfStore> {
-  const casDir = join(storageRoot, "cas");
-  await mkdir(casDir, { recursive: true });
-  const store = createFsStore(casDir);
-  const schemas = await registerUwfSchemas(store);
-  return { storageRoot, store, schemas };
-}
-
-async function registerDetailSchemas(store: ReturnType<typeof createFsStore>) {
-  await bootstrap(store);
-  const [turn, detail] = await Promise.all([
-    putSchema(store, TURN_SCHEMA),
-    putSchema(store, DETAIL_SCHEMA),
-  ]);
-  return { turn, detail };
-}
-
-// ── fixture ───────────────────────────────────────────────────────────────────
-
-let tmpDir: string;
-
-beforeEach(async () => {
-  tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-test-"));
-});
-
-afterEach(async () => {
-  await rm(tmpDir, { recursive: true, force: true });
-});
-
-// ── extractLastAssistantContent ───────────────────────────────────────────────
-
-describe("extractLastAssistantContent", () => {
-  test("returns last non-empty assistant content from turns", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-    const schemas = await registerDetailSchemas(uwf.store);
-
-    const turn1 = await uwf.store.put(schemas.turn, {
-      index: 0,
-      role: "assistant",
-      content: "intermediate",
-      toolCalls: null,
-      reasoning: null,
-    });
-    const turn2 = await uwf.store.put(schemas.turn, {
-      index: 1,
-      role: "tool",
-      content: "ok",
-      toolCalls: null,
-      reasoning: null,
-    });
-    const turn3 = await uwf.store.put(schemas.turn, {
-      index: 2,
-      role: "assistant",
-      content: "final answer",
-      toolCalls: null,
-      reasoning: null,
-    });
-
-    const detailHash = await uwf.store.put(schemas.detail, {
-      sessionId: "s1",
-      model: "m1",
-      duration: 1000,
-      turnCount: 3,
-      turns: [turn1, turn2, turn3],
-    });
-
-    expect(extractLastAssistantContent(uwf, detailHash)).toBe("final answer");
-  });
-
-  test("returns null when detail node does not exist in store", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-    expect(extractLastAssistantContent(uwf, "nonexistent00" as CasRef)).toBeNull();
-  });
-
-  test("returns null when turns array is empty", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-    const schemas = await registerDetailSchemas(uwf.store);
-
-    const detailHash = await uwf.store.put(schemas.detail, {
-      sessionId: "s2",
-      model: "m2",
-      duration: 0,
-      turnCount: 0,
-      turns: [],
-    });
-
-    expect(extractLastAssistantContent(uwf, detailHash)).toBeNull();
-  });
-
-  test("returns null when all assistant turns have empty content", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-    const schemas = await registerDetailSchemas(uwf.store);
-
-    const turn1 = await uwf.store.put(schemas.turn, {
-      index: 0,
-      role: "assistant",
-      content: "",
-      toolCalls: null,
-      reasoning: null,
-    });
-
-    const detailHash = await uwf.store.put(schemas.detail, {
-      sessionId: "s3",
-      model: "m3",
-      duration: 0,
-      turnCount: 1,
-      turns: [turn1],
-    });
-
-    expect(extractLastAssistantContent(uwf, detailHash)).toBeNull();
-  });
-
-  test("skips whitespace-only assistant content and returns earlier match", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-    const schemas = await registerDetailSchemas(uwf.store);
-
-    const turn1 = await uwf.store.put(schemas.turn, {
-      index: 0,
-      role: "assistant",
-      content: "real content",
-      toolCalls: null,
-      reasoning: null,
-    });
-    const turn2 = await uwf.store.put(schemas.turn, {
-      index: 1,
-      role: "assistant",
-      content: "   ",
-      toolCalls: null,
-      reasoning: null,
-    });
-
-    const detailHash = await uwf.store.put(schemas.detail, {
-      sessionId: "s4",
-      model: "m4",
-      duration: 0,
-      turnCount: 2,
-      turns: [turn1, turn2],
-    });
-
-    expect(extractLastAssistantContent(uwf, detailHash)).toBe("real content");
-  });
-});
-
-// ── cmdThreadRead: ### Content section ───────────────────────────────────────
-
-describe("cmdThreadRead ### Content section", () => {
-  test("includes ### Content before ### Output when detail has assistant turns", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-    const detailSchemas = await registerDetailSchemas(uwf.store);
-
-    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
-      name: "test-wf",
-      description: "desc",
-      roles: {
-        writer: {
-          description: "Write",
-          systemPrompt: "You are a writer.",
-          outputSchema: "placeholder00" as CasRef,
-        },
-      },
-      conditions: {},
-      graph: {},
-    });
-
-    const startHash = await uwf.store.put(uwf.schemas.startNode, {
-      workflow: workflowHash,
-      prompt: "Write something",
-    });
-
-    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
-      name: "out",
-      description: "",
-      roles: {},
-      conditions: {},
-      graph: {},
-    });
-
-    const turnHash = await uwf.store.put(detailSchemas.turn, {
-      index: 0,
-      role: "assistant",
-      content: "The assistant response text",
-      toolCalls: null,
-      reasoning: null,
-    });
-    const detailHash = await uwf.store.put(detailSchemas.detail, {
-      sessionId: "sx",
-      model: "mx",
-      duration: 500,
-      turnCount: 1,
-      turns: [turnHash],
-    });
-
-    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
-      start: startHash,
-      prev: null,
-      role: "writer",
-      output: outputHash,
-      detail: detailHash,
-      agent: "uwf-hermes",
-    });
-
-    const threadId = "01JTEST0000000000000000001" as ThreadId;
-    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
-
-    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
-
-    expect(markdown).toContain("### Content");
-    expect(markdown).toContain("The assistant response text");
-
-    const contentIdx = markdown.indexOf("### Content");
-    const outputIdx = markdown.indexOf("### Output");
-    expect(contentIdx).toBeGreaterThanOrEqual(0);
-    expect(outputIdx).toBeGreaterThanOrEqual(0);
-    expect(contentIdx).toBeLessThan(outputIdx);
-  });
-
-  test("omits ### Content when detail has no matching assistant turns", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-
-    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
-      name: "test-wf2",
-      description: "desc",
-      roles: {},
-      conditions: {},
-      graph: {},
-    });
-    const startHash = await uwf.store.put(uwf.schemas.startNode, {
-      workflow: workflowHash,
-      prompt: "Do stuff",
-    });
-    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
-      name: "out",
-      description: "",
-      roles: {},
-      conditions: {},
-      graph: {},
-    });
-
-    // A detail ref that doesn't exist in the store → extractLastAssistantContent returns null
-    const missingDetailRef = "missingdetail0" as CasRef;
-
-    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
-      start: startHash,
-      prev: null,
-      role: "worker",
-      output: outputHash,
-      detail: missingDetailRef,
-      agent: "uwf-hermes",
-    });
-
-    const threadId = "01JTEST0000000000000000002" as ThreadId;
-    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
-
-    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
-
-    expect(markdown).not.toContain("### Content");
-    expect(markdown).toContain("### Output");
-  });
-});
-
-// ── cmdThreadStepDetails ──────────────────────────────────────────────────────
-
-describe("cmdThreadStepDetails", () => {
-  test("returns expanded detail node with turns inlined", async () => {
-    const uwf = await makeUwfStore(tmpDir);
-    const detailSchemas = await registerDetailSchemas(uwf.store);
-
-    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
-      name: "wf",
-      description: "",
-      roles: {},
-      conditions: {},
-      graph: {},
-    });
-    const startHash = await uwf.store.put(uwf.schemas.startNode, {
-      workflow: workflowHash,
-      prompt: "p",
-    });
-    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
-      name: "out",
-      description: "",
-      roles: {},
-      conditions: {},
-      graph: {},
-    });
-
-    const turnHash = await uwf.store.put(detailSchemas.turn, {
-      index: 0,
-      role: "assistant",
-      content: "done",
-      toolCalls: null,
-      reasoning: null,
-    });
-    const detailHash = await uwf.store.put(detailSchemas.detail, {
-      sessionId: "sess42",
-      model: "gpt-4o",
-      duration: 3000,
-      turnCount: 1,
-      turns: [turnHash],
-    });
-
-    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
-      start: startHash,
-      prev: null,
-      role: "coder",
-      output: outputHash,
-      detail: detailHash,
-      agent: "uwf-hermes",
-    });
-
-    const result = await cmdThreadStepDetails(tmpDir, stepHash);
-
-    expect(result).toMatchObject({
-      sessionId: "sess42",
-      model: "gpt-4o",
-      duration: 3000,
-      turnCount: 1,
-    });
-
-    const expanded = result as Record<string, unknown>;
-    expect(Array.isArray(expanded.turns)).toBe(true);
-    const turns = expanded.turns as unknown[];
-    expect(turns).toHaveLength(1);
-    expect(turns[0]).toMatchObject({
-      index: 0,
-      role: "assistant",
-      content: "done",
-    });
-  });
-
-  test("throws when step hash does not exist", async () => {
-    await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
-  });
-});

packages/cli-uwf/src/cli.ts

@@ -1,353 +0,0 @@
-#!/usr/bin/env bun
-
-import type { ThreadId } from "@uncaged/uwf-protocol";
-import { Command } from "commander";
-import { stringify as yamlStringify } from "yaml";
-import {
-  cmdCasGet,
-  cmdCasHas,
-  cmdCasPut,
-  cmdCasRefs,
-  cmdCasReindex,
-  cmdCasSchemaGet,
-  cmdCasSchemaList,
-  cmdCasWalk,
-} from "./commands/cas.js";
-import { cmdSetup, cmdSetupInteractive } from "./commands/setup.js";
-import {
-  cmdThreadFork,
-  cmdThreadKill,
-  cmdThreadList,
-  cmdThreadRead,
-  cmdThreadShow,
-  cmdThreadStart,
-  cmdThreadStep,
-  cmdThreadStepDetails,
-  cmdThreadSteps,
-  THREAD_READ_DEFAULT_QUOTA,
-} from "./commands/thread.js";
-import { cmdWorkflowList, cmdWorkflowPut, cmdWorkflowShow } from "./commands/workflow.js";
-import { formatOutput, type OutputFormat } from "./format.js";
-import { resolveStorageRoot } from "./store.js";
-
-function writeOutput(data: unknown): void {
-  const fmt = program.opts().format as OutputFormat;
-  process.stdout.write(`${formatOutput(data, fmt)}\n`);
-}
-
-function runAction(action: () => Promise<void>): void {
-  action().catch((e: unknown) => {
-    const message = e instanceof Error ? e.message : String(e);
-    process.stderr.write(`${message}\n`);
-    process.exit(1);
-  });
-}
-
-const program = new Command();
-
-program.name("uwf").description("Stateless workflow CLI");
-program.option("--format <fmt>", "Output format: json or yaml", "json");
-
-const workflow = program.command("workflow").description("Workflow registry and CAS");
-
-workflow
-  .command("put")
-  .description("Register a workflow from YAML")
-  .argument("<file>", "Workflow YAML file")
-  .action((file: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdWorkflowPut(storageRoot, file);
-      writeOutput(result);
-    });
-  });
-
-workflow
-  .command("show")
-  .description("Show a workflow by name or CAS hash")
-  .argument("<id>", "Workflow name or hash")
-  .action((id: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdWorkflowShow(storageRoot, id);
-      writeOutput(result);
-    });
-  });
-
-workflow
-  .command("list")
-  .description("List registered workflows")
-  .action(() => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdWorkflowList(storageRoot);
-      writeOutput(result);
-    });
-  });
-
-const thread = program.command("thread").description("Thread lifecycle and execution");
-
-thread
-  .command("start")
-  .description("Create a thread without executing")
-  .argument("<workflow>", "Workflow name or hash")
-  .requiredOption("-p, --prompt <text>", "User prompt")
-  .action((workflow: string, opts: { prompt: string }) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdThreadStart(storageRoot, workflow, opts.prompt);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("step")
-  .description("Execute one step")
-  .argument("<thread-id>", "Thread ULID")
-  .option("--agent <cmd>", "Override agent command")
-  .action((threadId: string, opts: { agent: string | undefined }) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const agentOverride = opts.agent ?? null;
-      const result = await cmdThreadStep(storageRoot, threadId, agentOverride);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("show")
-  .description("Show thread head pointer")
-  .argument("<thread-id>", "Thread ULID")
-  .action((threadId: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdThreadShow(storageRoot, threadId);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("list")
-  .description("List active threads")
-  .option("--all", "Include archived threads")
-  .action((opts: { all: boolean }) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdThreadList(storageRoot, opts.all);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("kill")
-  .description("Terminate and archive a thread")
-  .argument("<thread-id>", "Thread ULID")
-  .action((threadId: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdThreadKill(storageRoot, threadId);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("steps")
-  .description("List all steps in a thread")
-  .argument("<thread-id>", "Thread ULID")
-  .action((threadId: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdThreadSteps(storageRoot, threadId);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("read")
-  .description("Read thread context as human-readable markdown")
-  .argument("<thread-id>", "Thread ULID")
-  .option("--quota <chars>", "Max output characters", String(THREAD_READ_DEFAULT_QUOTA))
-  .option("--before <step-hash>", "Load steps before this hash (exclusive)")
-  .option("--start", "Include start step in output")
-  .action(
-    (threadId: string, opts: { quota: string; before: string | undefined; start: boolean }) => {
-      const storageRoot = resolveStorageRoot();
-      runAction(async () => {
-        const quota = Number.parseInt(opts.quota, 10);
-        if (!Number.isFinite(quota) || quota < 1) {
-          process.stderr.write("invalid --quota: must be a positive integer\n");
-          process.exit(1);
-        }
-        const before = opts.before ?? null;
-        const markdown = await cmdThreadRead(
-          storageRoot,
-          threadId as ThreadId,
-          quota,
-          before,
-          opts.start ?? false,
-        );
-        process.stdout.write(markdown.endsWith("\n") ? markdown : `${markdown}\n`);
-      });
-    },
-  );
-
-thread
-  .command("fork")
-  .description("Fork a thread from a specific step")
-  .argument("<step-hash>", "CAS hash of the StartNode or StepNode to fork from")
-  .action((stepHash: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdThreadFork(storageRoot, stepHash);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("step-details")
-  .description("Dump the full detail node of a step as YAML")
-  .argument("<step-hash>", "CAS hash of the StepNode")
-  .action((stepHash: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const detail = await cmdThreadStepDetails(storageRoot, stepHash);
-      process.stdout.write(yamlStringify(detail));
-    });
-  });
-
-program
-  .command("setup")
-  .description("Configure provider, model, and agent")
-  .option("--provider <name>", "Provider name")
-  .option("--base-url <url>", "OpenAI-compatible API base URL")
-  .option("--api-key <key>", "API key")
-  .option("--model <name>", "Default model name")
-  .option("--agent <name>", "Default agent alias")
-  .action(
-    (opts: {
-      provider?: string;
-      baseUrl?: string;
-      apiKey?: string;
-      model?: string;
-      agent?: string;
-    }) => {
-      const storageRoot = resolveStorageRoot();
-      runAction(async () => {
-        if (opts.provider && opts.baseUrl && opts.apiKey && opts.model) {
-          const result = await cmdSetup({
-            provider: opts.provider,
-            baseUrl: opts.baseUrl,
-            apiKey: opts.apiKey,
-            model: opts.model,
-            agent: opts.agent ?? undefined,
-            storageRoot,
-          });
-          writeOutput(result);
-        } else if (!opts.provider && !opts.baseUrl && !opts.apiKey && !opts.model) {
-          await cmdSetupInteractive(storageRoot);
-        } else {
-          throw new Error(
-            "Non-interactive setup requires all of: --provider, --base-url, --api-key, --model",
-          );
-        }
-      });
-    },
-  );
-
-const cas = program.command("cas").description("Content-addressable storage operations");
-
-cas
-  .command("get")
-  .description("Read a CAS node (type + payload; use --timestamp to include timestamp)")
-  .argument("<hash>", "CAS hash (13 char)")
-  .option("--timestamp", "Include timestamp in output")
-  .action((hash: string, opts: { timestamp?: boolean }) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasGet(storageRoot, hash, opts));
-    });
-  });
-
-cas
-  .command("put")
-  .description("Store a node, print its hash")
-  .argument("<type-hash>", "Type (schema) hash")
-  .argument("<data>", "JSON file path or inline JSON string")
-  .action((typeHash: string, data: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasPut(storageRoot, typeHash, data));
-    });
-  });
-
-cas
-  .command("has")
-  .description("Check if a hash exists")
-  .argument("<hash>", "CAS hash (13 char)")
-  .action((hash: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasHas(storageRoot, hash));
-    });
-  });
-
-cas
-  .command("refs")
-  .description("List direct CAS references from a node")
-  .argument("<hash>", "CAS hash (13 char)")
-  .action((hash: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasRefs(storageRoot, hash));
-    });
-  });
-
-cas
-  .command("walk")
-  .description("Recursive traversal from a node")
-  .argument("<hash>", "CAS hash (13 char)")
-  .action((hash: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasWalk(storageRoot, hash));
-    });
-  });
-
-cas
-  .command("reindex")
-  .description("Rebuild type index from all CAS nodes")
-  .action(() => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasReindex(storageRoot));
-    });
-  });
-
-const casSchema = cas.command("schema").description("CAS schema operations");
-
-casSchema
-  .command("list")
-  .description("List all registered schemas")
-  .action(() => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasSchemaList(storageRoot));
-    });
-  });
-
-casSchema
-  .command("get")
-  .description("Show a schema by its type hash")
-  .argument("<hash>", "Schema type hash")
-  .action((hash: string) => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      writeOutput(await cmdCasSchemaGet(storageRoot, hash));
-    });
-  });
-
-program.parseAsync(process.argv).catch((e: unknown) => {
-  const message = e instanceof Error ? e.message : String(e);
-  process.stderr.write(`${message}\n`);
-  process.exit(1);
-});

packages/cli-uwf/src/commands/setup.ts

@@ -1,332 +0,0 @@
-import { existsSync, readFileSync, writeFileSync, mkdirSync } from "node:fs";
-import { homedir } from "node:os";
-import { join, resolve } from "node:path";
-import { createInterface } from "node:readline/promises";
-import { stdin as input, stdout as output } from "node:process";
-
-import { stringify, parse } from "yaml";
-
-/**
- * Preset provider list — embedded to avoid runtime YAML loading dependency.
- * Keep in sync with providers.yaml in cli-workflow.
- */
-const PRESET_PROVIDERS = [
-  // International
-  { name: "openai", label: "OpenAI", baseUrl: "https://api.openai.com/v1" },
-  { name: "xai", label: "xAI", baseUrl: "https://api.x.ai/v1" },
-  { name: "openrouter", label: "OpenRouter", baseUrl: "https://openrouter.ai/api/v1" },
-  { name: "venice", label: "Venice", baseUrl: "https://api.venice.ai/api/v1" },
-  // China
-  { name: "dashscope", label: "DashScope (Alibaba)", baseUrl: "https://dashscope.aliyuncs.com/compatible-mode/v1" },
-  { name: "deepseek", label: "DeepSeek", baseUrl: "https://api.deepseek.com/v1" },
-  { name: "siliconflow", label: "SiliconFlow", baseUrl: "https://api.siliconflow.cn/v1" },
-  { name: "volcengine", label: "Volcengine (ByteDance)", baseUrl: "https://ark.cn-beijing.volces.com/api/v3" },
-  { name: "kimi", label: "Kimi (Moonshot)", baseUrl: "https://api.moonshot.cn/v1" },
-  { name: "glm", label: "GLM (Zhipu AI)", baseUrl: "https://open.bigmodel.cn/api/paas/v4" },
-  { name: "stepfun", label: "StepFun", baseUrl: "https://api.stepfun.com/v1" },
-  { name: "minimax", label: "MiniMax", baseUrl: "https://api.minimax.io/v1" },
-  // Local
-  { name: "ollama", label: "Ollama (local)", baseUrl: "http://localhost:11434/v1" },
-] as const;
-
-type SetupArgs = {
-  provider: string;
-  baseUrl: string;
-  apiKey: string;
-  model: string;
-  agent?: string | undefined;
-  storageRoot: string;
-};
-
-function getConfigPath(root: string): string {
-  return join(root, "config.yaml");
-}
-
-function getEnvPath(root: string): string {
-  return join(root, ".env");
-}
-
-/**
- * Load existing config.yaml or return empty structure.
- */
-function loadExistingConfig(configPath: string): Record<string, unknown> {
-  try {
-    if (existsSync(configPath)) {
-      const raw = parse(readFileSync(configPath, "utf8")) as unknown;
-      if (typeof raw === "object" && raw !== null && !Array.isArray(raw)) {
-        return raw as Record<string, unknown>;
-      }
-    }
-  } catch {
-    // ignore parse errors, start fresh
-  }
-  return {};
-}
-
-/**
- * Load existing .env as key=value map.
- */
-function loadEnvFile(envPath: string): Record<string, string> {
-  const env: Record<string, string> = {};
-  try {
-    if (existsSync(envPath)) {
-      for (const line of readFileSync(envPath, "utf8").split("\n")) {
-        const trimmed = line.trim();
-        if (trimmed === "" || trimmed.startsWith("#")) continue;
-        const eq = trimmed.indexOf("=");
-        if (eq > 0) {
-          env[trimmed.slice(0, eq)] = trimmed.slice(eq + 1);
-        }
-      }
-    }
-  } catch {
-    // ignore
-  }
-  return env;
-}
-
-function saveEnvFile(envPath: string, env: Record<string, string>): void {
-  const lines = Object.entries(env).map(([k, v]) => `${k}=${v}`);
-  writeFileSync(envPath, `${lines.join("\n")}\n`, "utf8");
-}
-
-function apiKeyEnvName(providerName: string): string {
-  return `${providerName.toUpperCase().replace(/[^A-Z0-9]/g, "_")}_API_KEY`;
-}
-
-/**
- * Merge setup args into config.yaml structure. Non-destructive — preserves existing entries.
- */
-function mergeConfig(existing: Record<string, unknown>, args: SetupArgs): Record<string, unknown> {
-  const providers = (typeof existing.providers === "object" && existing.providers !== null
-    ? { ...(existing.providers as Record<string, unknown>) }
-    : {}) as Record<string, unknown>;
-
-  const envName = apiKeyEnvName(args.provider);
-  providers[args.provider] = { baseUrl: args.baseUrl, apiKeyEnv: envName };
-
-  const models = (typeof existing.models === "object" && existing.models !== null
-    ? { ...(existing.models as Record<string, unknown>) }
-    : {}) as Record<string, unknown>;
-  models.default = { provider: args.provider, name: args.model };
-
-  const agents = (typeof existing.agents === "object" && existing.agents !== null
-    ? { ...(existing.agents as Record<string, unknown>) }
-    : {}) as Record<string, unknown>;
-
-  const agentName = args.agent ?? "hermes";
-  if (Object.keys(agents).length === 0) {
-    agents.hermes = { command: "uwf-hermes", args: [] };
-  }
-
-  return {
-    ...existing,
-    providers,
-    models,
-    agents,
-    defaultAgent: existing.defaultAgent ?? agentName,
-    defaultModel: existing.defaultModel ?? "default",
-  };
-}
-
-/**
- * Non-interactive setup. All required args provided via CLI flags.
- */
-export async function cmdSetup(args: SetupArgs): Promise<Record<string, unknown>> {
-  const { storageRoot } = args;
-  mkdirSync(storageRoot, { recursive: true });
-
-  const configPath = getConfigPath(storageRoot);
-  const envPath = getEnvPath(storageRoot);
-
-  const existing = loadExistingConfig(configPath);
-  const merged = mergeConfig(existing, args);
-
-  writeFileSync(configPath, stringify(merged, { indent: 2 }), "utf8");
-
-  // Write API key to .env
-  const envName = apiKeyEnvName(args.provider);
-  const envData = loadEnvFile(envPath);
-  envData[envName] = args.apiKey;
-  saveEnvFile(envPath, envData);
-
-  return {
-    configPath,
-    envPath,
-    provider: args.provider,
-    model: args.model,
-    defaultAgent: merged.defaultAgent,
-  };
-}
-
-/** Read a line with terminal echo disabled (for secrets). */
-async function promptSecret(label: string): Promise<string> {
-  process.stdout.write(label);
-  return new Promise((resolve) => {
-    const rawWasSet = process.stdin.isRaw;
-    if (process.stdin.isTTY) {
-      process.stdin.setRawMode(true);
-    }
-    process.stdin.resume();
-    process.stdin.setEncoding("utf8");
-
-    let buf = "";
-    const onData = (chunk: string) => {
-      for (const c of chunk.toString()) {
-        if (c === "\n" || c === "\r" || c === "\u0004") {
-          if (process.stdin.isTTY) process.stdin.setRawMode(rawWasSet);
-          process.stdin.pause();
-          process.stdin.removeListener("data", onData);
-          process.stdout.write("\n");
-          resolve(buf.trim());
-          return;
-        }
-        if (c === "\u007F" || c === "\b") {
-          if (buf.length > 0) {
-            buf = buf.slice(0, -1);
-            process.stdout.write("\b \b");
-          }
-          continue;
-        }
-        if (c === "\u0003") {
-          if (process.stdin.isTTY) process.stdin.setRawMode(rawWasSet);
-          process.exit(130);
-        }
-        buf += c;
-        process.stdout.write("*");
-      }
-    };
-    process.stdin.on("data", onData);
-  });
-}
-
-/** Fetch available models from an OpenAI-compatible /models endpoint. */
-async function fetchModels(baseUrl: string, apiKey: string): Promise<string[]> {
-  try {
-    const url = `${baseUrl.replace(/\/+$/, "")}/models`;
-    const res = await fetch(url, {
-      headers: { Authorization: `Bearer ${apiKey}` },
-      signal: AbortSignal.timeout(10_000),
-    });
-    if (!res.ok) return [];
-    const body = (await res.json()) as { data?: { id: string }[] };
-    if (!Array.isArray(body.data)) return [];
-    const NON_CHAT = /speech|embed|image|video|audio|ocr|rerank|tts|asr|paraformer|sambert|cosyvoice|wordart|wanx|wan2|flux|stable-diffusion|gui-/i;
-    return body.data.map((m) => m.id).filter((id) => !NON_CHAT.test(id)).sort();
-  } catch {
-    return [];
-  }
-}
-
-/**
- * Interactive setup — prompts user for provider, API key, model.
- */
-export async function cmdSetupInteractive(storageRoot: string): Promise<Record<string, unknown>> {
-  const rl = createInterface({ input, output });
-
-  try {
-    console.log("Configure LLM provider for uwf workflow agents.\n");
-
-    // 1. Provider selection
-    const numWidth = String(PRESET_PROVIDERS.length + 1).length;
-    console.log("Select a provider:\n");
-    for (let i = 0; i < PRESET_PROVIDERS.length; i++) {
-      const p = PRESET_PROVIDERS[i];
-      if (!p) continue;
-      const num = String(i + 1).padStart(numWidth);
-      console.log(`  ${num}) ${p.label.padEnd(28)} ${p.baseUrl}`);
-    }
-    const customNum = String(PRESET_PROVIDERS.length + 1).padStart(numWidth);
-    console.log(`  ${customNum}) Custom (enter name and URL manually)\n`);
-
-    const choice = (await rl.question(`Choose [1-${PRESET_PROVIDERS.length + 1}]: `)).trim();
-    const choiceNum = Number.parseInt(choice, 10);
-    if (Number.isNaN(choiceNum) || choiceNum < 1 || choiceNum > PRESET_PROVIDERS.length + 1) {
-      throw new Error(`Invalid choice: ${choice}`);
-    }
-
-    let providerName: string;
-    let baseUrl: string;
-
-    if (choiceNum <= PRESET_PROVIDERS.length) {
-      const selected = PRESET_PROVIDERS[choiceNum - 1];
-      if (!selected) throw new Error("Invalid selection");
-      providerName = selected.name;
-      baseUrl = selected.baseUrl;
-      console.log(`\n  → ${selected.label} (${selected.baseUrl})\n`);
-    } else {
-      providerName = (await rl.question("Provider name (e.g. my-proxy): ")).trim();
-      if (!providerName) throw new Error("Provider name required");
-      baseUrl = (await rl.question("OpenAI-compatible API base URL: ")).trim();
-      if (!baseUrl) throw new Error("Base URL required");
-    }
-
-    // 2. API key
-    rl.close();
-    const apiKey = await promptSecret("API key: ");
-    if (!apiKey) throw new Error("API key required");
-
-    // 3. Model selection
-    const rl2 = createInterface({ input, output });
-    console.log("\nFetching available models...");
-    const models = await fetchModels(baseUrl, apiKey);
-
-    let model: string;
-    if (models.length > 0) {
-      console.log(`\nAvailable models (${models.length}):\n`);
-      const nw = String(models.length).length;
-      // Multi-column layout
-      const maxLen = models.reduce((m, s) => Math.max(m, s.length), 0);
-      const colWidth = nw + 2 + maxLen + 4; // "  N) name    "
-      const termCols = process.stdout.columns || 100;
-      const cols = Math.max(1, Math.floor(termCols / colWidth));
-      const rows = Math.ceil(models.length / cols);
-      for (let r = 0; r < rows; r++) {
-        let line = "";
-        for (let c = 0; c < cols; c++) {
-          const idx = c * rows + r;
-          if (idx >= models.length) break;
-          const num = String(idx + 1).padStart(nw);
-          const name = (models[idx] ?? "").padEnd(maxLen);
-          line += `  ${num}) ${name}  `;
-        }
-        console.log(line.trimEnd());
-      }
-      console.log(`\nChoose a number, or type a model name directly.`);
-      const modelInput = (await rl2.question(`Default model [1-${models.length}]: `)).trim();
-      if (!modelInput) throw new Error("Model required");
-      const modelNum = Number.parseInt(modelInput, 10);
-      if (!Number.isNaN(modelNum) && modelNum >= 1 && modelNum <= models.length) {
-        model = models[modelNum - 1] ?? modelInput;
-      } else {
-        model = modelInput;
-      }
-    } else {
-      console.log("Could not fetch models. Enter model name manually.");
-      model = (await rl2.question("Default model (e.g. qwen-plus, gpt-4o): ")).trim();
-      if (!model) throw new Error("Model required");
-    }
-
-    rl2.close();
-
-    console.log(`  → ${providerName}/${model}\n`);
-
-    await cmdSetup({
-      provider: providerName,
-      baseUrl,
-      apiKey,
-      model,
-      storageRoot,
-    });
-
-    console.log("Setup complete! Get started:\n");
-    console.log("  uwf workflow put <workflow.yaml>   Register a workflow");
-    console.log('  uwf thread start <name> -p "..."   Start a thread');
-    console.log("  uwf thread step <thread-id>        Execute next step");
-    console.log("");
-
-    return null as unknown as Record<string, unknown>;
-  } finally {
-    rl.close();
-  }
-}

