refactor: rename status to $status, default to _ when absent

- evaluate() reads $status instead of status, defaults to _ when missing
- Update all YAML examples and .workflows to use $status
- Update cli-workflow resolveEvaluateArgs to use $status
- 10 moderator tests pass including new default _ test
- Single-exit roles no longer need to declare status field

Phase 1 of #499 (closes #500)

.workflows/solve-issue.yaml

@@ -22,43 +22,50 @@ roles:
       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)."
+    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:
+        $status:
           type: string
           enum: [ready, insufficient_info]
         plan:
           type: string
-      required: [status]
+      required: [$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: |
-      Before starting any work, ensure a clean worktree:
-      1. `git checkout main && git pull` to get the latest code
-      2. `git checkout -b fix/<issue-number>-<short-description>` to create a fresh branch
-         - If bounced back from reviewer or tester, reuse the existing branch and rebase onto latest main:
-           `git checkout main && git pull && git checkout <branch> && git rebase main`
+      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:
-      3. Read the test spec from CAS: `uwf cas get <plan hash>` (find the hash from the latest planner step's frontmatter.plan)
-      4. If bounced back from reviewer or tester: read the previous role's output to understand what needs fixing
-      5. Write tests first based on the spec
-      6. Implement the code to make tests pass
-      7. Ensure `bun run build` passes with no errors
-      8. Run `bun test` to verify all tests pass
-    output: "List all files changed and provide a summary. Frontmatter must include: status (done or failed)."
+      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:
+        $status:
           type: string
           enum: [done, failed]
-      required: [status]
+      required: [$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)."
@@ -66,6 +73,8 @@ roles:
       - 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
@@ -86,19 +95,22 @@ roles:
 
       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)."
+    output: "Explain your decision with specific file/line references. Frontmatter must include: $status (approved or rejected)."
     frontmatter:
       type: object
       properties:
-        approved:
-          type: boolean
-      required: [approved]
+        $status:
+          type: string
+          enum: [approved, rejected]
+      required: [$status]
   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
@@ -106,92 +118,58 @@ roles:
          - 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)."
+    output: "Report test results per scenario. Frontmatter must include: $status (passed, fix_code, or fix_spec)."
     frontmatter:
       type: object
       properties:
-        status:
+        $status:
           type: string
           enum: [passed, fix_code, fix_spec]
-      required: [status]
+      required: [$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 --title "..." --description "..."`
+      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
-    output: "Include PR URL on success or error log on failure. Frontmatter must include: success (true or false)."
+         - 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: $status (committed or hook_failed)."
     frontmatter:
       type: object
       properties:
-        success:
-          type: boolean
-      required: [success]
-conditions:
-  insufficientInfo:
-    description: "Planner determined there's not enough info to proceed"
-    expression: "$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"
+        $status:
+          type: string
+          enum: [committed, hook_failed]
+      required: [$status]
 graph:
   $START:
-    - role: "planner"
-      condition: null
-      prompt: "Analyze the issue and produce an implementation plan."
+    _: { role: "planner", prompt: "Analyze the issue and produce an implementation plan." }
   planner:
-    - role: "$END"
-      condition: "insufficientInfo"
-      prompt: "Insufficient information to proceed; end the workflow."
-    - role: "developer"
-      condition: null
-      prompt: "Implement the plan from the planner."
+    insufficient_info: { role: "$END", prompt: "Insufficient information to proceed; end the workflow." }
+    ready: { role: "developer", prompt: "Implement the plan from the planner." }
   developer:
-    - role: "$END"
-      condition: "devFailed"
-      prompt: "Development failed; end the workflow."
-    - role: "reviewer"
-      condition: null
-      prompt: "Send the implementation to the reviewer."
+    failed: { role: "$END", prompt: "Development failed; end the workflow." }
+    done: { role: "reviewer", prompt: "Send the implementation to the reviewer." }
   reviewer:
-    - role: "developer"
-      condition: "rejected"
-      prompt: "Reviewer rejected the implementation; fix the issues."
-    - role: "tester"
-      condition: null
-      prompt: "Review passed; run tests on the implementation."
+    rejected: { role: "developer", prompt: "Reviewer rejected the implementation; fix the issues." }
+    approved: { role: "tester", prompt: "Review passed; run tests on the implementation." }
   tester:
-    - role: "developer"
-      condition: "fixCode"
-      prompt: "Tests found code issues; return to developer."
-    - role: "planner"
-      condition: "fixSpec"
-      prompt: "Tests found spec issues; return to planner."
-    - role: "committer"
-      condition: null
-      prompt: "Tests passed; commit and push the changes."
+    fix_code: { role: "developer", prompt: "Tests found code issues; return to developer." }
+    fix_spec: { role: "planner", prompt: "Tests found spec issues; return to planner." }
+    passed: { role: "committer", prompt: "Tests passed; commit and push the changes." }
   committer:
-    - role: "developer"
-      condition: "hookFailed"
-      prompt: "Push hook failed; return to developer to fix."
-    - role: "$END"
-      condition: null
-      prompt: "Commit succeeded; complete the workflow."
+    hook_failed: { role: "developer", prompt: "Push hook failed; return to developer to fix." }
+    committed: { role: "$END", prompt: "Commit succeeded; complete the workflow." }