packages/cli-uwf/src/commands/thread.ts

@@ -1,844 +0,0 @@
-import { execFileSync } from "node:child_process";
-import type { Store as CasStore, JSONSchema } from "@uncaged/json-cas";
-import { getSchema, validate } from "@uncaged/json-cas";
-import { getEnvPath, loadWorkflowConfig } from "@uncaged/uwf-agent-kit";
-import { evaluate } from "@uncaged/uwf-moderator";
-import type {
-  AgentAlias,
-  AgentConfig,
-  CasRef,
-  ModeratorContext,
-  StartEntry,
-  StartNodePayload,
-  StartOutput,
-  StepContext,
-  StepEntry,
-  StepNodePayload,
-  StepOutput,
-  ThreadForkOutput,
-  ThreadId,
-  ThreadListItem,
-  ThreadStepsOutput,
-  WorkflowConfig,
-  WorkflowPayload,
-} from "@uncaged/uwf-protocol";
-import { generateUlid } from "@uncaged/workflow-util";
-import { config as loadDotenv } from "dotenv";
-import { stringify } from "yaml";
-
-import {
-  appendThreadHistory,
-  createUwfStore,
-  findThreadInHistory,
-  loadThreadHistory,
-  loadThreadsIndex,
-  loadWorkflowRegistry,
-  resolveWorkflowHash,
-  saveThreadsIndex,
-  type ThreadHistoryLine,
-  type UwfStore,
-} from "../store.js";
-import { isCasRef } from "../validate.js";
-
-const END_ROLE = "$END";
-export const THREAD_READ_DEFAULT_QUOTA = 4000;
-
-type ChainState = {
-  startHash: CasRef;
-  start: StartNodePayload;
-  stepsNewestFirst: StepNodePayload[];
-  headIsStart: boolean;
-};
-
-type OrderedStepItem = {
-  hash: CasRef;
-  payload: StepNodePayload;
-  timestamp: number;
-};
-
-export type KillOutput = {
-  thread: ThreadId;
-  archived: boolean;
-};
-
-function fail(message: string): never {
-  process.stderr.write(`${message}\n`);
-  process.exit(1);
-}
-
-async function resolveWorkflowCasRef(
-  uwf: UwfStore,
-  storageRoot: string,
-  workflowId: string,
-): Promise<CasRef> {
-  const registry = await loadWorkflowRegistry(storageRoot);
-  const hash = resolveWorkflowHash(registry, workflowId);
-  if (!isCasRef(hash)) {
-    fail(`workflow not found: ${workflowId}`);
-  }
-  const node = uwf.store.get(hash);
-  if (node === null) {
-    fail(`CAS node not found: ${hash}`);
-  }
-  if (node.type !== uwf.schemas.workflow) {
-    fail(`node ${hash} is not a Workflow (type ${node.type})`);
-  }
-  return hash;
-}
-
-function resolveWorkflowFromHead(uwf: UwfStore, head: CasRef): CasRef | null {
-  const node = uwf.store.get(head);
-  if (node === null) {
-    return null;
-  }
-
-  if (node.type === uwf.schemas.startNode) {
-    const payload = node.payload as StartNodePayload;
-    return payload.workflow;
-  }
-
-  const payload = node.payload as StepNodePayload;
-  if (typeof payload.start !== "string") {
-    return null;
-  }
-
-  const startNode = uwf.store.get(payload.start);
-  if (startNode === null || startNode.type !== uwf.schemas.startNode) {
-    return null;
-  }
-
-  return (startNode.payload as StartNodePayload).workflow;
-}
-
-export async function cmdThreadStart(
-  storageRoot: string,
-  workflowId: string,
-  prompt: string,
-): Promise<StartOutput> {
-  const uwf = await createUwfStore(storageRoot);
-  const workflowHash = await resolveWorkflowCasRef(uwf, storageRoot, workflowId);
-
-  const threadId = generateUlid(Date.now()) as ThreadId;
-  const startPayload: StartNodePayload = {
-    workflow: workflowHash,
-    prompt,
-  };
-
-  const headHash = await uwf.store.put(uwf.schemas.startNode, startPayload);
-  const node = uwf.store.get(headHash);
-  if (node === null || !validate(uwf.store, node)) {
-    fail("stored StartNode failed schema validation");
-  }
-
-  const index = await loadThreadsIndex(storageRoot);
-  index[threadId] = headHash;
-  await saveThreadsIndex(storageRoot, index);
-
-  return { workflow: workflowHash, thread: threadId };
-}
-
-export async function cmdThreadShow(storageRoot: string, threadId: ThreadId): Promise<StepOutput> {
-  const index = await loadThreadsIndex(storageRoot);
-  const activeHead = index[threadId];
-  if (activeHead !== undefined) {
-    const uwf = await createUwfStore(storageRoot);
-    const workflow = resolveWorkflowFromHead(uwf, activeHead);
-    if (workflow === null) {
-      fail(`failed to resolve workflow from head: ${activeHead}`);
-    }
-    return {
-      workflow,
-      thread: threadId,
-      head: activeHead,
-      done: false,
-    };
-  }
-
-  const hist = await findThreadInHistory(storageRoot, threadId);
-  if (hist !== null) {
-    return {
-      workflow: hist.workflow,
-      thread: threadId,
-      head: hist.head,
-      done: true,
-    };
-  }
-
-  fail(`thread not found: ${threadId}`);
-}
-
-async function threadListItemFromActive(
-  uwf: UwfStore,
-  threadId: ThreadId,
-  head: CasRef,
-): Promise<ThreadListItem | null> {
-  const workflow = resolveWorkflowFromHead(uwf, head);
-  if (workflow === null) {
-    return null;
-  }
-  return { thread: threadId, workflow, head };
-}
-
-export async function cmdThreadList(
-  storageRoot: string,
-  includeAll: boolean,
-): Promise<ThreadListItem[]> {
-  const uwf = await createUwfStore(storageRoot);
-  const index = await loadThreadsIndex(storageRoot);
-  const items: ThreadListItem[] = [];
-
-  for (const [threadId, head] of Object.entries(index)) {
-    const item = await threadListItemFromActive(uwf, threadId as ThreadId, head);
-    if (item !== null) {
-      items.push(item);
-    }
-  }
-
-  if (!includeAll) {
-    return items;
-  }
-
-  const activeIds = new Set(items.map((i) => i.thread));
-  const history = await loadThreadHistory(storageRoot);
-  for (const entry of history) {
-    if (!activeIds.has(entry.thread)) {
-      items.push({
-        thread: entry.thread,
-        workflow: entry.workflow,
-        head: entry.head,
-      });
-    }
-  }
-
-  return items;
-}
-
-function walkChain(uwf: UwfStore, headHash: CasRef): ChainState {
-  const headNode = uwf.store.get(headHash);
-  if (headNode === null) {
-    fail(`CAS node not found: ${headHash}`);
-  }
-
-  if (headNode.type === uwf.schemas.startNode) {
-    return {
-      startHash: headHash,
-      start: headNode.payload as StartNodePayload,
-      stepsNewestFirst: [],
-      headIsStart: true,
-    };
-  }
-
-  if (headNode.type !== uwf.schemas.stepNode) {
-    fail(`head ${headHash} is not a StartNode or StepNode`);
-  }
-
-  const stepsNewestFirst: StepNodePayload[] = [];
-  let hash: CasRef | null = headHash;
-
-  while (hash !== null) {
-    const node = uwf.store.get(hash);
-    if (node === null) {
-      fail(`CAS node not found while walking chain: ${hash}`);
-    }
-    if (node.type !== uwf.schemas.stepNode) {
-      break;
-    }
-    const payload = node.payload as StepNodePayload;
-    stepsNewestFirst.push(payload);
-    hash = payload.prev;
-  }
-
-  const newest = stepsNewestFirst[0];
-  if (newest === undefined) {
-    fail(`empty step chain at head ${headHash}`);
-  }
-
-  const startNode = uwf.store.get(newest.start);
-  if (startNode === null || startNode.type !== uwf.schemas.startNode) {
-    fail(`StartNode not found: ${newest.start}`);
-  }
-
-  return {
-    startHash: newest.start,
-    start: startNode.payload as StartNodePayload,
-    stepsNewestFirst,
-    headIsStart: false,
-  };
-}
-
-function expandOutput(uwf: UwfStore, outputRef: CasRef): unknown {
-  const node = uwf.store.get(outputRef);
-  if (node === null) {
-    return {};
-  }
-  return node.payload;
-}
-
-/**
- * Recursively expand all cas_ref fields in a CAS node's payload,
- * replacing hash strings with the referenced node's expanded payload.
- */
-function expandDeep(store: CasStore, hash: CasRef, visited?: Set<string>): unknown {
-  const seen = visited ?? new Set<string>();
-  if (seen.has(hash)) return hash; // cycle guard
-  seen.add(hash);
-
-  const node = store.get(hash);
-  if (node === null) return hash;
-
-  const schema = getSchema(store, node.type);
-  if (schema === null) return node.payload;
-
-  return expandValue(store, schema, node.payload, seen);
-}
-
-function expandValue(
-  store: CasStore,
-  schema: JSONSchema,
-  value: unknown,
-  visited: Set<string>,
-): unknown {
-  // If this field is a cas_ref, expand it
-  if (schema.format === "cas_ref") {
-    if (typeof value === "string") {
-      return expandDeep(store, value as CasRef, visited);
-    }
-    return value;
-  }
-
-  // anyOf (nullable refs)
-  if (Array.isArray(schema.anyOf)) {
-    for (const sub of schema.anyOf as JSONSchema[]) {
-      if (sub.format === "cas_ref" && typeof value === "string") {
-        return expandDeep(store, value as CasRef, visited);
-      }
-    }
-    return value;
-  }
-
-  // Array of cas_ref items
-  if (schema.type === "array" && schema.items && Array.isArray(value)) {
-    const itemSchema = schema.items as JSONSchema;
-    return (value as unknown[]).map((item) => expandValue(store, itemSchema, item, visited));
-  }
-
-  // Object with properties
-  if (value !== null && typeof value === "object" && !Array.isArray(value) && schema.properties) {
-    const props = schema.properties as Record<string, JSONSchema>;
-    const obj = value as Record<string, unknown>;
-    const result: Record<string, unknown> = {};
-    for (const [key, val] of Object.entries(obj)) {
-      const propSchema = props[key];
-      result[key] = propSchema ? expandValue(store, propSchema, val, visited) : val;
-    }
-    return result;
-  }
-
-  return value;
-}
-
-function collectOrderedSteps(
-  uwf: UwfStore,
-  headHash: CasRef,
-  chain: ChainState,
-): OrderedStepItem[] {
-  let hash: CasRef | null = headHash;
-  const hashToNode = new Map<string, { payload: StepNodePayload; timestamp: number }>();
-  while (hash !== null) {
-    const node = uwf.store.get(hash);
-    if (node === null || node.type !== uwf.schemas.stepNode) {
-      break;
-    }
-    const payload = node.payload as StepNodePayload;
-    hashToNode.set(hash, { payload, timestamp: node.timestamp });
-    hash = payload.prev;
-  }
-
-  let cur: CasRef | null = chain.headIsStart ? null : headHash;
-  const ordered: OrderedStepItem[] = [];
-  while (cur !== null) {
-    const entry = hashToNode.get(cur);
-    if (entry === undefined) {
-      break;
-    }
-    ordered.push({ hash: cur, ...entry });
-    cur = entry.payload.prev;
-  }
-  ordered.reverse();
-  return ordered;
-}
-
-function formatYaml(value: unknown): string {
-  return stringify(value).trimEnd();
-}
-
-function formatCompactStep(index: number, item: OrderedStepItem, outputYaml: string): string {
-  return [
-    `## Step ${index}: ${item.payload.role}`,
-    "",
-    `- **Hash:** \`${item.hash}\``,
-    `- **Agent:** ${item.payload.agent}`,
-    "",
-    "### Output",
-    "",
-    "```yaml",
-    outputYaml,
-    "```",
-  ].join("\n");
-}
-
-export function extractLastAssistantContent(uwf: UwfStore, detailRef: CasRef): string | null {
-  const detailNode = uwf.store.get(detailRef);
-  if (detailNode === null) {
-    return null;
-  }
-  const detail = detailNode.payload as Record<string, unknown>;
-  const turns = detail.turns;
-  if (!Array.isArray(turns) || turns.length === 0) {
-    return null;
-  }
-  for (let i = turns.length - 1; i >= 0; i--) {
-    const turnRef = turns[i];
-    if (typeof turnRef !== "string") {
-      continue;
-    }
-    const turnNode = uwf.store.get(turnRef as CasRef);
-    if (turnNode === null) {
-      continue;
-    }
-    const turn = turnNode.payload as Record<string, unknown>;
-    if (
-      turn.role === "assistant" &&
-      typeof turn.content === "string" &&
-      turn.content.trim() !== ""
-    ) {
-      return turn.content;
-    }
-  }
-  return null;
-}
-
-function formatThreadReadMarkdown(options: {
-  threadId: ThreadId;
-  workflowName: string;
-  workflowHash: CasRef;
-  prompt: string;
-  ordered: OrderedStepItem[];
-  uwf: UwfStore;
-  workflow: WorkflowPayload;
-  quota: number;
-  before: CasRef | null;
-  showStart: boolean;
-}): string {
-  const { ordered, uwf, workflow, quota, before, showStart } = options;
-
-  // Determine which steps to consider
-  let candidates = ordered;
-  if (before !== null) {
-    const idx = candidates.findIndex((s) => s.hash === before);
-    if (idx === -1) {
-      fail(`step ${before} not found in thread ${options.threadId}`);
-    }
-    candidates = candidates.slice(0, idx);
-  }
-
-  // Walk backward from newest, accumulating chars until quota exceeded
-  const selected: OrderedStepItem[] = [];
-  let totalChars = 0;
-  for (let i = candidates.length - 1; i >= 0; i--) {
-    const item = candidates[i];
-    if (item === undefined) continue;
-    const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
-    const blockLen = formatCompactStep(i + 1, item, outputYaml).length;
-    selected.unshift(item);
-    totalChars += blockLen;
-    if (totalChars > quota) break;
-  }
-
-  const skippedCount = candidates.length - selected.length;
-  const parts: string[] = [];
-
-  // Start section
-  if (before === null || showStart) {
-    parts.push(
-      [
-        `# Thread \`${options.threadId}\``,
-        "",
-        `**Workflow:** ${options.workflowName} (\`${options.workflowHash}\`)`,
-        "",
-        "## Task",
-        "",
-        options.prompt,
-      ].join("\n"),
-    );
-  }
-
-  // Skip hint
-  if (skippedCount > 0 && selected.length > 0) {
-    const firstSelected = selected[0];
-    if (firstSelected !== undefined) {
-      parts.push(
-        `*(${skippedCount} earlier step${skippedCount > 1 ? "s" : ""}, load with \`uwf thread read ${options.threadId} --before ${firstSelected.hash}\`)*`,
-      );
-    }
-  }
-
-  // Step blocks
-  const startIndex = candidates.length - selected.length;
-  for (let i = 0; i < selected.length; i++) {
-    const item = selected[i];
-    if (item === undefined) continue;
-    const stepNum = startIndex + i + 1;
-    const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
-    const ts = new Date(item.timestamp)
-      .toISOString()
-      .replace("T", " ")
-      .replace(/\.\d+Z$/, "");
-    const stepLines = [
-      `## Step ${stepNum}: ${item.payload.role} \`${item.hash}\``,
-      `**Agent:** ${item.payload.agent} | **Time:** ${ts}`,
-    ];
-    const roleDef = workflow.roles[item.payload.role];
-    if (roleDef) {
-      stepLines.push("", "### Prompt", "", roleDef.systemPrompt);
-    }
-    if (item.payload.detail) {
-      const content = extractLastAssistantContent(uwf, item.payload.detail);
-      if (content !== null) {
-        stepLines.push("", "### Content", "", content);
-      }
-    }
-    stepLines.push("", "### Output", "", "```yaml", outputYaml, "```");
-    parts.push(stepLines.join("\n"));
-  }
-
-  return parts.join("\n\n---\n\n");
-}
-
-function buildModeratorContext(uwf: UwfStore, chain: ChainState): ModeratorContext {
-  const chronological = [...chain.stepsNewestFirst].reverse();
-  const steps: StepContext[] = chronological.map((step) => ({
-    role: step.role,
-    output: expandOutput(uwf, step.output),
-    detail: step.detail,
-    agent: step.agent,
-  }));
-  return { start: chain.start, steps };
-}
-
-function loadWorkflowPayload(uwf: UwfStore, workflowRef: CasRef): WorkflowPayload {
-  const node = uwf.store.get(workflowRef);
-  if (node === null) {
-    fail(`workflow CAS node not found: ${workflowRef}`);
-  }
-  if (node.type !== uwf.schemas.workflow) {
-    fail(`node ${workflowRef} is not a Workflow`);
-  }
-  return node.payload as WorkflowPayload;
-}
-
-function parseAgentOverride(override: string): AgentConfig {
-  const parts = override
-    .trim()
-    .split(/\s+/)
-    .filter((p) => p.length > 0);
-  const command = parts[0];
-  if (command === undefined) {
-    fail("agent override must not be empty");
-  }
-  return { command, args: parts.slice(1) };
-}
-
-function resolveAgentConfig(
-  config: WorkflowConfig,
-  workflow: WorkflowPayload,
-  role: string,
-  agentOverride: string | null,
-): AgentConfig {
-  if (agentOverride !== null) {
-    return parseAgentOverride(agentOverride);
-  }
-
-  let alias: AgentAlias = config.defaultAgent;
-  if (config.agentOverrides !== null) {
-    const roleOverrides = config.agentOverrides[workflow.name];
-    if (roleOverrides !== undefined && roleOverrides[role] !== undefined) {
-      alias = roleOverrides[role];
-    }
-  }
-
-  const agentConfig = config.agents[alias];
-  if (agentConfig === undefined) {
-    fail(`unknown agent alias in config: ${alias}`);
-  }
-  return agentConfig;
-}
-
-function spawnAgent(agent: AgentConfig, threadId: ThreadId, role: string): CasRef {
-  const argv = [...agent.args, threadId, role];
-  let stdout: string;
-  try {
-    stdout = execFileSync(agent.command, argv, {
-      encoding: "utf8",
-      env: process.env,
-      stdio: ["ignore", "pipe", "pipe"],
-    });
-  } catch (e) {
-    const err = e as NodeJS.ErrnoException & { stderr?: Buffer | string };
-    const stderr =
-      err.stderr === undefined
-        ? ""
-        : typeof err.stderr === "string"
-          ? err.stderr
-          : err.stderr.toString("utf8");
-    const detail = stderr.trim() !== "" ? `: ${stderr.trim()}` : "";
-    fail(`agent command failed (${agent.command})${detail}`);
-  }
-
-  const line = stdout.trim().split("\n").pop()?.trim() ?? "";
-  if (!isCasRef(line)) {
-    fail(`agent stdout is not a valid CAS hash: ${line || "(empty)"}`);
-  }
-  return line;
-}
-
-async function archiveThread(
-  storageRoot: string,
-  threadId: ThreadId,
-  workflow: CasRef,
-  head: CasRef,
-): Promise<void> {
-  const index = await loadThreadsIndex(storageRoot);
-  delete index[threadId];
-  await saveThreadsIndex(storageRoot, index);
-  await appendThreadHistory(storageRoot, {
-    thread: threadId,
-    workflow,
-    head,
-    completedAt: Date.now(),
-  });
-}
-
-export async function cmdThreadStep(
-  storageRoot: string,
-  threadId: ThreadId,
-  agentOverride: string | null,
-): Promise<StepOutput> {
-  const index = await loadThreadsIndex(storageRoot);
-  const headHash = index[threadId];
-  if (headHash === undefined) {
-    fail(`thread not active: ${threadId}`);
-  }
-
-  const uwf = await createUwfStore(storageRoot);
-  const chain = walkChain(uwf, headHash);
-  const workflowHash = chain.start.workflow;
-  const workflow = loadWorkflowPayload(uwf, workflowHash);
-  const context = buildModeratorContext(uwf, chain);
-
-  const nextResult = await evaluate(workflow, context);
-  if (!nextResult.ok) {
-    fail(nextResult.error.message);
-  }
-
-  if (nextResult.value === END_ROLE) {
-    await archiveThread(storageRoot, threadId, workflowHash, headHash);
-    return {
-      workflow: workflowHash,
-      thread: threadId,
-      head: headHash,
-      done: true,
-    };
-  }
-
-  const role = nextResult.value;
-  const config = await loadWorkflowConfig(storageRoot);
-  const agent = resolveAgentConfig(config, workflow, role, agentOverride);
-
-  loadDotenv({ path: getEnvPath(storageRoot) });
-  const newHead = spawnAgent(agent, threadId, role);
-
-  // Re-create store to pick up nodes written by the agent subprocess
-  const uwfAfter = await createUwfStore(storageRoot);
-  const newNode = uwfAfter.store.get(newHead);
-  if (newNode === null || newNode.type !== uwfAfter.schemas.stepNode) {
-    fail(`agent returned hash that is not a StepNode: ${newHead}`);
-  }
-
-  // Reload threads index to avoid overwriting changes made by the agent subprocess
-  const freshIndex = await loadThreadsIndex(storageRoot);
-  freshIndex[threadId] = newHead;
-  await saveThreadsIndex(storageRoot, freshIndex);
-
-  const chainAfter = walkChain(uwfAfter, newHead);
-  const contextAfter = buildModeratorContext(uwfAfter, chainAfter);
-  const afterResult = await evaluate(workflow, contextAfter);
-  if (!afterResult.ok) {
-    fail(afterResult.error.message);
-  }
-
-  const done = afterResult.value === END_ROLE;
-  if (done) {
-    await archiveThread(storageRoot, threadId, workflowHash, newHead);
-  }
-
-  return {
-    workflow: workflowHash,
-    thread: threadId,
-    head: newHead,
-    done,
-  };
-}
-
-async function resolveHeadHash(storageRoot: string, threadId: ThreadId): Promise<CasRef> {
-  const index = await loadThreadsIndex(storageRoot);
-  const activeHead = index[threadId];
-  if (activeHead !== undefined) {
-    return activeHead;
-  }
-  const hist = await findThreadInHistory(storageRoot, threadId);
-  if (hist !== null) {
-    return hist.head;
-  }
-  fail(`thread not found: ${threadId}`);
-}
-
-export async function cmdThreadSteps(
-  storageRoot: string,
-  threadId: ThreadId,
-): Promise<ThreadStepsOutput> {
-  const headHash = await resolveHeadHash(storageRoot, threadId);
-  const uwf = await createUwfStore(storageRoot);
-  const chain = walkChain(uwf, headHash);
-
-  const startNode = uwf.store.get(chain.startHash);
-  if (startNode === null) {
-    fail(`StartNode not found: ${chain.startHash}`);
-  }
-
-  const startEntry: StartEntry = {
-    hash: chain.startHash,
-    workflow: chain.start.workflow,
-    prompt: chain.start.prompt,
-    timestamp: startNode.timestamp,
-  };
-
-  const stepEntries: StepEntry[] = [];
-  const ordered = collectOrderedSteps(uwf, headHash, chain);
-
-  for (const item of ordered) {
-    stepEntries.push({
-      hash: item.hash,
-      role: item.payload.role,
-      output: expandOutput(uwf, item.payload.output),
-      detail: item.payload.detail,
-      agent: item.payload.agent,
-      timestamp: item.timestamp,
-    });
-  }
-
-  return {
-    thread: threadId,
-    workflow: chain.start.workflow,
-    steps: [startEntry, ...stepEntries],
-  };
-}
-
-export async function cmdThreadRead(
-  storageRoot: string,
-  threadId: ThreadId,
-  quota: number = THREAD_READ_DEFAULT_QUOTA,
-  before: CasRef | null = null,
-  showStart: boolean = false,
-): Promise<string> {
-  const headHash = await resolveHeadHash(storageRoot, threadId);
-  const uwf = await createUwfStore(storageRoot);
-  const chain = walkChain(uwf, headHash);
-  const workflow = loadWorkflowPayload(uwf, chain.start.workflow);
-  const ordered = collectOrderedSteps(uwf, headHash, chain);
-
-  return formatThreadReadMarkdown({
-    threadId,
-    workflowName: workflow.name,
-    workflowHash: chain.start.workflow,
-    prompt: chain.start.prompt,
-    ordered,
-    uwf,
-    workflow,
-    quota,
-    before,
-    showStart,
-  });
-}
-
-export async function cmdThreadFork(
-  storageRoot: string,
-  stepHash: CasRef,
-): Promise<ThreadForkOutput> {
-  const uwf = await createUwfStore(storageRoot);
-  const node = uwf.store.get(stepHash);
-  if (node === null) {
-    fail(`CAS node not found: ${stepHash}`);
-  }
-  if (node.type !== uwf.schemas.startNode && node.type !== uwf.schemas.stepNode) {
-    fail(`node ${stepHash} is not a StartNode or StepNode`);
-  }
-
-  const newThreadId = generateUlid(Date.now()) as ThreadId;
-  const index = await loadThreadsIndex(storageRoot);
-  index[newThreadId] = stepHash;
-  await saveThreadsIndex(storageRoot, index);
-
-  return {
-    thread: newThreadId,
-    forkedFrom: {
-      step: stepHash,
-    },
-  };
-}
-
-export async function cmdThreadStepDetails(
-  storageRoot: string,
-  stepHash: CasRef,
-): Promise<unknown> {
-  const uwf = await createUwfStore(storageRoot);
-  const node = uwf.store.get(stepHash);
-  if (node === null) {
-    fail(`CAS node not found: ${stepHash}`);
-  }
-  if (node.type !== uwf.schemas.stepNode) {
-    fail(`node ${stepHash} is not a StepNode`);
-  }
-  const payload = node.payload as StepNodePayload;
-  if (!payload.detail) {
-    fail(`step ${stepHash} has no detail`);
-  }
-  return expandDeep(uwf.store, payload.detail);
-}
-
-export async function cmdThreadKill(storageRoot: string, threadId: ThreadId): Promise<KillOutput> {
-  const index = await loadThreadsIndex(storageRoot);
-  const head = index[threadId];
-  if (head === undefined) {
-    fail(`thread not active: ${threadId}`);
-  }
-
-  const uwf = await createUwfStore(storageRoot);
-  const workflow = resolveWorkflowFromHead(uwf, head);
-  if (workflow === null) {
-    fail(`failed to resolve workflow from head: ${head}`);
-  }
-
-  delete index[threadId];
-  await saveThreadsIndex(storageRoot, index);
-
-  const historyEntry: ThreadHistoryLine = {
-    thread: threadId,
-    workflow,
-    head,
-    completedAt: Date.now(),
-  };
-  await appendThreadHistory(storageRoot, historyEntry);
-
-  return { thread: threadId, archived: true };
-}

packages/cli-uwf/src/validate.ts

@@ -1,71 +0,0 @@
-import type { CasRef, WorkflowPayload } from "@uncaged/uwf-protocol";
-
-const CAS_REF_PATTERN = /^[0-9A-HJKMNP-TV-Z]{13}$/;
-
-export function isCasRef(value: string): value is CasRef {
-  return CAS_REF_PATTERN.test(value);
-}
-
-function isRecord(value: unknown): value is Record<string, unknown> {
-  return typeof value === "object" && value !== null && !Array.isArray(value);
-}
-
-function isRoleDefinition(value: unknown): boolean {
-  if (!isRecord(value)) {
-    return false;
-  }
-  const outputSchema = value.outputSchema;
-  const schemaOk = isRecord(outputSchema) && typeof outputSchema.type === "string";
-  return (
-    typeof value.description === "string" && typeof value.systemPrompt === "string" && schemaOk
-  );
-}
-
-function isConditionDefinition(value: unknown): boolean {
-  if (!isRecord(value)) {
-    return false;
-  }
-  return typeof value.description === "string" && typeof value.expression === "string";
-}
-
-function isTransition(value: unknown): boolean {
-  if (!isRecord(value)) {
-    return false;
-  }
-  const condition = value.condition;
-  return typeof value.role === "string" && (condition === null || typeof condition === "string");
-}
-
-function isStringRecord(value: unknown, itemCheck: (item: unknown) => boolean): boolean {
-  if (!isRecord(value)) {
-    return false;
-  }
-  return Object.values(value).every(itemCheck);
-}
-
-function isGraph(value: unknown): boolean {
-  if (!isRecord(value)) {
-    return false;
-  }
-  return Object.values(value).every(
-    (transitions) => Array.isArray(transitions) && transitions.every((t) => isTransition(t)),
-  );
-}
-
-/** Validate YAML-parsed workflow document shape (outputSchema may be inline JSON Schema). */
-export function parseWorkflowPayload(raw: unknown): WorkflowPayload | null {
-  if (!isRecord(raw)) {
-    return null;
-  }
-  if (typeof raw.name !== "string" || typeof raw.description !== "string") {
-    return null;
-  }
-  if (
-    !isStringRecord(raw.roles, isRoleDefinition) ||
-    !isStringRecord(raw.conditions, isConditionDefinition) ||
-    !isGraph(raw.graph)
-  ) {
-    return null;
-  }
-  return raw as WorkflowPayload;
-}

packages/cli-workflow/README.md

@@ -0,0 +1,211 @@
+# @uncaged/cli-workflow
+
+`uwf` CLI — thread lifecycle, workflow registry, CAS inspection, and setup.
+
+## Overview
+
+Layer 4 entry point for the workflow engine. The `uwf` binary orchestrates one step per invocation: load thread head from `threads.yaml`, run the moderator, spawn the configured agent CLI, run extract, append a CAS step node, and update the head pointer (or archive when `$END`).
+
+### Four-Layer Architecture
+
+```
+workflow → thread → step → turn
+模板定义   执行实例   单步结果   agent内部交互
+```
+
+- **Workflow** (layer 1): YAML template with roles and routing graph
+- **Thread** (layer 2): Single workflow execution instance
+- **Step** (layer 3): One moderator→agent→extract cycle
+- **Turn** (layer 4): Agent-internal interactions (use `step show` or CAS to inspect)
+
+This package has no library `src/index.ts` — it is consumed as a CLI binary only.
+
+**Dependencies:** `@uncaged/json-cas`, `@uncaged/json-cas-fs`, `@uncaged/workflow-agent-kit`, `@uncaged/workflow-moderator`, `@uncaged/workflow-protocol`, `@uncaged/workflow-util`, `commander`, `dotenv`, `yaml`
+
+## Installation
+
+Included as the `uwf` binary when you install `@uncaged/cli-workflow`:
+
+```bash
+bun add -g @uncaged/cli-workflow
+# or from the monorepo:
+bun link packages/cli-workflow
+```
+
+## CLI Usage
+
+### Global options
+
+```
+-V, --version          Show version
+--format <json|yaml>   Output format (default: json)
+-h, --help             Show help
+```
+
+### Thread (Layer 2: Execution Instances)
+
+| Command | Description |
+|---------|-------------|
+| `uwf thread start <workflow> -p <prompt>` | Create a thread without executing |
+| `uwf thread exec <thread-id> [--agent <cmd>] [-c <count>] [--background]` | Execute one or more moderator→agent→extract cycles |
+| `uwf thread show <thread-id>` | Show thread head pointer |
+| `uwf thread list [--status <status>] [--after <date>] [--before <date>] [--skip <n>] [--take <n>]` | List threads filtered by status (idle, running, completed, active, or comma-separated), time range (ISO or relative like '7d'), with pagination |
+| `uwf thread read <thread-id> [--quota N] [--before <hash>] [--start]` | Render thread as readable markdown |
+
+`thread read`, `step list`, and `step show` work on both active and completed threads.
+| `uwf thread stop <thread-id>` | Stop background execution (keep thread active) |
+| `uwf thread cancel <thread-id>` | Cancel thread (stop + archive to history) |
+
+Examples:
+
+```bash
+uwf thread start solve-issue -p "Fix the login redirect bug"
+uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV
+uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV -c 3 --agent uwf-builtin
+uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV --background
+uwf thread list --status running
+uwf thread list --status active
+uwf thread list --status idle,completed
+uwf thread list --after 7d --take 10
+uwf thread read 01ARZ3NDEKTSV4RRFFQ69G5FAV --quota 8000
+uwf thread stop 01ARZ3NDEKTSV4RRFFQ69G5FAV
+```
+
+### Step (Layer 3: Single Cycle Results)
+
+| Command | Description |
+|---------|-------------|
+| `uwf step list <thread-id>` | List all steps in a thread chronologically |
+| `uwf step show <step-hash>` | Show step metadata and frontmatter |
+| `uwf step read <step-hash> [--quota <chars>]` | Read a step's turns as human-readable markdown |
+| `uwf step fork <step-hash>` | Fork a thread from a specific step |
+
+Examples:
+
+```bash
+uwf step list 01ARZ3NDEKTSV4RRFFQ69G5FAV
+uwf step show 32GCDE899RRQ3
+uwf step read 32GCDE899RRQ3 --quota 2000
+uwf step fork 32GCDE899RRQ3
+```
+
+### Workflow (Layer 1: Templates)
+
+| Command | Description |
+|---------|-------------|
+| `uwf workflow add <file.yaml>` | Register a workflow from YAML |
+| `uwf workflow show <name-or-hash>` | Show workflow definition |
+| `uwf workflow list` | List registered workflows |
+
+### CAS
+
+| Command | Description |
+|---------|-------------|
+| `uwf cas get <hash> [--timestamp]` | Read a CAS node |
+| `uwf cas put <type-hash> <data>` | Store a node, print hash |
+| `uwf cas put-text <text>` | Store plain text, print hash |
+| `uwf cas has <hash>` | Check existence |
+| `uwf cas refs <hash>` | List direct references |
+| `uwf cas walk <hash>` | Recursive traversal |
+| `uwf cas reindex` | Rebuild type index |
+| `uwf cas schema list` | List registered schemas |
+| `uwf cas schema get <hash>` | Show a schema |
+
+### Setup
+
+```bash
+uwf setup
+uwf setup --provider openai --base-url https://api.openai.com/v1 \
+  --api-key sk-... --model gpt-4o --agent hermes
+```
+
+Config: `~/.uncaged/workflow/config.yaml`. API keys: `~/.uncaged/workflow/.env`.
+
+### Skill
+
+| Command | Description |
+|---------|-------------|
+| `uwf skill cli` | Print markdown reference of all uwf commands (for agent skills) |
+
+### Log
+
+| Command | Description |
+|---------|-------------|
+| `uwf log list` | List log files with sizes |
+| `uwf log show [--thread <id>] [--process <pid>] [--date YYYY-MM-DD]` | Show filtered log entries |
+| `uwf log clean [--before YYYY-MM-DD]` | Delete old log files |
+
+## Migration Guide
+
+### Breaking Changes (v0.x → v1.x)
+
+The CLI was reorganized to clarify the four-layer architecture. **No backward compatibility** — old commands have been removed.
+
+#### Renamed Commands
+
+| Old Command | New Command | Notes |
+|------------|-------------|-------|
+| `workflow put` | `workflow add` | More intuitive verb |
+| `thread step` | `thread exec` | Eliminates ambiguity with "step" noun |
+| `thread list --all` | `thread list --status completed` | Unified status filtering |
+
+#### Removed Commands (Merged)
+
+| Old Command | New Command | Notes |
+|------------|-------------|-------|
+| `thread running` | `thread list --status running` | Merged into unified list |
+
+#### Removed Commands (Split)
+
+| Old Command | New Commands | Notes |
+|------------|-------------|-------|
+| `thread kill` | `thread stop` or `thread cancel` | `stop` keeps thread active, `cancel` archives it |
+
+#### Moved Commands
+
+| Old Command | New Command | Notes |
+|------------|-------------|-------|
+| `thread steps` | `step list` | Moved to step layer |
+| `thread step-details` | `step show` | Moved to step layer |
+| `thread fork` | `step fork` | Moved to step layer (forks are step-based) |
+
+#### Deprecation Errors
+
+Old commands now show helpful error messages:
+
+```bash
+$ uwf thread step 01ARZ3NDEKTSV4RRFFQ69G5FAV
+Error: Command 'thread step' has been removed.
+Use 'thread exec' instead.
+
+For more information, see: uwf help thread exec
+```
+
+## Internal Structure
+
+```
+src/
+├── cli.ts              Commander entrypoint, command registration
+├── format.ts           JSON/YAML output formatting
+├── store.ts            CAS store + registry initialization
+├── validate.ts         Workflow YAML validation
+├── schemas.ts          CLI-local schema registration
+└── commands/
+    ├── thread.ts       Thread lifecycle and exec
+    ├── step.ts         Step operations (list/show/read/fork)
+    ├── workflow.ts     Workflow registry (add/show/list)
+    ├── cas.ts          CAS inspection and schema ops
+    ├── setup.ts        Interactive/non-interactive setup
+    ├── skill.ts        Built-in skill references
+    └── log.ts          Process debug log management
+```
+
+## Configuration
+
+| File | Purpose |
+|------|---------|
+| `~/.uncaged/workflow/config.yaml` | Providers, models, default agent |
+| `~/.uncaged/workflow/.env` | API keys (referenced by `apiKeyEnv` in config) |
+| `~/.uncaged/workflow/registry.yaml` | Workflow name → CAS hash |
+| `~/.uncaged/workflow/threads.yaml` | Active thread head pointers |
+| `~/.uncaged/workflow/cas/` | Content-addressed node storage |

packages/cli-workflow/package.json

@@ -1,6 +1,6 @@
 {
-  "name": "@uncaged/cli-uwf",
-  "version": "0.1.0",
+  "name": "@uncaged/cli-workflow",
+  "version": "0.5.0",
   "files": [
     "src",
     "dist",
@@ -11,11 +11,11 @@
     "uwf": "./src/cli.ts"
   },
   "dependencies": {
-    "@uncaged/json-cas": "^0.3.0",
-    "@uncaged/json-cas-fs": "^0.3.0",
-    "@uncaged/uwf-agent-kit": "workspace:^",
-    "@uncaged/uwf-moderator": "workspace:^",
-    "@uncaged/uwf-protocol": "workspace:^",
+    "@uncaged/json-cas": "^0.4.0",
+    "@uncaged/json-cas-fs": "^0.4.0",
+    "@uncaged/workflow-agent-kit": "workspace:^",
+    "@uncaged/workflow-moderator": "workspace:^",
+    "@uncaged/workflow-protocol": "workspace:^",
     "@uncaged/workflow-util": "workspace:^",
     "commander": "^14.0.3",
     "dotenv": "^16.6.1",

packages/cli-workflow/src/__tests__/cas-exit-code.test.ts

@@ -0,0 +1,152 @@
+import { execSync } from "node:child_process";
+import { mkdir, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { cmdCasPutText } from "../commands/cas.js";
+
+let storageRoot: string;
+let uwfPath: string;
+
+beforeEach(async () => {
+  storageRoot = join(
+    tmpdir(),
+    `uwf-cas-exit-test-${Date.now()}-${Math.random().toString(36).slice(2)}`,
+  );
+  await mkdir(storageRoot, { recursive: true });
+
+  // Find the uwf CLI path
+  uwfPath = join(__dirname, "../../src/cli.ts");
+});
+
+afterEach(async () => {
+  await rm(storageRoot, { recursive: true, force: true });
+});
+
+type ExecResult = {
+  stdout: string;
+  stderr: string;
+  exitCode: number;
+};
+
+function execUwf(args: string[]): ExecResult {
+  try {
+    const stdout = execSync(`bun ${uwfPath} ${args.join(" ")}`, {
+      env: { ...process.env, WORKFLOW_STORAGE_ROOT: storageRoot },
+      encoding: "utf-8",
+      stdio: ["pipe", "pipe", "pipe"],
+    });
+    return { stdout, stderr: "", exitCode: 0 };
+  } catch (error: unknown) {
+    if (
+      error &&
+      typeof error === "object" &&
+      "stdout" in error &&
+      "stderr" in error &&
+      "status" in error
+    ) {
+      return {
+        stdout: (error.stdout as Buffer | string).toString(),
+        stderr: (error.stderr as Buffer | string).toString(),
+        exitCode: error.status as number,
+      };
+    }
+    throw error;
+  }
+}
+
+describe("uwf cas has CLI exit codes", () => {
+  test("exits 0 when hash exists", async () => {
+    // Setup: Create a temp storage root, put a text node, capture hash
+    const putResult = await cmdCasPutText(storageRoot, "test content");
+    const hash = putResult.hash;
+
+    // Execute: uwf cas has <hash>
+    const result = execUwf(["cas", "has", hash]);
+
+    // Assert: stdout contains {"exists":true}, exit code === 0
+    expect(result.stdout).toContain('"exists":true');
+    expect(result.exitCode).toBe(0);
+  });
+
+  test("exits 1 when hash does not exist", () => {
+    // Setup: Create a temp storage root (empty CAS store)
+    // Execute: uwf cas has NOSUCHHASH123
+    const result = execUwf(["cas", "has", "NOSUCHHASH123"]);
+
+    // Assert: stdout contains {"exists":false}, exit code === 1
+    expect(result.stdout).toContain('"exists":false');
+    expect(result.exitCode).toBe(1);
+  });
+
+  test("JSON output format unchanged for exists=true", async () => {
+    // Setup: Create store, put node
+    const putResult = await cmdCasPutText(storageRoot, "test");
+    const hash = putResult.hash;
+
+    // Execute: uwf cas has <hash>
+    const result = execUwf(["cas", "has", hash]);
+
+    // Assert: stdout JSON parses correctly to {exists: true}
+    const parsed = JSON.parse(result.stdout.trim());
+    expect(parsed).toEqual({ exists: true });
+  });
+
+  test("JSON output format unchanged for exists=false", () => {
+    // Setup: Create empty store
+    // Execute: uwf cas has INVALID
+    const result = execUwf(["cas", "has", "INVALID"]);
+
+    // Assert: stdout JSON parses correctly to {exists: false}
+    const parsed = JSON.parse(result.stdout.trim());
+    expect(parsed).toEqual({ exists: false });
+  });
+
+  test("YAML output format preserves exit code behavior for exists=true", async () => {
+    // Setup: Create store with node
+    const putResult = await cmdCasPutText(storageRoot, "test");
+    const hash = putResult.hash;
+
+    // Execute: uwf --format yaml cas has <hash>
+    const result = execUwf(["--format", "yaml", "cas", "has", hash]);
+
+    // Assert: exit code === 0, output is YAML format
+    expect(result.exitCode).toBe(0);
+    expect(result.stdout).toContain("exists:");
+    expect(result.stdout).toContain("true");
+  });
+
+  test("YAML output format preserves exit code behavior for exists=false", () => {
+    // Setup: Create empty store
+    // Execute: uwf --format yaml cas has INVALID
+    const result = execUwf(["--format", "yaml", "cas", "has", "INVALID"]);
+
+    // Assert: exit code === 1, output is YAML format
+    expect(result.exitCode).toBe(1);
+    expect(result.stdout).toContain("exists:");
+    expect(result.stdout).toContain("false");
+  });
+});
+
+describe("regression: other cas commands unaffected", () => {
+  test("uwf cas get still exits 1 on not-found with error message", () => {
+    // Execute: uwf cas get NOSUCHHASH
+    const result = execUwf(["cas", "get", "NOSUCHHASH"]);
+
+    // Assert: exit code === 1, stderr contains "Node not found"
+    expect(result.exitCode).toBe(1);
+    expect(result.stderr).toContain("Node not found");
+  });
+
+  test("uwf cas put-text behavior unchanged", () => {
+    // Execute: uwf cas put-text "hello"
+    const result = execUwf(["cas", "put-text", "hello"]);
+
+    // Assert: exit code === 0, returns hash
+    expect(result.exitCode).toBe(0);
+    const parsed = JSON.parse(result.stdout.trim());
+    expect(parsed).toHaveProperty("hash");
+    expect(typeof parsed.hash).toBe("string");
+    expect(parsed.hash.length).toBe(13); // Crockford Base32 XXH64 hash length
+  });
+});

packages/cli-workflow/src/__tests__/cas.test.ts

@@ -0,0 +1,74 @@
+import { mkdir, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { cmdCasHas, cmdCasPutText } from "../commands/cas.js";
+
+let storageRoot: string;
+
+beforeEach(async () => {
+  storageRoot = join(tmpdir(), `uwf-cas-test-${Date.now()}-${Math.random().toString(36).slice(2)}`);
+  await mkdir(storageRoot, { recursive: true });
+});
+
+afterEach(async () => {
+  await rm(storageRoot, { recursive: true, force: true });
+});
+
+describe("cmdCasHas", () => {
+  test("returns {exists: true} for existing hash", async () => {
+    // Setup: Create a test store, put a node, get its hash
+    const putResult = await cmdCasPutText(storageRoot, "test content");
+    const hash = putResult.hash;
+
+    // Execute: Call cmdCasHas with the valid hash
+    const result = await cmdCasHas(storageRoot, hash);
+
+    // Assert: Result equals {exists: true}
+    expect(result).toEqual({ exists: true });
+  });
+
+  test("returns {exists: false} for non-existent hash", async () => {
+    // Setup: Create an empty test store
+    // (storageRoot already created in beforeEach)
+
+    // Execute: Call cmdCasHas with an invalid hash
+    const result = await cmdCasHas(storageRoot, "INVALIDHASH12");
+
+    // Assert: Result equals {exists: false}
+    expect(result).toEqual({ exists: false });
+  });
+
+  test("does not throw for non-existent hash", async () => {
+    // Setup: Create an empty test store
+    // Execute & Assert: Does not throw, returns {exists: false}
+    await expect(cmdCasHas(storageRoot, "NOSUCHHASH123")).resolves.toEqual({
+      exists: false,
+    });
+  });
+
+  test("handles malformed hash gracefully", async () => {
+    // Setup: Create a test store
+    // Execute: Call cmdCasHas with a too-short hash
+    const result = await cmdCasHas(storageRoot, "xyz");
+
+    // Assert: Returns {exists: false} (store.has() returns false)
+    expect(result).toEqual({ exists: false });
+  });
+
+  test("handles empty hash string", async () => {
+    // Execute: Call cmdCasHas with an empty string
+    const result = await cmdCasHas(storageRoot, "");
+
+    // Assert: Returns {exists: false}
+    expect(result).toEqual({ exists: false });
+  });
+
+  test("handles hash with special characters", async () => {
+    // Execute: Call cmdCasHas with special characters
+    const result = await cmdCasHas(storageRoot, "HASH!@#");
+
+    // Assert: Returns {exists: false}
+    expect(result).toEqual({ exists: false });
+  });
+});

packages/cli-workflow/src/__tests__/log.test.ts

@@ -0,0 +1,181 @@
+import { mkdir, readdir, rm, writeFile } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { cmdLogClean, cmdLogList, cmdLogShow } from "../commands/log.js";
+
+let storageRoot: string;
+
+beforeEach(async () => {
+  storageRoot = join(tmpdir(), `uwf-log-test-${Date.now()}-${Math.random().toString(36).slice(2)}`);
+  await mkdir(join(storageRoot, "logs"), { recursive: true });
+});
+
+afterEach(async () => {
+  await rm(storageRoot, { recursive: true, force: true });
+});
+
+const entry1 = JSON.stringify({
+  ts: "2026-05-20T10:00:00.000Z",
+  pid: "1716200000000-1234",
+  tag: "W9F3RK2M",
+  msg: "process start",
+  thread: "01J1234ABCDEF",
+  workflow: "solve-issue",
+});
+
+const entry2 = JSON.stringify({
+  ts: "2026-05-20T10:00:01.000Z",
+  pid: "1716200000000-1234",
+  tag: "ABC12345",
+  msg: "step executed",
+  thread: "01J1234ABCDEF",
+  workflow: "solve-issue",
+});
+
+const entry3 = JSON.stringify({
+  ts: "2026-05-20T10:00:02.000Z",
+  pid: "1716200000000-5678",
+  tag: "XYZ98765",
+  msg: "different process",
+  thread: "01JOTHER000000",
+  workflow: "review-code",
+});
+
+const oldEntry = JSON.stringify({
+  ts: "2026-05-19T08:00:00.000Z",
+  pid: "1716200000000-9999",
+  tag: "OLD1TAG1",
+  msg: "old entry",
+  thread: "01JOLD0000000",
+  workflow: "solve-issue",
+});
+
+const olderEntry = JSON.stringify({
+  ts: "2026-05-18T08:00:00.000Z",
+  pid: "1716200000000-0001",
+  tag: "OLD2TAG2",
+  msg: "older entry",
+  thread: "01JOLDER00000",
+  workflow: "review-code",
+});
+
+async function writeLogFiles(): Promise<void> {
+  const logsDir = join(storageRoot, "logs");
+  await writeFile(join(logsDir, "2026-05-20.jsonl"), `${[entry1, entry2, entry3].join("\n")}\n`);
+  await writeFile(join(logsDir, "2026-05-19.jsonl"), `${oldEntry}\n`);
+  await writeFile(join(logsDir, "2026-05-18.jsonl"), `${olderEntry}\n`);
+}
+
+describe("cmdLogList", () => {
+  test("lists log files with sizes sorted by date descending", async () => {
+    await writeLogFiles();
+    const result = await cmdLogList(storageRoot);
+    expect(result).toHaveLength(3);
+    expect(result[0].name).toBe("2026-05-20.jsonl");
+    expect(result[0].date).toBe("2026-05-20");
+    expect(result[0].size).toBeGreaterThan(0);
+    expect(result[1].name).toBe("2026-05-19.jsonl");
+    expect(result[2].name).toBe("2026-05-18.jsonl");
+  });
+
+  test("returns empty array when no log files exist", async () => {
+    const result = await cmdLogList(storageRoot);
+    expect(result).toEqual([]);
+  });
+
+  test("returns empty array when logs directory does not exist", async () => {
+    const noLogsRoot = join(storageRoot, "nonexistent");
+    await mkdir(noLogsRoot, { recursive: true });
+    const result = await cmdLogList(noLogsRoot);
+    expect(result).toEqual([]);
+  });
+});
+
+describe("cmdLogShow", () => {
+  test("filters by thread ID", async () => {
+    await writeLogFiles();
+    const result = await cmdLogShow(storageRoot, {
+      thread: "01J1234ABCDEF",
+      process: null,
+      date: null,
+    });
+    expect(result).toHaveLength(2);
+    expect(result.every((e) => e.thread === "01J1234ABCDEF")).toBe(true);
+  });
+
+  test("filters by process ID", async () => {
+    await writeLogFiles();
+    const result = await cmdLogShow(storageRoot, {
+      thread: null,
+      process: "1716200000000-1234",
+      date: null,
+    });
+    expect(result).toHaveLength(2);
+    expect(result.every((e) => e.pid === "1716200000000-1234")).toBe(true);
+  });
+
+  test("filters by date", async () => {
+    await writeLogFiles();
+    const result = await cmdLogShow(storageRoot, {
+      thread: null,
+      process: null,
+      date: "2026-05-19",
+    });
+    expect(result).toHaveLength(1);
+    expect(result[0].msg).toBe("old entry");
+  });
+
+  test("reads all files when no date filter", async () => {
+    await writeLogFiles();
+    const result = await cmdLogShow(storageRoot, { thread: null, process: null, date: null });
+    expect(result).toHaveLength(5);
+    // sorted by ts ascending
+    expect(result[0].ts).toBe("2026-05-18T08:00:00.000Z");
+    expect(result[4].ts).toBe("2026-05-20T10:00:02.000Z");
+  });
+
+  test("returns empty when no matches", async () => {
+    await writeLogFiles();
+    const result = await cmdLogShow(storageRoot, {
+      thread: "NONEXISTENT",
+      process: null,
+      date: null,
+    });
+    expect(result).toEqual([]);
+  });
+
+  test("combined thread + date filter", async () => {
+    await writeLogFiles();
+    const result = await cmdLogShow(storageRoot, {
+      thread: "01J1234ABCDEF",
+      process: null,
+      date: "2026-05-20",
+    });
+    expect(result).toHaveLength(2);
+    expect(result.every((e) => e.thread === "01J1234ABCDEF")).toBe(true);
+  });
+});
+
+describe("cmdLogClean", () => {
+  test("deletes files before given date", async () => {
+    await writeLogFiles();
+    const result = await cmdLogClean(storageRoot, "2026-05-20");
+    expect(result.deleted).toBe(2);
+    const remaining = await readdir(join(storageRoot, "logs"));
+    expect(remaining).toEqual(["2026-05-20.jsonl"]);
+  });
+
+  test("deletes nothing when all files are newer", async () => {
+    await writeLogFiles();
+    const result = await cmdLogClean(storageRoot, "2026-05-18");
+    expect(result.deleted).toBe(0);
+  });
+
+  test("handles missing logs directory gracefully", async () => {
+    const noLogsRoot = join(storageRoot, "nonexistent");
+    await mkdir(noLogsRoot, { recursive: true });
+    const result = await cmdLogClean(noLogsRoot, "2026-05-20");
+    expect(result).toEqual({ deleted: 0 });
+  });
+});

packages/cli-workflow/src/__tests__/resolve-head-hash.test.ts

@@ -0,0 +1,108 @@
+import { mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { resolveHeadHash } from "../commands/shared.js";
+import { appendThreadHistory, saveThreadsIndex } from "../store.js";
+
+let tmpDir: string;
+
+beforeEach(async () => {
+  tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-resolve-head-"));
+});
+
+afterEach(async () => {
+  await rm(tmpDir, { recursive: true, force: true });
+});
+
+describe("resolveHeadHash", () => {
+  test("returns head hash from threads.yaml for active thread", async () => {
+    const threadId = "01JTEST0000000000000000001" as ThreadId;
+    const headHash = "active_hash_123" as CasRef;
+
+    await saveThreadsIndex(tmpDir, { [threadId]: headHash });
+
+    const result = await resolveHeadHash(tmpDir, threadId);
+
+    expect(result).toBe(headHash);
+  });
+
+  test("falls back to history.jsonl when thread not in threads.yaml", async () => {
+    const threadId = "01JTEST0000000000000000002" as ThreadId;
+    const headHash = "completed_hash_456" as CasRef;
+    const workflowHash = "workflow_hash_789" as CasRef;
+
+    // No entry in threads.yaml, only in history.jsonl
+    await saveThreadsIndex(tmpDir, {});
+    await appendThreadHistory(tmpDir, {
+      thread: threadId,
+      workflow: workflowHash,
+      head: headHash,
+      completedAt: Date.now(),
+    });
+
+    const result = await resolveHeadHash(tmpDir, threadId);
+
+    expect(result).toBe(headHash);
+  });
+
+  // Note: Testing the error case requires CLI-level testing because resolveHeadHash
+  // calls fail() which does process.exit(1), terminating the test runner.
+  // The error behavior is tested in integration tests below via CLI invocation.
+
+  test("prioritizes active thread over history when thread exists in both", async () => {
+    const threadId = "01JTEST0000000000000000004" as ThreadId;
+    const activeHash = "active_hash_v2" as CasRef;
+    const historicalHash = "historical_hash_v1" as CasRef;
+    const workflowHash = "workflow_hash_xyz" as CasRef;
+
+    // Thread exists in both locations (should not happen normally, but test the precedence)
+    await saveThreadsIndex(tmpDir, { [threadId]: activeHash });
+    await appendThreadHistory(tmpDir, {
+      thread: threadId,
+      workflow: workflowHash,
+      head: historicalHash,
+      completedAt: Date.now(),
+    });
+
+    const result = await resolveHeadHash(tmpDir, threadId);
+
+    // Should return the active head, not the historical one
+    expect(result).toBe(activeHash);
+  });
+
+  test("finds thread from multiple history entries", async () => {
+    const threadId1 = "01JTEST0000000000000000005" as ThreadId;
+    const threadId2 = "01JTEST0000000000000000006" as ThreadId;
+    const threadId3 = "01JTEST0000000000000000007" as ThreadId;
+    const hash1 = "hash_thread1" as CasRef;
+    const hash2 = "hash_thread2" as CasRef;
+    const hash3 = "hash_thread3" as CasRef;
+    const workflowHash = "workflow_hash_abc" as CasRef;
+
+    await saveThreadsIndex(tmpDir, {});
+    await appendThreadHistory(tmpDir, {
+      thread: threadId1,
+      workflow: workflowHash,
+      head: hash1,
+      completedAt: Date.now() - 2000,
+    });
+    await appendThreadHistory(tmpDir, {
+      thread: threadId2,
+      workflow: workflowHash,
+      head: hash2,
+      completedAt: Date.now() - 1000,
+    });
+    await appendThreadHistory(tmpDir, {
+      thread: threadId3,
+      workflow: workflowHash,
+      head: hash3,
+      completedAt: Date.now(),
+    });
+
+    const result = await resolveHeadHash(tmpDir, threadId2);
+
+    expect(result).toBe(hash2);
+  });
+});

packages/cli-workflow/src/__tests__/setup-complexity.test.ts

@@ -0,0 +1,381 @@
+import { mkdirSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterEach, describe, expect, test, vi } from "vitest";
+import {
+  _discoverAgents,
+  _isBackspace,
+  _isTerminator,
+  _parseWhichOutput,
+  _printModelMenu,
+  _printProviderMenu,
+  _printValidationResult,
+  _resolveModelChoice,
+  _resolveProviderChoice,
+  _searchPathDirs,
+} from "../commands/setup.js";
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 1a. _searchPathDirs
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_searchPathDirs", () => {
+  test("returns empty array for empty PATH", async () => {
+    const result = await _searchPathDirs("");
+    expect(result).toEqual([]);
+  });
+
+  test("finds uwf-hermes in a single dir", async () => {
+    const dir = mkdirSync(join(tmpdir(), `uwf-test-${Date.now()}`), { recursive: true }) as
+      | string
+      | undefined;
+    const actualDir = dir ?? join(tmpdir(), `uwf-test-${Date.now()}`);
+    mkdirSync(actualDir, { recursive: true });
+    const filePath = join(actualDir, "uwf-hermes");
+    writeFileSync(filePath, "#!/bin/sh\n", { mode: 0o755 });
+    const result = await _searchPathDirs(actualDir);
+    expect(result).toContain("uwf-hermes");
+  });
+
+  test("skips non-uwf- prefixed binaries", async () => {
+    const dir = join(tmpdir(), `uwf-test-${Date.now()}-2`);
+    mkdirSync(dir, { recursive: true });
+    writeFileSync(join(dir, "hermes"), "#!/bin/sh\n", { mode: 0o755 });
+    writeFileSync(join(dir, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
+    const result = await _searchPathDirs(dir);
+    expect(result).toEqual(["uwf-hermes"]);
+  });
+
+  test("skips entry named exactly 'uwf'", async () => {
+    const dir = join(tmpdir(), `uwf-test-${Date.now()}-3`);
+    mkdirSync(dir, { recursive: true });
+    writeFileSync(join(dir, "uwf"), "#!/bin/sh\n", { mode: 0o755 });
+    writeFileSync(join(dir, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
+    const result = await _searchPathDirs(dir);
+    expect(result).toEqual(["uwf-hermes"]);
+  });
+
+  test("skips non-executable files", async () => {
+    const dir = join(tmpdir(), `uwf-test-${Date.now()}-4`);
+    mkdirSync(dir, { recursive: true });
+    writeFileSync(join(dir, "uwf-foo"), "#!/bin/sh\n", { mode: 0o644 });
+    const result = await _searchPathDirs(dir);
+    expect(result).toEqual([]);
+  });
+
+  test("deduplicates across PATH dirs", async () => {
+    const dir1 = join(tmpdir(), `uwf-test-${Date.now()}-5a`);
+    const dir2 = join(tmpdir(), `uwf-test-${Date.now()}-5b`);
+    mkdirSync(dir1, { recursive: true });
+    mkdirSync(dir2, { recursive: true });
+    writeFileSync(join(dir1, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
+    writeFileSync(join(dir2, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
+    const result = await _searchPathDirs(`${dir1}:${dir2}`);
+    expect(result).toEqual(["uwf-hermes"]);
+  });
+
+  test("returns sorted array", async () => {
+    const dir = join(tmpdir(), `uwf-test-${Date.now()}-6`);
+    mkdirSync(dir, { recursive: true });
+    writeFileSync(join(dir, "uwf-zoo"), "#!/bin/sh\n", { mode: 0o755 });
+    writeFileSync(join(dir, "uwf-alpha"), "#!/bin/sh\n", { mode: 0o755 });
+    writeFileSync(join(dir, "uwf-mid"), "#!/bin/sh\n", { mode: 0o755 });
+    const result = await _searchPathDirs(dir);
+    expect(result).toEqual(["uwf-alpha", "uwf-mid", "uwf-zoo"]);
+  });
+
+  test("skips inaccessible/nonexistent directories silently", async () => {
+    const result = await _searchPathDirs("/nonexistent-dir-xyz-abc-12345");
+    expect(result).toEqual([]);
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 1b. _parseWhichOutput
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_parseWhichOutput", () => {
+  test("returns empty array for empty string", () => {
+    expect(_parseWhichOutput("")).toEqual([]);
+  });
+
+  test("parses single path", () => {
+    expect(_parseWhichOutput("/usr/local/bin/uwf-hermes")).toEqual(["uwf-hermes"]);
+  });
+
+  test("parses multiple paths", () => {
+    expect(_parseWhichOutput("/usr/local/bin/uwf-hermes\n/usr/bin/uwf-claude-code")).toEqual([
+      "uwf-claude-code",
+      "uwf-hermes",
+    ]);
+  });
+
+  test("deduplicates identical basenames from different dirs", () => {
+    expect(_parseWhichOutput("/a/uwf-hermes\n/b/uwf-hermes")).toEqual(["uwf-hermes"]);
+  });
+
+  test("skips blank lines", () => {
+    expect(_parseWhichOutput("/a/uwf-hermes\n\n/b/uwf-cursor")).toEqual([
+      "uwf-cursor",
+      "uwf-hermes",
+    ]);
+  });
+
+  test("skips entry named exactly 'uwf'", () => {
+    expect(_parseWhichOutput("/usr/bin/uwf")).toEqual([]);
+  });
+
+  test("skips basenames not starting with uwf-", () => {
+    expect(_parseWhichOutput("/usr/bin/node")).toEqual([]);
+  });
+
+  test("returns sorted array", () => {
+    expect(_parseWhichOutput("/a/uwf-zoo\n/a/uwf-alpha")).toEqual(["uwf-alpha", "uwf-zoo"]);
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 2a. _isTerminator
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_isTerminator", () => {
+  test("\\n is a terminator", () => {
+    expect(_isTerminator("\n")).toBe(true);
+  });
+  test("\\r is a terminator", () => {
+    expect(_isTerminator("\r")).toBe(true);
+  });
+  test("\\u0004 (EOT) is a terminator", () => {
+    expect(_isTerminator("")).toBe(true);
+  });
+  test("regular char is not a terminator", () => {
+    expect(_isTerminator("a")).toBe(false);
+  });
+  test("empty string is not a terminator", () => {
+    expect(_isTerminator("")).toBe(false);
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 2b. _isBackspace
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_isBackspace", () => {
+  test("\\u007F is a backspace", () => {
+    expect(_isBackspace("")).toBe(true);
+  });
+  test("\\b is a backspace", () => {
+    expect(_isBackspace("\b")).toBe(true);
+  });
+  test("regular char is not a backspace", () => {
+    expect(_isBackspace("x")).toBe(false);
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 3a. _printProviderMenu
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_printProviderMenu", () => {
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  const providers = [
+    { name: "openai", label: "OpenAI", baseUrl: "https://api.openai.com/v1" },
+    { name: "xai", label: "xAI", baseUrl: "https://api.x.ai/v1" },
+  ] as const;
+
+  test("prints correct number of lines (one per provider + custom)", () => {
+    const lines: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      lines.push(msg);
+    });
+    _printProviderMenu(providers);
+    // 2 providers + 1 custom = 3 lines
+    expect(lines.length).toBe(3);
+  });
+
+  test("custom option number = providers.length + 1", () => {
+    const lines: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      lines.push(msg);
+    });
+    _printProviderMenu(providers);
+    const lastLine = lines[lines.length - 1] ?? "";
+    expect(lastLine).toMatch(/3\)/);
+  });
+
+  test("each provider line contains its label and baseUrl", () => {
+    const lines: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      lines.push(msg);
+    });
+    _printProviderMenu(providers);
+    expect(lines[0]).toContain("OpenAI");
+    expect(lines[0]).toContain("https://api.openai.com/v1");
+    expect(lines[1]).toContain("xAI");
+    expect(lines[1]).toContain("https://api.x.ai/v1");
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 3b. _resolveProviderChoice
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_resolveProviderChoice", () => {
+  const providers = [
+    { name: "openai", label: "OpenAI", baseUrl: "https://api.openai.com/v1" },
+    { name: "xai", label: "xAI", baseUrl: "https://api.x.ai/v1" },
+    { name: "deepseek", label: "DeepSeek", baseUrl: "https://api.deepseek.com/v1" },
+  ] as const;
+
+  test("valid index 1 returns first provider", () => {
+    const result = _resolveProviderChoice("1", providers);
+    expect(result).toEqual({ providerName: "openai", baseUrl: "https://api.openai.com/v1" });
+  });
+
+  test("valid index N (last preset) returns last provider", () => {
+    const result = _resolveProviderChoice("3", providers);
+    expect(result).toEqual({ providerName: "deepseek", baseUrl: "https://api.deepseek.com/v1" });
+  });
+
+  test("index providers.length+1 (custom) returns null", () => {
+    const result = _resolveProviderChoice("4", providers);
+    expect(result).toBeNull();
+  });
+
+  test("non-numeric string returns null", () => {
+    expect(_resolveProviderChoice("abc", providers)).toBeNull();
+  });
+
+  test("0 returns null (out of range)", () => {
+    expect(_resolveProviderChoice("0", providers)).toBeNull();
+  });
+
+  test("N+2 returns null (out of range)", () => {
+    expect(_resolveProviderChoice("5", providers)).toBeNull();
+  });
+
+  test("negative number returns null", () => {
+    expect(_resolveProviderChoice("-1", providers)).toBeNull();
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 3c. _resolveModelChoice
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_resolveModelChoice", () => {
+  test("numeric input within range returns model at that index", () => {
+    expect(_resolveModelChoice("2", ["a", "b", "c"])).toBe("b");
+  });
+
+  test("numeric input out of range returns input as-is", () => {
+    expect(_resolveModelChoice("5", ["a"])).toBe("5");
+  });
+
+  test("non-numeric input returns input as-is", () => {
+    expect(_resolveModelChoice("gpt-4o", ["a", "b"])).toBe("gpt-4o");
+  });
+
+  test("numeric input 1 returns first model", () => {
+    expect(_resolveModelChoice("1", ["alpha", "beta"])).toBe("alpha");
+  });
+
+  test("empty models list with numeric input returns input as-is", () => {
+    expect(_resolveModelChoice("1", [])).toBe("1");
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 3d. _printModelMenu
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_printModelMenu", () => {
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  test("prints all models — each model name appears in output", () => {
+    const output: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      output.push(msg);
+    });
+    const models = ["model-a", "model-b", "model-c"];
+    _printModelMenu(models, 100);
+    const combined = output.join("\n");
+    for (const m of models) {
+      expect(combined).toContain(m);
+    }
+  });
+
+  test("single column when termCols is very small", () => {
+    const output: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      output.push(msg);
+    });
+    _printModelMenu(["a", "b", "c"], 1);
+    // Each model on its own row → 3 lines
+    expect(output.length).toBe(3);
+  });
+
+  test("wide terminal fits multiple columns", () => {
+    const output: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      output.push(msg);
+    });
+    const models = Array.from({ length: 6 }, (_, i) => `m${i}`);
+    _printModelMenu(models, 200);
+    // With wide terminal and short names, should fit in fewer than 6 rows
+    expect(output.length).toBeLessThan(6);
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 3e. _printValidationResult
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_printValidationResult", () => {
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  test("ok=true prints success message containing '✓'", () => {
+    const lines: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      lines.push(msg);
+    });
+    _printValidationResult({ ok: true, error: null });
+    expect(lines.join("\n")).toContain("✓");
+  });
+
+  test("ok=false prints warning message containing '⚠'", () => {
+    const lines: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      lines.push(msg);
+    });
+    _printValidationResult({ ok: false, error: "HTTP 401" });
+    expect(lines.join("\n")).toContain("⚠");
+  });
+
+  test("ok=false includes the error string in output", () => {
+    const lines: string[] = [];
+    vi.spyOn(console, "log").mockImplementation((msg: string) => {
+      lines.push(msg);
+    });
+    _printValidationResult({ ok: false, error: "HTTP 401" });
+    expect(lines.join("\n")).toContain("HTTP 401");
+  });
+});
+
+// ──────────────────────────────────────────────────────────────────────────────
+// 4. Regression
+// ──────────────────────────────────────────────────────────────────────────────
+
+describe("_discoverAgents regression", () => {
+  test("returns an array (may be empty) — never throws", async () => {
+    const result = await _discoverAgents();
+    expect(Array.isArray(result)).toBe(true);
+  });
+});

packages/cli-workflow/src/__tests__/setup-validate.test.ts

@@ -0,0 +1,150 @@
+import { mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterEach, beforeEach, describe, expect, test, vi } from "vitest";
+import { cmdSetup, validateModel } from "../commands/setup.js";
+
+describe("validateModel", () => {
+  const BASE_URL = "https://api.example.com/v1";
+  const API_KEY = "sk-test-key";
+  const MODEL = "test-model";
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  test("success path — returns ok on 200", async () => {
+    const mockFetch = vi
+      .spyOn(globalThis, "fetch")
+      .mockResolvedValue(new Response(JSON.stringify({}), { status: 200 }));
+
+    const result = await validateModel(BASE_URL, API_KEY, MODEL);
+
+    expect(result).toEqual({ ok: true, value: undefined });
+    expect(mockFetch).toHaveBeenCalledOnce();
+
+    const [url, opts] = mockFetch.mock.calls[0]!;
+    expect(url).toBe(`${BASE_URL}/chat/completions`);
+    expect((opts as RequestInit).headers).toEqual(
+      expect.objectContaining({ Authorization: `Bearer ${API_KEY}` }),
+    );
+    const body = JSON.parse((opts as RequestInit).body as string);
+    expect(body).toEqual({
+      model: MODEL,
+      messages: [{ role: "user", content: "hi" }],
+      max_tokens: 1,
+    });
+  });
+
+  test("HTTP 401 — returns error containing 401", async () => {
+    vi.spyOn(globalThis, "fetch").mockResolvedValue(
+      new Response("Unauthorized", { status: 401, statusText: "Unauthorized" }),
+    );
+
+    const result = await validateModel(BASE_URL, API_KEY, MODEL);
+
+    expect(result.ok).toBe(false);
+    if (!result.ok) {
+      expect(result.error).toContain("401");
+    }
+  });
+
+  test("HTTP 404 — returns error containing 404", async () => {
+    vi.spyOn(globalThis, "fetch").mockResolvedValue(
+      new Response("Not Found", { status: 404, statusText: "Not Found" }),
+    );
+
+    const result = await validateModel(BASE_URL, API_KEY, MODEL);
+
+    expect(result.ok).toBe(false);
+    if (!result.ok) {
+      expect(result.error).toContain("404");
+    }
+  });
+
+  test("network timeout — returns error mentioning timeout", async () => {
+    const err = new DOMException("signal timed out", "AbortError");
+    vi.spyOn(globalThis, "fetch").mockRejectedValue(err);
+
+    const result = await validateModel(BASE_URL, API_KEY, MODEL);
+
+    expect(result.ok).toBe(false);
+    if (!result.ok) {
+      expect(result.error.toLowerCase()).toMatch(/timeout|timed out/);
+    }
+  });
+
+  test("network error (DNS/connection) — returns error mentioning connectivity", async () => {
+    vi.spyOn(globalThis, "fetch").mockRejectedValue(new TypeError("fetch failed"));
+
+    const result = await validateModel(BASE_URL, API_KEY, MODEL);
+
+    expect(result.ok).toBe(false);
+    if (!result.ok) {
+      expect(result.error.toLowerCase()).toMatch(/connect|reach|network/);
+    }
+  });
+
+  test("request body correctness", async () => {
+    const mockFetch = vi
+      .spyOn(globalThis, "fetch")
+      .mockResolvedValue(new Response(JSON.stringify({}), { status: 200 }));
+
+    await validateModel(BASE_URL, API_KEY, "my-special-model");
+
+    const body = JSON.parse((mockFetch.mock.calls[0]![1] as RequestInit).body as string);
+    expect(body).toEqual({
+      model: "my-special-model",
+      messages: [{ role: "user", content: "hi" }],
+      max_tokens: 1,
+    });
+  });
+});
+
+describe("cmdSetup with validation", () => {
+  let storageRoot: string;
+
+  beforeEach(async () => {
+    storageRoot = await mkdtemp(join(tmpdir(), "uwf-setup-validate-"));
+  });
+
+  afterEach(async () => {
+    vi.restoreAllMocks();
+    await rm(storageRoot, { recursive: true, force: true });
+  });
+
+  const setupArgs = () => ({
+    provider: "testprovider",
+    baseUrl: "https://api.test.com/v1",
+    apiKey: "sk-test",
+    model: "test-model",
+    storageRoot,
+  });
+
+  test("includes validation result on success", async () => {
+    vi.spyOn(globalThis, "fetch").mockResolvedValue(
+      new Response(JSON.stringify({}), { status: 200 }),
+    );
+
+    const result = await cmdSetup(setupArgs());
+
+    expect(result.validation).toEqual({ ok: true, value: undefined });
+    // Config files should still be written
+    expect(result.configPath).toBeTruthy();
+    expect(result.envPath).toBeTruthy();
+  });
+
+  test("includes validation failure — config still saved", async () => {
+    vi.spyOn(globalThis, "fetch").mockResolvedValue(
+      new Response("Unauthorized", { status: 401, statusText: "Unauthorized" }),
+    );
+
+    const result = await cmdSetup(setupArgs());
+
+    expect(result.validation).toBeDefined();
+    expect((result.validation as { ok: boolean }).ok).toBe(false);
+    // Config files should still be written despite validation failure
+    expect(result.configPath).toBeTruthy();
+    expect(result.envPath).toBeTruthy();
+  });
+});

packages/cli-workflow/src/__tests__/solve-issue-tea-worktree.test.ts

@@ -0,0 +1,98 @@
+import { readFile } from "node:fs/promises";
+import { join } from "node:path";
+import type { WorkflowPayload } from "@uncaged/workflow-protocol";
+import { describe, expect, test } from "vitest";
+import { parse } from "yaml";
+
+/**
+ * Test: Issue #474 - tea pr create fails in git worktree directories
+ *
+ * This test verifies that the solve-issue workflow's committer role
+ * includes the --repo flag when running tea pr create, which fixes
+ * the "path segment [0] is empty" error in worktree directories.
+ */
+
+describe("solve-issue workflow: tea pr create worktree fix", () => {
+  // Navigate up from packages/cli-workflow to repo root
+  const workflowPath = join(process.cwd(), "..", "..", ".workflows", "solve-issue.yaml");
+
+  test("committer procedure should include --repo flag in tea pr create command", async () => {
+    const yamlContent = await readFile(workflowPath, "utf-8");
+    const workflow = parse(yamlContent) as WorkflowPayload;
+
+    expect(workflow.roles.committer).toBeDefined();
+    const committerProcedure = workflow.roles.committer?.procedure;
+    expect(committerProcedure).toBeDefined();
+
+    // Verify the procedure includes tea pr create with --repo flag
+    expect(committerProcedure).toContain("tea pr create");
+    expect(committerProcedure).toContain("--repo");
+
+    // Verify the --repo flag appears before or together with tea pr create
+    // This ensures the command is: tea pr create --repo <owner/repo> ...
+    const teaPrCreateMatch = committerProcedure?.match(/tea pr create[^\n]*/);
+    expect(teaPrCreateMatch).not.toBeNull();
+
+    if (teaPrCreateMatch) {
+      const teaCommandLine = teaPrCreateMatch[0];
+      expect(teaCommandLine).toContain("--repo");
+    }
+  });
+
+  test("committer procedure should mention repo extraction from git remote", async () => {
+    const yamlContent = await readFile(workflowPath, "utf-8");
+    const workflow = parse(yamlContent) as WorkflowPayload;
+
+    const committerProcedure = workflow.roles.committer?.procedure;
+    expect(committerProcedure).toBeDefined();
+
+    // Verify the procedure mentions extracting repo info from git remote
+    // This ensures fallback logic is documented
+    expect(committerProcedure).toMatch(/git remote/i);
+  });
+
+  test("committer procedure should include error handling for tea failures", async () => {
+    const yamlContent = await readFile(workflowPath, "utf-8");
+    const workflow = parse(yamlContent) as WorkflowPayload;
+
+    const committerProcedure = workflow.roles.committer?.procedure;
+    expect(committerProcedure).toBeDefined();
+
+    // Verify the procedure includes error handling guidance
+    // This ensures we capture failures and provide actionable output
+    expect(committerProcedure).toMatch(/error|fail/i);
+  });
+
+  test("workflow should be parseable as valid WorkflowPayload", async () => {
+    const yamlContent = await readFile(workflowPath, "utf-8");
+    const workflow = parse(yamlContent) as WorkflowPayload;
+
+    // Basic structure validation
+    expect(workflow.name).toBe("solve-issue");
+    expect(workflow.roles).toBeDefined();
+    expect(workflow.conditions).toBeDefined();
+    expect(workflow.graph).toBeDefined();
+
+    // Verify committer role exists with required fields
+    expect(workflow.roles.committer).toBeDefined();
+    expect(workflow.roles.committer?.description).toBeDefined();
+    expect(workflow.roles.committer?.goal).toBeDefined();
+    expect(workflow.roles.committer?.procedure).toBeDefined();
+    expect(workflow.roles.committer?.output).toBeDefined();
+    expect(workflow.roles.committer?.frontmatter).toBeDefined();
+  });
+
+  test("committer frontmatter schema should require success field", async () => {
+    const yamlContent = await readFile(workflowPath, "utf-8");
+    // Parse as any to access the raw YAML structure (frontmatter is inline JSON Schema in YAML)
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    const workflow = parse(yamlContent) as any;
+
+    const frontmatter = workflow.roles.committer?.frontmatter;
+    expect(frontmatter).toBeDefined();
+    expect(frontmatter?.type).toBe("object");
+    expect(frontmatter?.properties?.success).toBeDefined();
+    expect(frontmatter?.properties?.success?.type).toBe("boolean");
+    expect(frontmatter?.required).toContain("success");
+  });
+});

packages/cli-workflow/src/__tests__/step-read.test.ts

@@ -0,0 +1,519 @@
+import { mkdir, mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { bootstrap, putSchema } from "@uncaged/json-cas";
+import { createFsStore } from "@uncaged/json-cas-fs";
+import type { CasRef } from "@uncaged/workflow-protocol";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { cmdStepRead } from "../commands/step.js";
+import { registerUwfSchemas } from "../schemas.js";
+
+// ── schemas used in tests ────────────────────────────────────────────────────
+
+const TURN_SCHEMA = {
+  title: "hermes-turn",
+  type: "object" as const,
+  required: ["index", "role", "content"],
+  properties: {
+    index: { type: "integer" as const },
+    role: { type: "string" as const },
+    content: { type: "string" as const },
+    toolCalls: {
+      anyOf: [
+        { type: "array" as const, items: { type: "object" as const } },
+        { type: "null" as const },
+      ],
+    },
+    reasoning: { anyOf: [{ type: "string" as const }, { type: "null" as const }] },
+  },
+  additionalProperties: false,
+};
+
+const DETAIL_SCHEMA = {
+  title: "hermes-detail",
+  type: "object" as const,
+  required: ["sessionId", "model", "duration", "turnCount", "turns"],
+  properties: {
+    sessionId: { type: "string" as const },
+    model: { type: "string" as const },
+    duration: { type: "integer" as const },
+    turnCount: { type: "integer" as const },
+    turns: {
+      type: "array" as const,
+      items: { type: "string" as const, format: "cas_ref" },
+    },
+  },
+  additionalProperties: false,
+};
+
+// ── helpers ───────────────────────────────────────────────────────────────────
+
+async function registerDetailSchemas(store: ReturnType<typeof createFsStore>) {
+  await bootstrap(store);
+  const [turn, detail] = await Promise.all([
+    putSchema(store, TURN_SCHEMA),
+    putSchema(store, DETAIL_SCHEMA),
+  ]);
+  return { turn, detail };
+}
+
+function generateContent(size: number, prefix = "Content"): string {
+  const base = `${prefix} `;
+  const repeat = Math.ceil(size / base.length);
+  return base.repeat(repeat).slice(0, size);
+}
+
+// ── fixture ───────────────────────────────────────────────────────────────────
+
+let tmpDir: string;
+
+beforeEach(async () => {
+  tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-step-read-test-"));
+});
+
+afterEach(async () => {
+  await rm(tmpDir, { recursive: true, force: true });
+});
+
+// ── step read tests ───────────────────────────────────────────────────────────
+
+describe("step read", () => {
+  test("test 1: basic single-step read with 3 turns", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 3 turns
+    const turnHashes: CasRef[] = [];
+    for (let i = 1; i <= 3; i++) {
+      const content = `Turn ${i} content with some text to make it readable.`;
+      const turnHash = await store.put(detailSchemas.turn, {
+        index: i - 1,
+        role: "assistant",
+        content,
+        toolCalls: null,
+        reasoning: null,
+      });
+      turnHashes.push(turnHash);
+    }
+
+    const detailHash = await store.put(detailSchemas.detail, {
+      sessionId: "session-1",
+      model: "test-model",
+      duration: 1000,
+      turnCount: 3,
+      turns: turnHashes,
+    });
+
+    const stepHash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-test",
+    });
+
+    // Read step with large quota
+    const markdown = await cmdStepRead(tmpDir, stepHash, 10000);
+
+    // Assert structure
+    expect(markdown).toContain(`# Step ${stepHash}`);
+    expect(markdown).toContain("**Role:** worker");
+    expect(markdown).toContain("**Agent:** uwf-test");
+    expect(markdown).toContain("## Turn 1");
+    expect(markdown).toContain("## Turn 2");
+    expect(markdown).toContain("## Turn 3");
+    expect(markdown).toContain("Turn 1 content with some text to make it readable.");
+    expect(markdown).toContain("Turn 2 content with some text to make it readable.");
+    expect(markdown).toContain("Turn 3 content with some text to make it readable.");
+  });
+
+  test("test 2: quota enforcement - multiple turns", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 4 turns of ~300 chars each
+    const turnHashes: CasRef[] = [];
+    for (let i = 1; i <= 4; i++) {
+      const content = generateContent(300, `Turn${i}`);
+      const turnHash = await store.put(detailSchemas.turn, {
+        index: i - 1,
+        role: "assistant",
+        content,
+        toolCalls: null,
+        reasoning: null,
+      });
+      turnHashes.push(turnHash);
+    }
+
+    const detailHash = await store.put(detailSchemas.detail, {
+      sessionId: "session-1",
+      model: "test-model",
+      duration: 1000,
+      turnCount: 4,
+      turns: turnHashes,
+    });
+
+    const stepHash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-test",
+    });
+
+    // Read step with limited quota (700 chars)
+    const markdown = await cmdStepRead(tmpDir, stepHash, 700);
+
+    // Assert only most recent turns fit
+    expect(markdown).toContain(`# Step ${stepHash}`);
+    // Should have skip hint
+    expect(markdown).toContain("Earlier turns omitted");
+    // Should include at least Turn 4 (most recent)
+    expect(markdown).toContain("Turn4");
+    // Total length should respect quota (with tolerance for structural overhead)
+    expect(markdown.length).toBeLessThanOrEqual(900); // 700 quota + 200 buffer tolerance
+  });
+
+  test("test 3: minimal quota edge case - always show at least one turn", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 1 turn of 500 chars
+    const content = generateContent(500, "LongTurn");
+    const turnHash = await store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content,
+      toolCalls: null,
+      reasoning: null,
+    });
+
+    const detailHash = await store.put(detailSchemas.detail, {
+      sessionId: "session-1",
+      model: "test-model",
+      duration: 1000,
+      turnCount: 1,
+      turns: [turnHash],
+    });
+
+    const stepHash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-test",
+    });
+
+    // Read step with minimal quota (1 char)
+    const markdown = await cmdStepRead(tmpDir, stepHash, 1);
+
+    // Assert at least one turn is always shown
+    expect(markdown).toContain("LongTurn");
+    expect(markdown.length).toBeGreaterThan(1);
+  });
+
+  test("test 4: step with no detail field", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const stepHash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    // Read step - should return metadata only (no error)
+    const markdown = await cmdStepRead(tmpDir, stepHash, 4000);
+
+    // Assert metadata is present
+    expect(markdown).toContain(`# Step ${stepHash}`);
+    expect(markdown).toContain("**Role:** worker");
+    expect(markdown).toContain("**Agent:** uwf-test");
+    // Should not have turn sections
+    expect(markdown).not.toContain("## Turn");
+  });
+
+  test("test 5: step with detail but no turns array", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create detail with different schema (no turns)
+    const SIMPLE_DETAIL_SCHEMA = {
+      title: "simple-detail",
+      type: "object" as const,
+      required: ["sessionId"],
+      properties: {
+        sessionId: { type: "string" as const },
+      },
+      additionalProperties: false,
+    };
+
+    await bootstrap(store);
+    const simpleDetailType = await putSchema(store, SIMPLE_DETAIL_SCHEMA);
+    const detailHash = await store.put(simpleDetailType, {
+      sessionId: "session-1",
+    });
+
+    const stepHash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-test",
+    });
+
+    // Read step - should return metadata only (no error)
+    const markdown = await cmdStepRead(tmpDir, stepHash, 4000);
+
+    // Assert metadata is present
+    expect(markdown).toContain(`# Step ${stepHash}`);
+    expect(markdown).toContain("**Role:** worker");
+    // Should not have turn sections
+    expect(markdown).not.toContain("## Turn");
+  });
+
+  test("test 6: turn content with special characters", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create turn with special markdown characters
+    const content = "This has `backticks`, **bold**, *italic*, and [links](http://example.com)";
+    const turnHash = await store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content,
+      toolCalls: null,
+      reasoning: null,
+    });
+
+    const detailHash = await store.put(detailSchemas.detail, {
+      sessionId: "session-1",
+      model: "test-model",
+      duration: 1000,
+      turnCount: 1,
+      turns: [turnHash],
+    });
+
+    const stepHash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-test",
+    });
+
+    // Read step
+    const markdown = await cmdStepRead(tmpDir, stepHash, 4000);
+
+    // Assert content is rendered correctly without corruption
+    expect(markdown).toContain("`backticks`");
+    expect(markdown).toContain("**bold**");
+    expect(markdown).toContain("*italic*");
+    expect(markdown).toContain("[links](http://example.com)");
+  });
+});