CLAUDE.md

@@ -8,10 +8,10 @@ This monorepo implements a stateless workflow engine driven by a single-step CLI
 
 | Concept | What it is |
 |---------|-----------|
-| **Workflow** | A YAML definition (`WorkflowPayload`) with roles, conditions, and a routing graph. Stored as a CAS node, identified by its XXH64 hash. |
+| **Workflow** | A YAML definition (`WorkflowPayload`) with roles, status-based routing, and a directed 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 `$END`) with zero LLM cost. |
+| **Moderator** | Status-based graph evaluator — determines the next role (or `$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. |
@@ -23,7 +23,7 @@ workflow/
   packages/
     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-moderator/   # @uncaged/workflow-moderator — Status-based 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

README.md

@@ -1,10 +1,10 @@
 # @uncaged/workflow
 
-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.
+A stateless workflow engine driven by a single-step CLI. Workflows are YAML definitions with roles, status-based routing, and a directed graph. Threads are immutable CAS-linked chains — each `uwf thread step` runs one moderator→agent→extract cycle and exits.
 
 ## Overview
 
-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 `$END`. Each step is a complete process: the moderator evaluates JSONata conditions to pick the next role, an external agent CLI produces frontmatter markdown output, and an extract pipeline validates or structures that output against the role's JSON Schema.
+This monorepo implements **uwf**, a workflow engine with no long-running daemon. You register YAML workflow definitions in a content-addressed store (CAS), start a thread with an initial prompt, then invoke `uwf thread step` repeatedly until the moderator routes to `$END`. Each step is a complete process: the moderator evaluates status-based routing 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.
 
 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.
 
@@ -20,7 +20,7 @@ Layer 0 — Contract
 
 Layer 1 — Shared infra
   workflow-util              Encoding, IDs, logging, frontmatter, paths
-  workflow-moderator         JSONata graph evaluator
+  workflow-moderator         Status-based graph evaluator
 
 Layer 2 — Agent framework
   workflow-agent-kit         createAgent factory, context builder, extract pipeline
@@ -47,7 +47,7 @@ See [docs/architecture.md](docs/architecture.md) for the full design — three-p
 |---------|-----|-------------|------|--------|
 | `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 `$END` | lib | [README](packages/workflow-moderator/README.md) |
+| `workflow-moderator` | `@uncaged/workflow-moderator` | Status-based graph evaluator — next role or `$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) |
@@ -62,16 +62,16 @@ See [docs/architecture.md](docs/architecture.md) for the full design — three-p
 uwf setup
 
 # 2. Register a workflow from YAML
-uwf workflow put examples/solve-issue.yaml
+uwf workflow add examples/solve-issue.yaml
 
 # 3. Start a thread (creates head pointer; does not execute)
 uwf thread start solve-issue -p "Fix the login redirect bug"
 