packages/cli-workflow/src/__tests__/thread-list-filters.test.ts

@@ -0,0 +1,550 @@
+import { mkdir, mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
+import { extractUlidTimestamp, generateUlid } from "@uncaged/workflow-util";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { createMarker, deleteMarker } from "../background/index.js";
+import { cmdThreadList } from "../commands/thread.js";
+import { parseTimeInput } from "../commands/thread-time-parser.js";
+import type { UwfStore } from "../store.js";
+import { appendThreadHistory, createUwfStore, saveThreadsIndex } from "../store.js";
+
+// ── helpers ───────────────────────────────────────────────────────────────────
+
+async function makeUwfStore(storageRoot: string): Promise<UwfStore> {
+  const casDir = join(storageRoot, "cas");
+  await mkdir(casDir, { recursive: true });
+  return createUwfStore(storageRoot);
+}
+
+async function createTestWorkflow(uwf: UwfStore): Promise<CasRef> {
+  const workflowPayload = {
+    name: "test-workflow",
+    roles: {
+      role1: {
+        goal: "test goal",
+        outputSchema: { type: "object" as const, properties: {} },
+      },
+    },
+    graph: { start: "role1" },
+    conditions: {},
+  };
+  return await uwf.store.put(uwf.schemas.workflow, workflowPayload);
+}
+
+async function createTestThread(
+  uwf: UwfStore,
+  storageRoot: string,
+  workflowHash: CasRef,
+  timestamp: number,
+): Promise<ThreadId> {
+  const threadId = generateUlid(timestamp) as ThreadId;
+  const startPayload = {
+    workflow: workflowHash,
+    prompt: "test prompt",
+  };
+  const headHash = await uwf.store.put(uwf.schemas.startNode, startPayload);
+  const index = await import("../store.js").then((m) => m.loadThreadsIndex(storageRoot));
+  index[threadId] = headHash;
+  await saveThreadsIndex(storageRoot, index);
+  return threadId;
+}
+
+async function markThreadRunning(storageRoot: string, threadId: ThreadId, workflow: CasRef) {
+  await createMarker(storageRoot, {
+    thread: threadId,
+    workflow,
+    pid: process.pid, // Use current process PID so isPidAlive returns true
+    startedAt: Date.now(),
+  });
+}
+
+async function completeThread(
+  storageRoot: string,
+  threadId: ThreadId,
+  workflowHash: CasRef,
+  headHash: CasRef,
+) {
+  const index = await import("../store.js").then((m) => m.loadThreadsIndex(storageRoot));
+  delete index[threadId];
+  await saveThreadsIndex(storageRoot, index);
+  await appendThreadHistory(storageRoot, {
+    thread: threadId,
+    workflow: workflowHash,
+    head: headHash,
+    completedAt: Date.now(),
+  });
+}
+
+// ── test setup ────────────────────────────────────────────────────────────────
+
+let tmpDir: string;
+
+beforeEach(async () => {
+  tmpDir = await mkdtemp(join(tmpdir(), "thread-list-filters-test-"));
+});
+
+afterEach(async () => {
+  await rm(tmpDir, { recursive: true, force: true });
+});
+
+// ── status filter tests ───────────────────────────────────────────────────────
+
+describe("cmdThreadList status filter", () => {
+  test("should return idle and running threads when status=active", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const thread1 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 3000);
+    const thread2 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 2000);
+    const thread3 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 1000);
+
+    await markThreadRunning(tmpDir, thread2, workflowHash);
+
+    const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+    const thread3Head = index[thread3];
+    if (thread3Head === undefined) throw new Error("thread3 head not found");
+    await completeThread(tmpDir, thread3, workflowHash, thread3Head);
+
+    const result = await cmdThreadList(tmpDir, ["idle", "running"], null, null, null, null);
+
+    expect(result).toHaveLength(2);
+    expect(result.map((r) => r.thread).sort()).toEqual([thread1, thread2].sort());
+
+    // Clean up marker after test
+    await deleteMarker(tmpDir, thread2);
+  });
+
+  test("should support comma-separated status values", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const thread1 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 3000);
+    const thread2 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 2000);
+    const thread3 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 1000);
+
+    await markThreadRunning(tmpDir, thread2, workflowHash);
+
+    const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+    const thread3Head = index[thread3];
+    if (thread3Head === undefined) throw new Error("thread3 head not found");
+    await completeThread(tmpDir, thread3, workflowHash, thread3Head);
+
+    const result = await cmdThreadList(tmpDir, ["idle", "completed"], null, null, null, null);
+
+    // Clean up marker
+    await deleteMarker(tmpDir, thread2);
+
+    // thread2 is running (not idle), so should not be included
+    // Expected: thread1 (idle) and thread3 (completed)
+    expect(result).toHaveLength(2);
+    expect(result.map((r) => r.thread).sort()).toEqual([thread1, thread3].sort());
+  });
+
+  test("should support single status filter (backward compat)", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const _thread1 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 3000);
+    const _thread2 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 2000);
+    const thread3 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 1000);
+
+    const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+    const thread3Head = index[thread3];
+    if (thread3Head === undefined) throw new Error("thread3 head not found");
+    await completeThread(tmpDir, thread3, workflowHash, thread3Head);
+
+    const result = await cmdThreadList(tmpDir, ["completed"], null, null, null, null);
+
+    expect(result).toHaveLength(1);
+    expect(result[0]?.thread).toBe(thread3);
+    expect(result[0]?.status).toBe("completed");
+  });
+
+  test("should return all threads when no status filter provided", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const thread1 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 3000);
+    const thread2 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 2000);
+    const thread3 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 1000);
+
+    await markThreadRunning(tmpDir, thread2, workflowHash);
+
+    const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+    const thread3Head = index[thread3];
+    if (thread3Head === undefined) throw new Error("thread3 head not found");
+    await completeThread(tmpDir, thread3, workflowHash, thread3Head);
+
+    const result = await cmdThreadList(tmpDir, null, null, null, null, null);
+
+    expect(result).toHaveLength(3);
+    expect(result.map((r) => r.thread).sort()).toEqual([thread1, thread2, thread3].sort());
+  });
+});
+
+// ── time range filtering tests ────────────────────────────────────────────────
+
+describe("cmdThreadList time filters", () => {
+  test("should filter threads created after given timestamp", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const ts1 = Date.UTC(2026, 4, 20, 0, 0, 0);
+    const ts2 = Date.UTC(2026, 4, 21, 0, 0, 0);
+    const ts3 = Date.UTC(2026, 4, 22, 0, 0, 0);
+
+    const _threadA = await createTestThread(uwf, tmpDir, workflowHash, ts1);
+    const threadB = await createTestThread(uwf, tmpDir, workflowHash, ts2);
+    const threadC = await createTestThread(uwf, tmpDir, workflowHash, ts3);
+
+    // Use a timestamp slightly before ts2 to include threadB
+    const afterMs = Date.UTC(2026, 4, 20, 12, 0, 0);
+    const result = await cmdThreadList(tmpDir, null, afterMs, null, null, null);
+
+    expect(result).toHaveLength(2);
+    expect(result.map((r) => r.thread).sort()).toEqual([threadB, threadC].sort());
+  });
+
+  test("should filter threads created before given timestamp", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const ts1 = Date.UTC(2026, 4, 20, 0, 0, 0);
+    const ts2 = Date.UTC(2026, 4, 21, 0, 0, 0);
+    const ts3 = Date.UTC(2026, 4, 22, 0, 0, 0);
+
+    const threadA = await createTestThread(uwf, tmpDir, workflowHash, ts1);
+    const threadB = await createTestThread(uwf, tmpDir, workflowHash, ts2);
+    const _threadC = await createTestThread(uwf, tmpDir, workflowHash, ts3);
+
+    const beforeMs = Date.UTC(2026, 4, 22, 0, 0, 0);
+    const result = await cmdThreadList(tmpDir, null, null, beforeMs, null, null);
+
+    expect(result).toHaveLength(2);
+    expect(result.map((r) => r.thread).sort()).toEqual([threadA, threadB].sort());
+  });
+
+  test("should support both after and before filters (time range)", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const ts1 = Date.UTC(2026, 4, 20, 0, 0, 0);
+    const ts2 = Date.UTC(2026, 4, 21, 0, 0, 0);
+    const ts3 = Date.UTC(2026, 4, 22, 0, 0, 0);
+
+    const _threadA = await createTestThread(uwf, tmpDir, workflowHash, ts1);
+    const threadB = await createTestThread(uwf, tmpDir, workflowHash, ts2);
+    const _threadC = await createTestThread(uwf, tmpDir, workflowHash, ts3);
+
+    const afterMs = Date.UTC(2026, 4, 20, 12, 0, 0);
+    const beforeMs = Date.UTC(2026, 4, 22, 0, 0, 0);
+    const result = await cmdThreadList(tmpDir, null, afterMs, beforeMs, null, null);
+
+    expect(result).toHaveLength(1);
+    expect(result[0]?.thread).toBe(threadB);
+  });
+});
+
+// ── pagination tests ──────────────────────────────────────────────────────────
+
+describe("cmdThreadList pagination", () => {
+  test("should limit results with --take", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const threads: ThreadId[] = [];
+    for (let i = 0; i < 10; i++) {
+      threads.push(await createTestThread(uwf, tmpDir, workflowHash, Date.now() - i * 1000));
+    }
+
+    const result = await cmdThreadList(tmpDir, null, null, null, null, 5);
+
+    expect(result).toHaveLength(5);
+  });
+
+  test("should skip first N threads with --skip", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const threads: ThreadId[] = [];
+    // Create threads in chronological order, but they'll be sorted newest first
+    for (let i = 0; i < 10; i++) {
+      threads.push(await createTestThread(uwf, tmpDir, workflowHash, Date.now() + i * 100));
+      // Small delay to ensure distinct timestamps
+      await new Promise((resolve) => setTimeout(resolve, 10));
+    }
+
+    const result = await cmdThreadList(tmpDir, null, null, null, 3, null);
+
+    expect(result).toHaveLength(7);
+    // The 3 newest threads should be skipped, so we should get the 7 oldest
+  });
+
+  test("should support skip + take for pagination", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const threads: ThreadId[] = [];
+    for (let i = 0; i < 10; i++) {
+      threads.push(await createTestThread(uwf, tmpDir, workflowHash, Date.now() + i * 100));
+      await new Promise((resolve) => setTimeout(resolve, 10));
+    }
+
+    const result = await cmdThreadList(tmpDir, null, null, null, 5, 3);
+
+    expect(result).toHaveLength(3);
+    // Should skip first 5 (newest), then take 3
+  });
+
+  test("should handle take > available threads", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const _thread1 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 3000);
+    const _thread2 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 2000);
+    const _thread3 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 1000);
+
+    const result = await cmdThreadList(tmpDir, null, null, null, null, 10);
+
+    expect(result).toHaveLength(3);
+  });
+
+  test("should return empty array when skip >= thread count", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 3000);
+    await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 2000);
+    await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 1000);
+
+    const result = await cmdThreadList(tmpDir, null, null, null, 5, null);
+
+    expect(result).toHaveLength(0);
+  });
+});
+
+// ── combined filters tests ────────────────────────────────────────────────────
+
+describe("combined filters", () => {
+  test("should combine status and time range filters", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const ts1 = Date.UTC(2026, 4, 20, 0, 0, 0);
+    const ts2 = Date.UTC(2026, 4, 21, 0, 0, 0);
+    const ts3 = Date.UTC(2026, 4, 22, 0, 0, 0);
+    const ts4 = Date.UTC(2026, 4, 23, 0, 0, 0);
+
+    const _thread1 = await createTestThread(uwf, tmpDir, workflowHash, ts1);
+    const thread2 = await createTestThread(uwf, tmpDir, workflowHash, ts2);
+    const thread3 = await createTestThread(uwf, tmpDir, workflowHash, ts3);
+    const thread4 = await createTestThread(uwf, tmpDir, workflowHash, ts4);
+
+    await markThreadRunning(tmpDir, thread2, workflowHash);
+
+    const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+    const thread3Head = index[thread3];
+    if (thread3Head === undefined) throw new Error("thread3 head not found");
+    await completeThread(tmpDir, thread3, workflowHash, thread3Head);
+
+    const afterMs = Date.UTC(2026, 4, 20, 12, 0, 0);
+    const result = await cmdThreadList(tmpDir, ["idle"], afterMs, null, null, null);
+
+    expect(result).toHaveLength(1);
+    expect(result[0]?.thread).toBe(thread4);
+    expect(result[0]?.status).toBe("idle");
+
+    // Clean up marker
+    await deleteMarker(tmpDir, thread2);
+  });
+
+  test("should combine status filter and pagination", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const threads: ThreadId[] = [];
+    for (let i = 9; i >= 0; i--) {
+      const thread = await createTestThread(uwf, tmpDir, workflowHash, Date.now() + i * 1000);
+      threads.push(thread);
+      const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+      const headHash = index[thread];
+      if (headHash === undefined) throw new Error("head not found");
+      await completeThread(tmpDir, thread, workflowHash, headHash);
+    }
+
+    const result = await cmdThreadList(tmpDir, ["completed"], null, null, 3, 5);
+
+    expect(result).toHaveLength(5);
+    for (const r of result) {
+      expect(r.status).toBe("completed");
+    }
+  });
+
+  test("should combine time range and pagination", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const threads: ThreadId[] = [];
+    for (let i = 0; i < 20; i++) {
+      const ts = Date.UTC(2026, 4, 1 + i, 0, 0, 0);
+      threads.push(await createTestThread(uwf, tmpDir, workflowHash, ts));
+    }
+
+    const afterMs = Date.UTC(2026, 4, 10, 0, 0, 0);
+    const result = await cmdThreadList(tmpDir, null, afterMs, null, 2, 5);
+
+    expect(result).toHaveLength(5);
+    for (const r of result) {
+      const ts = extractUlidTimestamp(r.thread);
+      expect(ts).not.toBeNull();
+      if (ts !== null) {
+        expect(ts).toBeGreaterThan(afterMs);
+      }
+    }
+  });
+
+  async function setupMixedStatusThreads(
+    uwf: UwfStore,
+    workflowHash: string,
+    count: number,
+  ): Promise<ThreadId[]> {
+    const threads: ThreadId[] = [];
+    for (let i = 0; i < count; i++) {
+      const ts = Date.UTC(2026, 4, 10 + i, 0, 0, 0);
+      const thread = await createTestThread(uwf, tmpDir, workflowHash, ts);
+      threads.push(thread);
+
+      if (i % 2 === 0) {
+        const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+        const headHash = index[thread];
+        if (headHash === undefined) throw new Error("head not found");
+        await completeThread(tmpDir, thread, workflowHash, headHash);
+      } else {
+        await markThreadRunning(tmpDir, thread, workflowHash);
+      }
+    }
+    return threads;
+  }
+
+  async function cleanupRunningMarkers(threads: ThreadId[]): Promise<void> {
+    for (let i = 0; i < threads.length; i++) {
+      if (i % 2 !== 0) {
+        await deleteMarker(tmpDir, threads[i] as ThreadId);
+      }
+    }
+  }
+
+  test("should combine all filters (status + time + pagination)", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+    const threads = await setupMixedStatusThreads(uwf, workflowHash, 15);
+
+    const afterMs = Date.UTC(2026, 4, 14, 12, 0, 0);
+    const beforeMs = Date.UTC(2026, 4, 20, 0, 0, 0);
+    const result = await cmdThreadList(tmpDir, ["idle", "running"], afterMs, beforeMs, 1, 3);
+
+    expect(result.length).toBeLessThanOrEqual(3);
+    for (const r of result) {
+      expect(["idle", "running"]).toContain(r.status);
+      const ts = extractUlidTimestamp(r.thread);
+      if (ts !== null) {
+        expect(ts).toBeGreaterThan(afterMs);
+        expect(ts).toBeLessThan(beforeMs);
+      }
+    }
+
+    await cleanupRunningMarkers(threads);
+  });
+});
+
+// ── edge cases tests ──────────────────────────────────────────────────────────
+
+describe("edge cases", () => {
+  test("should handle empty thread list", async () => {
+    await makeUwfStore(tmpDir);
+    const result = await cmdThreadList(tmpDir, null, null, null, null, null);
+    expect(result).toHaveLength(0);
+  });
+
+  test("should skip threads with invalid ULID when time filtering", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const workflowHash = await createTestWorkflow(uwf);
+
+    const thread1 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 2000);
+    const thread2 = await createTestThread(uwf, tmpDir, workflowHash, Date.now() - 1000);
+
+    const index = await import("../store.js").then((m) => m.loadThreadsIndex(tmpDir));
+    index["INVALID_ULID_FORMAT_HERE" as ThreadId] = "01J6HMVRNQKJV2";
+    await saveThreadsIndex(tmpDir, index);
+
+    const afterMs = Date.now() - 3000;
+    const result = await cmdThreadList(tmpDir, null, afterMs, null, null, null);
+
+    expect(result).toHaveLength(2);
+    expect(result.map((r) => r.thread).sort()).toEqual([thread1, thread2].sort());
+  });
+});
+
+// ── time parsing tests ────────────────────────────────────────────────────────
+
+describe("relative time parsing", () => {
+  test("should parse '7d' as 7 days ago", () => {
+    const nowMs = Date.UTC(2026, 4, 24, 12, 0, 0);
+    const result = parseTimeInput("7d", nowMs);
+    const expected = Date.UTC(2026, 4, 17, 12, 0, 0);
+    expect(result).toBe(expected);
+  });
+
+  test("should parse '24h' as 24 hours ago", () => {
+    const nowMs = Date.UTC(2026, 4, 24, 12, 0, 0);
+    const result = parseTimeInput("24h", nowMs);
+    const expected = Date.UTC(2026, 4, 23, 12, 0, 0);
+    expect(result).toBe(expected);
+  });
+
+  test("should parse '30m' as 30 minutes ago", () => {
+    const nowMs = Date.UTC(2026, 4, 24, 12, 30, 0);
+    const result = parseTimeInput("30m", nowMs);
+    const expected = Date.UTC(2026, 4, 24, 12, 0, 0);
+    expect(result).toBe(expected);
+  });
+
+  test("should parse '1d' as 1 day ago", () => {
+    const nowMs = Date.UTC(2026, 4, 24, 0, 0, 0);
+    const result = parseTimeInput("1d", nowMs);
+    const expected = Date.UTC(2026, 4, 23, 0, 0, 0);
+    expect(result).toBe(expected);
+  });
+});
+
+describe("ISO date parsing", () => {
+  test("should parse ISO date (YYYY-MM-DD)", () => {
+    const nowMs = Date.now();
+    const result = parseTimeInput("2026-05-20", nowMs);
+    const expected = Date.UTC(2026, 4, 20, 0, 0, 0);
+    expect(result).toBe(expected);
+  });
+
+  test("should parse ISO datetime (YYYY-MM-DDTHH:MM:SS)", () => {
+    const nowMs = Date.now();
+    const result = parseTimeInput("2026-05-20T14:30:00", nowMs);
+    const expected = Date.parse("2026-05-20T14:30:00");
+    expect(result).toBe(expected);
+  });
+
+  test("should parse ISO datetime with Z suffix", () => {
+    const nowMs = Date.now();
+    const result = parseTimeInput("2026-05-20T14:30:00Z", nowMs);
+    const expected = Date.UTC(2026, 4, 20, 14, 30, 0);
+    expect(result).toBe(expected);
+  });
+
+  test("should reject invalid date formats", () => {
+    const nowMs = Date.now();
+    expect(() => parseTimeInput("not-a-date", nowMs)).toThrow();
+    expect(() => parseTimeInput("2026-13-01", nowMs)).toThrow();
+    expect(() => parseTimeInput("invalid", nowMs)).toThrow();
+  });
+});

packages/cli-workflow/src/__tests__/thread-read-quota.test.ts

@@ -0,0 +1,583 @@
+import { mkdir, mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { bootstrap, putSchema } from "@uncaged/json-cas";
+import { createFsStore } from "@uncaged/json-cas-fs";
+import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { cmdThreadRead } from "../commands/thread.js";
+import { registerUwfSchemas } from "../schemas.js";
+import { saveThreadsIndex } from "../store.js";
+
+// ── schemas used in tests ────────────────────────────────────────────────────
+
+const TURN_SCHEMA = {
+  title: "hermes-turn",
+  type: "object" as const,
+  required: ["index", "role", "content"],
+  properties: {
+    index: { type: "integer" as const },
+    role: { type: "string" as const },
+    content: { type: "string" as const },
+    toolCalls: {
+      anyOf: [
+        { type: "array" as const, items: { type: "object" as const } },
+        { type: "null" as const },
+      ],
+    },
+    reasoning: { anyOf: [{ type: "string" as const }, { type: "null" as const }] },
+  },
+  additionalProperties: false,
+};
+
+const DETAIL_SCHEMA = {
+  title: "hermes-detail",
+  type: "object" as const,
+  required: ["sessionId", "model", "duration", "turnCount", "turns"],
+  properties: {
+    sessionId: { type: "string" as const },
+    model: { type: "string" as const },
+    duration: { type: "integer" as const },
+    turnCount: { type: "integer" as const },
+    turns: {
+      type: "array" as const,
+      items: { type: "string" as const, format: "cas_ref" },
+    },
+  },
+  additionalProperties: false,
+};
+
+// ── helpers ───────────────────────────────────────────────────────────────────
+
+async function registerDetailSchemas(store: ReturnType<typeof createFsStore>) {
+  await bootstrap(store);
+  const [turn, detail] = await Promise.all([
+    putSchema(store, TURN_SCHEMA),
+    putSchema(store, DETAIL_SCHEMA),
+  ]);
+  return { turn, detail };
+}
+
+function generateContent(size: number, prefix = "Content"): string {
+  const base = `${prefix} `;
+  const repeat = Math.ceil(size / base.length);
+  return base.repeat(repeat).slice(0, size);
+}
+
+// ── fixture ───────────────────────────────────────────────────────────────────
+
+let tmpDir: string;
+
+beforeEach(async () => {
+  tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-quota-test-"));
+});
+
+afterEach(async () => {
+  await rm(tmpDir, { recursive: true, force: true });
+});
+
+// ── thread read quota enforcement ─────────────────────────────────────────────
+
+describe("thread read --quota flag", () => {
+  test("test 1: basic quota enforcement with 3 steps", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 3 steps with ~500 chars each
+    const steps: CasRef[] = [];
+    for (let i = 1; i <= 3; i++) {
+      const content = generateContent(500, `Step${i}`);
+      const turnHash = await store.put(detailSchemas.turn, {
+        index: 0,
+        role: "assistant",
+        content,
+        toolCalls: null,
+        reasoning: null,
+      });
+      const detailHash = await store.put(detailSchemas.detail, {
+        sessionId: `session-${i}`,
+        model: "test-model",
+        duration: 1000,
+        turnCount: 1,
+        turns: [turnHash],
+      });
+      const stepHash = await store.put(schemas.stepNode, {
+        start: startHash,
+        prev: steps[i - 2] ?? null,
+        role: "worker",
+        output: outputHash,
+        detail: detailHash,
+        agent: "uwf-test",
+      });
+      steps.push(stepHash);
+    }
+
+    const threadId = "01HX2Q3R4S5T6V7W8X9YZ0" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: steps[2] as CasRef });
+
+    // Set quota to 800 chars - should only fit most recent steps
+    const markdown = await cmdThreadRead(tmpDir, threadId, 800, null, false);
+
+    // Quota must be reasonably enforced (allow ~200 char tolerance for skip hint)
+    expect(markdown.length).toBeLessThanOrEqual(1000);
+
+    // Should contain skip hint since not all steps fit
+    expect(markdown).toMatch(/earlier step/);
+
+    // Most recent step should be included
+    expect(markdown).toMatch(/Step3/);
+  });
+
+  test("test 2: quota check order - verifies bug is fixed", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 2 steps: first=300 chars, second=600 chars
+    const step1Content = generateContent(300, "First");
+    const step1TurnHash = await store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content: step1Content,
+      toolCalls: null,
+      reasoning: null,
+    });
+    const step1DetailHash = await store.put(detailSchemas.detail, {
+      sessionId: "session-1",
+      model: "test-model",
+      duration: 1000,
+      turnCount: 1,
+      turns: [step1TurnHash],
+    });
+    const step1Hash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: step1DetailHash,
+      agent: "uwf-test",
+    });
+
+    const step2Content = generateContent(600, "Second");
+    const step2TurnHash = await store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content: step2Content,
+      toolCalls: null,
+      reasoning: null,
+    });
+    const step2DetailHash = await store.put(detailSchemas.detail, {
+      sessionId: "session-2",
+      model: "test-model",
+      duration: 1000,
+      turnCount: 1,
+      turns: [step2TurnHash],
+    });
+    const step2Hash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: step1Hash,
+      role: "worker",
+      output: outputHash,
+      detail: step2DetailHash,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01HX2Q3R4S5T6V7W8X9YZ1" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: step2Hash });
+
+    // Set quota to 500 chars
+    const markdown = await cmdThreadRead(tmpDir, threadId, 500, null, false);
+
+    // Bug fix verification: output must be limited (allow ~200 char tolerance)
+    expect(markdown.length).toBeLessThanOrEqual(1100);
+
+    // Should contain "Second" (most recent step)
+    expect(markdown).toMatch(/Second/);
+
+    // Should skip first step
+    expect(markdown).toMatch(/earlier step/);
+
+    // Verify improvement: before fix would be ~1264, now should be much closer to 500
+    expect(markdown.length).toBeLessThan(1200);
+  });
+
+  test("test 3: quota with --start section", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task with a moderately long prompt to test quota accounting",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 2 steps
+    const steps: CasRef[] = [];
+    for (let i = 1; i <= 2; i++) {
+      const content = generateContent(400, `Step${i}`);
+      const turnHash = await store.put(detailSchemas.turn, {
+        index: 0,
+        role: "assistant",
+        content,
+        toolCalls: null,
+        reasoning: null,
+      });
+      const detailHash = await store.put(detailSchemas.detail, {
+        sessionId: `session-${i}`,
+        model: "test-model",
+        duration: 1000,
+        turnCount: 1,
+        turns: [turnHash],
+      });
+      const stepHash = await store.put(schemas.stepNode, {
+        start: startHash,
+        prev: steps[i - 2] ?? null,
+        role: "worker",
+        output: outputHash,
+        detail: detailHash,
+        agent: "uwf-test",
+      });
+      steps.push(stepHash);
+    }
+
+    const threadId = "01HX2Q3R4S5T6V7W8X9YZ2" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: steps[1] as CasRef });
+
+    // Set tight quota with --start flag
+    const markdown = await cmdThreadRead(tmpDir, threadId, 600, null, true);
+
+    // Quota must be reasonably enforced (allow ~210 char tolerance for structure)
+    expect(markdown.length).toBeLessThanOrEqual(810);
+
+    // Should contain thread header
+    expect(markdown).toMatch(/# Thread/);
+    expect(markdown).toMatch(/test-wf/);
+  });
+
+  test("test 5a: quota edge case - minimal quota", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const content = generateContent(500, "Test");
+    const turnHash = await store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content,
+      toolCalls: null,
+      reasoning: null,
+    });
+    const detailHash = await store.put(detailSchemas.detail, {
+      sessionId: "session-1",
+      model: "test-model",
+      duration: 1000,
+      turnCount: 1,
+      turns: [turnHash],
+    });
+    const stepHash = await store.put(schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01HX2Q3R4S5T6V7W8X9YZ4" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    // Minimal quota
+    const markdown = await cmdThreadRead(tmpDir, threadId, 1, null, false);
+
+    // Should handle gracefully - always shows at least one step
+    expect(markdown.length).toBeGreaterThan(1);
+    expect(markdown).toMatch(/Test/);
+  });
+
+  test("test 5b: quota edge case - very large quota", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 3 steps
+    const steps: CasRef[] = [];
+    for (let i = 1; i <= 3; i++) {
+      const content = generateContent(300, `Step${i}`);
+      const turnHash = await store.put(detailSchemas.turn, {
+        index: 0,
+        role: "assistant",
+        content,
+        toolCalls: null,
+        reasoning: null,
+      });
+      const detailHash = await store.put(detailSchemas.detail, {
+        sessionId: `session-${i}`,
+        model: "test-model",
+        duration: 1000,
+        turnCount: 1,
+        turns: [turnHash],
+      });
+      const stepHash = await store.put(schemas.stepNode, {
+        start: startHash,
+        prev: steps[i - 2] ?? null,
+        role: "worker",
+        output: outputHash,
+        detail: detailHash,
+        agent: "uwf-test",
+      });
+      steps.push(stepHash);
+    }
+
+    const threadId = "01HX2Q3R4S5T6V7W8X9YZ5" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: steps[2] as CasRef });
+
+    // Very large quota
+    const markdown = await cmdThreadRead(tmpDir, threadId, 1000000, null, false);
+
+    // Should show all steps (no skipping)
+    expect(markdown).not.toMatch(/earlier step/);
+    expect(markdown).toMatch(/Step1/);
+    expect(markdown).toMatch(/Step2/);
+    expect(markdown).toMatch(/Step3/);
+  });
+
+  test("test 6: quota with --before parameter", async () => {
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const detailSchemas = await registerDetailSchemas(store);
+
+    const workflowHash = await store.put(schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do the work.",
+          output: "Summarize the work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await store.put(schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Test task",
+    });
+
+    const outputHash = await store.put(schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // Create 5 steps
+    const steps: CasRef[] = [];
+    for (let i = 1; i <= 5; i++) {
+      const content = generateContent(300, `Step${i}`);
+      const turnHash = await store.put(detailSchemas.turn, {
+        index: 0,
+        role: "assistant",
+        content,
+        toolCalls: null,
+        reasoning: null,
+      });
+      const detailHash = await store.put(detailSchemas.detail, {
+        sessionId: `session-${i}`,
+        model: "test-model",
+        duration: 1000,
+        turnCount: 1,
+        turns: [turnHash],
+      });
+      const stepHash = await store.put(schemas.stepNode, {
+        start: startHash,
+        prev: steps[i - 2] ?? null,
+        role: "worker",
+        output: outputHash,
+        detail: detailHash,
+        agent: "uwf-test",
+      });
+      steps.push(stepHash);
+    }
+
+    const threadId = "01HX2Q3R4S5T6V7W8X9YZ6" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: steps[4] as CasRef });
+
+    // Use --before to limit to steps 1-2, then set quota that allows only 1
+    const markdown = await cmdThreadRead(tmpDir, threadId, 500, steps[2] as CasRef, false);
+
+    // Should not contain Step3 or later
+    expect(markdown).not.toMatch(/Step3/);
+    expect(markdown).not.toMatch(/Step4/);
+    expect(markdown).not.toMatch(/Step5/);
+
+    // Quota should select most recent of candidates (Step2)
+    expect(markdown).toMatch(/Step2/);
+
+    // Quota enforcement (allow ~200 char tolerance)
+    expect(markdown.length).toBeLessThanOrEqual(700);
+  });
+});

packages/cli-workflow/src/__tests__/thread-read-xml-tags.test.ts

@@ -0,0 +1,683 @@
+import { mkdir, mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { bootstrap, putSchema } from "@uncaged/json-cas";
+import { createFsStore } from "@uncaged/json-cas-fs";
+import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { cmdThreadRead, THREAD_READ_DEFAULT_QUOTA } from "../commands/thread.js";
+import { registerUwfSchemas } from "../schemas.js";
+import type { UwfStore } from "../store.js";
+import { saveThreadsIndex } from "../store.js";
+
+// ── schemas used in tests ────────────────────────────────────────────────────
+
+const TURN_SCHEMA = {
+  title: "hermes-turn",
+  type: "object" as const,
+  required: ["index", "role", "content"],
+  properties: {
+    index: { type: "integer" as const },
+    role: { type: "string" as const },
+    content: { type: "string" as const },
+    toolCalls: {
+      anyOf: [
+        { type: "array" as const, items: { type: "object" as const } },
+        { type: "null" as const },
+      ],
+    },
+    reasoning: { anyOf: [{ type: "string" as const }, { type: "null" as const }] },
+  },
+  additionalProperties: false,
+};
+
+const DETAIL_SCHEMA = {
+  title: "hermes-detail",
+  type: "object" as const,
+  required: ["sessionId", "model", "duration", "turnCount", "turns"],
+  properties: {
+    sessionId: { type: "string" as const },
+    model: { type: "string" as const },
+    duration: { type: "integer" as const },
+    turnCount: { type: "integer" as const },
+    turns: {
+      type: "array" as const,
+      items: { type: "string" as const, format: "cas_ref" },
+    },
+  },
+  additionalProperties: false,
+};
+
+// ── helpers ───────────────────────────────────────────────────────────────────
+
+async function makeUwfStore(storageRoot: string): Promise<UwfStore> {
+  const casDir = join(storageRoot, "cas");
+  await mkdir(casDir, { recursive: true });
+  const store = createFsStore(casDir);
+  const schemas = await registerUwfSchemas(store);
+  return { storageRoot, store, schemas };
+}
+
+async function registerDetailSchemas(store: ReturnType<typeof createFsStore>) {
+  await bootstrap(store);
+  const [turn, detail] = await Promise.all([
+    putSchema(store, TURN_SCHEMA),
+    putSchema(store, DETAIL_SCHEMA),
+  ]);
+  return { turn, detail };
+}
+
+// ── fixture ───────────────────────────────────────────────────────────────────
+
+let tmpDir: string;
+
+beforeEach(async () => {
+  tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-test-"));
+});
+
+afterEach(async () => {
+  await rm(tmpDir, { recursive: true, force: true });
+});
+
+// ── thread read XML tag isolation ─────────────────────────────────────────────
+
+describe("thread read XML tag isolation", () => {
+  test("scenario 1: wraps output in XML tags instead of heading", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const detailSchemas = await registerDetailSchemas(uwf.store);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        planner: {
+          description: "Planner",
+          goal: "You are a planning agent. Your task is to...",
+          capabilities: [],
+          procedure: "Plan the work.",
+          output: "Summarize the plan.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Fix issue #459",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const turnHash = await uwf.store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content:
+        "---\nstatus: ready\nplan: CMWGHQKT58RY4\n---\n\n# Analysis Complete\n## Issue Summary\nThe issue requires XML tag isolation.",
+      toolCalls: null,
+      reasoning: null,
+    });
+    const detailHash = await uwf.store.put(detailSchemas.detail, {
+      sessionId: "sx",
+      model: "mx",
+      duration: 500,
+      turnCount: 1,
+      turns: [turnHash],
+    });
+
+    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "planner",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-claude-code",
+    });
+
+    const threadId = "01JTEST0000000000000001" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+
+    // Should wrap output in XML tags
+    expect(markdown).toContain("<output>");
+    expect(markdown).toContain("</output>");
+
+    // Should not have ### Content heading
+    expect(markdown).not.toContain("### Content");
+
+    // Should preserve markdown headings inside output tags
+    expect(markdown).toContain("# Analysis Complete");
+    expect(markdown).toContain("## Issue Summary");
+  });
+
+  test("scenario 2: wraps prompt in XML tags", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const detailSchemas = await registerDetailSchemas(uwf.store);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        planner: {
+          description: "Planner",
+          goal: "You are a planning agent. Your task is to analyze and plan.",
+          capabilities: [],
+          procedure: "Plan the work.",
+          output: "Summarize the plan.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Fix issue",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const turnHash = await uwf.store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content: "---\nstatus: ready\n---\n\nContent here...",
+      toolCalls: null,
+      reasoning: null,
+    });
+    const detailHash = await uwf.store.put(detailSchemas.detail, {
+      sessionId: "sx",
+      model: "mx",
+      duration: 500,
+      turnCount: 1,
+      turns: [turnHash],
+    });
+
+    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "planner",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-claude-code",
+    });
+
+    const threadId = "01JTEST0000000000000002" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+
+    // Should wrap prompt in XML tags
+    expect(markdown).toContain("<prompt>");
+    expect(markdown).toContain("</prompt>");
+    expect(markdown).toContain("You are a planning agent. Your task is to analyze and plan.");
+
+    // Should not have ### Prompt heading
+    expect(markdown).not.toContain("### Prompt");
+
+    // Should wrap output in XML tags
+    expect(markdown).toContain("<output>");
+    expect(markdown).toContain("</output>");
+  });
+
+  test("scenario 3: same role repeated does not show prompt twice", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        writer: {
+          description: "Writer",
+          goal: "You are a writer agent.",
+          capabilities: [],
+          procedure: "Write content.",
+          output: "Summarize writing.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Write something",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const step1 = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "writer",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const step2 = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step1 as CasRef,
+      role: "writer",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000003" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: step2 });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+
+    // Should only show prompt tags once
+    const promptCount = (markdown.match(/<prompt>/g) ?? []).length;
+    expect(promptCount).toBe(1);
+  });
+
+  test("scenario 4: step with no detail shows no output tags", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        worker: {
+          description: "Worker",
+          goal: "You are a worker agent.",
+          capabilities: [],
+          procedure: "Do work.",
+          output: "Summarize work.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Do stuff",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000004" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+
+    // Should not have output tags
+    expect(markdown).not.toContain("<output>");
+    expect(markdown).not.toContain("</output>");
+
+    // Step header should still be displayed
+    expect(markdown).toContain("## Step 1: worker");
+
+    // Prompt should still be shown
+    expect(markdown).toContain("<prompt>");
+  });
+
+  test("scenario 5: empty content shows no output tags", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Do stuff",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    // A detail ref that doesn't exist → extractLastAssistantContent returns null
+    const missingDetailRef = "missingdetail0" as CasRef;
+
+    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "worker",
+      output: outputHash,
+      detail: missingDetailRef,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000005" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+
+    // Should not have output tags
+    expect(markdown).not.toContain("<output>");
+    expect(markdown).not.toContain("</output>");
+  });
+
+  test("scenario 6: thread read with --start flag shows task section", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        roleA: {
+          description: "Role A",
+          goal: "Goal for roleA",
+          capabilities: [],
+          procedure: "Do stuff.",
+          output: "Output.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Initial prompt",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "roleA",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000006" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, true);
+
+    // Should include task section
+    expect(markdown).toContain("# Thread");
+    expect(markdown).toContain("## Task");
+    expect(markdown).toContain("Initial prompt");
+
+    // Prompts should use XML tags
+    expect(markdown).toContain("<prompt>");
+  });
+
+  test("scenario 7: thread read with --before parameter", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        roleA: {
+          description: "Role A",
+          goal: "Goal for roleA",
+          capabilities: [],
+          procedure: "Do stuff.",
+          output: "Output.",
+          meta: "placeholder00" as CasRef,
+        },
+        roleB: {
+          description: "Role B",
+          goal: "Goal for roleB",
+          capabilities: [],
+          procedure: "Do stuff.",
+          output: "Output.",
+          meta: "placeholder00" as CasRef,
+        },
+        roleC: {
+          description: "Role C",
+          goal: "Goal for roleC",
+          capabilities: [],
+          procedure: "Do stuff.",
+          output: "Output.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Initial prompt",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const step1 = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "roleA",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const step2 = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step1 as CasRef,
+      role: "roleB",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const step3 = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step2 as CasRef,
+      role: "roleC",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000007" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: step3 });
+
+    const markdown = await cmdThreadRead(
+      tmpDir,
+      threadId,
+      THREAD_READ_DEFAULT_QUOTA,
+      step2 as CasRef,
+      false,
+    );
+
+    // Should only show roleA
+    expect(markdown).toContain("roleA");
+    expect(markdown).not.toContain("roleB");
+    expect(markdown).not.toContain("roleC");
+
+    // Should use XML tags
+    expect(markdown).toContain("<prompt>");
+  });
+
+  test("scenario 9: special characters in content are preserved", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const detailSchemas = await registerDetailSchemas(uwf.store);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        writer: {
+          description: "Writer",
+          goal: "You are a writer.",
+          capabilities: [],
+          procedure: "Write content.",
+          output: "Summarize.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Write something",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const turnHash = await uwf.store.put(detailSchemas.turn, {
+      index: 0,
+      role: "assistant",
+      content: "Content with <special> & characters > like <this>",
+      toolCalls: null,
+      reasoning: null,
+    });
+    const detailHash = await uwf.store.put(detailSchemas.detail, {
+      sessionId: "sx",
+      model: "mx",
+      duration: 500,
+      turnCount: 1,
+      turns: [turnHash],
+    });
+
+    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "writer",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000008" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+
+    // Special characters should be preserved as-is
+    expect(markdown).toContain("Content with <special> & characters > like <this>");
+  });
+
+  test("scenario 10: quota limit with XML tags", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf",
+      description: "desc",
+      roles: {
+        roleA: {
+          description: "Role A",
+          goal: "Goal for roleA",
+          capabilities: [],
+          procedure: "Do stuff.",
+          output: "Output.",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Initial prompt",
+    });
+
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const steps: CasRef[] = [];
+    let prev: CasRef | null = null;
+    for (let i = 0; i < 5; i++) {
+      const step = (await uwf.store.put(uwf.schemas.stepNode, {
+        start: startHash,
+        prev,
+        role: "roleA",
+        output: outputHash,
+        detail: null,
+        agent: "uwf-test",
+      })) as CasRef;
+      steps.push(step);
+      prev = step;
+    }
+
+    const threadId = "01JTEST0000000000000009" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: steps[steps.length - 1]! });
+
+    // Use very small quota
+    const markdown = await cmdThreadRead(tmpDir, threadId, 1, null, false);
+
+    // Should have skip hint
+    expect(markdown).toContain("earlier step");
+
+    // Should have XML tags for displayed steps
+    if (markdown.includes("<prompt>")) {
+      expect(markdown).toContain("</prompt>");
+    }
+  });
+});

packages/cli-workflow/src/__tests__/thread-step-count.test.ts

@@ -0,0 +1,71 @@
+import { execFileSync } from "node:child_process";
+import { join } from "node:path";
+import { describe, expect, test } from "vitest";
+
+const CLI_PATH = join(import.meta.dirname, "..", "cli.js");
+
+function runCli(args: string[]): { stdout: string; stderr: string; exitCode: number } {
+  try {
+    const stdout = execFileSync("bun", ["run", CLI_PATH, ...args], {
+      encoding: "utf8",
+      env: { ...process.env, WORKFLOW_STORAGE_ROOT: "/tmp/uwf-test-nonexistent" },
+      stdio: ["ignore", "pipe", "pipe"],
+    });
+    return { stdout, stderr: "", exitCode: 0 };
+  } catch (e: unknown) {
+    const err = e as NodeJS.ErrnoException & { stdout?: string; stderr?: string; status?: number };
+    return {
+      stdout: err.stdout ?? "",
+      stderr: err.stderr ?? "",
+      exitCode: err.status ?? 1,
+    };
+  }
+}
+
+describe("thread exec --count CLI parsing", () => {
+  test("--help shows -c/--count option", () => {
+    const result = runCli(["thread", "exec", "--help"]);
+    expect(result.stdout).toContain("--count");
+    expect(result.stdout).toContain("-c");
+  });
+
+  test("description says 'one or more steps'", () => {
+    const result = runCli(["thread", "exec", "--help"]);
+    expect(result.stdout).toContain("one or more steps");
+  });
+});
+
+describe("cmdThreadExec count logic", () => {
+  test("count=0 fails with validation error", () => {
+    const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "0"]);
+    expect(result.exitCode).not.toBe(0);
+    expect(result.stderr).toContain("positive integer");
+  });
+
+  test("negative count fails with validation error", () => {
+    const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "-1"]);
+    expect(result.exitCode).not.toBe(0);
+    expect(result.stderr).toContain("positive integer");
+  });
+
+  test("non-integer count fails with validation error", () => {
+    const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "1.5"]);
+    expect(result.exitCode).not.toBe(0);
+    expect(result.stderr).toContain("positive integer");
+  });
+
+  test("count=1 is the default (no -c flag)", () => {
+    // Without -c, it should attempt to run 1 step (failing on missing thread, not on count validation)
+    const result = runCli(["thread", "exec", "FAKE_THREAD_ID"]);
+    expect(result.exitCode).not.toBe(0);
+    // Should NOT contain "positive integer" error — should fail on thread lookup instead
+    expect(result.stderr).not.toContain("positive integer");
+  });
+
+  test("count=3 passes validation (fails on thread lookup)", () => {
+    const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "3"]);
+    expect(result.exitCode).not.toBe(0);
+    // Should NOT contain "positive integer" error — should fail on thread/storage lookup
+    expect(result.stderr).not.toContain("positive integer");
+  });
+});

packages/cli-workflow/src/__tests__/workflow-resolution.test.ts

@@ -0,0 +1,367 @@
+import { mkdir, mkdtemp, rm, writeFile } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { createFsStore } from "@uncaged/json-cas-fs";
+import type { CasRef, WorkflowPayload } from "@uncaged/workflow-protocol";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+import { stringify } from "yaml";
+import { cmdThreadStart } from "../commands/thread.js";
+import { registerUwfSchemas } from "../schemas.js";
+import type { UwfStore } from "../store.js";
+import { loadWorkflowRegistry, saveWorkflowRegistry } from "../store.js";
+
+// ── helpers ───────────────────────────────────────────────────────────────────
+
+async function makeUwfStore(storageRoot: string): Promise<UwfStore> {
+  const casDir = join(storageRoot, "cas");
+  await mkdir(casDir, { recursive: true });
+  const store = createFsStore(casDir);
+  const schemas = await registerUwfSchemas(store);
+  return { storageRoot, store, schemas };
+}
+
+async function storeWorkflow(uwf: UwfStore, name: string): Promise<CasRef> {
+  const payload: WorkflowPayload = {
+    name,
+    description: "Test workflow",
+    roles: {},
+    conditions: {},
+    graph: {},
+  };
+  return await uwf.store.put(uwf.schemas.workflow, payload);
+}
+
+async function createWorkflowYaml(name: string, version: string | null = null): Promise<string> {
+  const payload: WorkflowPayload = {
+    name,
+    description: version !== null ? `Test workflow (${version})` : "Test workflow",
+    roles: {},
+    conditions: {},
+    graph: {},
+  };
+  const yaml = stringify(payload);
+  return yaml;
+}
+
+// ── fixture ───────────────────────────────────────────────────────────────────
+
+let tmpDir: string;
+let storageRoot: string;
+let projectRoot: string;
+
+beforeEach(async () => {
+  tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-wf-resolve-test-"));
+  storageRoot = join(tmpDir, "storage");
+  projectRoot = join(tmpDir, "project");
+  await mkdir(storageRoot, { recursive: true });
+  await mkdir(projectRoot, { recursive: true });
+});
+
+afterEach(async () => {
+  await rm(tmpDir, { recursive: true, force: true });
+});
+
+// ── Strategy 1: CAS Hash Resolution ───────────────────────────────────────────
+
+describe("Strategy 1: CAS Hash Resolution", () => {
+  test("should resolve valid 13-char Crockford Base32 hash", async () => {
+    const uwf = await makeUwfStore(storageRoot);
+    const hash = await storeWorkflow(uwf, "test-workflow");
+
+    const result = await cmdThreadStart(storageRoot, hash, "test prompt", projectRoot);
+
+    expect(result.workflow).toBe(hash);
+    expect(result.thread).toMatch(/^[0-9A-HJKMNP-TV-Z]{26}$/);
+  });
+
+  test("should fail on invalid hash format (non-Crockford characters)", async () => {
+    await makeUwfStore(storageRoot);
+
+    await expect(
+      cmdThreadStart(storageRoot, "123456789ABCD", "prompt", projectRoot),
+    ).rejects.toThrow();
+  });
+
+  test("should fail on valid-format hash not present in CAS", async () => {
+    await makeUwfStore(storageRoot);
+    const fakeHash = "0000000000000"; // valid format, doesn't exist
+
+    await expect(cmdThreadStart(storageRoot, fakeHash, "prompt", projectRoot)).rejects.toThrow();
+  });
+
+  test("should reject 40-char hex hash (legacy format not supported)", async () => {
+    await makeUwfStore(storageRoot);
+    const hexHash = "a".repeat(40);
+
+    await expect(cmdThreadStart(storageRoot, hexHash, "prompt", projectRoot)).rejects.toThrow();
+  });
+});
+
+// ── Strategy 2: File Path Resolution ──────────────────────────────────────────
+
+describe("Strategy 2: File Path Resolution", () => {
+  test("should load workflow from absolute file path", async () => {
+    await makeUwfStore(storageRoot);
+    const yamlPath = join(tmpDir, "test-workflow.yaml");
+    await writeFile(yamlPath, await createWorkflowYaml("test-workflow"));
+
+    const result = await cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+    const uwf = await makeUwfStore(storageRoot);
+    const node = uwf.store.get(result.workflow);
+    expect(node).not.toBeNull();
+    if (node !== null) {
+      expect((node.payload as WorkflowPayload).name).toBe("test-workflow");
+    }
+  });
+
+  test("should load workflow from relative file path", async () => {
+    await makeUwfStore(storageRoot);
+    const yamlPath = "test-workflow.yaml";
+    await writeFile(join(projectRoot, yamlPath), await createWorkflowYaml("test-workflow"));
+
+    const result = await cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+  });
+
+  test("should fail when file path does not exist", async () => {
+    await makeUwfStore(storageRoot);
+
+    await expect(
+      cmdThreadStart(storageRoot, "./nonexistent.yaml", "prompt", projectRoot),
+    ).rejects.toThrow();
+  });
+
+  test("should fail on invalid YAML syntax in file", async () => {
+    await makeUwfStore(storageRoot);
+    const yamlPath = join(tmpDir, "bad-syntax.yaml");
+    await writeFile(yamlPath, "invalid: yaml: : :");
+
+    await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
+  });
+
+  test("should fail on valid YAML with invalid WorkflowPayload shape", async () => {
+    await makeUwfStore(storageRoot);
+    const yamlPath = join(tmpDir, "invalid-workflow.yaml");
+    await writeFile(yamlPath, "name: test\n# missing roles, conditions, and graph");
+
+    await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
+  });
+
+  test("should enforce filename matches workflow name", async () => {
+    await makeUwfStore(storageRoot);
+    const yamlPath = join(tmpDir, "solve-issue.yaml");
+    await writeFile(yamlPath, await createWorkflowYaml("wrong-name"));
+
+    await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
+  });
+});
+
+// ── Strategy 3: Local Discovery (Parent Traversal) ────────────────────────────
+
+describe("Strategy 3: Local Discovery", () => {
+  test("should find workflow in current directory .workflow/", async () => {
+    await makeUwfStore(storageRoot);
+    const workflowDir = join(projectRoot, ".workflow");
+    await mkdir(workflowDir, { recursive: true });
+    await writeFile(join(workflowDir, "solve-issue.yaml"), await createWorkflowYaml("solve-issue"));
+
+    const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+    const uwf = await makeUwfStore(storageRoot);
+    const node = uwf.store.get(result.workflow);
+    expect(node).not.toBeNull();
+    if (node !== null) {
+      expect((node.payload as WorkflowPayload).name).toBe("solve-issue");
+    }
+  });
+
+  test("should find workflow in parent directory .workflow/", async () => {
+    await makeUwfStore(storageRoot);
+    const workflowDir = join(projectRoot, ".workflow");
+    await mkdir(workflowDir, { recursive: true });
+    await writeFile(join(workflowDir, "solve-issue.yaml"), await createWorkflowYaml("solve-issue"));
+
+    const subdir = join(projectRoot, "packages", "cli-workflow", "src");
+    await mkdir(subdir, { recursive: true });
+
+    const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", subdir);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+  });
+
+  test("should stop at filesystem root when traversing", async () => {
+    await makeUwfStore(storageRoot);
+    const deepPath = join(tmpDir, "deep", "path", "that", "does", "not", "have", "workflow");
+    await mkdir(deepPath, { recursive: true });
+
+    await expect(cmdThreadStart(storageRoot, "nonexistent", "prompt", deepPath)).rejects.toThrow();
+  });
+
+  test("should prefer .workflow/ over .workflows/ directory", async () => {
+    await makeUwfStore(storageRoot);
+    const workflowDir = join(projectRoot, ".workflow");
+    const workflowsDir = join(projectRoot, ".workflows");
+    await mkdir(workflowDir, { recursive: true });
+    await mkdir(workflowsDir, { recursive: true });
+
+    await writeFile(
+      join(workflowDir, "solve-issue.yaml"),
+      await createWorkflowYaml("solve-issue", "1"),
+    );
+    await writeFile(
+      join(workflowsDir, "solve-issue.yaml"),
+      await createWorkflowYaml("solve-issue", "2"),
+    );
+
+    const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
+
+    const uwf = await makeUwfStore(storageRoot);
+    const node = uwf.store.get(result.workflow);
+    expect(node).not.toBeNull();
+    if (node !== null) {
+      expect((node.payload as WorkflowPayload).description).toBe("Test workflow (1)");
+    }
+  });
+
+  test("should support .yml extension in local discovery", async () => {
+    await makeUwfStore(storageRoot);
+    const workflowDir = join(projectRoot, ".workflow");
+    await mkdir(workflowDir, { recursive: true });
+    await writeFile(join(workflowDir, "solve-issue.yml"), await createWorkflowYaml("solve-issue"));
+
+    const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+  });
+});
+
+// ── Strategy 4: Global Registry Fallback ──────────────────────────────────────
+
+describe("Strategy 4: Global Registry Resolution", () => {
+  test("should resolve workflow from global registry when not found locally", async () => {
+    const uwf = await makeUwfStore(storageRoot);
+    const hash = await storeWorkflow(uwf, "deploy-pipeline");
+    const registry = await loadWorkflowRegistry(storageRoot);
+    registry["deploy-pipeline"] = hash;
+    await saveWorkflowRegistry(storageRoot, registry);
+
+    const isolatedRoot = join(tmpDir, "isolated");
+    await mkdir(isolatedRoot, { recursive: true });
+
+    const result = await cmdThreadStart(storageRoot, "deploy-pipeline", "prompt", isolatedRoot);
+
+    expect(result.workflow).toBe(hash);
+  });
+
+  test("should fail when workflow not found in any strategy", async () => {
+    await makeUwfStore(storageRoot);
+
+    await expect(cmdThreadStart(storageRoot, "nonexistent", "prompt", tmpDir)).rejects.toThrow();
+  });
+});
+
+// ── Strategy Priority Order ───────────────────────────────────────────────────
+
+describe("Resolution Priority", () => {
+  test("should use explicit file path over local discovery", async () => {
+    await makeUwfStore(storageRoot);
+
+    // Setup: Create workflow in .workflow/ AND as explicit file
+    const workflowDir = join(projectRoot, ".workflow");
+    await mkdir(workflowDir, { recursive: true });
+    await writeFile(
+      join(workflowDir, "solve-issue.yaml"),
+      await createWorkflowYaml("solve-issue", "discovery"),
+    );
+
+    const explicitPath = join(projectRoot, "custom-solve-issue.yaml");
+    await writeFile(explicitPath, await createWorkflowYaml("custom-solve-issue", "explicit"));
+
+    // Execute with explicit path
+    const result = await cmdThreadStart(storageRoot, explicitPath, "prompt", projectRoot);
+
+    const uwf = await makeUwfStore(storageRoot);
+    const node = uwf.store.get(result.workflow);
+    expect(node).not.toBeNull();
+    if (node !== null) {
+      expect((node.payload as WorkflowPayload).description).toBe("Test workflow (explicit)");
+    }
+  });
+
+  test("should use local discovery over global registry", async () => {
+    const uwf = await makeUwfStore(storageRoot);
+
+    // Setup: Register globally
+    const globalHash = await storeWorkflow(uwf, "solve-issue");
+    const registry = await loadWorkflowRegistry(storageRoot);
+    registry["solve-issue"] = globalHash;
+    await saveWorkflowRegistry(storageRoot, registry);
+
+    // Setup: Create local .workflow/
+    const workflowDir = join(projectRoot, ".workflow");
+    await mkdir(workflowDir, { recursive: true });
+    const localYaml = await createWorkflowYaml("solve-issue", "local");
+    await writeFile(join(workflowDir, "solve-issue.yaml"), localYaml);
+
+    const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
+
+    const uwf2 = await makeUwfStore(storageRoot);
+    const node = uwf2.store.get(result.workflow);
+    expect(node).not.toBeNull();
+    if (node !== null) {
+      expect((node.payload as WorkflowPayload).description).toBe("Test workflow (local)");
+    }
+  });
+});
+
+// ── Edge Cases ────────────────────────────────────────────────────────────────
+
+describe("Edge Cases", () => {
+  test("should treat '13-char-string.yaml' as file path, not CAS hash", async () => {
+    await makeUwfStore(storageRoot);
+    const fileName = "0123456789ABC.yaml"; // 13 chars + .yaml
+    await writeFile(join(projectRoot, fileName), await createWorkflowYaml("0123456789ABC"));
+
+    const result = await cmdThreadStart(storageRoot, fileName, "prompt", projectRoot);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+  });
+
+  test("should handle workflow names containing slashes as file paths", async () => {
+    await makeUwfStore(storageRoot);
+    const filePath = "subdir/solve-issue.yaml";
+    const fullPath = join(projectRoot, filePath);
+    await mkdir(join(projectRoot, "subdir"), { recursive: true });
+    await writeFile(fullPath, await createWorkflowYaml("solve-issue"));
+
+    const result = await cmdThreadStart(storageRoot, filePath, "prompt", projectRoot);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+  });
+
+  test("should handle absolute paths correctly", async () => {
+    await makeUwfStore(storageRoot);
+    const absPath = join(tmpDir, "abs-workflow.yaml");
+    await writeFile(absPath, await createWorkflowYaml("abs-workflow"));
+
+    const result = await cmdThreadStart(storageRoot, absPath, "prompt", projectRoot);
+
+    expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
+  });
+
+  test("should fail on empty workflow ID", async () => {
+    await makeUwfStore(storageRoot);
+
+    await expect(cmdThreadStart(storageRoot, "", "prompt", projectRoot)).rejects.toThrow();
+  });
+
+  test("should fail on whitespace-only workflow ID", async () => {
+    await makeUwfStore(storageRoot);
+
+    await expect(cmdThreadStart(storageRoot, "   ", "prompt", projectRoot)).rejects.toThrow();
+  });
+});

packages/cli-workflow/src/background/background.ts

@@ -0,0 +1,147 @@
+import { mkdir, readdir, readFile, rename, rm, writeFile } from "node:fs/promises";
+import { join } from "node:path";
+import type { RunningThreadItem, ThreadId } from "@uncaged/workflow-protocol";
+
+import type { RunningMarker } from "./types.js";
+
+/**
+ * Get the path to the running markers directory.
+ */
+export function getRunningDir(storageRoot: string): string {
+  return join(storageRoot, "running");
+}
+
+/**
+ * Get the path to a specific thread's marker file.
+ */
+export function getMarkerPath(storageRoot: string, threadId: ThreadId): string {
+  return join(getRunningDir(storageRoot), `${threadId}.json`);
+}
+
+/**
+ * Check if a PID is still running.
+ * Returns true if the process exists, false otherwise.
+ */
+export function isPidAlive(pid: number): boolean {
+  try {
+    // process.kill with signal 0 checks existence without killing
+    process.kill(pid, 0);
+    return true;
+  } catch {
+    // ESRCH means process doesn't exist
+    return false;
+  }
+}
+
+/**
+ * Create a marker file for a running thread.
+ * Writes to a temp file in the same directory, then atomically renames.
+ */
+export async function createMarker(storageRoot: string, marker: RunningMarker): Promise<void> {
+  const runningDir = getRunningDir(storageRoot);
+  await mkdir(runningDir, { recursive: true });
+
+  const markerPath = getMarkerPath(storageRoot, marker.thread);
+  const tempPath = join(runningDir, `.${marker.thread}-${process.pid}.tmp`);
+
+  const content = JSON.stringify(marker, null, 2);
+  await writeFile(tempPath, content, "utf8");
+  await rename(tempPath, markerPath);
+}
+
+/**
+ * Delete a marker file for a thread.
+ */
+export async function deleteMarker(storageRoot: string, threadId: ThreadId): Promise<void> {
+  const markerPath = getMarkerPath(storageRoot, threadId);
+  try {
+    await rm(markerPath);
+  } catch {
+    // Ignore errors if file doesn't exist
+  }
+}
+
+/**
+ * Read a marker file. Returns null if file doesn't exist or is invalid.
+ */
+export async function readMarker(
+  storageRoot: string,
+  threadId: ThreadId,
+): Promise<RunningMarker | null> {
+  const markerPath = getMarkerPath(storageRoot, threadId);
+  try {
+    const content = await readFile(markerPath, "utf8");
+    const marker = JSON.parse(content) as RunningMarker;
+    return marker;
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * List all running threads, filtering out stale markers.
+ */
+export async function listRunningThreads(storageRoot: string): Promise<RunningThreadItem[]> {
+  const runningDir = getRunningDir(storageRoot);
+
+  let files: string[];
+  try {
+    files = await readdir(runningDir);
+  } catch {
+    // Directory doesn't exist or can't be read
+    return [];
+  }
+
+  const results: RunningThreadItem[] = [];
+
+  for (const filename of files) {
+    if (!filename.endsWith(".json")) {
+      continue;
+    }
+
+    const threadId = filename.slice(0, -5) as ThreadId;
+    const marker = await readMarker(storageRoot, threadId);
+
+    if (marker === null) {
+      // Invalid marker file
+      continue;
+    }
+
+    if (!isPidAlive(marker.pid)) {
+      // Stale marker - process no longer exists
+      await deleteMarker(storageRoot, threadId);
+      continue;
+    }
+
+    results.push({
+      thread: marker.thread,
+      workflow: marker.workflow,
+      pid: marker.pid,
+      startedAt: marker.startedAt,
+    });
+  }
+
+  return results;
+}
+
+/**
+ * Check if a thread is currently executing in the background.
+ * Returns the marker if running, null otherwise.
+ */
+export async function isThreadRunning(
+  storageRoot: string,
+  threadId: ThreadId,
+): Promise<RunningMarker | null> {
+  const marker = await readMarker(storageRoot, threadId);
+  if (marker === null) {
+    return null;
+  }
+
+  if (!isPidAlive(marker.pid)) {
+    // Stale marker
+    await deleteMarker(storageRoot, threadId);
+    return null;
+  }
+
+  return marker;
+}

packages/cli-workflow/src/background/index.ts

@@ -0,0 +1,11 @@
+export {
+  createMarker,
+  deleteMarker,
+  getMarkerPath,
+  getRunningDir,
+  isPidAlive,
+  isThreadRunning,
+  listRunningThreads,
+  readMarker,
+} from "./background.js";
+export type { RunningMarker } from "./types.js";

packages/cli-workflow/src/background/types.ts

@@ -0,0 +1,9 @@
+import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
+
+/** Marker file stored at ~/.uncaged/workflow/running/<thread-id>.json */
+export type RunningMarker = {
+  thread: ThreadId;
+  workflow: CasRef;
+  pid: number;
+  startedAt: number;
+};

packages/cli-workflow/src/cli.ts

@@ -0,0 +1,684 @@
+#!/usr/bin/env bun
+
+import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
+import { Command } from "commander";
+import {
+  cmdCasGet,
+  cmdCasHas,
+  cmdCasPut,
+  cmdCasPutText,
+  cmdCasRefs,
+  cmdCasReindex,
+  cmdCasSchemaGet,
+  cmdCasSchemaList,
+  cmdCasWalk,
+} from "./commands/cas.js";
+import { cmdLogClean, cmdLogList, cmdLogShow } from "./commands/log.js";
+import { cmdSetup, cmdSetupInteractive } from "./commands/setup.js";
+import { cmdSkillCli } from "./commands/skill.js";
+import { cmdStepFork, cmdStepList, cmdStepRead, cmdStepShow } from "./commands/step.js";
+import {
+  cmdThreadCancel,
+  cmdThreadExec,
+  cmdThreadList,
+  cmdThreadRead,
+  cmdThreadShow,
+  cmdThreadStart,
+  cmdThreadStop,
+  THREAD_READ_DEFAULT_QUOTA,
+  type ThreadStatus,
+} from "./commands/thread.js";
+import { parseTimeInput } from "./commands/thread-time-parser.js";
+import { cmdWorkflowAdd, cmdWorkflowList, cmdWorkflowShow } from "./commands/workflow.js";
+import { formatOutput, type OutputFormat } from "./format.js";
+import { resolveStorageRoot } from "./store.js";
+
+function writeOutput(data: unknown): void {
+  const fmt = program.opts().format as OutputFormat;
+  process.stdout.write(`${formatOutput(data, fmt)}\n`);
+}
+
+function runAction(action: () => Promise<void>): void {
+  action().catch((e: unknown) => {
+    const message = e instanceof Error ? e.message : String(e);
+    process.stderr.write(`${message}\n`);
+    process.exit(1);
+  });
+}
+
+const program = new Command();
+
+// eslint-disable-next-line -- dynamic import for version
+const pkg = await import("../package.json", { with: { type: "json" } });
+program
+  .name("uwf")
+  .description(
+    "Stateless workflow CLI\n\n" +
+      "Four-layer architecture:\n" +
+      "  workflow → thread → step → turn\n" +
+      "  模板定义   执行实例   单步结果   agent内部交互",
+  )
+  .version(pkg.default.version, "-V, --version");
+program.option("--format <fmt>", "Output format: json or yaml", "json");
+
+const workflow = program
+  .command("workflow")
+  .description("Workflow definitions (layer 1: templates)");
+
+workflow
+  .command("add")
+  .description("Register a workflow from YAML")
+  .argument("<file>", "Workflow YAML file")
+  .action((file: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdWorkflowAdd(storageRoot, file);
+      writeOutput(result);
+    });
+  });
+
+workflow
+  .command("show")
+  .description("Show a workflow by name or CAS hash")
+  .argument("<id>", "Workflow name or hash")
+  .action((id: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdWorkflowShow(storageRoot, id);
+      writeOutput(result);
+    });
+  });
+
+workflow
+  .command("list")
+  .description("List registered workflows")
+  .action(() => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdWorkflowList(storageRoot, process.cwd());
+      writeOutput(result);
+    });
+  });
+
+const thread = program.command("thread").description("Thread execution (layer 2: instances)");
+
+thread
+  .command("start")
+  .description("Create a thread without executing")
+  .argument("<workflow>", "Workflow name or hash")
+  .requiredOption("-p, --prompt <text>", "User prompt")
+  .action((workflow: string, opts: { prompt: string }) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdThreadStart(storageRoot, workflow, opts.prompt, process.cwd());
+      writeOutput(result);
+    });
+  });
+
+thread
+  .command("exec")
+  .description("Execute one or more steps")
+  .argument("<thread-id>", "Thread ULID")
+  .option("--agent <cmd>", "Override agent command")
+  .option("-c, --count <number>", "Number of steps to run (default: 1)")
+  .option("--background", "Run in background and return immediately")
+  .option("--_background-worker", "Internal flag for background worker process", false)
+  .action(
+    (
+      threadId: string,
+      opts: {
+        agent: string | undefined;
+        count: string | undefined;
+        background: boolean;
+        _backgroundWorker: boolean;
+      },
+    ) => {
+      const storageRoot = resolveStorageRoot();
+      runAction(async () => {
+        const agentOverride = opts.agent ?? null;
+        const count = opts.count !== undefined ? Number(opts.count) : 1;
+        const background = opts.background ?? false;
+        const backgroundWorker = opts._backgroundWorker ?? false;
+
+        const results = await cmdThreadExec(
+          storageRoot,
+          threadId,
+          agentOverride,
+          count,
+          background,
+          backgroundWorker,
+        );
+        if (results.length === 1) {
+          writeOutput(results[0]);
+        } else {
+          writeOutput(results);
+        }
+      });
+    },
+  );
+
+thread
+  .command("show")
+  .description("Show thread head pointer")
+  .argument("<thread-id>", "Thread ULID")
+  .action((threadId: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdThreadShow(storageRoot, threadId);
+      writeOutput(result);
+    });
+  });
+
+// Helper functions for thread list command parsing
+function parseStatusFilter(status: string | undefined): ThreadStatus[] | null {
+  if (status === undefined) return null;
+  const raw = status.trim();
+  if (raw === "active") return ["idle", "running"];
+
+  const parts = raw.split(",").map((s) => s.trim());
+  const validStatuses: ThreadStatus[] = ["idle", "running", "completed"];
+  for (const part of parts) {
+    if (!validStatuses.includes(part as ThreadStatus)) {
+      process.stderr.write(
+        `Invalid status: ${part}. Must be one of: idle, running, completed, active\n`,
+      );
+      process.exit(1);
+    }
+  }
+  return parts as ThreadStatus[];
+}
+
+function parseTimeFilters(
+  after: string | undefined,
+  before: string | undefined,
+  nowMs: number,
+): { afterMs: number | null; beforeMs: number | null } {
+  try {
+    const afterMs = after !== undefined ? parseTimeInput(after, nowMs) : null;
+    const beforeMs = before !== undefined ? parseTimeInput(before, nowMs) : null;
+    return { afterMs, beforeMs };
+  } catch (e) {
+    const message = e instanceof Error ? e.message : String(e);
+    process.stderr.write(`${message}\n`);
+    process.exit(1);
+  }
+}
+
+function parsePaginationOptions(
+  skip: string | undefined,
+  take: string | undefined,
+): { skip: number | null; take: number | null } {
+  let skipVal: number | null = null;
+  let takeVal: number | null = null;
+
+  if (skip !== undefined) {
+    skipVal = Number.parseInt(skip, 10);
+    if (!Number.isInteger(skipVal) || skipVal < 0) {
+      process.stderr.write("--skip must be a non-negative integer\n");
+      process.exit(1);
+    }
+  }
+  if (take !== undefined) {
+    takeVal = Number.parseInt(take, 10);
+    if (!Number.isInteger(takeVal) || takeVal < 1) {
+      process.stderr.write("--take must be a positive integer\n");
+      process.exit(1);
+    }
+  }
+  return { skip: skipVal, take: takeVal };
+}
+
+thread
+  .command("list")
+  .description("List threads")
+  .option(
+    "--status <status>",
+    "Filter by status: idle, running, completed, active (idle+running), or comma-separated values",
+  )
+  .option("--after <date>", "Filter threads created after this date (ISO or relative like '7d')")
+  .option("--before <date>", "Filter threads created before this date (ISO or relative like '7d')")
+  .option("--skip <n>", "Skip first n threads")
+  .option("--take <n>", "Return at most n threads")
+  .action(
+    (opts: {
+      status: string | undefined;
+      after: string | undefined;
+      before: string | undefined;
+      skip: string | undefined;
+      take: string | undefined;
+    }) => {
+      const storageRoot = resolveStorageRoot();
+      runAction(async () => {
+        const statusFilter = parseStatusFilter(opts.status);
+        const nowMs = Date.now();
+        const { afterMs, beforeMs } = parseTimeFilters(opts.after, opts.before, nowMs);
+        const { skip, take } = parsePaginationOptions(opts.skip, opts.take);
+
+        const result = await cmdThreadList(
+          storageRoot,
+          statusFilter,
+          afterMs,
+          beforeMs,
+          skip,
+          take,
+        );
+        writeOutput(result);
+      });
+    },
+  );
+
+thread
+  .command("stop")
+  .description("Stop background execution of a thread (keep thread active)")
+  .argument("<thread-id>", "Thread ULID")
+  .action((threadId: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdThreadStop(storageRoot, threadId);
+      writeOutput(result);
+    });
+  });
+
+thread
+  .command("cancel")
+  .description("Cancel a thread (stop execution and move to history)")
+  .argument("<thread-id>", "Thread ULID")
+  .action((threadId: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdThreadCancel(storageRoot, threadId);
+      writeOutput(result);
+    });
+  });
+
+thread
+  .command("read")
+  .description("Read thread context as human-readable markdown")
+  .argument("<thread-id>", "Thread ULID")
+  .option("--quota <chars>", "Max output characters", String(THREAD_READ_DEFAULT_QUOTA))
+  .option("--before <step-hash>", "Load steps before this hash (exclusive)")
+  .option("--start", "Include start step in output")
+  .action(
+    (threadId: string, opts: { quota: string; before: string | undefined; start: boolean }) => {
+      const storageRoot = resolveStorageRoot();
+      runAction(async () => {
+        const quota = Number.parseInt(opts.quota, 10);
+        if (!Number.isFinite(quota) || quota < 1) {
+          process.stderr.write("invalid --quota: must be a positive integer\n");
+          process.exit(1);
+        }
+        const before = opts.before ?? null;
+        const markdown = await cmdThreadRead(
+          storageRoot,
+          threadId as ThreadId,
+          quota,
+          before,
+          opts.start ?? false,
+        );
+        process.stdout.write(markdown.endsWith("\n") ? markdown : `${markdown}\n`);
+      });
+    },
+  );
+
+const step = program.command("step").description("Step results (layer 3: single cycle)");
+
+step
+  .command("list")
+  .description("List all steps in a thread")
+  .argument("<thread-id>", "Thread ULID")
+  .action((threadId: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdStepList(storageRoot, threadId);
+      writeOutput(result);
+    });
+  });
+
+step
+  .command("show")
+  .description("Show details of a specific step")
+  .argument("<step-hash>", "CAS hash of the StepNode")
+  .action((stepHash: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const detail = await cmdStepShow(storageRoot, stepHash as CasRef);
+      writeOutput(detail);
+    });
+  });
+
+step
+  .command("read")
+  .description("Read a step's turns as human-readable markdown")
+  .argument("<step-hash>", "CAS hash of the StepNode")
+  .option("--quota <chars>", "Max output characters", "4000")
+  .action((stepHash: string, opts: { quota: string }) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const quota = Number.parseInt(opts.quota, 10);
+      if (!Number.isFinite(quota) || quota < 1) {
+        process.stderr.write("invalid --quota: must be a positive integer\n");
+        process.exit(1);
+      }
+      const markdown = await cmdStepRead(storageRoot, stepHash as CasRef, quota);
+      process.stdout.write(markdown.endsWith("\n") ? markdown : `${markdown}\n`);
+    });
+  });
+
+step
+  .command("fork")
+  .description("Fork a thread from a specific step")
+  .argument("<step-hash>", "CAS hash of the StartNode or StepNode to fork from")
+  .action((stepHash: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdStepFork(storageRoot, stepHash as CasRef);
+      writeOutput(result);
+    });
+  });
+
+// ── Deprecation Handlers ──────────────────────────────────────────────────────
+// These commands have been removed. Show helpful error messages.
+
+workflow
+  .command("put")
+  .description("[DEPRECATED] Use 'workflow add' instead")
+  .argument("<file>", "Workflow YAML file")
+  .action(() => {
+    process.stderr.write(`Error: Command 'workflow put' has been removed.
+Use 'workflow add' instead.
+
+For more information, see: uwf help workflow add
+`);
+    process.exit(1);
+  });
+
+thread
+  .command("step")
+  .description("[DEPRECATED] Use 'thread exec' instead")
+  .argument("<thread-id>", "Thread ULID")
+  .allowUnknownOption()
+  .action(() => {
+    process.stderr.write(`Error: Command 'thread step' has been removed.
+Use 'thread exec' instead.
+
+For more information, see: uwf help thread exec
+`);
+    process.exit(1);
+  });
+
+thread
+  .command("steps")
+  .description("[DEPRECATED] Use 'step list' instead")
+  .argument("<thread-id>", "Thread ULID")
+  .action(() => {
+    process.stderr.write(`Error: Command 'thread steps' has been removed.
+Use 'step list' instead.
+
+For more information, see: uwf help step list
+`);
+    process.exit(1);
+  });
+
+thread
+  .command("step-details")
+  .description("[DEPRECATED] Use 'step show' instead")
+  .argument("<step-hash>", "Step hash")
+  .action(() => {
+    process.stderr.write(`Error: Command 'thread step-details' has been removed.
+Use 'step show' instead.
+
+For more information, see: uwf help step show
+`);
+    process.exit(1);
+  });
+
+thread
+  .command("fork")
+  .description("[DEPRECATED] Use 'step fork' instead")
+  .argument("<step-hash>", "Step hash")
+  .action(() => {
+    process.stderr.write(`Error: Command 'thread fork' has been removed.
+Use 'step fork' instead.
+
+For more information, see: uwf help step fork
+`);
+    process.exit(1);
+  });
+
+thread
+  .command("kill")
+  .description("[DEPRECATED] Use 'thread stop' or 'thread cancel' instead")
+  .argument("<thread-id>", "Thread ULID")
+  .action(() => {
+    process.stderr.write(`Error: Command 'thread kill' has been removed.
+Use 'thread stop' to stop background execution (keep thread active),
+or 'thread cancel' to cancel and archive the thread.
+
+For more information, see:
+  uwf help thread stop
+  uwf help thread cancel
+`);
+    process.exit(1);
+  });
+
+thread
+  .command("running")
+  .description("[DEPRECATED] Use 'thread list --status running' instead")
+  .action(() => {
+    process.stderr.write(`Error: Command 'thread running' has been removed.
+Use 'thread list --status running' instead.
+
+For more information, see: uwf help thread list
+`);
+    process.exit(1);
+  });
+
+const skill = program.command("skill").description("Built-in skill references for agents");
+
+skill
+  .command("cli")
+  .description("Print a markdown reference of all uwf commands")
+  .action(() => {
+    console.log(cmdSkillCli());
+  });
+
+program
+  .command("setup")
+  .description("Configure provider, model, and agent")
+  .option("--provider <name>", "Provider name")
+  .option("--base-url <url>", "OpenAI-compatible API base URL")
+  .option("--api-key <key>", "API key")
+  .option("--model <name>", "Default model name")
+  .option("--agent <name>", "Default agent alias")
+  .action(
+    (opts: {
+      provider?: string;
+      baseUrl?: string;
+      apiKey?: string;
+      model?: string;
+      agent?: string;
+    }) => {
+      const storageRoot = resolveStorageRoot();
+      runAction(async () => {
+        if (opts.provider && opts.baseUrl && opts.apiKey && opts.model) {
+          const result = await cmdSetup({
+            provider: opts.provider,
+            baseUrl: opts.baseUrl,
+            apiKey: opts.apiKey,
+            model: opts.model,
+            agent: opts.agent ?? undefined,
+            storageRoot,
+          });
+          writeOutput(result);
+        } else if (!opts.provider && !opts.baseUrl && !opts.apiKey && !opts.model) {
+          await cmdSetupInteractive(storageRoot);
+        } else {
+          throw new Error(
+            "Non-interactive setup requires all of: --provider, --base-url, --api-key, --model",
+          );
+        }
+      });
+    },
+  );
+
+const cas = program.command("cas").description("Content-addressable storage operations");
+
+cas
+  .command("get")
+  .description("Read a CAS node (type + payload; use --timestamp to include timestamp)")
+  .argument("<hash>", "CAS hash (13 char)")
+  .option("--timestamp", "Include timestamp in output")
+  .action((hash: string, opts: { timestamp?: boolean }) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasGet(storageRoot, hash, opts));
+    });
+  });
+
+cas
+  .command("put")
+  .description("Store a node, print its hash")
+  .argument("<type-hash>", "Type (schema) hash")
+  .argument("<data>", "JSON file path or inline JSON string")
+  .action((typeHash: string, data: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasPut(storageRoot, typeHash, data));
+    });
+  });
+
+cas
+  .command("put-text")
+  .description("Store a plain text string, print its hash")
+  .argument("<text>", "Text content to store")
+  .action((text: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasPutText(storageRoot, text));
+    });
+  });
+
+cas
+  .command("has")
+  .description("Check if a hash exists")
+  .argument("<hash>", "CAS hash (13 char)")
+  .action((hash: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdCasHas(storageRoot, hash);
+      writeOutput(result);
+      if (!result.exists) {
+        process.exit(1);
+      }
+    });
+  });
+
+cas
+  .command("refs")
+  .description("List direct CAS references from a node")
+  .argument("<hash>", "CAS hash (13 char)")
+  .action((hash: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasRefs(storageRoot, hash));
+    });
+  });
+
+cas
+  .command("walk")
+  .description("Recursive traversal from a node")
+  .argument("<hash>", "CAS hash (13 char)")
+  .action((hash: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasWalk(storageRoot, hash));
+    });
+  });
+
+cas
+  .command("reindex")
+  .description("Rebuild type index from all CAS nodes")
+  .action(() => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasReindex(storageRoot));
+    });
+  });
+
+const casSchema = cas.command("schema").description("CAS schema operations");
+
+casSchema
+  .command("list")
+  .description("List all registered schemas")
+  .action(() => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasSchemaList(storageRoot));
+    });
+  });
+
+casSchema
+  .command("get")
+  .description("Show a schema by its type hash")
+  .argument("<hash>", "Schema type hash")
+  .action((hash: string) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      writeOutput(await cmdCasSchemaGet(storageRoot, hash));
+    });
+  });
+
+const log = program.command("log").description("Process-level debug logs");
+
+log
+  .command("list")
+  .description("List log files with sizes")
+  .action(() => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdLogList(storageRoot);
+      writeOutput(result);
+    });
+  });
+
+log
+  .command("show")
+  .description("Show and filter log entries")
+  .option("--thread <thread-id>", "Filter by thread ID")
+  .option("--process <pid>", "Filter by process ID")
+  .option("--date <date>", "Filter by date (YYYY-MM-DD)")
+  .action(
+    (opts: {
+      thread: string | undefined;
+      process: string | undefined;
+      date: string | undefined;
+    }) => {
+      const storageRoot = resolveStorageRoot();
+      runAction(async () => {
+        const result = await cmdLogShow(storageRoot, {
+          thread: opts.thread ?? null,
+          process: opts.process ?? null,
+          date: opts.date ?? null,
+        });
+        writeOutput(result);
+      });
+    },
+  );
+
+log
+  .command("clean")
+  .description("Delete log files older than given date")
+  .requiredOption("--before <date>", "Delete files before this date (YYYY-MM-DD)")
+  .action((opts: { before: string }) => {
+    const storageRoot = resolveStorageRoot();
+    runAction(async () => {
+      const result = await cmdLogClean(storageRoot, opts.before);
+      writeOutput(result);
+    });
+  });
+
+program.parseAsync(process.argv).catch((e: unknown) => {
+  const message = e instanceof Error ? e.message : String(e);
+  process.stderr.write(`${message}\n`);
+  process.exit(1);
+});

packages/cli-workflow/src/commands/cas.ts

@@ -1,10 +1,12 @@
 import { readFileSync } from "node:fs";
 import { join } from "node:path";
 
-import type { Hash, JSONSchema, Store } from "@uncaged/json-cas";
-import { bootstrap, getSchema, refs, walk } from "@uncaged/json-cas";
+import type { JSONSchema, Store } from "@uncaged/json-cas";
+import { bootstrap, getSchema, putSchema, refs, walk } from "@uncaged/json-cas";
 import { createFsStore } from "@uncaged/json-cas-fs";
 
+import { TEXT_SCHEMA } from "../schemas.js";
+
 // ---- Helpers ----
 
 function openStore(storageRoot: string): Store {
@@ -53,18 +55,12 @@ export async function cmdCasPut(
   return { hash };
 }
 
-export async function cmdCasHas(
-  storageRoot: string,
-  hash: string,
-): Promise<{ exists: boolean }> {
+export async function cmdCasHas(storageRoot: string, hash: string): Promise<{ exists: boolean }> {
   const store = openStore(storageRoot);
   return { exists: store.has(hash) };
 }
 
-export async function cmdCasRefs(
-  storageRoot: string,
-  hash: string,
-): Promise<{ refs: string[] }> {
+export async function cmdCasRefs(storageRoot: string, hash: string): Promise<{ refs: string[] }> {
   const store = openStore(storageRoot);
   const node = store.get(hash);
   if (node === null) {
@@ -73,10 +69,7 @@ export async function cmdCasRefs(
   return { refs: refs(store, node) };
 }
 
-export async function cmdCasWalk(
-  storageRoot: string,
-  hash: string,
-): Promise<{ hashes: string[] }> {
+export async function cmdCasWalk(storageRoot: string, hash: string): Promise<{ hashes: string[] }> {
   const store = openStore(storageRoot);
   const result: string[] = [];
   walk(store, hash, (h) => {
@@ -90,9 +83,7 @@ export type SchemaListEntry = {
   title: string;
 };
 
-export async function cmdCasSchemaList(
-  storageRoot: string,
-): Promise<SchemaListEntry[]> {
+export async function cmdCasSchemaList(storageRoot: string): Promise<SchemaListEntry[]> {
   const store = openStore(storageRoot);
   const metaHash = await bootstrap(store);
   const entries: SchemaListEntry[] = [];
@@ -115,9 +106,7 @@ export async function cmdCasSchemaList(
   return entries;
 }
 
-export async function cmdCasReindex(
-  storageRoot: string,
-): Promise<{ status: string }> {
+export async function cmdCasReindex(storageRoot: string): Promise<{ status: string }> {
   const indexDir = join(storageRoot, "cas", "_index");
   const { rmSync } = await import("node:fs");
   rmSync(indexDir, { recursive: true, force: true });
@@ -126,10 +115,7 @@ export async function cmdCasReindex(
   return { status: "reindexed" };
 }
 