 # 4. Execute steps (one at a time, until done)
-uwf thread step <thread-id>
+uwf thread exec <thread-id>
 ```
 
-Use `-c, --count <number>` on `thread step` to run multiple steps in one invocation. Override the agent with `--agent <cmd>`.
+Use `-c, --count <number>` on `thread exec` to run multiple steps in one invocation. Override the agent with `--agent <cmd>`.
 
 ## CLI Reference
 
@@ -79,8 +79,9 @@ Global options: `-V, --version`, `--format <json|yaml>`, `-h, --help`.
 
 | Group | Commands |
 |-------|----------|
-| **thread** | `start`, `step`, `show`, `list`, `kill`, `steps`, `read`, `fork`, `step-details` |
-| **workflow** | `put`, `show`, `list` |
+| **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 |

docs/architecture.md

@@ -16,7 +16,7 @@ The implementation lives in **6** active packages under `packages/`, plus two ex
 |-------|---------|---------------|
 | 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/workflow-moderator` → `workflow-moderator` | JSONata-based graph evaluator: given a `WorkflowPayload` and `ModeratorContext`, returns the next role or `$END`. |
+| Moderator | `@uncaged/workflow-moderator` → `workflow-moderator` | Status-based graph evaluator: given a routing graph, last role, and last output, returns the next role or `$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. |
@@ -27,7 +27,7 @@ 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 `workflow-moderator`). |
+| `mustache` | Template renderer for edge prompts (used by `workflow-moderator`). |
 | `commander` | CLI argument parsing (used by `cli-workflow`). |
 | `dotenv` | Loads `.env` files for API keys. |
 | `yaml` | YAML parse/stringify. |
@@ -148,8 +148,7 @@ graph:
 Key properties:
 
 - **`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 | "$START", Transition[]>` — first matching transition wins; `condition: null` = fallback
+- **`graph`** — `Record<Role | "$START", Record<Status, Target>>` — status-based routing; each role maps statuses to targets
 - **No agent binding** — agent selection is a deployment concern, configured in `config.yaml`
 - **No Zod** — all schemas are JSON Schema, validated through `@uncaged/json-cas`
 
@@ -159,8 +158,8 @@ Each `uwf thread step` runs exactly one cycle: moderator → agent → extract.
 
 ```
 ┌─→ Phase 1: MODERATOR
-│   Input:  WorkflowPayload + ModeratorContext { start, steps[] }
-│   Engine: JSONata conditions evaluated against the graph
+│   Input:  graph + lastRole + lastOutput
+│   Engine: Status-based map lookup against lastOutput.status
 │   Output: next role name | $END
 │
 │   Phase 2: AGENT
@@ -207,7 +206,7 @@ type AgentContext = ModeratorContext & {
 
 ### Key properties
 
-- **Moderator** — pure JSONata evaluation; no LLM call, no I/O beyond CAS reads. Evaluates `workflow.graph[currentRole]` transitions in order, returns first match.
+- **Moderator** — pure status-based map lookup; no LLM call, no I/O beyond CAS reads. Looks up `graph[lastRole][lastOutput.status]` to get the next target.
 - **Agent** — receives `AgentContext` with thread history + role system prompt + output format instruction. Raw output is frontmatter markdown.
 - **Extractor** — two-layer: tries frontmatter fast-path first (zero LLM cost), falls back to LLM extract if frontmatter is absent or invalid.
 - **Stateless** — each `uwf thread step` is an atomic, self-contained operation. No in-memory state between steps.
@@ -485,7 +484,7 @@ Binary: `uwf`
 | **YAML workflow definitions** | Human-readable, versionable, no build step required. JSON Schema inline in YAML, registered as CAS nodes on `workflow put`. |
 | **Stateless single-step CLI** | Each `uwf thread step` is atomic — no in-memory state, no daemon, no long-running process. OS handles lifecycle. |
 | **CAS-backed thread state** | Immutable linked nodes enable fork, replay, and GC without copying data. Content-addressed deduplication across threads. |
-| **JSONata moderator** | Declarative condition expressions evaluated against thread history. No LLM cost for routing decisions. |
+| **Status-based moderator** | Status-based map routing — `graph[role][status]` lookup against last output. No LLM cost for routing decisions. |
 | **Frontmatter markdown output** | Agents produce structured meta (YAML frontmatter) alongside free-form content (markdown body). Enables zero-cost extraction when frontmatter is well-formed. |
 | **Two-layer extract** | Fast path avoids LLM calls when agents follow the format; LLM fallback handles messy output gracefully. |
 | **Prompt injection for format** | Output format instruction prepended to system prompt ensures agents produce parseable output without per-agent configuration. |

docs/builtin-agent-research.md

@@ -288,7 +288,7 @@ export type BuildContextMeta = {
 
 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）
+3. `buildHistory`：反转为时间序，`expandOutput` 把每步 `output` CasRef 展开为 JSON payload（供 prompt / moderator 使用）
 4. `loadWorkflow`：从 `start.workflow` CasRef 加载 `WorkflowPayload`
 
 #### Role definition 来源
@@ -572,7 +572,7 @@ Hermes 自带完整 agent runtime（`--yolo`、max-turns），tool 集由 Hermes
 | 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。
+**不需要**在 builtin 里实现 moderator / workflow 路由工具——仍由 `uwf thread step` + status-based moderator 负责。
 
 #### Agent loop 必须能力
 

docs/wf-stateless-design.md

@@ -75,7 +75,7 @@ uwf thread step 01J7K9M2XNPQR5VWBCDF8G3H4T --agent "bunx uwf-cursor"
 **做的事：**
 1. 读链头 → 当前 StepNode（或 StartNode）
 2. 收集 thread 历史（遍历链）
-3. 调 moderator：评估 JSONata conditions → 得到下一个 role（或 END）
+3. 调 moderator：status-based map lookup → 得到下一个 role（或 END）
 4. 若 END → 归档 thread，输出最后链头，退出
 5. 确定 agent command（`--agent` override > config.yaml per-workflow/role > config.yaml defaultAgent）
 6. 调用：`<agent-cmd> <thread-id> <role>`，捕获 stdout 得到新 StepNode hash
@@ -199,29 +199,21 @@ payload:
 ```
 
 - `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 | "$START", Transition[]>`，每个 Transition = `{ role, condition }`
-- `condition` 引用 conditions 中的 key，`null` = fallback
-- 按数组顺序求值，第一个匹配的 transition 胜出
+- `graph` — `Record<Role | "$START", Record<Status, Target>>`，每个 Target = `{ role, prompt }`
+- Status 来自上一个 role 输出的 `status` 字段，`$START` 用 `_` 作为初始 status
+- Prompt 模板使用 Mustache 渲染，变量来自 lastOutput
 - 不含 agent binding — agent 配置在 `~/.uncaged/workflow/config.yaml` 中管理
 
-JSONata 表达式的求值上下文：
+Moderator 的求值逻辑：
 
-```jsonc
-{
-  "start": {                          // StartNode 信息
-    "workflow": "4KNM2PXR3B1QW",
-    "prompt": "Fix the login bug..."
-  },
-  "steps": [                          // 所有已完成 steps，从旧到新
-    { "role": "planner", "output": { "phases": [...] }, "detail": "7BQST3VW9F2MA", "agent": "uwf-hermes" },
-    { "role": "developer", "output": { "filesChanged": ["src/auth.ts"], "summary": "Fixed redirect" }, "detail": "9KRVW3TN5F1QA", "agent": "uwf-cursor" },
-    { "role": "reviewer", "output": { "approved": false }, "detail": "2MXBG6PN4A8JR", "agent": "uwf-hermes" }
-  ]
-}
+```typescript
+evaluate(graph, lastRole, lastOutput) → { role, prompt }
+// 1. status = lastRole === "$START" ? "_" : lastOutput.status
+// 2. target = graph[lastRole][status]
+// 3. prompt = mustache.render(target.prompt, lastOutput)
 ```
 
-注：`output` 在上下文中会被自动展开为实际的 CAS 节点内容（而非 hash），方便 JSONata 表达式直接访问字段。
+注：routing 基于 `lastOutput.status` 字段的值，直接在 graph map 中查找对应的 Target。
 