-export async function cmdCasSchemaGet(
-  storageRoot: string,
-  hash: string,
-): Promise<unknown> {
+export async function cmdCasSchemaGet(storageRoot: string, hash: string): Promise<unknown> {
   const store = openStore(storageRoot);
   const schema = getSchema(store, hash);
   if (schema === null) {
@@ -137,3 +123,10 @@ export async function cmdCasSchemaGet(
   }
   return schema;
 }
+
+export async function cmdCasPutText(storageRoot: string, text: string): Promise<{ hash: string }> {
+  const store = openStore(storageRoot);
+  const typeHash = await putSchema(store, TEXT_SCHEMA);
+  const hash = await store.put(typeHash, text);
+  return { hash };
+}

packages/cli-workflow/src/commands/log.ts

@@ -0,0 +1,116 @@
+import { readdir, readFile, stat, unlink } from "node:fs/promises";
+import { join } from "node:path";
+
+type LogListItem = {
+  name: string;
+  size: number;
+  date: string;
+};
+
+type LogShowFilter = {
+  thread: string | null;
+  process: string | null;
+  date: string | null;
+};
+
+type LogEntry = {
+  ts: string;
+  pid: string;
+  tag: string;
+  msg: string;
+  thread: string | null;
+  workflow: string | null;
+};
+
+type LogCleanResult = {
+  deleted: number;
+};
+
+function logsDir(storageRoot: string): string {
+  return join(storageRoot, "logs");
+}
+
+async function listLogFiles(dir: string): Promise<Array<string>> {
+  try {
+    const files = await readdir(dir);
+    return files.filter((f) => f.endsWith(".jsonl")).sort();
+  } catch {
+    return [];
+  }
+}
+
+function dateFromFilename(name: string): string {
+  return name.replace(".jsonl", "");
+}
+
+async function parseJsonlFile(path: string): Promise<Array<LogEntry>> {
+  const content = await readFile(path, "utf-8");
+  const lines = content
+    .trim()
+    .split("\n")
+    .filter((l) => l.length > 0);
+  return lines.map((line) => JSON.parse(line) as LogEntry);
+}
+
+export async function cmdLogList(storageRoot: string): Promise<Array<LogListItem>> {
+  const dir = logsDir(storageRoot);
+  const files = await listLogFiles(dir);
+  const items: Array<LogListItem> = [];
+  for (const name of files) {
+    const s = await stat(join(dir, name));
+    items.push({ name, size: s.size, date: dateFromFilename(name) });
+  }
+  // sort by date descending
+  items.sort((a, b) => (a.date > b.date ? -1 : a.date < b.date ? 1 : 0));
+  return items;
+}
+
+export async function cmdLogShow(
+  storageRoot: string,
+  filter: LogShowFilter,
+): Promise<Array<LogEntry>> {
+  const dir = logsDir(storageRoot);
+  let files: Array<string>;
+
+  if (filter.date !== null) {
+    files = [`${filter.date}.jsonl`];
+  } else {
+    files = await listLogFiles(dir);
+  }
+
+  let entries: Array<LogEntry> = [];
+  for (const file of files) {
+    try {
+      const parsed = await parseJsonlFile(join(dir, file));
+      entries = entries.concat(parsed);
+    } catch {
+      // file doesn't exist or is unreadable, skip
+    }
+  }
+
+  if (filter.thread !== null) {
+    entries = entries.filter((e) => e.thread === filter.thread);
+  }
+  if (filter.process !== null) {
+    entries = entries.filter((e) => e.pid === filter.process);
+  }
+
+  entries.sort((a, b) => (a.ts < b.ts ? -1 : a.ts > b.ts ? 1 : 0));
+  return entries;
+}
+
+export async function cmdLogClean(storageRoot: string, before: string): Promise<LogCleanResult> {
+  const dir = logsDir(storageRoot);
+  const files = await listLogFiles(dir);
+  let deleted = 0;
+
+  for (const name of files) {
+    const date = dateFromFilename(name);
+    if (date < before) {
+      await unlink(join(dir, name));
+      deleted++;
+    }
+  }
+
+  return { deleted };
+}

packages/cli-workflow/src/commands/setup.ts

@@ -0,0 +1,568 @@
+import { existsSync, mkdirSync, readdirSync, readFileSync, statSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+import { stdin as input, stdout as output } from "node:process";
+import { createInterface } from "node:readline/promises";
+import type { Result } from "@uncaged/workflow-util";
+import { parse, stringify } from "yaml";
+
+/**
+ * Send a minimal chat completion request to verify the model is reachable.
+ * Returns ok on 2xx, error with reason string otherwise.
+ */
+export async function validateModel(
+  baseUrl: string,
+  apiKey: string,
+  model: string,
+): Promise<Result<void, string>> {
+  try {
+    const url = `${baseUrl.replace(/\/+$/, "")}/chat/completions`;
+    const res = await fetch(url, {
+      method: "POST",
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        "Content-Type": "application/json",
+      },
+      body: JSON.stringify({
+        model,
+        messages: [{ role: "user", content: "hi" }],
+        max_tokens: 1,
+      }),
+      signal: AbortSignal.timeout(15_000),
+    });
+    if (!res.ok) {
+      return { ok: false, error: `HTTP ${res.status} ${res.statusText}` };
+    }
+    return { ok: true, value: undefined };
+  } catch (err: unknown) {
+    if (err instanceof DOMException && err.name === "AbortError") {
+      return { ok: false, error: "Request timed out — model endpoint unreachable" };
+    }
+    return { ok: false, error: `Network error — could not reach endpoint (${String(err)})` };
+  }
+}
+
+/**
+ * Preset provider list — embedded to avoid runtime YAML loading dependency.
+ * Keep in sync with providers.yaml in cli-workflow.
+ */
+const PRESET_PROVIDERS = [
+  // International
+  { name: "openai", label: "OpenAI", baseUrl: "https://api.openai.com/v1" },
+  { name: "xai", label: "xAI", baseUrl: "https://api.x.ai/v1" },
+  { name: "openrouter", label: "OpenRouter", baseUrl: "https://openrouter.ai/api/v1" },
+  { name: "venice", label: "Venice", baseUrl: "https://api.venice.ai/api/v1" },
+  // China
+  {
+    name: "dashscope",
+    label: "DashScope (Alibaba)",
+    baseUrl: "https://dashscope.aliyuncs.com/compatible-mode/v1",
+  },
+  { name: "deepseek", label: "DeepSeek", baseUrl: "https://api.deepseek.com/v1" },
+  { name: "siliconflow", label: "SiliconFlow", baseUrl: "https://api.siliconflow.cn/v1" },
+  {
+    name: "volcengine",
+    label: "Volcengine (ByteDance)",
+    baseUrl: "https://ark.cn-beijing.volces.com/api/v3",
+  },
+  { name: "kimi", label: "Kimi (Moonshot)", baseUrl: "https://api.moonshot.cn/v1" },
+  { name: "glm", label: "GLM (Zhipu AI)", baseUrl: "https://open.bigmodel.cn/api/paas/v4" },
+  { name: "stepfun", label: "StepFun", baseUrl: "https://api.stepfun.com/v1" },
+  { name: "minimax", label: "MiniMax", baseUrl: "https://api.minimax.io/v1" },
+  // Local
+  { name: "ollama", label: "Ollama (local)", baseUrl: "http://localhost:11434/v1" },
+] as const;
+
+type SetupArgs = {
+  provider: string;
+  baseUrl: string;
+  apiKey: string;
+  model: string;
+  agent?: string | undefined;
+  storageRoot: string;
+};
+
+function getConfigPath(root: string): string {
+  return join(root, "config.yaml");
+}
+
+function getEnvPath(root: string): string {
+  return join(root, ".env");
+}
+
+/**
+ * Load existing config.yaml or return empty structure.
+ */
+function loadExistingConfig(configPath: string): Record<string, unknown> {
+  try {
+    if (existsSync(configPath)) {
+      const raw = parse(readFileSync(configPath, "utf8")) as unknown;
+      if (typeof raw === "object" && raw !== null && !Array.isArray(raw)) {
+        return raw as Record<string, unknown>;
+      }
+    }
+  } catch {
+    // ignore parse errors, start fresh
+  }
+  return {};
+}
+
+/**
+ * Load existing .env as key=value map.
+ */
+function loadEnvFile(envPath: string): Record<string, string> {
+  const env: Record<string, string> = {};
+  try {
+    if (existsSync(envPath)) {
+      for (const line of readFileSync(envPath, "utf8").split("\n")) {
+        const trimmed = line.trim();
+        if (trimmed === "" || trimmed.startsWith("#")) continue;
+        const eq = trimmed.indexOf("=");
+        if (eq > 0) {
+          env[trimmed.slice(0, eq)] = trimmed.slice(eq + 1);
+        }
+      }
+    }
+  } catch {
+    // ignore
+  }
+  return env;
+}
+
+function saveEnvFile(envPath: string, env: Record<string, string>): void {
+  const lines = Object.entries(env).map(([k, v]) => `${k}=${v}`);
+  writeFileSync(envPath, `${lines.join("\n")}\n`, "utf8");
+}
+
+function apiKeyEnvName(providerName: string): string {
+  return `${providerName.toUpperCase().replace(/[^A-Z0-9]/g, "_")}_API_KEY`;
+}
+
+// ──────────────────────────────────────────────────────────────────────────────
+// Extracted helpers — _discoverAgents
+// ──────────────────────────────────────────────────────────────────────────────
+
+/**
+ * Scans directories from a PATH string for uwf-* executables.
+ */
+export async function _searchPathDirs(pathEnv: string): Promise<string[]> {
+  if (!pathEnv) return [];
+  const dirs = pathEnv.split(":").filter((d) => d.length > 0);
+  const agents = new Set<string>();
+  for (const dir of dirs) {
+    _scanDirForAgents(dir, agents);
+  }
+  return Array.from(agents).sort();
+}
+
+function _scanDirForAgents(dir: string, agents: Set<string>): void {
+  try {
+    if (!existsSync(dir)) return;
+    const entries = readdirSync(dir);
+    for (const entry of entries) {
+      if (!entry.startsWith("uwf-") || entry === "uwf") continue;
+      if (_isExecutableFile(join(dir, entry))) {
+        agents.add(entry);
+      }
+    }
+  } catch {
+    // Skip inaccessible directories
+  }
+}
+
+function _isExecutableFile(fullPath: string): boolean {
+  try {
+    const s = statSync(fullPath);
+    return s.isFile() && (s.mode & 0o111) !== 0;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Parses the stdout of `which -a` into sorted unique basenames.
+ */
+export function _parseWhichOutput(text: string): string[] {
+  if (!text) return [];
+  const agents = new Set<string>();
+  for (const line of text.trim().split("\n")) {
+    if (!line) continue;
+    const basename = line.split("/").pop() ?? "";
+    if (basename.startsWith("uwf-") && basename !== "uwf") {
+      agents.add(basename);
+    }
+  }
+  return Array.from(agents).sort();
+}
+
+/**
+ * Discover uwf-* agent binaries in PATH.
+ * Returns sorted list of binary names (e.g., ["uwf-hermes", "uwf-claude-code"]).
+ */
+export async function _discoverAgents(): Promise<string[]> {
+  try {
+    const agents = await _tryWhichDiscovery();
+    if (agents !== null) return agents;
+    return await _searchPathDirs(process.env.PATH ?? "");
+  } catch {
+    return [];
+  }
+}
+
+async function _tryWhichDiscovery(): Promise<string[] | null> {
+  try {
+    const proc = Bun.spawn(["which", "-a", "uwf-hermes", "uwf-claude-code", "uwf-cursor"], {
+      stdout: "pipe",
+      stderr: "pipe",
+    });
+    const text = await new Response(proc.stdout).text();
+    await proc.exited;
+    if (proc.exitCode !== 0) return null;
+    return _parseWhichOutput(text);
+  } catch {
+    return null;
+  }
+}
+
+// ──────────────────────────────────────────────────────────────────────────────
+// Extracted helpers — onData closure (promptSecret)
+// ──────────────────────────────────────────────────────────────────────────────
+
+/** Returns true for newline, carriage return, or EOF (EOT). */
+export function _isTerminator(c: string): boolean {
+  return c === "\n" || c === "\r" || c === "";
+}
+
+/** Returns true for DEL or backspace. */
+export function _isBackspace(c: string): boolean {
+  return c === "" || c === "\b";
+}
+
+// ──────────────────────────────────────────────────────────────────────────────
+// Extracted helpers — cmdSetupInteractive
+// ──────────────────────────────────────────────────────────────────────────────
+
+type ProviderEntry = { name: string; label: string; baseUrl: string };
+
+/** Prints the numbered provider list and custom option to stdout. */
+export function _printProviderMenu(providers: readonly ProviderEntry[]): void {
+  const numWidth = String(providers.length + 1).length;
+  for (let i = 0; i < providers.length; i++) {
+    const p = providers[i];
+    if (!p) continue;
+    const num = String(i + 1).padStart(numWidth);
+    console.log(`  ${num}) ${p.label.padEnd(28)} ${p.baseUrl}`);
+  }
+  const customNum = String(providers.length + 1).padStart(numWidth);
+  console.log(`  ${customNum}) Custom (enter name and URL manually)\n`);
+}
+
+/** Resolves a numeric choice string to a preset provider, or null for custom/invalid. */
+export function _resolveProviderChoice(
+  choice: string,
+  providers: readonly ProviderEntry[],
+): { providerName: string; baseUrl: string } | null {
+  const n = Number.parseInt(choice, 10);
+  if (Number.isNaN(n) || n < 1 || n > providers.length) return null;
+  const p = providers[n - 1];
+  if (!p) return null;
+  return { providerName: p.name, baseUrl: p.baseUrl };
+}
+
+/** Resolves numeric index or literal model name to a model string. */
+export function _resolveModelChoice(input: string, models: string[]): string {
+  const n = Number.parseInt(input, 10);
+  if (!Number.isNaN(n) && n >= 1 && n <= models.length) {
+    return models[n - 1] ?? input;
+  }
+  return input;
+}
+
+/** Prints the multi-column model list to stdout. */
+export function _printModelMenu(models: string[], termCols: number): void {
+  const nw = String(models.length).length;
+  const maxLen = models.reduce((m, s) => Math.max(m, s.length), 0);
+  const colWidth = nw + 2 + maxLen + 4;
+  const cols = Math.max(1, Math.floor(termCols / colWidth));
+  const rows = Math.ceil(models.length / cols);
+  for (let r = 0; r < rows; r++) {
+    let line = "";
+    for (let c = 0; c < cols; c++) {
+      const idx = c * rows + r;
+      if (idx >= models.length) break;
+      const num = String(idx + 1).padStart(nw);
+      const name = (models[idx] ?? "").padEnd(maxLen);
+      line += `  ${num}) ${name}  `;
+    }
+    console.log(line.trimEnd());
+  }
+}
+
+type ValidationResult = { ok: boolean; error: string | null };
+
+/** Prints the model validation result to stdout. */
+export function _printValidationResult(validation: ValidationResult): void {
+  if (validation.ok) {
+    console.log("✓ Model verified — connection successful.\n");
+  } else {
+    console.log(`\n⚠ Warning: Could not reach model — ${validation.error}`);
+    console.log(
+      "  Config saved, but you may want to try a different model or check your API key.\n",
+    );
+  }
+}
+
+// ──────────────────────────────────────────────────────────────────────────────
+
+/**
+ * Merge setup args into config.yaml structure. Non-destructive — preserves existing entries.
+ */
+function mergeConfig(existing: Record<string, unknown>, args: SetupArgs): Record<string, unknown> {
+  const providers = (
+    typeof existing.providers === "object" && existing.providers !== null
+      ? { ...(existing.providers as Record<string, unknown>) }
+      : {}
+  ) as Record<string, unknown>;
+
+  const envName = apiKeyEnvName(args.provider);
+  providers[args.provider] = { baseUrl: args.baseUrl, apiKeyEnv: envName };
+
+  const models = (
+    typeof existing.models === "object" && existing.models !== null
+      ? { ...(existing.models as Record<string, unknown>) }
+      : {}
+  ) as Record<string, unknown>;
+  models.default = { provider: args.provider, name: args.model };
+
+  const agents = (
+    typeof existing.agents === "object" && existing.agents !== null
+      ? { ...(existing.agents as Record<string, unknown>) }
+      : {}
+  ) as Record<string, unknown>;
+
+  const agentName = args.agent ?? "hermes";
+  if (Object.keys(agents).length === 0) {
+    agents.hermes = { command: "uwf-hermes", args: [] };
+  }
+
+  return {
+    ...existing,
+    providers,
+    models,
+    agents,
+    defaultAgent: existing.defaultAgent ?? agentName,
+    defaultModel: existing.defaultModel ?? "default",
+  };
+}
+
+/**
+ * Non-interactive setup. All required args provided via CLI flags.
+ */
+export async function cmdSetup(args: SetupArgs): Promise<Record<string, unknown>> {
+  const { storageRoot } = args;
+  mkdirSync(storageRoot, { recursive: true });
+
+  const configPath = getConfigPath(storageRoot);
+  const envPath = getEnvPath(storageRoot);
+
+  const existing = loadExistingConfig(configPath);
+  const merged = mergeConfig(existing, args);
+
+  writeFileSync(configPath, stringify(merged, { indent: 2 }), "utf8");
+
+  // Write API key to .env
+  const envName = apiKeyEnvName(args.provider);
+  const envData = loadEnvFile(envPath);
+  envData[envName] = args.apiKey;
+  saveEnvFile(envPath, envData);
+
+  // Validate model connectivity
+  const validation = await validateModel(args.baseUrl, args.apiKey, args.model);
+
+  return {
+    configPath,
+    envPath,
+    provider: args.provider,
+    model: args.model,
+    defaultAgent: merged.defaultAgent,
+    validation,
+  };
+}
+
+type SecretState = {
+  buf: string;
+  rawWasSet: boolean;
+  resolve: (value: string) => void;
+  onData: (chunk: string) => void;
+};
+
+function _handleSecretTerminator(state: SecretState): void {
+  if (process.stdin.isTTY) process.stdin.setRawMode(state.rawWasSet);
+  process.stdin.pause();
+  process.stdin.removeListener("data", state.onData);
+  process.stdout.write("\n");
+  state.resolve(state.buf.trim());
+}
+
+function _handleSecretBackspace(state: SecretState): void {
+  if (state.buf.length > 0) {
+    state.buf = state.buf.slice(0, -1);
+    process.stdout.write("\b \b");
+  }
+}
+
+function _handleSecretChar(c: string, state: SecretState): boolean {
+  if (_isTerminator(c)) {
+    _handleSecretTerminator(state);
+    return true;
+  }
+  if (_isBackspace(c)) {
+    _handleSecretBackspace(state);
+    return false;
+  }
+  if (c === "") {
+    if (process.stdin.isTTY) process.stdin.setRawMode(state.rawWasSet);
+    process.exit(130);
+  }
+  state.buf += c;
+  process.stdout.write("*");
+  return false;
+}
+
+/** Read a line with terminal echo disabled (for secrets). */
+async function promptSecret(label: string): Promise<string> {
+  process.stdout.write(label);
+  return new Promise((resolve) => {
+    const rawWasSet = process.stdin.isRaw;
+    if (process.stdin.isTTY) {
+      process.stdin.setRawMode(true);
+    }
+    process.stdin.resume();
+    process.stdin.setEncoding("utf8");
+
+    const state: SecretState = { buf: "", rawWasSet, resolve, onData: () => {} };
+    state.onData = (chunk: string) => {
+      for (const c of chunk.toString()) {
+        if (_handleSecretChar(c, state)) return;
+      }
+    };
+    process.stdin.on("data", state.onData);
+  });
+}
+
+/** Fetch available models from an OpenAI-compatible /models endpoint. */
+async function fetchModels(baseUrl: string, apiKey: string): Promise<string[]> {
+  try {
+    const url = `${baseUrl.replace(/\/+$/, "")}/models`;
+    const res = await fetch(url, {
+      headers: { Authorization: `Bearer ${apiKey}` },
+      signal: AbortSignal.timeout(10_000),
+    });
+    if (!res.ok) return [];
+    const body = (await res.json()) as { data?: { id: string }[] };
+    if (!Array.isArray(body.data)) return [];
+    const NON_CHAT =
+      /speech|embed|image|video|audio|ocr|rerank|tts|asr|paraformer|sambert|cosyvoice|wordart|wanx|wan2|flux|stable-diffusion|gui-/i;
+    return body.data
+      .map((m) => m.id)
+      .filter((id) => !NON_CHAT.test(id))
+      .sort();
+  } catch {
+    return [];
+  }
+}
+
+async function _promptProviderSelection(
+  rl: ReturnType<typeof createInterface>,
+): Promise<{ providerName: string; baseUrl: string }> {
+  console.log("Select a provider:\n");
+  _printProviderMenu(PRESET_PROVIDERS);
+
+  const choice = (await rl.question(`Choose [1-${PRESET_PROVIDERS.length + 1}]: `)).trim();
+  const choiceNum = Number.parseInt(choice, 10);
+  if (Number.isNaN(choiceNum) || choiceNum < 1 || choiceNum > PRESET_PROVIDERS.length + 1) {
+    throw new Error(`Invalid choice: ${choice}`);
+  }
+
+  const preset = _resolveProviderChoice(choice, PRESET_PROVIDERS);
+  if (preset) {
+    const selected = PRESET_PROVIDERS[choiceNum - 1];
+    if (selected) {
+      console.log(`\n  → ${selected.label} (${selected.baseUrl})\n`);
+    }
+    return preset;
+  }
+
+  const providerName = (await rl.question("Provider name (e.g. my-proxy): ")).trim();
+  if (!providerName) throw new Error("Provider name required");
+  const baseUrl = (await rl.question("OpenAI-compatible API base URL: ")).trim();
+  if (!baseUrl) throw new Error("Base URL required");
+  return { providerName, baseUrl };
+}
+
+async function _promptModelSelection(
+  rl: ReturnType<typeof createInterface>,
+  baseUrl: string,
+  apiKey: string,
+): Promise<string> {
+  console.log("\nFetching available models...");
+  const models = await fetchModels(baseUrl, apiKey);
+
+  if (models.length === 0) {
+    console.log("Could not fetch models. Enter model name manually.");
+    const model = (await rl.question("Default model (e.g. qwen-plus, gpt-4o): ")).trim();
+    if (!model) throw new Error("Model required");
+    return model;
+  }
+  console.log(`\nAvailable models (${models.length}):\n`);
+  _printModelMenu(models, process.stdout.columns || 100);
+  console.log(`\nChoose a number, or type a model name directly.`);
+  const modelInput = (await rl.question(`Default model [1-${models.length}]: `)).trim();
+  if (!modelInput) throw new Error("Model required");
+  return _resolveModelChoice(modelInput, models);
+}
+
+/**
+ * Interactive setup — prompts user for provider, API key, model.
+ */
+export async function cmdSetupInteractive(storageRoot: string): Promise<Record<string, unknown>> {
+  const rl = createInterface({ input, output });
+
+  try {
+    console.log("Configure LLM provider for uwf workflow agents.\n");
+
+    const { providerName, baseUrl } = await _promptProviderSelection(rl);
+
+    // 2. API key
+    rl.close();
+    const apiKey = await promptSecret("API key: ");
+    if (!apiKey) throw new Error("API key required");
+
+    // 3. Model selection
+    const rl2 = createInterface({ input, output });
+    const model = await _promptModelSelection(rl2, baseUrl, apiKey);
+    rl2.close();
+    console.log(`  → ${providerName}/${model}\n`);
+
+    const setupResult = await cmdSetup({
+      provider: providerName,
+      baseUrl,
+      apiKey,
+      model,
+      storageRoot,
+    });
+
+    // Show validation result
+    if (setupResult.validation && typeof setupResult.validation === "object") {
+      _printValidationResult(setupResult.validation as ValidationResult);
+    }
+    console.log("Setup complete! Get started:\n");
+    console.log("  uwf workflow put <workflow.yaml>   Register a workflow");
+    console.log('  uwf thread start <name> -p "..."   Start a thread');
+    console.log("  uwf thread step <thread-id>        Execute next step");
+    console.log("");
+
+    return null as unknown as Record<string, unknown>;
+  } finally {
+    rl.close();
+  }
+}

packages/cli-workflow/src/commands/shared.ts

@@ -0,0 +1,231 @@
+import type { Store as CasStore, JSONSchema } from "@uncaged/json-cas";
+import { getSchema } from "@uncaged/json-cas";
+import type {
+  CasRef,
+  StartNodePayload,
+  StepNodePayload,
+  ThreadId,
+} from "@uncaged/workflow-protocol";
+import { findThreadInHistory, loadThreadsIndex, type UwfStore } from "../store.js";
+
+type ChainState = {
+  startHash: CasRef;
+  start: StartNodePayload;
+  stepsNewestFirst: StepNodePayload[];
+  headIsStart: boolean;
+};
+
+type OrderedStepItem = {
+  hash: CasRef;
+  payload: StepNodePayload;
+  timestamp: number;
+};
+
+function fail(message: string): never {
+  process.stderr.write(`${message}\n`);
+  process.exit(1);
+}
+
+function walkChain(uwf: UwfStore, headHash: CasRef): ChainState {
+  const headNode = uwf.store.get(headHash);
+  if (headNode === null) {
+    fail(`CAS node not found: ${headHash}`);
+  }
+
+  if (headNode.type === uwf.schemas.startNode) {
+    return {
+      startHash: headHash,
+      start: headNode.payload as StartNodePayload,
+      stepsNewestFirst: [],
+      headIsStart: true,
+    };
+  }
+
+  if (headNode.type !== uwf.schemas.stepNode) {
+    fail(`head ${headHash} is not a StartNode or StepNode`);
+  }
+
+  const stepsNewestFirst: StepNodePayload[] = [];
+  let hash: CasRef | null = headHash;
+
+  while (hash !== null) {
+    const node = uwf.store.get(hash);
+    if (node === null) {
+      fail(`CAS node not found while walking chain: ${hash}`);
+    }
+    if (node.type !== uwf.schemas.stepNode) {
+      break;
+    }
+    const payload = node.payload as StepNodePayload;
+    stepsNewestFirst.push(payload);
+    hash = payload.prev;
+  }
+
+  const newest = stepsNewestFirst[0];
+  if (newest === undefined) {
+    fail(`empty step chain at head ${headHash}`);
+  }
+
+  const startNode = uwf.store.get(newest.start);
+  if (startNode === null || startNode.type !== uwf.schemas.startNode) {
+    fail(`StartNode not found: ${newest.start}`);
+  }
+
+  return {
+    startHash: newest.start,
+    start: startNode.payload as StartNodePayload,
+    stepsNewestFirst,
+    headIsStart: false,
+  };
+}
+
+function expandOutput(uwf: UwfStore, outputRef: CasRef): unknown {
+  const node = uwf.store.get(outputRef);
+  if (node === null) {
+    return {};
+  }
+  return node.payload;
+}
+
+/**
+ * Recursively expand all cas_ref fields in a CAS node's payload,
+ * replacing hash strings with the referenced node's expanded payload.
+ */
+function expandDeep(store: CasStore, hash: CasRef, visited?: Set<string>): unknown {
+  const seen = visited ?? new Set<string>();
+  if (seen.has(hash)) return hash; // cycle guard
+  seen.add(hash);
+
+  const node = store.get(hash);
+  if (node === null) return hash;
+
+  const schema = getSchema(store, node.type);
+  if (schema === null) return node.payload;
+
+  return expandValue(store, schema, node.payload, seen);
+}
+
+function expandCasRefField(store: CasStore, value: unknown, visited: Set<string>): unknown {
+  if (typeof value === "string") {
+    return expandDeep(store, value as CasRef, visited);
+  }
+  return value;
+}
+
+function expandAnyOfField(
+  store: CasStore,
+  schema: JSONSchema,
+  value: unknown,
+  visited: Set<string>,
+): unknown {
+  if (!Array.isArray(schema.anyOf)) return value;
+  for (const sub of schema.anyOf as JSONSchema[]) {
+    if (sub.format === "cas_ref" && typeof value === "string") {
+      return expandDeep(store, value as CasRef, visited);
+    }
+  }
+  return value;
+}
+
+function expandArrayField(
+  store: CasStore,
+  schema: JSONSchema,
+  value: unknown,
+  visited: Set<string>,
+): unknown {
+  if (!schema.items || !Array.isArray(value)) return value;
+  const itemSchema = schema.items as JSONSchema;
+  return (value as unknown[]).map((item) => expandValue(store, itemSchema, item, visited));
+}
+
+function expandObjectField(
+  store: CasStore,
+  schema: JSONSchema,
+  value: unknown,
+  visited: Set<string>,
+): unknown {
+  if (value === null || typeof value !== "object" || Array.isArray(value) || !schema.properties) {
+    return value;
+  }
+  const props = schema.properties as Record<string, JSONSchema>;
+  const obj = value as Record<string, unknown>;
+  const result: Record<string, unknown> = {};
+  for (const [key, val] of Object.entries(obj)) {
+    const propSchema = props[key];
+    result[key] = propSchema ? expandValue(store, propSchema, val, visited) : val;
+  }
+  return result;
+}
+
+function expandValue(
+  store: CasStore,
+  schema: JSONSchema,
+  value: unknown,
+  visited: Set<string>,
+): unknown {
+  if (schema.format === "cas_ref") return expandCasRefField(store, value, visited);
+  if (Array.isArray(schema.anyOf)) return expandAnyOfField(store, schema, value, visited);
+  if (schema.type === "array") return expandArrayField(store, schema, value, visited);
+  return expandObjectField(store, schema, value, visited);
+}
+
+function collectOrderedSteps(
+  uwf: UwfStore,
+  headHash: CasRef,
+  chain: ChainState,
+): OrderedStepItem[] {
+  let hash: CasRef | null = headHash;
+  const hashToNode = new Map<string, { payload: StepNodePayload; timestamp: number }>();
+  while (hash !== null) {
+    const node = uwf.store.get(hash);
+    if (node === null || node.type !== uwf.schemas.stepNode) {
+      break;
+    }
+    const payload = node.payload as StepNodePayload;
+    hashToNode.set(hash, { payload, timestamp: node.timestamp });
+    hash = payload.prev;
+  }
+
+  let cur: CasRef | null = chain.headIsStart ? null : headHash;
+  const ordered: OrderedStepItem[] = [];
+  while (cur !== null) {
+    const entry = hashToNode.get(cur);
+    if (entry === undefined) {
+      break;
+    }
+    ordered.push({ hash: cur, ...entry });
+    cur = entry.payload.prev;
+  }
+
+  ordered.reverse();
+  return ordered;
+}
+
+async function resolveHeadHash(storageRoot: string, threadId: ThreadId): Promise<CasRef> {
+  const index = await loadThreadsIndex(storageRoot);
+  const activeHead = index[threadId];
+  if (activeHead !== undefined) {
+    return activeHead;
+  }
+  const hist = await findThreadInHistory(storageRoot, threadId);
+  if (hist !== null) {
+    return hist.head;
+  }
+  fail(`thread not found: ${threadId}`);
+}
+
+export {
+  type ChainState,
+  collectOrderedSteps,
+  expandAnyOfField,
+  expandArrayField,
+  expandCasRefField,
+  expandDeep,
+  expandObjectField,
+  expandOutput,
+  expandValue,
+  fail,
+  type OrderedStepItem,
+  resolveHeadHash,
+  walkChain,
+};

packages/cli-workflow/src/commands/skill.ts

@@ -0,0 +1 @@
+export { generateCliReference as cmdSkillCli } from "@uncaged/workflow-util";

packages/cli-workflow/src/commands/step.ts

@@ -0,0 +1,256 @@
+import type { BootstrapCapableStore } from "@uncaged/json-cas";
+import type {
+  CasRef,
+  StartEntry,
+  StepEntry,
+  StepNodePayload,
+  ThreadForkOutput,
+  ThreadId,
+  ThreadStepsOutput,
+} from "@uncaged/workflow-protocol";
+import { generateUlid } from "@uncaged/workflow-util";
+import { createUwfStore, loadThreadsIndex, saveThreadsIndex } from "../store.js";
+import {
+  collectOrderedSteps,
+  expandDeep,
+  expandOutput,
+  fail,
+  resolveHeadHash,
+  walkChain,
+} from "./shared.js";
+
+type TurnData = {
+  index: number;
+  content: string;
+};
+
+/**
+ * List all steps in a thread (previously: thread steps)
+ */
+export async function cmdStepList(
+  storageRoot: string,
+  threadId: ThreadId,
+): Promise<ThreadStepsOutput> {
+  const headHash = await resolveHeadHash(storageRoot, threadId);
+  const uwf = await createUwfStore(storageRoot);
+  const chain = walkChain(uwf, headHash);
+
+  const startNode = uwf.store.get(chain.startHash);
+  if (startNode === null) {
+    fail(`StartNode not found: ${chain.startHash}`);
+  }
+
+  const startEntry: StartEntry = {
+    hash: chain.startHash,
+    workflow: chain.start.workflow,
+    prompt: chain.start.prompt,
+    timestamp: startNode.timestamp,
+  };
+
+  const stepEntries: StepEntry[] = [];
+  const ordered = collectOrderedSteps(uwf, headHash, chain);
+
+  for (const item of ordered) {
+    stepEntries.push({
+      hash: item.hash,
+      role: item.payload.role,
+      output: expandOutput(uwf, item.payload.output),
+      detail: item.payload.detail ?? null,
+      agent: item.payload.agent,
+      timestamp: item.timestamp,
+    });
+  }
+
+  return {
+    thread: threadId,
+    workflow: chain.start.workflow,
+    steps: [startEntry, ...stepEntries],
+  };
+}
+
+/**
+ * Show details of a specific step (previously: thread step-details)
+ */
+export async function cmdStepShow(storageRoot: string, stepHash: CasRef): Promise<unknown> {
+  const uwf = await createUwfStore(storageRoot);
+  const node = uwf.store.get(stepHash);
+  if (node === null) {
+    fail(`CAS node not found: ${stepHash}`);
+  }
+  if (node.type !== uwf.schemas.stepNode) {
+    fail(`node ${stepHash} is not a StepNode`);
+  }
+  const payload = node.payload as StepNodePayload;
+  if (!payload.detail) {
+    fail(`step ${stepHash} has no detail`);
+  }
+  return expandDeep(uwf.store, payload.detail);
+}
+
+/**
+ * Fork a thread from a specific step (previously: thread fork)
+ */
+export async function cmdStepFork(
+  storageRoot: string,
+  stepHash: CasRef,
+): Promise<ThreadForkOutput> {
+  const uwf = await createUwfStore(storageRoot);
+  const node = uwf.store.get(stepHash);
+  if (node === null) {
+    fail(`CAS node not found: ${stepHash}`);
+  }
+  if (node.type !== uwf.schemas.startNode && node.type !== uwf.schemas.stepNode) {
+    fail(`node ${stepHash} is not a StartNode or StepNode`);
+  }
+
+  const newThreadId = generateUlid(Date.now()) as ThreadId;
+  const index = await loadThreadsIndex(storageRoot);
+  index[newThreadId] = stepHash;
+  await saveThreadsIndex(storageRoot, index);
+
+  return {
+    thread: newThreadId,
+    forkedFrom: {
+      step: stepHash,
+    },
+  };
+}
+
+/**
+ * Load and validate step detail node from CAS store
+ */
+function loadStepDetail(store: BootstrapCapableStore, detailRef: CasRef): Record<string, unknown> {
+  const detailNode = store.get(detailRef);
+  if (detailNode === null) {
+    fail(`detail node not found: ${detailRef}`);
+  }
+  return detailNode.payload as Record<string, unknown>;
+}
+
+/**
+ * Load all turn nodes from CAS store and extract content
+ */
+function loadTurnData(store: BootstrapCapableStore, turns: unknown): TurnData[] {
+  if (!Array.isArray(turns) || turns.length === 0) {
+    return [];
+  }
+
+  const turnData: TurnData[] = [];
+  for (const turnRef of turns) {
+    if (typeof turnRef !== "string") {
+      continue;
+    }
+    const turnNode = store.get(turnRef as CasRef);
+    if (turnNode === null) {
+      continue;
+    }
+    const turn = turnNode.payload as Record<string, unknown>;
+    if (typeof turn.content === "string") {
+      turnData.push({
+        index: typeof turn.index === "number" ? turn.index : turnData.length,
+        content: turn.content,
+      });
+    }
+  }
+  return turnData;
+}
+
+/**
+ * Select turns that fit within quota, working backwards from most recent
+ */
+function selectTurnsForQuota(turnData: TurnData[], availableQuota: number): TurnData[] {
+  const selectedTurns: TurnData[] = [];
+  let totalChars = 0;
+
+  for (let i = turnData.length - 1; i >= 0; i--) {
+    const turn = turnData[i];
+    if (turn === undefined) continue;
+
+    const turnHeader = `## Turn ${turn.index + 1}\n\n`;
+    const turnBlock = turnHeader + turn.content;
+    const separatorCost = selectedTurns.length > 0 ? 2 : 0;
+    const addCost = turnBlock.length + separatorCost;
+
+    if (totalChars + addCost > availableQuota && selectedTurns.length > 0) {
+      break;
+    }
+
+    selectedTurns.unshift(turn);
+    totalChars += addCost;
+  }
+
+  return selectedTurns;
+}
+
+/**
+ * Assemble final markdown output from header and selected turns
+ */
+function formatStepMarkdown(
+  stepHash: CasRef,
+  role: string,
+  agent: string,
+  turnData: TurnData[],
+  selectedTurns: TurnData[],
+): string {
+  const parts: string[] = [];
+  parts.push(`# Step ${stepHash}`);
+  parts.push("");
+  parts.push(`**Role:** ${role}`);
+  parts.push(`**Agent:** ${agent}`);
+
+  if (selectedTurns.length === 0) {
+    return parts.join("\n");
+  }
+
+  const skippedCount = turnData.length - selectedTurns.length;
+  if (skippedCount > 0) {
+    parts.push("");
+    parts.push(`_[Earlier turns omitted due to quota. Use --quota to increase.]_`);
+  }
+
+  for (const turn of selectedTurns) {
+    parts.push("");
+    parts.push(`## Turn ${turn.index + 1}`);
+    parts.push("");
+    parts.push(turn.content);
+  }
+
+  return parts.join("\n");
+}
+
+/**
+ * Read a step's agent turns as human-readable markdown with quota enforcement
+ */
+export async function cmdStepRead(
+  storageRoot: string,
+  stepHash: CasRef,
+  quota: number,
+): Promise<string> {
+  const uwf = await createUwfStore(storageRoot);
+  const node = uwf.store.get(stepHash);
+  if (node === null) {
+    fail(`CAS node not found: ${stepHash}`);
+  }
+  if (node.type !== uwf.schemas.stepNode) {
+    fail(`node ${stepHash} is not a StepNode`);
+  }
+  const payload = node.payload as StepNodePayload;
+
+  if (payload.detail === null) {
+    return formatStepMarkdown(stepHash, payload.role, payload.agent, [], []);
+  }
+
+  const detail = loadStepDetail(uwf.store, payload.detail);
+  const turnData = loadTurnData(uwf.store, detail.turns);
+
+  if (turnData.length === 0) {
+    return formatStepMarkdown(stepHash, payload.role, payload.agent, [], []);
+  }
+
+  const headerSection = formatStepMarkdown(stepHash, payload.role, payload.agent, [], []);
+  const BUFFER = 200;
+  const availableQuota = quota - headerSection.length - BUFFER;
+  const selectedTurns = selectTurnsForQuota(turnData, availableQuota);
+
+  return formatStepMarkdown(stepHash, payload.role, payload.agent, turnData, selectedTurns);
+}

packages/cli-workflow/src/commands/thread-time-parser.ts

@@ -0,0 +1,23 @@
+/**
+ * Parse time input: ISO date (YYYY-MM-DD, YYYY-MM-DDTHH:MM:SS) or relative (7d, 24h, 30m)
+ * Returns Unix timestamp in milliseconds.
+ */
+export function parseTimeInput(input: string, nowMs: number): number {
+  const trimmed = input.trim();
+
+  // Relative time: 7d, 24h, 30m
+  const relativeMatch = /^(\d+)(d|h|m)$/.exec(trimmed);
+  if (relativeMatch !== null) {
+    const value = Number.parseInt(relativeMatch[1], 10);
+    const unit = relativeMatch[2];
+    const multiplier = unit === "d" ? 86400000 : unit === "h" ? 3600000 : 60000;
+    return nowMs - value * multiplier;
+  }
+
+  // ISO date: try parsing
+  const parsed = Date.parse(trimmed);
+  if (Number.isNaN(parsed)) {
+    throw new Error(`invalid time format: ${trimmed} (expected ISO date or relative like '7d')`);
+  }
+  return parsed;
+}

packages/cli-workflow/src/commands/workflow.ts

@@ -2,25 +2,34 @@ import { readFile } from "node:fs/promises";
 
 import type { JSONSchema } from "@uncaged/json-cas";
 import { putSchema, validate } from "@uncaged/json-cas";
-import type { CasRef, RoleDefinition, WorkflowPayload } from "@uncaged/uwf-protocol";
+import type {
+  CasRef,
+  RoleDefinition,
+  Transition,
+  WorkflowPayload,
+} from "@uncaged/workflow-protocol";
 import { parse } from "yaml";
 
 import {
   createUwfStore,
+  discoverProjectWorkflows,
   findRegistryName,
   loadWorkflowRegistry,
   resolveWorkflowHash,
   saveWorkflowRegistry,
   type UwfStore,
 } from "../store.js";
-import { parseWorkflowPayload } from "../validate.js";
+import { checkWorkflowFilenameConsistency, parseWorkflowPayload } from "../validate.js";
+
+export type WorkflowOrigin = "local" | "global";
 
 export type WorkflowListEntry = {
   name: string;
   hash: CasRef;
+  origin: WorkflowOrigin;
 };
 
-export type WorkflowPutOutput = {
+export type WorkflowAddOutput = {
   name: string;
   hash: CasRef;
 };
@@ -42,35 +51,55 @@ function isJsonSchema(value: unknown): value is JSONSchema {
   return typeof value === "object" && value !== null && !Array.isArray(value);
 }
 
-async function resolveOutputSchemaRef(
+/** Normalize graph transitions: ensure condition is null (not undefined) for fallback entries. */
+function normalizeGraph(graph: Record<string, Transition[]>): Record<string, Transition[]> {
+  const result: Record<string, Transition[]> = {};
+  for (const [node, transitions] of Object.entries(graph)) {
+    result[node] = transitions.map((t) => {
+      if (typeof t.prompt !== "string" || t.prompt.trim() === "") {
+        fail(`graph[${node}] transition to "${t.role}": prompt is required (non-empty string)`);
+      }
+      return {
+        role: t.role,
+        condition: t.condition ?? null,
+        prompt: t.prompt,
+      };
+    });
+  }
+  return result;
+}
+
+async function resolveFrontmatterRef(
   uwf: UwfStore,
   roleName: string,
-  outputSchema: unknown,
+  frontmatter: unknown,
 ): Promise<CasRef> {
-  if (!isJsonSchema(outputSchema)) {
-    fail(`role "${roleName}": outputSchema must be a JSON Schema object`);
+  if (!isJsonSchema(frontmatter)) {
+    fail(`role "${roleName}": frontmatter must be a JSON Schema object`);
   }
-  const schema: JSONSchema = outputSchema.title === undefined
-    ? { ...outputSchema, title: roleName }
-    : outputSchema;
+  const schema: JSONSchema =
+    frontmatter.title === undefined ? { ...frontmatter, title: roleName } : frontmatter;
   return putSchema(uwf.store, schema);
 }
 
-async function materializeWorkflowPayload(
+export async function materializeWorkflowPayload(
   uwf: UwfStore,
   raw: WorkflowPayload,
 ): Promise<WorkflowPayload> {
   const roles: Record<string, RoleDefinition> = {};
   for (const [roleName, role] of Object.entries(raw.roles)) {
-    const outputSchema = await resolveOutputSchemaRef(
+    const frontmatter = await resolveFrontmatterRef(
       uwf,
       `${raw.name}.${roleName}`,
-      role.outputSchema,
+      role.frontmatter,
     );
     roles[roleName] = {
       description: role.description,
-      systemPrompt: role.systemPrompt,
-      outputSchema,
+      goal: role.goal,
+      capabilities: role.capabilities,
+      procedure: role.procedure,
+      output: role.output,
+      frontmatter,
     };
   }
   return {
@@ -78,14 +107,14 @@ async function materializeWorkflowPayload(
     description: raw.description,
     roles,
     conditions: raw.conditions,
-    graph: raw.graph,
+    graph: normalizeGraph(raw.graph),
   };
 }
 
-export async function cmdWorkflowPut(
+export async function cmdWorkflowAdd(
   storageRoot: string,
   filePath: string,
-): Promise<WorkflowPutOutput> {
+): Promise<WorkflowAddOutput> {
   let text: string;
   try {
     text = await readFile(filePath, "utf8");
@@ -105,6 +134,11 @@ export async function cmdWorkflowPut(
     fail("invalid workflow YAML: expected WorkflowPayload shape");
   }
 
+  const filenameError = checkWorkflowFilenameConsistency(filePath, payload);
+  if (filenameError !== null) {
+    fail(filenameError);
+  }
+
   const uwf = await createUwfStore(storageRoot);
   const materialized = await materializeWorkflowPayload(uwf, payload);
 
@@ -147,7 +181,26 @@ export async function cmdWorkflowShow(
   };
 }
 
-export async function cmdWorkflowList(storageRoot: string): Promise<WorkflowListEntry[]> {
+export async function cmdWorkflowList(
+  storageRoot: string,
+  projectRoot: string,
+): Promise<WorkflowListEntry[]> {
+  const localEntries = await discoverProjectWorkflows(projectRoot);
   const registry = await loadWorkflowRegistry(storageRoot);
-  return Object.entries(registry).map(([name, hash]) => ({ name, hash }));
+
+  const result: WorkflowListEntry[] = [];
+  const localNames = new Set<string>();
+
+  for (const entry of localEntries) {
+    localNames.add(entry.name);
+    result.push({ name: entry.name, hash: "(local)", origin: "local" });
+  }
+
+  for (const [name, hash] of Object.entries(registry)) {
+    if (!localNames.has(name)) {
+      result.push({ name, hash, origin: "global" });
+    }
+  }
+
+  return result;
 }

packages/cli-workflow/src/format.ts

@@ -7,6 +7,6 @@ export function formatOutput(data: unknown, format: OutputFormat): string {
     case "json":
       return JSON.stringify(data);
     case "yaml":
-      return stringify(data).trimEnd();
+      return stringify(data, { aliasDuplicateObjects: false }).trimEnd();
   }
 }

packages/cli-workflow/src/schemas.ts

@@ -1,15 +1,14 @@
 import type { Hash, Store } from "@uncaged/json-cas";
 import { putSchema } from "@uncaged/json-cas";
-import {
-  START_NODE_SCHEMA,
-  STEP_NODE_SCHEMA,
-  WORKFLOW_SCHEMA,
-} from "@uncaged/uwf-protocol";
+import { START_NODE_SCHEMA, STEP_NODE_SCHEMA, WORKFLOW_SCHEMA } from "@uncaged/workflow-protocol";
+
+export const TEXT_SCHEMA = { type: "string" as const };
 
 export type UwfSchemaHashes = {
   workflow: Hash;
   startNode: Hash;
   stepNode: Hash;
+  text: Hash;
 };
 
 /**
@@ -17,10 +16,11 @@ export type UwfSchemaHashes = {
  * Idempotent: safe to call on every CLI invocation.
  */
 export async function registerUwfSchemas(store: Store): Promise<UwfSchemaHashes> {
-  const [workflow, startNode, stepNode] = await Promise.all([
+  const [workflow, startNode, stepNode, text] = await Promise.all([
     putSchema(store, WORKFLOW_SCHEMA),
     putSchema(store, START_NODE_SCHEMA),
     putSchema(store, STEP_NODE_SCHEMA),
+    putSchema(store, TEXT_SCHEMA),
   ]);
-  return { workflow, startNode, stepNode };
+  return { workflow, startNode, stepNode, text };
 }

packages/cli-workflow/src/store.ts

@@ -1,16 +1,54 @@
-import { appendFile, mkdir, readFile, writeFile } from "node:fs/promises";
+import { appendFile, mkdir, readdir, readFile, writeFile } from "node:fs/promises";
 import { homedir } from "node:os";
 import { join } from "node:path";
 
-import type { Hash, Store } from "@uncaged/json-cas";
+import type { BootstrapCapableStore, Hash } from "@uncaged/json-cas";
 import { createFsStore } from "@uncaged/json-cas-fs";
-import type { CasRef, ThreadId, ThreadListItem, ThreadsIndex } from "@uncaged/uwf-protocol";
+import type { CasRef, ThreadId, ThreadListItem, ThreadsIndex } from "@uncaged/workflow-protocol";
 import { parse, stringify } from "yaml";
 
 import { registerUwfSchemas, type UwfSchemaHashes } from "./schemas.js";
 
 export type WorkflowRegistry = Record<string, CasRef>;
 
+/** A workflow entry discovered from the project-local .workflows/ directory. */
+export type ProjectWorkflowEntry = {
+  /** Workflow name (from YAML `name` field, equals filename stem). */
+  name: string;
+  /** Absolute path to the YAML file. */
+  filePath: string;
+};
+
+/**
+ * Scan `<projectRoot>/.workflows/*.yaml` (non-recursive) and return discovered entries.
+ * Returns an empty array if the directory does not exist.
+ */
+export async function discoverProjectWorkflows(
+  projectRoot: string,
+): Promise<ProjectWorkflowEntry[]> {
+  const dir = join(projectRoot, ".workflows");
+  let entries: string[];
+  try {
+    entries = await readdir(dir);
+  } catch (e) {
+    const err = e as NodeJS.ErrnoException;
+    if (err.code === "ENOENT" || err.code === "ENOTDIR") {
+      return [];
+    }
+    throw e;
+  }
+
+  const result: ProjectWorkflowEntry[] = [];
+  for (const entry of entries) {
+    if (!entry.endsWith(".yaml") && !entry.endsWith(".yml")) {
+      continue;
+    }
+    const stem = entry.endsWith(".yaml") ? entry.slice(0, -5) : entry.slice(0, -4);
+    result.push({ name: stem, filePath: join(dir, entry) });
+  }
+  return result;
+}
+
 /** Default filesystem root for uwf data (`~/.uncaged/workflow`). */
 export function getDefaultStorageRoot(): string {
   return join(homedir(), ".uncaged", "workflow");
@@ -54,7 +92,7 @@ export type ThreadHistoryLine = ThreadListItem & {
 
 export type UwfStore = {
   storageRoot: string;
-  store: Store;
+  store: BootstrapCapableStore;
   schemas: UwfSchemaHashes;
 };
 
@@ -104,6 +142,22 @@ export function resolveWorkflowHash(registry: WorkflowRegistry, id: string): Cas
   return registry[id] !== undefined ? registry[id] : id;
 }
 
+/**
+ * Resolve a workflow name to a project-local YAML file path.
+ * Returns null if the name is not found in the local entries.
+ */
+export function resolveProjectWorkflowFile(
+  localEntries: ProjectWorkflowEntry[],
+  name: string,
+): string | null {
+  for (const entry of localEntries) {
+    if (entry.name === name) {
+      return entry.filePath;
+    }
+  }
+  return null;
+}
+
 export function findRegistryName(registry: WorkflowRegistry, hash: Hash): string | null {
   for (const [name, h] of Object.entries(registry)) {
     if (h === hash) {

packages/cli-workflow/src/validate.ts

@@ -0,0 +1,112 @@
+import { basename } from "node:path";
+import type { CasRef, WorkflowPayload } from "@uncaged/workflow-protocol";
+
+const CAS_REF_PATTERN = /^[0-9A-HJKMNP-TV-Z]{13}$/;
+
+export function isCasRef(value: string): value is CasRef {
+  return CAS_REF_PATTERN.test(value);
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+
+function isRoleDefinition(value: unknown): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  const frontmatter = value.frontmatter;
+  const frontmatterOk = isRecord(frontmatter) && typeof frontmatter.type === "string";
+  const capabilities = value.capabilities;
+  const capabilitiesOk =
+    Array.isArray(capabilities) && capabilities.every((c) => typeof c === "string");
+  return (
+    typeof value.description === "string" &&
+    typeof value.goal === "string" &&
+    capabilitiesOk &&
+    typeof value.procedure === "string" &&
+    typeof value.output === "string" &&
+    frontmatterOk
+  );
+}
+
+function isConditionDefinition(value: unknown): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  return typeof value.description === "string" && typeof value.expression === "string";
+}
+
+function isTransition(value: unknown): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  const condition = value.condition;
+  return (
+    typeof value.role === "string" &&
+    typeof value.prompt === "string" &&
+    value.prompt.trim() !== "" &&
+    (condition === null || condition === undefined || typeof condition === "string")
+  );
+}
+
+function isStringRecord(value: unknown, itemCheck: (item: unknown) => boolean): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  return Object.values(value).every(itemCheck);
+}
+
+function isGraph(value: unknown): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  return Object.values(value).every(
+    (transitions) => Array.isArray(transitions) && transitions.every((t) => isTransition(t)),
+  );
+}
+
+/**
+ * Derive the expected workflow name from a file path (stem without extension).
+ * Returns the stem for `.yaml` / `.yml` files.
+ */
+export function workflowNameFromPath(filePath: string): string {
+  const base = basename(filePath);
+  if (base.endsWith(".yaml")) return base.slice(0, -5);
+  if (base.endsWith(".yml")) return base.slice(0, -4);
+  return base;
+}
+
+/**
+ * Check that the `name` field in a parsed payload matches the expected name
+ * derived from the file path.  Returns an error message string on mismatch,
+ * or null when the names are consistent.
+ */
+export function checkWorkflowFilenameConsistency(
+  filePath: string,
+  payload: WorkflowPayload,
+): string | null {
+  const expected = workflowNameFromPath(filePath);
+  if (payload.name !== expected) {
+    return `workflow name mismatch: file "${basename(filePath)}" implies name "${expected}" but YAML declares name "${payload.name}"`;
+  }
+  return null;
+}
+
+/** Validate YAML-parsed workflow document shape (outputSchema may be inline JSON Schema). */
+export function parseWorkflowPayload(raw: unknown): WorkflowPayload | null {
+  if (!isRecord(raw)) {
+    return null;
+  }
+  if (typeof raw.name !== "string" || typeof raw.description !== "string") {
+    return null;
+  }
+  if (
+    !isStringRecord(raw.roles, isRoleDefinition) ||
+    !isStringRecord(raw.conditions, isConditionDefinition) ||
+    !isGraph(raw.graph)
+  ) {
+    return null;
+  }
+  return raw as WorkflowPayload;
+}

packages/cli-workflow/tsconfig.json

@@ -6,8 +6,8 @@
   },
   "include": ["src"],
   "references": [
-    { "path": "../uwf-protocol" },
-    { "path": "../uwf-moderator" },
-    { "path": "../uwf-agent-kit" }
+    { "path": "../workflow-protocol" },
+    { "path": "../workflow-moderator" },
+    { "path": "../workflow-agent-kit" }
   ]
 }

packages/uwf-agent-hermes/src/hermes.ts

@@ -1,117 +0,0 @@
-import { spawn } from "node:child_process";
-
-import { type AgentContext, type AgentRunResult, createAgent } from "@uncaged/uwf-agent-kit";
-
-import {
-  loadHermesSession,
-  parseSessionIdFromStdout,
-  storeHermesRawOutput,
-  storeHermesSessionDetail,
-} from "./session-detail.js";
-
-const HERMES_COMMAND = "hermes";
-const HERMES_MAX_TURNS = 90;
-
-function buildHistorySummary(steps: AgentContext["steps"]): string {
-  if (steps.length === 0) {
-    return "";
-  }
-
-  const lines: string[] = ["## Previous Steps"];
-  for (let i = 0; i < steps.length; i++) {
-    const step = steps[i];
-    if (step === undefined) {
-      continue;
-    }
-    lines.push("");
-    lines.push(`### Step ${i + 1}: ${step.role}`);
-    lines.push(`Output: ${JSON.stringify(step.output)}`);
-    lines.push(`Agent: ${step.agent}`);
-  }
-  return lines.join("\n");
-}
-
-/** Assemble system prompt, task, and prior step outputs for Hermes. */
-export function buildHermesPrompt(ctx: AgentContext): string {
-  const roleDef = ctx.workflow.roles[ctx.role];
-  const systemPrompt = roleDef?.systemPrompt ?? "";
-  const parts: string[] = [];
-  if (ctx.outputFormatInstruction !== undefined && ctx.outputFormatInstruction !== "") {
-    parts.push(ctx.outputFormatInstruction, "");
-  }
-  parts.push(systemPrompt, "", "## Task", ctx.start.prompt);
-  const historyBlock = buildHistorySummary(ctx.steps);
-  if (historyBlock !== "") {
-    parts.push("", historyBlock);
-  }
-  return parts.join("\n");
-}
-
-function spawnHermesChat(prompt: string): Promise<{ stdout: string; stderr: string }> {
-  return new Promise((resolve, reject) => {
-    const args = [
-      "chat",
-      "-q",
-      prompt,
-      "--yolo",
-      "--max-turns",
-      String(HERMES_MAX_TURNS),
-      "--quiet",
-    ];
-    const child = spawn(HERMES_COMMAND, args, {
-      env: process.env,
-      shell: false,
-      stdio: ["ignore", "pipe", "pipe"],
-    });
-
-    let stdout = "";
-    let stderr = "";
-    child.stdout?.on("data", (chunk: Buffer) => {
-      stdout += chunk.toString();
-    });
-    child.stderr?.on("data", (chunk: Buffer) => {
-      stderr += chunk.toString();
-    });
-
-    child.on("error", (cause) => {
-      const message = cause instanceof Error ? cause.message : String(cause);
-      reject(new Error(`hermes spawn failed: ${message}`));
-    });
-
-    child.on("close", (code) => {
-      if (code === 0) {
-        resolve({ stdout, stderr });
-        return;
-      }
-      const detail = stderr.trim() !== "" ? ` stderr=${stderr.trim()}` : "";
-      reject(new Error(`hermes exited with code ${code ?? "null"}${detail}`));
-    });
-  });
-}
-
-async function runHermes(ctx: AgentContext): Promise<AgentRunResult> {
-  const fullPrompt = buildHermesPrompt(ctx);
-  const { stdout, stderr } = await spawnHermesChat(fullPrompt);
-  const { store } = ctx;
-
-  // --quiet mode: session_id may be on stdout or stderr
-  const sessionId = parseSessionIdFromStdout(stderr) ?? parseSessionIdFromStdout(stdout);
-  if (sessionId !== null) {
-    const session = await loadHermesSession(sessionId);
-    if (session !== null) {
-      const { detailHash, output } = await storeHermesSessionDetail(store, session);
-      return { output, detailHash };
-    }
-  }
-
-  const detailHash = await storeHermesRawOutput(store, stdout);
-  return { output: stdout, detailHash };
-}
-
-/** Agent CLI factory: parses argv, runs Hermes, extracts output, writes StepNode. */
-export function createHermesAgent(): () => Promise<void> {
-  return createAgent({
-    name: "hermes",
-    run: runHermes,
-  });
-}

packages/uwf-agent-kit/__tests__/build-output-format-instruction.test.ts

@@ -1,89 +0,0 @@
-import { describe, expect, test } from "vitest";
-
-import { buildOutputFormatInstruction } from "../src/build-output-format-instruction.js";
-
-describe("buildOutputFormatInstruction", () => {
-  test("always includes the frontmatter example block", () => {
-    const result = buildOutputFormatInstruction({});
-    expect(result).toContain("---");
-    expect(result).toContain("status: done");
-    expect(result).toContain("confidence:");
-    expect(result).toContain("scope: role");
-  });
-
-  test("always marks frontmatter as the primary deliverable", () => {
-    const result = buildOutputFormatInstruction({});
-    expect(result).toContain("primary deliverable");
-  });
-
-  test("lists fields from a flat object schema", () => {
-    const schema = {
-      type: "object",
-      properties: {
-        status: { type: "string" },
-        confidence: { type: "number" },
-      },
-    };
-    const result = buildOutputFormatInstruction(schema);
-    expect(result).toContain("`status`");
-    expect(result).toContain("`confidence`");
-  });
-
-  test("lists union of fields from an anyOf schema", () => {
-    const schema = {
-      anyOf: [
-        {
-          type: "object",
-          properties: { alpha: { type: "string" } },
-        },
-        {
-          type: "object",
-          properties: { beta: { type: "number" } },
-        },
-      ],
-    };
-    const result = buildOutputFormatInstruction(schema);
-    expect(result).toContain("`alpha`");
-    expect(result).toContain("`beta`");
-  });
-
-  test("lists union of fields from a oneOf schema", () => {
-    const schema = {
-      oneOf: [
-        {
-          type: "object",
-          properties: { foo: { type: "string" } },
-        },
-        {
-          type: "object",
-          properties: { bar: { type: "boolean" } },
-        },
-      ],
-    };
-    const result = buildOutputFormatInstruction(schema);
-    expect(result).toContain("`foo`");
-    expect(result).toContain("`bar`");
-  });
-
-  test("falls back gracefully for a non-object schema with no properties", () => {
-    const result = buildOutputFormatInstruction({ type: "string" });
-    expect(result).toContain("schema fields will be extracted automatically");
-  });
-
-  test("does not list a field more than once for a union with overlapping keys", () => {
-    const schema = {
-      anyOf: [
-        { type: "object", properties: { shared: { type: "string" } } },
-        { type: "object", properties: { shared: { type: "number" } } },
-      ],
-    };
-    const result = buildOutputFormatInstruction(schema);
-    const matches = [...result.matchAll(/`shared`/g)];
-    expect(matches.length).toBe(1);
-  });
-
-  test("includes focus reminder about role scope", () => {
-    const result = buildOutputFormatInstruction({});
-    expect(result).toContain("Focus exclusively on YOUR role");
-  });
-});

packages/uwf-agent-kit/src/build-output-format-instruction.ts

@@ -1,75 +0,0 @@
-import type { JSONSchema } from "@uncaged/json-cas";
-
-/**
- * Extract top-level property names from a JSON Schema object.
- *
- * Handles:
- * - Object schemas with a `properties` key
- * - Union schemas via `anyOf` / `oneOf` — union of all variant property names
- *
- * Returns an empty array for schemas with no inspectable property definitions.
- */
-function extractSchemaFields(schema: JSONSchema): string[] {
-  if (typeof schema.properties === "object" && schema.properties !== null) {
-    return Object.keys(schema.properties as Record<string, unknown>);
-  }
-
-  const unionKey = Array.isArray(schema.anyOf)
-    ? "anyOf"
-    : Array.isArray(schema.oneOf)
-      ? "oneOf"
-      : null;
-
-  if (unionKey !== null) {
-    const variants = schema[unionKey] as JSONSchema[];
-    const fieldSet = new Set<string>();
-    for (const variant of variants) {
-      for (const field of extractSchemaFields(variant)) {
-        fieldSet.add(field);
-      }
-    }
-    return [...fieldSet];
-  }
-
-  return [];
-}
-
-/**
- * Build a concise output format instruction block for an agent role.
- *
- * The instruction describes the expected frontmatter markdown format and lists
- * the meta fields derived from the JSON Schema.  It is prepended to the agent's
- * system prompt so the deliverable format is the first thing the agent sees.
- */
-export function buildOutputFormatInstruction(schema: JSONSchema): string {
-  const fields = extractSchemaFields(schema);
-
-  const fieldList =
-    fields.length > 0
-      ? fields.map((f) => `  - \`${f}\``).join("\n")
-      : "  (schema fields will be extracted automatically)";
-
-  return `## Deliverable Format
-
-Your response MUST begin with a YAML frontmatter block followed by your markdown work:
-
-\`\`\`
----
-status: done          # done | needs_input | in_progress | failed
-next: <role-name>     # suggested next role, or omit
-confidence: 0.9       # 0.0–1.0, your self-assessed confidence
-artifacts:            # list of file paths or CAS hashes you produced
-  - path/to/file.ts
-scope: role           # role | thread
----
-
-... your markdown work here ...
-\`\`\`
-
-The frontmatter is the **primary deliverable** — the engine reads it directly.
-Your meta output must satisfy these fields:
-
-${fieldList}
-
-Focus exclusively on YOUR role's deliverable. Do not perform actions outside your role's scope.`;
-}

packages/uwf-agent-kit/src/frontmatter.ts

@@ -1,61 +0,0 @@
-import { validate } from "@uncaged/json-cas";
-import type { Store } from "@uncaged/json-cas";
-import type { CasRef } from "@uncaged/uwf-protocol";
-import { parseFrontmatterMarkdown, validateFrontmatter } from "@uncaged/workflow-util";
-
-export type FrontmatterFastPathResult = {
-  body: string;
-  outputHash: CasRef;
-};
-
-/**
- * Try to satisfy `outputSchema` from frontmatter fields alone.
- *
- * Returns a result containing the stored CAS hash and stripped body on success,
- * or `null` when frontmatter is absent, invalid, or does not satisfy the schema.
- * Never throws.
- *
- * The candidate object is put into the real CAS store (idempotent content-addressed
- * write) and validated against the output schema.  If validation fails the node
- * is orphaned — it will be GC'd on the next collection pass.
- */
-export async function tryFrontmatterFastPath(
-  raw: string,
-  outputSchema: CasRef,
-  store: Store,
-): Promise<FrontmatterFastPathResult | null> {
-  const { frontmatter, body } = parseFrontmatterMarkdown(raw);
-
-  if (frontmatter === null) {
-    return null;
-  }
-
-  const validationErrors = validateFrontmatter(frontmatter);
-  if (validationErrors.length > 0) {
-    return null;
-  }
-
-  const candidate: Record<string, unknown> = {
-    status: frontmatter.status,
-    next: frontmatter.next,
-    confidence: frontmatter.confidence,
-    artifacts: [...frontmatter.artifacts],
-    scope: frontmatter.scope,
-  };
-
-  let outputHash: CasRef;
-  let node: ReturnType<Store["get"]>;
-
-  try {
-    outputHash = await store.put(outputSchema, candidate);
-    node = store.get(outputHash);
-  } catch {
-    return null;
-  }
-
-  if (node === null || !validate(store, node)) {
-    return null;
-  }
-
-  return { body, outputHash };
-}

packages/uwf-moderator/__tests__/evaluate.test.ts

@@ -1,120 +0,0 @@
-import { describe, expect, test } from "bun:test";
-import type { ModeratorContext, WorkflowPayload } from "@uncaged/uwf-protocol";
-
-import { evaluate } from "../src/evaluate.js";
-
-const solveIssueWorkflow: WorkflowPayload = {
-  name: "solve-issue",
-  description: "End-to-end issue resolution",
-  roles: {
-    planner: {
-      description: "Creates implementation plan",
-      systemPrompt: "You are a planning agent...",
-      outputSchema: "5GWKR8TN1V3JA",
-    },
-    developer: {
-      description: "Implements code changes",
-      systemPrompt: "You are a developer agent...",
-      outputSchema: "8CNWT4KR6D1HV",
-    },
-    reviewer: {
-      description: "Reviews code changes",
-      systemPrompt: "You are a code reviewer...",
-      outputSchema: "1VPBG9SM5E7WK",
-    },
-  },
-  conditions: {
-    needsClarification: {
-      description: "Planner requests clarification from user",
-      expression: "$exists(steps[-1].output.needsClarification)",
-    },
-    notApproved: {
-      description: "Reviewer rejected the implementation",
-      expression: "steps[-1].output.approved = false",
-    },
-  },
-  graph: {
-    $START: [{ role: "planner", condition: null }],
-    planner: [
-      { role: "developer", condition: "needsClarification" },
-      { role: "$END", condition: null },
-    ],
-    developer: [{ role: "reviewer", condition: null }],
-    reviewer: [
-      { role: "developer", condition: "notApproved" },
-      { role: "$END", condition: null },
-    ],
-  },
-};
-
-function makeContext(steps: ModeratorContext["steps"]): ModeratorContext {
-  return {
-    start: {
-      workflow: "4KNM2PXR3B1QW",
-      prompt: "Fix the login bug",
-    },
-    steps,
-  };
-}
-
-describe("evaluate", () => {
-  test("$START → first role (fallback)", async () => {
-    const result = await evaluate(solveIssueWorkflow, makeContext([]));
-    expect(result).toEqual({ ok: true, value: "planner" });
-  });
-
-  test("condition match (notApproved → developer)", async () => {
-    const context = makeContext([
-      {
-        role: "reviewer",
-        output: { approved: false },
-        detail: "2MXBG6PN4A8JR",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(solveIssueWorkflow, context);
-    expect(result).toEqual({ ok: true, value: "developer" });
-  });
-
-  test("fallback when condition does not match → $END", async () => {
-    const context = makeContext([
-      {
-        role: "reviewer",
-        output: { approved: true },
-        detail: "2MXBG6PN4A8JR",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(solveIssueWorkflow, context);
-    expect(result).toEqual({ ok: true, value: "$END" });
-  });
-
-  test("missing role in graph → error", async () => {
-    const context = makeContext([
-      {
-        role: "unknown-role",
-        output: {},
-        detail: "2MXBG6PN4A8JR",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(solveIssueWorkflow, context);
-    expect(result.ok).toBe(false);
-    if (!result.ok) {
-      expect(result.error.message).toBe('no transitions defined for role "unknown-role"');
-    }
-  });
-
-  test("output expansion in context works with JSONata", async () => {
-    const context = makeContext([
-      {
-        role: "planner",
-        output: { needsClarification: true },
-        detail: "7BQST3VW9F2MA",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(solveIssueWorkflow, context);
-    expect(result).toEqual({ ok: true, value: "developer" });
-  });
-});

packages/uwf-moderator/src/index.ts

@@ -1 +0,0 @@
-export { evaluate } from "./evaluate.js";

packages/uwf-moderator/src/types.ts

@@ -1 +0,0 @@
-export type Result<T, E> = { ok: true; value: T } | { ok: false; error: E };

packages/uwf-protocol/pnpm-lock.yaml

@@ -1,68 +0,0 @@
-lockfileVersion: '9.0'
-
-settings:
-  autoInstallPeers: true
-  excludeLinksFromLockfile: false
-
-importers:
-
-  .:
-    dependencies:
-      '@uncaged/json-cas':
-        specifier: ^0.3.0
-        version: 0.3.0
-
-packages:
-
-  '@uncaged/json-cas@0.3.0':
-    resolution: {integrity: sha512-LR8Uow7cBdvH+6y9mh9Fd7zDs8fWhfhpVZVsexfdK1KKnGaR7WvukuhBj6r0FbOZ78j7jhjeEfzsUXR2cHELwQ==}
-
-  ajv@8.20.0:
-    resolution: {integrity: sha512-Thbli+OlOj+iMPYFBVBfJ3OmCAnaSyNn4M1vz9T6Gka5Jt9ba/HIR56joy65tY6kx/FCF5VXNB819Y7/GUrBGA==}
-
-  cborg@4.5.8:
-    resolution: {integrity: sha512-6/viltD51JklRhq4L7jC3zgy6gryuG5xfZ3kzpE+PravtyeQLeQmCYLREhQH7pWENg5pY4Yu/XCd6a7dKScVlw==}
-    hasBin: true
-
-  fast-deep-equal@3.1.3:
-    resolution: {integrity: sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q==}
-
-  fast-uri@3.1.2:
-    resolution: {integrity: sha512-rVjf7ArG3LTk+FS6Yw81V1DLuZl1bRbNrev6Tmd/9RaroeeRRJhAt7jg/6YFxbvAQXUCavSoZhPPj6oOx+5KjQ==}
-
-  json-schema-traverse@1.0.0:
-    resolution: {integrity: sha512-NM8/P9n3XjXhIZn1lLhkFaACTOURQXjWhV4BA/RnOv8xvgqtqpAX9IO4mRQxSx1Rlo4tqzeqb0sOlruaOy3dug==}
-
-  require-from-string@2.0.2:
-    resolution: {integrity: sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw==}
-    engines: {node: '>=0.10.0'}
-
-  xxhash-wasm@1.1.0:
-    resolution: {integrity: sha512-147y/6YNh+tlp6nd/2pWq38i9h6mz/EuQ6njIrmW8D1BS5nCqs0P6DG+m6zTGnNz5I+uhZ0SHxBs9BsPrwcKDA==}
-
-snapshots:
-
-  '@uncaged/json-cas@0.3.0':
-    dependencies:
-      ajv: 8.20.0
-      cborg: 4.5.8
-      xxhash-wasm: 1.1.0
-
-  ajv@8.20.0:
-    dependencies:
-      fast-deep-equal: 3.1.3
-      fast-uri: 3.1.2
-      json-schema-traverse: 1.0.0
-      require-from-string: 2.0.2
-
-  cborg@4.5.8: {}
-
-  fast-deep-equal@3.1.3: {}
-
-  fast-uri@3.1.2: {}
-
-  json-schema-traverse@1.0.0: {}
-
-  require-from-string@2.0.2: {}
-
-  xxhash-wasm@1.1.0: {}

packages/workflow-agent-builtin/README.md

@@ -0,0 +1,141 @@
+# @uncaged/workflow-agent-builtin
+
+`uwf-builtin` agent — built-in LLM agent with file read/write and shell tools.
+
+## Overview
+
+Layer 3 agent implementation. Runs an OpenAI-compatible chat completion loop with built-in tools (`read_file`, `write_file`, `run_command`). Uses the configured provider/model from `config.yaml`. Produces frontmatter markdown output and stores turn-by-turn session detail in CAS.
+
+Useful when you want a self-contained agent without an external CLI like Hermes or Claude Code.
+
+**Dependencies:** `@uncaged/json-cas`, `@uncaged/workflow-agent-kit`, `@uncaged/workflow-util`
+
+## Installation
+
+Included as the `uwf-builtin` binary when you install `@uncaged/workflow-agent-builtin`:
+
+```bash
+bun add -g @uncaged/workflow-agent-builtin
+```
+
+## CLI Usage
+
+Invoked by `uwf thread step`:
+
+```bash
+uwf-builtin <thread-id> <role>
+```
+
+Configure as default agent:
+
+```bash
+uwf setup --agent builtin
+```
+
+Override per step:
+
+```bash
+uwf thread step <thread-id> --agent uwf-builtin
+```
+
+Environment variables set by the engine:
+
+| Variable | Purpose |
+|----------|---------|
+| `UWF_EDGE_PROMPT` | Moderator edge instruction for this step |
+
+## API
+
+All exports come from `src/index.ts`.
+
+### Agent factory
+
+```typescript
+function createBuiltinAgent(): () => Promise<void>
+function buildBuiltinMessages(ctx: AgentContext): ChatMessage[]
+```
+
+### LLM loop
+
+```typescript
+const BUILTIN_MAX_TURNS = 30;
+const BUILTIN_CONTINUE_MAX_TURNS = 5;
+
+function runBuiltinLoop(/* options: RunBuiltinLoopOptions */): Promise<RunBuiltinLoopResult>
+function chatCompletionWithTools(
+  provider: ResolvedLlmProvider,
+  messages: ChatMessage[],
+  tools: OpenAiToolDefinition[],
+): Promise<LlmAssistantResponse>
+```
+
+`RunBuiltinLoopOptions` and `RunBuiltinLoopResult` are internal to `loop.ts` and not re-exported from `index.ts`.
+
+### Tools
+
+```typescript
+function getBuiltinTools(): readonly BuiltinTool[]
+function executeBuiltinTool(
+  name: string,
+  args: Record<string, unknown>,
+  ctx: ToolContext,
+): Promise<string>
+```
+
+### Session and detail
+
+```typescript
+function initSessionDir(storageRoot: string): Promise<void>
+function appendSessionTurn(storageRoot: string, sessionId: string, turn: BuiltinTurnPayload): Promise<void>
+function readSessionTurns(storageRoot: string, sessionId: string): Promise<BuiltinTurnPayload[]>
+function removeSession(storageRoot: string, sessionId: string): Promise<void>
+function registerBuiltinSchemas(store: Store): Promise<BuiltinSchemaHashes>
+function storeBuiltinDetail(store: Store, payload: BuiltinDetailPayload): Promise<string>
+```
+
+### Types
+
+```typescript
+type ChatMessage = /* system | user | assistant | tool */;
+type LlmAssistantResponse = { content: string | null; toolCalls: LlmToolCall[] | null };
+type LlmToolCall = { id: string; name: string; arguments: string };
+type BuiltinTool = { name: string; description: string; parameters: Record<string, unknown> };
+type ToolContext = { cwd: string; storageRoot: string };
+type BuiltinDetailPayload = { /* session turns, model, timestamps */ };
+type BuiltinLoopTurn = { /* single loop iteration record */ };
+type BuiltinToolCallRecord = { /* tool call audit */ };
+type BuiltinToolResultRecord = { /* tool result audit */ };
+type BuiltinTurnPayload = { /* persisted turn */ };
+```
+
+## Internal Structure
+
+```
+src/
+├── index.ts
+├── cli.ts              Binary entrypoint
+├── agent.ts            createBuiltinAgent
+├── loop.ts             Multi-turn LLM + tool loop
+├── prompt.ts           buildBuiltinMessages
+├── session.ts          Session directory persistence
+├── detail.ts           CAS detail node storage
+├── schemas.ts          Builtin CAS schemas
+├── types.ts            Detail and turn payload types
+├── llm/
+│   ├── index.ts
+│   ├── llm.ts          chatCompletionWithTools
+│   └── types.ts        ChatMessage, LlmToolCall, etc.
+└── tools/
+    ├── index.ts        getBuiltinTools, executeBuiltinTool
+    ├── read-file.ts
+    ├── write-file.ts
+    ├── run-command.ts
+    ├── path.ts
+    └── types.ts
+```
+
+## Configuration
+
+Requires a configured OpenAI-compatible provider and model in `~/.uncaged/workflow/config.yaml` (via `uwf setup`). API keys are loaded from `~/.uncaged/workflow/.env`.
+
+Tools run with the current working directory as `ToolContext.cwd` (typically the directory where `uwf thread step` was invoked).

packages/workflow-agent-builtin/__tests__/llm-parse.test.ts

@@ -0,0 +1,16 @@
+import { describe, expect, test } from "bun:test";
+
+import type { LlmToolCall } from "../src/llm/types.js";
+
+/** Mirror OpenAI response shape for parser coverage via chatCompletionWithTools integration later. */
+describe("LlmToolCall shape", () => {
+  test("tool call record fields", () => {
+    const call: LlmToolCall = {
+      id: "call_1",
+      name: "read_file",
+      arguments: '{"path":"README.md"}',
+    };
+    expect(call.name).toBe("read_file");
+    expect(JSON.parse(call.arguments)).toEqual({ path: "README.md" });
+  });
+});

packages/workflow-agent-builtin/__tests__/loop.test.ts

@@ -0,0 +1,256 @@
+import { beforeEach, describe, expect, mock, test } from "bun:test";
+
+const mockChatCompletionWithTools = mock(async () => ({
+  content: "---\nstatus: done\n---",
+  toolCalls: [],
+}));
+const mockAppendSessionTurn = mock(async () => {});
+const mockExecuteBuiltinTool = mock(async () => "tool-result");
+
+mock.module("../src/llm/index.js", () => ({
+  chatCompletionWithTools: mockChatCompletionWithTools,
+}));
+mock.module("../src/session.js", () => ({
+  appendSessionTurn: mockAppendSessionTurn,
+}));
+mock.module("../src/tools/index.js", () => ({
+  builtinToolsToOpenAi: () => [],
+  executeBuiltinTool: mockExecuteBuiltinTool,
+  getBuiltinTools: () => [],
+}));
+
+import {
+  executeTurnTools,
+  extractFinalText,
+  runBuiltinLoop,
+  shouldInjectDeadlineWarning,
+  shouldNudge,
+  shouldProcessToolCalls,
+} from "../src/loop.js";
+
+const fakeProvider = {} as any;
+const fakeToolCtx = {} as any;
+
+function makeOptions(overrides: Partial<Parameters<typeof runBuiltinLoop>[0]> = {}) {
+  return {
+    provider: fakeProvider,
+    messages: [{ role: "system" as const, content: "sys" }],
+    toolCtx: fakeToolCtx,
+    maxTurns: 5,
+    storageRoot: "/tmp",
+    sessionId: "sess",
+    noTools: false,
+    ...overrides,
+  };
+}
+
+beforeEach(() => {
+  mockChatCompletionWithTools.mockReset();
+  mockAppendSessionTurn.mockReset();
+  mockExecuteBuiltinTool.mockReset();
+});
+
+describe("shouldNudge", () => {
+  test("2.1 returns true when all conditions met", () => {
+    expect(shouldNudge({ noTools: false, text: "some text", turn: 0, maxTurns: 5 })).toBe(true);
+  });
+  test("2.2 returns false when noTools=true", () => {
+    expect(shouldNudge({ noTools: true, text: "some text", turn: 0, maxTurns: 5 })).toBe(false);
+  });
+  test("2.3 returns false when text starts with ---", () => {
+    expect(shouldNudge({ noTools: false, text: "---\nstatus: done", turn: 0, maxTurns: 5 })).toBe(
+      false,
+    );
+  });
+  test("2.4 returns false on last turn", () => {
+    expect(shouldNudge({ noTools: false, text: "some text", turn: 4, maxTurns: 5 })).toBe(false);
+  });
+  test("2.5 returns true on second-to-last turn", () => {
+    expect(shouldNudge({ noTools: false, text: "some text", turn: 3, maxTurns: 5 })).toBe(true);
+  });
+  test("2.6 leading whitespace before --- suppresses nudge", () => {
+    expect(shouldNudge({ noTools: false, text: "  ---\nstatus: done", turn: 0, maxTurns: 5 })).toBe(
+      false,
+    );
+  });
+});
+
+describe("executeTurnTools", () => {
+  test("4.1 executes each tool call and pushes tool result messages", async () => {
+    mockExecuteBuiltinTool.mockResolvedValue("result");
+    const messages: any[] = [];
+    const calls = [
+      { id: "c1", name: "tool_a", arguments: "{}" },
+      { id: "c2", name: "tool_b", arguments: "{}" },
+    ];
+    const count = await executeTurnTools(calls, fakeToolCtx, messages, "/tmp", "sess");
+    expect(messages.length).toBe(2);
+    expect(messages[0].role).toBe("tool");
+    expect(messages[1].role).toBe("tool");
+    expect(count).toBe(2);
+  });
+  test("4.2 tool result content matches executeBuiltinTool return value", async () => {
+    mockExecuteBuiltinTool.mockResolvedValue("result-A");
+    const messages: any[] = [];
+    await executeTurnTools(
+      [{ id: "c1", name: "read_file", arguments: "{}" }],
+      fakeToolCtx,
+      messages,
+      "/tmp",
+      "sess",
+    );
+    expect(messages[0].content).toBe("result-A");
+  });
+});
+
+describe("runBuiltinLoop integration", () => {
+  test("3.1 single text-only response returns finalText immediately", async () => {
+    mockChatCompletionWithTools.mockResolvedValue({
+      content: "---\nstatus: done\n---",
+      toolCalls: [],
+    });
+    const result = await runBuiltinLoop(makeOptions());
+    expect(result.finalText).toBe("---\nstatus: done\n---");
+    expect(result.turnCount).toBe(1);
+  });
+  test("3.2 noTools=true suppresses tool calls", async () => {
+    mockChatCompletionWithTools.mockResolvedValue({
+      content: "ok",
+      toolCalls: [{ id: "c1", name: "read_file", arguments: "{}" }],
+    });
+    const result = await runBuiltinLoop(makeOptions({ noTools: true }));
+    expect(result.finalText).toBe("ok");
+    expect(result.turnCount).toBe(1);
+  });
+  test("3.3 tool call followed by text response", async () => {
+    mockChatCompletionWithTools
+      .mockResolvedValueOnce({
+        content: null,
+        toolCalls: [{ id: "c1", name: "read_file", arguments: "{}" }],
+      })
+      .mockResolvedValueOnce({ content: "---\nstatus: done\n---", toolCalls: [] });
+    mockExecuteBuiltinTool.mockResolvedValue("file contents");
+    const result = await runBuiltinLoop(makeOptions());
+    expect(result.finalText).toBe("---\nstatus: done\n---");
+    expect(result.turnCount).toBe(3);
+  });
+  test("3.4 nudge cycle inserts nudge message", async () => {
+    mockChatCompletionWithTools
+      .mockResolvedValueOnce({ content: "I am thinking", toolCalls: [] })
+      .mockResolvedValueOnce({ content: "---\nstatus: done\n---", toolCalls: [] });
+    const result = await runBuiltinLoop(makeOptions());
+    expect(result.finalText).toBe("---\nstatus: done\n---");
+    const nudgeMsg = result.messages.find(
+      (m) =>
+        m.role === "user" && typeof m.content === "string" && m.content.includes("frontmatter"),
+    );
+    expect(nudgeMsg).toBeDefined();
+  });
+  test("3.5 maxTurns exhaustion falls back to last assistant content", async () => {
+    mockChatCompletionWithTools.mockResolvedValue({ content: "still thinking", toolCalls: [] });
+    const result = await runBuiltinLoop(makeOptions({ maxTurns: 3 }));
+    expect(result.finalText).toBe("still thinking");
+  });
+  test("3.6 original messages array is not mutated", async () => {
+    mockChatCompletionWithTools.mockResolvedValue({
+      content: "---\nstatus: done\n---",
+      toolCalls: [],
+    });
+    const original = [{ role: "system" as const, content: "sys" }];
+    await runBuiltinLoop(makeOptions({ messages: original }));
+    expect(original.length).toBe(1);
+  });
+});
+
+describe("shouldInjectDeadlineWarning", () => {
+  test("5.1 returns true when turn count reaches warning threshold and not yet warned", () => {
+    expect(shouldInjectDeadlineWarning(7, 10, false, false)).toBe(true);
+  });
+  test("5.2 returns false when already warned", () => {
+    expect(shouldInjectDeadlineWarning(7, 10, true, false)).toBe(false);
+  });
+  test("5.3 returns false when noTools is true", () => {
+    expect(shouldInjectDeadlineWarning(7, 10, false, true)).toBe(false);
+  });
+  test("5.4 returns false when turns remaining > DEADLINE_WARNING_TURNS", () => {
+    expect(shouldInjectDeadlineWarning(5, 10, false, false)).toBe(false);
+  });
+  test("5.5 returns true when exactly at warning threshold", () => {
+    expect(shouldInjectDeadlineWarning(7, 10, false, false)).toBe(true);
+  });
+  test("5.6 returns false when turns remaining is 0", () => {
+    expect(shouldInjectDeadlineWarning(10, 10, false, false)).toBe(false);
+  });
+});
+
+describe("shouldProcessToolCalls", () => {
+  test("6.1 returns true when toolCalls present and noTools=false", () => {
+    expect(shouldProcessToolCalls([{ id: "x", name: "read", arguments: "{}" }], false)).toBe(true);
+  });
+  test("6.2 returns false when toolCalls is null", () => {
+    expect(shouldProcessToolCalls(null, false)).toBe(false);
+  });
+  test("6.3 returns false when toolCalls is empty array", () => {
+    expect(shouldProcessToolCalls([], false)).toBe(false);
+  });
+  test("6.4 returns false when noTools=true", () => {
+    expect(shouldProcessToolCalls([{ id: "x", name: "read", arguments: "{}" }], true)).toBe(false);
+  });
+  test("6.5 returns true when multiple tool calls present", () => {
+    expect(
+      shouldProcessToolCalls(
+        [
+          { id: "x1", name: "read", arguments: "{}" },
+          { id: "x2", name: "write", arguments: "{}" },
+        ],
+        false,
+      ),
+    ).toBe(true);
+  });
+});
+
+describe("extractFinalText", () => {
+  test("7.1 returns last assistant message content", () => {
+    const messages = [
+      { role: "system" as const, content: "sys", tool_calls: null },
+      { role: "assistant" as const, content: "first", tool_calls: null },
+      { role: "assistant" as const, content: "last", tool_calls: null },
+    ];
+    expect(extractFinalText(messages)).toBe("last");
+  });
+  test("7.2 returns empty string when no assistant messages", () => {
+    expect(extractFinalText([{ role: "system" as const, content: "sys", tool_calls: null }])).toBe(
+      "",
+    );
+  });
+  test("7.3 skips assistant messages with null content", () => {
+    const messages = [
+      { role: "assistant" as const, content: "first", tool_calls: null },
+      {
+        role: "assistant" as const,
+        content: null,
+        tool_calls: [{ id: "x", name: "t", arguments: "{}" }],
+      },
+      { role: "assistant" as const, content: "second", tool_calls: null },
+    ];
+    expect(extractFinalText(messages)).toBe("second");
+  });
+  test("7.4 skips assistant messages with empty content", () => {
+    const messages = [
+      { role: "assistant" as const, content: "first", tool_calls: null },
+      { role: "assistant" as const, content: "", tool_calls: null },
+      { role: "user" as const, content: "nudge", tool_calls: null },
+    ];
+    expect(extractFinalText(messages)).toBe("first");
+  });
+  test("7.5 handles empty messages array", () => {
+    expect(extractFinalText([])).toBe("");
+  });
+  test("7.6 handles messages with only user and system roles", () => {
+    const messages = [
+      { role: "system" as const, content: "sys", tool_calls: null },
+      { role: "user" as const, content: "query", tool_calls: null },
+    ];
+    expect(extractFinalText(messages)).toBe("");
+  });
+});

packages/workflow-agent-builtin/__tests__/path.test.ts

@@ -0,0 +1,21 @@
+import { describe, expect, test } from "bun:test";
+import { resolve } from "node:path";
+import { resolvePath } from "../src/tools/path.js";
+
+describe("resolvePath", () => {
+  test("resolves relative paths against cwd", () => {
+    const root = "/workspace/project";
+    const resolved = resolvePath(root, "src/foo.ts");
+    expect(resolved).toBe(resolve(root, "src/foo.ts"));
+  });
+
+  test("resolves absolute paths as-is", () => {
+    const resolved = resolvePath("/workspace", "/etc/hosts");
+    expect(resolved).toBe("/etc/hosts");
+  });
+
+  test("resolves parent traversal normally", () => {
+    const resolved = resolvePath("/workspace/project", "../other/file.ts");
+    expect(resolved).toBe(resolve("/workspace/project", "../other/file.ts"));
+  });
+});

packages/workflow-agent-builtin/__tests__/prompt.test.ts

@@ -0,0 +1,236 @@
+import { describe, expect, test } from "bun:test";
+
+import type { AgentContext } from "@uncaged/workflow-agent-kit";
+
+import { buildBuiltinMessages } from "../src/prompt.js";
+
+function minimalContext(overrides: Partial<AgentContext> = {}): AgentContext {
+  return {
+    threadId: "00000000000000000000000000" as AgentContext["threadId"],
+    role: "developer",
+    store: {} as AgentContext["store"],
+    workflow: {
+      name: "test",
+      description: "test workflow",
+      roles: {
+        developer: {
+          description: "Developer role",
+          goal: "Ship the fix",
+          capabilities: ["file-edit"],
+          procedure: "Edit files",
+          output: "A patch",
+          frontmatter: "schema-hash",
+        },
+      },
+      conditions: {},
+      graph: {},
+    },
+    start: { workflow: "wf-hash", prompt: "Fix the bug" },
+    steps: [],
+    outputFormatInstruction: "---\nstatus: done\n---",
+    edgePrompt: "Implement the fix described in the plan.",
+    isFirstVisit: true,
+    ...overrides,
+  };
+}
+
+describe("buildBuiltinMessages", () => {
+  test("system includes output format and role goal", () => {
+    const messages = buildBuiltinMessages(minimalContext());
+    const system = messages[0];
+    expect(system?.role).toBe("system");
+    if (system?.role === "system") {
+      expect(system.content).toContain("status: done");
+      expect(system.content).toContain("## Goal");
+      expect(system.content).toContain("Ship the fix");
+    }
+  });
+
+  test("first visit produces system + single user message with edge prompt", () => {
+    const messages = buildBuiltinMessages(minimalContext());
+    expect(messages).toHaveLength(2);
+    expect(messages[1]?.role).toBe("user");
+    if (messages[1]?.role === "user") {
+      expect(messages[1].content).toContain("Implement the fix");
+      expect(messages[1].content).not.toContain("## What Happened Since Your Last Turn");
+    }
+  });
+
+  test("first visit with prior steps includes inter-step summary in final user message", () => {
+    const messages = buildBuiltinMessages(
+      minimalContext({
+        steps: [
+          {
+            role: "planner",
+            output: { plan: "step 1" },
+            agent: "uwf-builtin",
+            detail: "detail-hash",
+            edgePrompt: "Create a plan.",
+          },
+        ],
+      }),
+    );
+    expect(messages).toHaveLength(2);
+    const finalUser = messages[1];
+    if (finalUser?.role === "user") {
+      expect(finalUser.content).toContain("Implement the fix");
+      expect(finalUser.content).toContain("## What Happened Since Your Last Turn");
+      expect(finalUser.content).toContain("planner");
+    }
+  });
+
+  test("re-entry reconstructs prior user/assistant turns plus current user message", () => {
+    const messages = buildBuiltinMessages(
+      minimalContext({
+        isFirstVisit: false,
+        edgePrompt: "Fix the reviewer's feedback.",
+        steps: [
+          {
+            role: "developer",
+            output: { summary: "Initial fix" },
+            agent: "uwf-builtin",
+            detail: "detail-1",
+            edgePrompt: "Implement the fix.",
+          },
+          {
+            role: "reviewer",
+            output: { approved: false, comments: "Missing tests" },
+            agent: "uwf-builtin",
+            detail: "detail-2",
+            edgePrompt: "Review the implementation.",
+          },
+        ],
+      }),
+    );
+
+    expect(messages).toHaveLength(4);
+    expect(messages[0]?.role).toBe("system");
+    expect(messages[1]?.role).toBe("user");
+    expect(messages[2]?.role).toBe("assistant");
+    expect(messages[3]?.role).toBe("user");
+
+    if (messages[1]?.role === "user") {
+      expect(messages[1].content).toBe("Implement the fix.");
+    }
+    if (messages[2]?.role === "assistant") {
+      expect(messages[2].content).toBe(JSON.stringify({ summary: "Initial fix" }));
+    }
+    if (messages[3]?.role === "user") {
+      expect(messages[3].content).toContain("Fix the reviewer's feedback.");
+      expect(messages[3].content).toContain("## What Happened Since Your Last Turn");
+      expect(messages[3].content).toContain("reviewer");
+      expect(messages[3].content).toContain("Missing tests");
+    }
+  });
+
+  test("prefix is stable across re-entry for LLM cache hits", () => {
+    const firstVisitMessages = buildBuiltinMessages(
+      minimalContext({
+        edgePrompt: "Implement the fix.",
+        steps: [],
+      }),
+    );
+
+    const reEntryMessages = buildBuiltinMessages(
+      minimalContext({
+        isFirstVisit: false,
+        edgePrompt: "Fix the reviewer's feedback.",
+        steps: [
+          {
+            role: "developer",
+            output: { summary: "Initial fix" },
+            agent: "uwf-builtin",
+            detail: "detail-1",
+            edgePrompt: "Implement the fix.",
+          },
+          {
+            role: "reviewer",
+            output: { approved: false },
+            agent: "uwf-builtin",
+            detail: "detail-2",
+            edgePrompt: "Review the code.",
+          },
+        ],
+      }),
+    );
+
+    expect(reEntryMessages[0]).toEqual(firstVisitMessages[0]);
+    expect(reEntryMessages[1]).toEqual(firstVisitMessages[1]);
+    expect(reEntryMessages[2]?.role).toBe("assistant");
+    if (reEntryMessages[2]?.role === "assistant") {
+      expect(reEntryMessages[2].content).toBe(JSON.stringify({ summary: "Initial fix" }));
+    }
+    expect(reEntryMessages[3]?.role).toBe("user");
+    if (reEntryMessages[3]?.role === "user") {
+      expect(reEntryMessages[3].content).toContain("Fix the reviewer's feedback.");
+    }
+  });
+
+  test("multiple prior visits emit one user/assistant pair per visit", () => {
+    const messages = buildBuiltinMessages(
+      minimalContext({
+        isFirstVisit: false,
+        edgePrompt: "Third round fix.",
+        steps: [
+          {
+            role: "developer",
+            output: { round: 1 },
+            agent: "uwf-builtin",
+            detail: "d1",
+            edgePrompt: "First attempt.",
+          },
+          {
+            role: "reviewer",
+            output: { approved: false },
+            agent: "uwf-builtin",
+            detail: "d2",
+            edgePrompt: "Review round 1.",
+          },
+          {
+            role: "developer",
+            output: { round: 2 },
+            agent: "uwf-builtin",
+            detail: "d3",
+            edgePrompt: "Second attempt.",
+          },
+          {
+            role: "reviewer",
+            output: { approved: false },
+            agent: "uwf-builtin",
+            detail: "d4",
+            edgePrompt: "Review round 2.",
+          },
+        ],
+      }),
+    );
+
+    expect(messages).toHaveLength(6);
+    expect(messages.map((m) => m.role)).toEqual([
+      "system",
+      "user",
+      "assistant",
+      "user",
+      "assistant",
+      "user",
+    ]);
+
+    if (messages[1]?.role === "user") {
+      expect(messages[1].content).toBe("First attempt.");
+    }
+    if (messages[2]?.role === "assistant") {
+      expect(messages[2].content).toBe(JSON.stringify({ round: 1 }));
+    }
+    if (messages[3]?.role === "user") {
+      expect(messages[3].content).toContain("Second attempt.");
+      expect(messages[3].content).toContain("reviewer");
+    }
+    if (messages[4]?.role === "assistant") {
+      expect(messages[4].content).toBe(JSON.stringify({ round: 2 }));
+    }
+    if (messages[5]?.role === "user") {
+      expect(messages[5].content).toContain("Third round fix.");
+      expect(messages[5].content).toContain("### Step 4: reviewer");
+      expect(messages[5].content).toContain('"approved":false');
+    }
+  });
+});

packages/workflow-agent-builtin/package.json

@@ -0,0 +1,34 @@
+{
+  "name": "@uncaged/workflow-agent-builtin",
+  "version": "0.5.0",
+  "files": [
+    "src",
+    "dist",
+    "package.json"
+  ],
+  "type": "module",
+  "bin": {
+    "uwf-builtin": "./src/cli.ts"
+  },
+  "exports": {
+    ".": {
+      "bun": "./src/index.ts",
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js"
+    }
+  },
+  "scripts": {
+    "test": "bun test"
+  },
+  "dependencies": {
+    "@uncaged/json-cas": "^0.4.0",
+    "@uncaged/workflow-agent-kit": "workspace:^",
+    "@uncaged/workflow-util": "workspace:^"
+  },
+  "devDependencies": {
+    "typescript": "^5.8.3"
+  },
+  "publishConfig": {
+    "access": "public"
+  }
+}

packages/workflow-agent-builtin/src/agent.ts

@@ -0,0 +1,158 @@
+import type { Store } from "@uncaged/json-cas";
+import {
+  type AgentContext,
+  type AgentRunResult,
+  createAgent,
+  loadWorkflowConfig,
+  resolveModel,
+  resolveStorageRoot,
+} from "@uncaged/workflow-agent-kit";
+import { createLogger, generateUlid } from "@uncaged/workflow-util";
+
+import { storeBuiltinDetail } from "./detail.js";
+import type { ChatMessage } from "./llm/index.js";
+import { BUILTIN_CONTINUE_MAX_TURNS, BUILTIN_MAX_TURNS, runBuiltinLoop } from "./loop.js";
+import { buildBuiltinMessages } from "./prompt.js";
+import { initSessionDir } from "./session.js";
+
+const log = createLogger({ sink: { kind: "stderr" } });
+
+const FRONTMATTER_FENCE = "---";
+
+/**
+ * Strip any text before the first `---` fence.
+ * LLMs sometimes emit preamble text before the frontmatter block.
+ */
+function stripPreamble(text: string): string {
+  if (text.startsWith(FRONTMATTER_FENCE)) {
+    return text;
+  }
+  const idx = text.indexOf(`\n${FRONTMATTER_FENCE}\n`);
+  if (idx !== -1) {
+    log("6GWRP3QX", `stripped ${idx + 1} chars of preamble before frontmatter`);
+    return text.slice(idx + 1);
+  }
+  return text;
+}
+
+type SessionRecord = {
+  sessionId: string;
+  model: string;
+  startedAtMs: number;
+  messages: ChatMessage[];
+};
+
+const sessions = new Map<string, SessionRecord>();
+
+function getSession(sessionId: string): SessionRecord {
+  const session = sessions.get(sessionId);
+  if (session === undefined) {
+    throw new Error(`builtin session not found: ${sessionId}`);
+  }
+  return session;
+}
+
+function buildToolContext(storageRoot: string): { cwd: string; storageRoot: string } {
+  return {
+    cwd: process.cwd(),
+    storageRoot,
+  };
+}
+
+async function runBuiltinWithMessages(
+  storageRoot: string,
+  provider: ReturnType<typeof resolveModel>,
+  messages: ChatMessage[],
+  session: SessionRecord,
+  store: Store,
+  maxTurns: number,
+  noTools: boolean,
+): Promise<AgentRunResult> {
+  const loopResult = await runBuiltinLoop({
+    provider,
+    messages,
+    toolCtx: buildToolContext(storageRoot),
+    maxTurns,
+    storageRoot,
+    sessionId: session.sessionId,
+    noTools,
+  });
+
+  session.messages = loopResult.messages;
+
+  if (loopResult.turnCount === 0) {
+    log("5RWTK9NB", "no turns produced, returning empty output");
+    return { output: "", detailHash: "", sessionId: session.sessionId };
+  }
+
+  // Read jsonl → persist turns to CAS → store detail
+  const { detailHash } = await storeBuiltinDetail(
+    store,
+    storageRoot,
+    session.sessionId,
+    session.model,
+    session.startedAtMs,
+  );
+
+  return { output: stripPreamble(loopResult.finalText), detailHash, sessionId: session.sessionId };
+}
+
+async function runBuiltin(ctx: AgentContext): Promise<AgentRunResult> {
+  const storageRoot = resolveStorageRoot();
+  const config = await loadWorkflowConfig(storageRoot);
+  const provider = resolveModel(config, config.defaultModel);
+
+  const sessionId = generateUlid(Date.now());
+  await initSessionDir(storageRoot);
+  const messages = buildBuiltinMessages(ctx);
+
+  const session: SessionRecord = {
+    sessionId,
+    model: provider.model,
+    startedAtMs: Date.now(),
+    messages,
+  };
+  sessions.set(sessionId, session);
+
+  return runBuiltinWithMessages(
+    storageRoot,
+    provider,
+    messages,
+    session,
+    ctx.store,
+    BUILTIN_MAX_TURNS,
+    false,
+  );
+}
+
+async function continueBuiltin(
+  sessionId: string,
+  message: string,
+  store: Store,
+): Promise<AgentRunResult> {
+  const session = getSession(sessionId);
+  const storageRoot = resolveStorageRoot();
+  const config = await loadWorkflowConfig(storageRoot);
+  const provider = resolveModel(config, config.defaultModel);
+
+  const messages: ChatMessage[] = [...session.messages, { role: "user", content: message }];
+
+  return runBuiltinWithMessages(
+    storageRoot,
+    provider,
+    messages,
+    session,
+    store,
+    BUILTIN_CONTINUE_MAX_TURNS,
+    true,
+  );
+}
+
+/** Agent CLI factory: built-in LLM loop with file/shell tools. */
+export function createBuiltinAgent(): () => Promise<void> {
+  return createAgent({
+    name: "builtin",
+    run: runBuiltin,
+    continue: continueBuiltin,
+  });
+}

packages/workflow-agent-builtin/src/cli.ts

@@ -0,0 +1,6 @@
+#!/usr/bin/env bun
+
+import { createBuiltinAgent } from "./agent.js";
+
+const main = createBuiltinAgent();
+void main();

packages/workflow-agent-builtin/src/detail.ts

@@ -0,0 +1,49 @@
+import { bootstrap, putSchema, type Store } from "@uncaged/json-cas";
+
+import { BUILTIN_DETAIL_SCHEMA, BUILTIN_TURN_SCHEMA } from "./schemas.js";
+import { readSessionTurns } from "./session.js";
+import type { BuiltinDetailPayload } from "./types.js";
+
+type BuiltinSchemaHashes = {
+  turn: string;
+  detail: string;
+};
+
+export async function registerBuiltinSchemas(store: Store): Promise<BuiltinSchemaHashes> {
+  await bootstrap(store);
+  const [turn, detail] = await Promise.all([
+    putSchema(store, BUILTIN_TURN_SCHEMA),
+    putSchema(store, BUILTIN_DETAIL_SCHEMA),
+  ]);
+  return { turn, detail };
+}
+
+/** Read session jsonl, persist each turn to CAS, return detail hash. */
+export async function storeBuiltinDetail(
+  store: Store,
+  storageRoot: string,
+  sessionId: string,
+  model: string,
+  startedAtMs: number,
+  nowMs: number = Date.now(),
+): Promise<{ detailHash: string; turnCount: number }> {
+  const schemas = await registerBuiltinSchemas(store);
+  const turns = await readSessionTurns(storageRoot, sessionId);
+
+  const turnHashes: string[] = [];
+  for (const turn of turns) {
+    const hash = await store.put(schemas.turn, turn);
+    turnHashes.push(hash);
+  }
+
+  const duration = Math.max(0, nowMs - startedAtMs);
+  const detail: BuiltinDetailPayload = {
+    sessionId,
+    model,
+    duration,
+    turnCount: turnHashes.length,
+    turns: turnHashes,
+  };
+  const detailHash = await store.put(schemas.detail, detail);
+  return { detailHash, turnCount: turnHashes.length };
+}

packages/workflow-agent-builtin/src/index.ts

@@ -0,0 +1,16 @@
+export { createBuiltinAgent } from "./agent.js";
+export { registerBuiltinSchemas, storeBuiltinDetail } from "./detail.js";
+export type { ChatMessage, LlmAssistantResponse, LlmToolCall } from "./llm/index.js";
+export { chatCompletionWithTools } from "./llm/index.js";
+export { BUILTIN_CONTINUE_MAX_TURNS, BUILTIN_MAX_TURNS, runBuiltinLoop } from "./loop.js";
+export { buildBuiltinMessages } from "./prompt.js";
+export { appendSessionTurn, initSessionDir, readSessionTurns, removeSession } from "./session.js";
+export type { BuiltinTool, ToolContext } from "./tools/index.js";
+export { executeBuiltinTool, getBuiltinTools } from "./tools/index.js";
+export type {
+  BuiltinDetailPayload,
+  BuiltinLoopTurn,
+  BuiltinToolCallRecord,
+  BuiltinToolResultRecord,
+  BuiltinTurnPayload,
+} from "./types.js";

packages/workflow-agent-builtin/src/llm/index.ts

@@ -0,0 +1,7 @@
+export { chatCompletionWithTools } from "./llm.js";
+export type {
+  ChatMessage,
+  LlmAssistantResponse,
+  LlmToolCall,
+  OpenAiToolDefinition,
+} from "./types.js";

packages/workflow-agent-builtin/src/llm/llm.ts

@@ -0,0 +1,139 @@
+import type { ResolvedLlmProvider } from "@uncaged/workflow-agent-kit";
+
+import type {
+  ChatMessage,
+  LlmAssistantResponse,
+  LlmToolCall,
+  OpenAiToolDefinition,
+} from "./types.js";
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+
+function chatUrl(baseUrl: string): string {
+  const trimmed = baseUrl.replace(/\/+$/, "");
+  return `${trimmed}/chat/completions`;
+}
+
+function parseToolCalls(raw: unknown): LlmToolCall[] | null {
+  if (!Array.isArray(raw) || raw.length === 0) {
+    return null;
+  }
+  const calls: LlmToolCall[] = [];
+  for (const entry of raw) {
+    if (!isRecord(entry)) {
+      continue;
+    }
+    const id = entry.id;
+    const fn = entry.function;
+    if (typeof id !== "string" || !isRecord(fn)) {
+      continue;
+    }
+    const name = fn.name;
+    const args = fn.arguments;
+    if (typeof name !== "string" || typeof args !== "string") {
+      continue;
+    }
+    calls.push({ id, name, arguments: args });
+  }
+  return calls.length > 0 ? calls : null;
+}
+
+function parseAssistantMessage(parsed: unknown): LlmAssistantResponse {
+  if (!isRecord(parsed)) {
+    throw new Error("LLM response is not an object");
+  }
+  const choices = parsed.choices;
+  if (!Array.isArray(choices) || choices.length === 0) {
+    throw new Error("LLM response has no choices");
+  }
+  const c0 = choices[0];
+  if (!isRecord(c0)) {
+    throw new Error("LLM choice is not an object");
+  }
+  const messageObj = c0.message;
+  if (!isRecord(messageObj)) {
+    throw new Error("LLM message is not an object");
+  }
+  const contentRaw = messageObj.content;
+  const content =
+    typeof contentRaw === "string"
+      ? contentRaw
+      : contentRaw === null || contentRaw === undefined
+        ? null
+        : null;
+  const toolCalls = parseToolCalls(messageObj.tool_calls);
+  return { content, toolCalls };
+}
+
+function serializeMessage(message: ChatMessage): Record<string, unknown> {
+  if (message.role === "tool") {
+    return {
+      role: "tool",
+      tool_call_id: message.tool_call_id,
+      content: message.content,
+    };
+  }
+  if (message.role === "assistant") {
+    const base: Record<string, unknown> = {
+      role: "assistant",
+      content: message.content,
+    };
+    if (message.tool_calls !== null && message.tool_calls.length > 0) {
+      base.tool_calls = message.tool_calls.map((call) => ({
+        id: call.id,
+        type: "function",
+        function: { name: call.name, arguments: call.arguments },
+      }));
+    }
+    return base;
+  }
+  return { role: message.role, content: message.content };
+}
+
+/** OpenAI-compatible chat completion with tool calling (non-streaming). */
+export async function chatCompletionWithTools(
+  provider: ResolvedLlmProvider,
+  messages: ChatMessage[],
+  tools: OpenAiToolDefinition[] | null,
+): Promise<LlmAssistantResponse> {
+  const body: Record<string, unknown> = {
+    model: provider.model,
+    messages: messages.map(serializeMessage),
+  };
+  if (tools !== null && tools.length > 0) {
+    body.tools = tools;
+    body.tool_choice = "auto";
+  }
+
+  let response: Response;
+  try {
+    response = await fetch(chatUrl(provider.baseUrl), {
+      method: "POST",
+      headers: {
+        Authorization: `Bearer ${provider.apiKey}`,
+        "Content-Type": "application/json",
+      },
+      body: JSON.stringify(body),
+    });
+  } catch (cause) {
+    const message = cause instanceof Error ? cause.message : String(cause);
+    throw new Error(`LLM network error: ${message}`);
+  }
+
+  const responseText = await response.text();
+  if (!response.ok) {
+    throw new Error(`LLM HTTP ${response.status}: ${responseText.slice(0, 2000)}`);
+  }
+
+  let parsed: unknown;
+  try {
+    parsed = JSON.parse(responseText) as unknown;
+  } catch (cause) {
+    const message = cause instanceof Error ? cause.message : String(cause);
+    throw new Error(`LLM invalid JSON response: ${message}`);
+  }
+
+  return parseAssistantMessage(parsed);
+}

packages/workflow-agent-builtin/src/llm/types.ts

@@ -0,0 +1,29 @@
+export type LlmToolCall = {
+  id: string;
+  name: string;
+  arguments: string;
+};
+
+export type LlmAssistantResponse = {
+  content: string | null;
+  toolCalls: LlmToolCall[] | null;
+};
+
+export type ChatMessage =
+  | { role: "system"; content: string }
+  | { role: "user"; content: string }
+  | {
+      role: "assistant";
+      content: string | null;
+      tool_calls: LlmToolCall[] | null;
+    }
+  | { role: "tool"; tool_call_id: string; content: string };
+
+export type OpenAiToolDefinition = {
+  type: "function";
+  function: {
+    name: string;
+    description: string;
+    parameters: Record<string, unknown>;
+  };
+};

packages/workflow-agent-builtin/src/loop.ts

@@ -0,0 +1,303 @@
+import type { ResolvedLlmProvider } from "@uncaged/workflow-agent-kit";
+import { createLogger } from "@uncaged/workflow-util";
+
+import {
+  type ChatMessage,
+  chatCompletionWithTools,
+  type LlmToolCall,
+  type OpenAiToolDefinition,
+} from "./llm/index.js";
+import { appendSessionTurn } from "./session.js";
+import {
+  builtinToolsToOpenAi,
+  executeBuiltinTool,
+  getBuiltinTools,
+  type ToolContext,
+} from "./tools/index.js";
+import type { BuiltinToolCall, BuiltinTurnPayload } from "./types.js";
+
+const log = createLogger({ sink: { kind: "stderr" } });
+
+export const BUILTIN_MAX_TURNS = 30;
+export const BUILTIN_CONTINUE_MAX_TURNS = 5;
+
+export type RunBuiltinLoopOptions = {
+  provider: ResolvedLlmProvider;
+  messages: ChatMessage[];
+  toolCtx: ToolContext;
+  maxTurns: number;
+  storageRoot: string;
+  sessionId: string;
+  /** When true, do not provide tools — force LLM to emit text only. */
+  noTools: boolean;
+};
+
+export type RunBuiltinLoopResult = {
+  finalText: string;
+  messages: ChatMessage[];
+  turnCount: number;
+};
+
+function mapToolCallsForPayload(calls: LlmToolCall[]): BuiltinToolCall[] {
+  return calls.map((call) => ({
+    name: call.name,
+    args: call.arguments,
+  }));
+}
+
+async function appendTurn(
+  storageRoot: string,
+  sessionId: string,
+  payload: BuiltinTurnPayload,
+): Promise<void> {
+  await appendSessionTurn(storageRoot, sessionId, payload);
+}
+
+export async function executeTurnTools(
+  calls: Array<{ id: string; name: string; arguments: string }>,
+  toolCtx: ToolContext,
+  messages: ChatMessage[],
+  storageRoot: string,
+  sessionId: string,
+): Promise<number> {
+  let turnCount = 0;
+  for (const call of calls) {
+    const result = await executeBuiltinTool(call.name, call.arguments, toolCtx);
+    messages.push({ role: "tool", tool_call_id: call.id, content: result });
+    await appendTurn(storageRoot, sessionId, {
+      role: "tool",
+      content: result,
+      toolCalls: null,
+      reasoning: null,
+    });
+    turnCount += 1;
+  }
+  return turnCount;
+}
+
+export type ShouldNudgeOptions = {
+  noTools: boolean;
+  text: string;
+  turn: number;
+  maxTurns: number;
+};
+
+const MAX_NUDGES = 3;
+const DEADLINE_WARNING_TURNS = 3;
+
+export function shouldInjectDeadlineWarning(
+  turn: number,
+  maxTurns: number,
+  alreadyWarned: boolean,
+  noTools: boolean,
+): boolean {
+  const turnsRemaining = maxTurns - turn;
+  return (
+    !noTools && !alreadyWarned && turnsRemaining > 0 && turnsRemaining <= DEADLINE_WARNING_TURNS
+  );
+}
+
+export function shouldProcessToolCalls(toolCalls: LlmToolCall[] | null, noTools: boolean): boolean {
+  return !noTools && toolCalls !== null && toolCalls.length > 0;
+}
+
+export function extractFinalText(messages: ChatMessage[]): string {
+  for (let i = messages.length - 1; i >= 0; i--) {
+    const msg = messages[i];
+    if (
+      msg !== undefined &&
+      msg.role === "assistant" &&
+      msg.content !== null &&
+      msg.content.trim() !== ""
+    ) {
+      return msg.content;
+    }
+  }
+  return "";
+}
+
+function injectDeadlineWarning(messages: ChatMessage[], turnsRemaining: number): void {
+  log("4NRXW6KT", `${turnsRemaining} turns remaining, injecting deadline warning`);
+  messages.push({
+    role: "user",
+    content:
+      `⚠️ You have ${turnsRemaining} turns remaining. ` +
+      "Wrap up your work and output the YAML frontmatter starting with `---`. " +
+      "If you cannot finish in time, output frontmatter with `status: failed` and describe what remains.",
+  });
+}
+
+type HandleTextOnlyTurnResult = {
+  shouldBreak: boolean;
+  finalText: string;
+  turnCount: number;
+  nudgeCount: number;
+  turnAdjustment: number;
+};
+
+async function handleTextOnlyTurn(
+  text: string,
+  messages: ChatMessage[],
+  storageRoot: string,
+  sessionId: string,
+  noTools: boolean,
+  turn: number,
+  maxTurns: number,
+  currentNudgeCount: number,
+): Promise<HandleTextOnlyTurnResult> {
+  await appendTurn(storageRoot, sessionId, {
+    role: "assistant",
+    content: text,
+    toolCalls: null,
+    reasoning: null,
+  });
+  const turnCount = 1;
+  let nudgeCount = currentNudgeCount;
+  let turnAdjustment = 0;
+
+  if (shouldNudge({ noTools, text, turn, maxTurns })) {
+    nudgeCount += 1;
+    log("7FXQM2KN", `text-only turn without frontmatter, nudge ${nudgeCount}/${MAX_NUDGES}`);
+    const nudge =
+      "You stopped calling tools but your response does not start with the required `---` YAML frontmatter. " +
+      "Either continue using tools to complete your work, or output your final response starting with `---`.";
+    messages.push({ role: "user", content: nudge });
+    // Nudge doesn't consume turn budget (up to MAX_NUDGES)
+    if (nudgeCount <= MAX_NUDGES) {
+      turnAdjustment = -1;
+    }
+    return { shouldBreak: false, finalText: "", turnCount, nudgeCount, turnAdjustment };
+  }
+
+  return { shouldBreak: true, finalText: text, turnCount, nudgeCount, turnAdjustment };
+}
+
+async function handleToolCallTurn(
+  content: string,
+  toolCalls: LlmToolCall[],
+  messages: ChatMessage[],
+  storageRoot: string,
+  sessionId: string,
+  toolCtx: ToolContext,
+): Promise<number> {
+  await appendTurn(storageRoot, sessionId, {
+    role: "assistant",
+    content,
+    toolCalls: mapToolCallsForPayload(toolCalls),
+    reasoning: null,
+  });
+  let turnCount = 1;
+
+  // Execute tools
+  turnCount += await executeTurnTools(toolCalls, toolCtx, messages, storageRoot, sessionId);
+
+  return turnCount;
+}
+
+export function shouldNudge({ noTools, text, turn, maxTurns }: ShouldNudgeOptions): boolean {
+  return !noTools && !text.trimStart().startsWith("---") && turn < maxTurns - 1;
+}
+
+type ProcessLoopIterationResult = {
+  shouldBreak: boolean;
+  finalText: string;
+  turnCount: number;
+  nudgeCount: number;
+  turnAdjustment: number;
+};
+
+async function processLoopIteration(
+  options: RunBuiltinLoopOptions,
+  messages: ChatMessage[],
+  openAiTools: OpenAiToolDefinition[],
+  turn: number,
+  nudgeCount: number,
+): Promise<ProcessLoopIterationResult> {
+  const response = await chatCompletionWithTools(
+    options.provider,
+    messages,
+    openAiTools.length > 0 ? openAiTools : null,
+  );
+
+  // When noTools is set, ignore any tool_calls the LLM might still return
+  const effectiveToolCalls = options.noTools ? null : (response.toolCalls ?? null);
+
+  const assistantMessage: ChatMessage = {
+    role: "assistant",
+    content: response.content,
+    tool_calls: effectiveToolCalls,
+  };
+  messages.push(assistantMessage);
+
+  if (!shouldProcessToolCalls(effectiveToolCalls, options.noTools)) {
+    const text = response.content ?? "";
+    const result = await handleTextOnlyTurn(
+      text,
+      messages,
+      options.storageRoot,
+      options.sessionId,
+      options.noTools,
+      turn,
+      options.maxTurns,
+      nudgeCount,
+    );
+    return result;
+  }
+
+  // At this point, effectiveToolCalls is guaranteed to be non-null and non-empty
+  const turnCount = await handleToolCallTurn(
+    response.content ?? "",
+    effectiveToolCalls as LlmToolCall[],
+    messages,
+    options.storageRoot,
+    options.sessionId,
+    options.toolCtx,
+  );
+
+  return {
+    shouldBreak: false,
+    finalText: "",
+    turnCount,
+    nudgeCount,
+    turnAdjustment: 0,
+  };
+}
+
+/** Agent run loop: LLM ↔ tools until no tool_calls or maxTurns. */
+export async function runBuiltinLoop(
+  options: RunBuiltinLoopOptions,
+): Promise<RunBuiltinLoopResult> {
+  const messages = [...options.messages];
+  const openAiTools = options.noTools ? [] : builtinToolsToOpenAi(getBuiltinTools());
+  let finalText = "";
+  let turnCount = 0;
+  let nudgeCount = 0;
+  let deadlineWarned = false;
+
+  for (let turn = 0; turn < options.maxTurns; turn++) {
+    log("8K2M4N7P", `builtin loop turn ${turn + 1}/${options.maxTurns}`);
+
+    // Warn agent when approaching turn limit
+    if (shouldInjectDeadlineWarning(turn, options.maxTurns, deadlineWarned, options.noTools)) {
+      deadlineWarned = true;
+      const turnsRemaining = options.maxTurns - turn;
+      injectDeadlineWarning(messages, turnsRemaining);
+    }
+
+    const result = await processLoopIteration(options, messages, openAiTools, turn, nudgeCount);
+    turnCount += result.turnCount;
+    nudgeCount = result.nudgeCount;
+    turn += result.turnAdjustment;
+
+    if (result.shouldBreak) {
+      finalText = result.finalText;
+      break;
+    }
+  }
+
+  if (finalText === "") {
+    finalText = extractFinalText(messages);
+  }
+
+  return { finalText, messages, turnCount };
+}

packages/workflow-agent-builtin/src/prompt.ts

@@ -0,0 +1,115 @@
+import { type AgentContext, buildRolePrompt } from "@uncaged/workflow-agent-kit";
+
+import type { ChatMessage } from "./llm/index.js";
+
+type StepContext = AgentContext["steps"][number];
+
+function formatStep(step: StepContext, stepNumber: number): string {
+  return [
+    `### Step ${stepNumber}: ${step.role}`,
+    `Output: ${JSON.stringify(step.output)}`,
+    `Agent: ${step.agent}`,
+  ].join("\n");
+}
+
+function buildStepsSummary(steps: StepContext[], fromIndex: number, toIndex: number): string {
+  if (fromIndex >= toIndex) {
+    return "";
+  }
+
+  const lines: string[] = ["## What Happened Since Your Last Turn"];
+  for (let i = fromIndex; i < toIndex; i++) {
+    const step = steps[i];
+    if (step === undefined) {
+      continue;
+    }
+    lines.push("");
+    lines.push(formatStep(step, i + 1));
+  }
+  return lines.join("\n");
+}
+
+function buildUserTurnContent(edgePrompt: string, summary: string): string {
+  const parts: string[] = [];
+  if (edgePrompt !== "") {
+    parts.push(edgePrompt);
+  }
+  if (summary !== "") {
+    if (parts.length > 0) {
+      parts.push("");
+    }
+    parts.push(summary);
+  }
+  return parts.join("\n");
+}
+
+/**
+ * Reconstruct multi-turn chat messages from thread history for cache-friendly session resume.
+ *
+ * - system: role prompt + output format (stable prefix)
+ * - For each prior visit of this role: user (edgePrompt + inter-step summary) + assistant (output JSON)
+ * - Final user: current edgePrompt + summary since last visit of this role
+ */
+export function buildBuiltinMessages(ctx: AgentContext): ChatMessage[] {
+  const roleDef = ctx.workflow.roles[ctx.role];
+  const rolePrompt = roleDef !== undefined ? buildRolePrompt(roleDef) : "";
+  const systemParts: string[] = [];
+  if (ctx.outputFormatInstruction !== "") {
+    systemParts.push(ctx.outputFormatInstruction, "");
+  }
+  systemParts.push(rolePrompt);
+
+  systemParts.push(
+    "",
+    "## Workflow",
+    "",
+    `Your working directory is: ${process.cwd()}`,
+    "",
+    "You have tools available (read_file, write_file, run_command). " +
+      "Use them to complete your task — read files, run commands, make changes as needed. " +
+      "Your task is described in the user message below — do NOT use uwf or workflow CLI commands to discover your task. " +
+      "When you are done, output your final response with the YAML frontmatter block as specified above. " +
+      "Do NOT output the frontmatter until you have completed all necessary work. " +
+      "If you are running low on turns and cannot finish, output the frontmatter with `status: failed` and explain what remains in the body. " +
+      "CRITICAL: Your final output MUST start with the `---` fence on the very first line — " +
+      "no preamble text, no explanation before it. The parser requires `---` at position 0.",
+  );
+
+  const messages: ChatMessage[] = [{ role: "system", content: systemParts.join("\n") }];
+
+  const roleVisitIndices: number[] = [];
+  for (let i = 0; i < ctx.steps.length; i++) {
+    const step = ctx.steps[i];
+    if (step !== undefined && step.role === ctx.role) {
+      roleVisitIndices.push(i);
+    }
+  }
+
+  let prevVisitIndex = -1;
+  for (const visitIndex of roleVisitIndices) {
+    const visitStep = ctx.steps[visitIndex];
+    if (visitStep === undefined) {
+      continue;
+    }
+
+    const summary = buildStepsSummary(ctx.steps, prevVisitIndex + 1, visitIndex);
+    messages.push({
+      role: "user",
+      content: buildUserTurnContent(visitStep.edgePrompt, summary),
+    });
+    messages.push({
+      role: "assistant",
+      content: JSON.stringify(visitStep.output),
+      tool_calls: null,
+    });
+    prevVisitIndex = visitIndex;
+  }
+
+  const finalSummary = buildStepsSummary(ctx.steps, prevVisitIndex + 1, ctx.steps.length);
+  messages.push({
+    role: "user",
+    content: buildUserTurnContent(ctx.edgePrompt, finalSummary),
+  });
+
+  return messages;
+}

packages/workflow-agent-builtin/src/schemas.ts

@@ -0,0 +1,45 @@
+import type { JSONSchema } from "@uncaged/json-cas";
+
+const BUILTIN_TOOL_CALL_SCHEMA: JSONSchema = {
+  type: "object",
+  required: ["name", "args"],
+  properties: {
+    name: { type: "string" },
+    args: { type: "string" },
+  },
+  additionalProperties: false,
+};
+
+export const BUILTIN_TURN_SCHEMA: JSONSchema = {
+  title: "builtin-turn",
+  type: "object",
+  required: ["role", "content"],
+  properties: {
+    role: { type: "string", enum: ["assistant", "tool"] },
+    content: { type: "string" },
+    toolCalls: {
+      anyOf: [{ type: "array", items: BUILTIN_TOOL_CALL_SCHEMA }, { type: "null" }],
+    },
+    reasoning: {
+      anyOf: [{ type: "string" }, { type: "null" }],
+    },
+  },
+  additionalProperties: false,
+};
+
+export const BUILTIN_DETAIL_SCHEMA: JSONSchema = {
+  title: "builtin-detail",
+  type: "object",
+  required: ["sessionId", "model", "duration", "turnCount", "turns"],
+  properties: {
+    sessionId: { type: "string" },
+    model: { type: "string" },
+    duration: { type: "integer" },
+    turnCount: { type: "integer" },
+    turns: {
+      type: "array",
+      items: { type: "string", format: "cas_ref" },
+    },
+  },
+  additionalProperties: false,
+};