 #### `StartNode`（Thread 起点）
 
@@ -350,7 +342,7 @@ OPENROUTER_API_KEY=sk-or-...
 ```
 packages/
 ├── cli-workflow/              # @uncaged/cli-workflow — uwf CLI（thread/workflow 命令）
-├── workflow-moderator/        # @uncaged/workflow-moderator — JSONata moderator 引擎
+├── workflow-moderator/        # @uncaged/workflow-moderator — Status-based 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
@@ -367,7 +359,7 @@ packages/
 
 ## 4. 关键数据类型
 
-JSONata 求值上下文本质上是 thread 链表的线性化表达。StepNode payload 和上下文中的 step 共享大量字段，提取为公共类型。
+Moderator 通过 status-based map lookup 进行路由。StepNode payload 和上下文中的 step 共享大量字段，提取为公共类型。
 
 ### 4.1 公共类型
 
@@ -378,7 +370,7 @@ type CasRef = string;
 /** Thread ID — ULID, 26-char Crockford Base32 */
 type ThreadId = string;
 
-/** 一个 step 的核心数据，被 StepNode payload 和 JSONata 上下文共享 */
+/** 一个 step 的核心数据，被 StepNode payload 和 moderator 上下文共享 */
 type StepRecord = {
   role: string;
   output: CasRef;                    // cas_ref → 结构化输出节点（符合 role meta schema）
@@ -399,22 +391,16 @@ type RoleDefinition = {
   meta: CasRef;                      // cas_ref → json-cas 内置 JSON Schema 节点
 };
 
-type Transition = {
+type Target = {
   role: string;                      // 目标 role 名 或 "$END"
-  condition: string | null;          // 引用 conditions 中的 key，null = fallback
-};
-
-type ConditionDefinition = {
-  description: string;
-  expression: string;                           // JSONata expression
+  prompt: string;                    // Mustache 模板，渲染时注入 lastOutput
 };
 
 type WorkflowPayload = {
   name: string;
   description: string;
   roles: Record<string, RoleDefinition>;
-  conditions: Record<string, ConditionDefinition>;
-  graph: Record<string, Transition[]>;          // Record<Role | "$START", Transition[]>
+  graph: Record<string, Record<string, Target>>;  // Record<Role | "$START", Record<Status, Target>>
 };
 ```
 
@@ -432,20 +418,14 @@ type StepNodePayload = StepRecord & {
 };
 ```
 
-### 4.4 JSONata 求值上下文
+### 4.4 Moderator 求值
 
-Thread 链表的线性化。`steps[n]` 的字段和 `StepRecord` 一致，但 `output` 被展开为实际内容。
+Moderator 使用 `evaluate(graph, lastRole, lastOutput)` 进行同步 status-based routing：
 
 ```typescript
-/** JSONata 上下文中的 step — output 被展开 */
-type StepContext = Omit<StepRecord, "output"> & {
-  output: unknown;                   // 展开后的 CAS 节点内容，非 hash
-};
-
-type ModeratorContext = {
-  start: StartNodePayload;
-  steps: StepContext[];              // 从旧到新
-};
+// graph[lastRole][lastOutput.status] → Target { role, prompt }
+// $START 角色使用 "_" 作为初始 status
+// prompt 通过 Mustache 模板渲染，变量来自 lastOutput
 ```
 
 ### 4.5 CLI 输出
@@ -534,6 +514,5 @@ StepNodePayload ──extends──→ StepRecord ←──maps to──→ Step
     │
     └── start.workflow → WorkflowPayload
                              ├── roles: Record<name, RoleDefinition>
-                             ├── conditions: Record<name, JSONata>
-                             └── graph: Record<role, Transition[]>
+                             └── graph: Record<role, Record<status, Target>>
 ```

examples/analyze-topic.yaml

@@ -22,6 +22,8 @@ roles:
     frontmatter:
       type: object
       properties:
+        $status:
+          enum: ["_"]
         thesis:
           type: string
         keyPoints:
@@ -30,14 +32,9 @@ roles:
             type: string
         caveats:
           type: string
-      required: [thesis, keyPoints]
-conditions: {}
+      required: [$status, thesis, keyPoints]
 graph:
   $START:
-    - role: "analyst"
-      condition: null
-      prompt: "Analyze the topic in the task and produce a structured summary with key points."
+    _: { role: "analyst", prompt: "Analyze the topic in the task and produce a structured summary with key points." }
   analyst:
-    - role: "$END"
-      condition: null
-      prompt: "Analysis complete. Finish the workflow."
+    _: { role: "$END", prompt: "Analysis complete. Finish the workflow." }

examples/debate.yaml

@@ -16,15 +16,16 @@ roles:
       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.
+      Set status to "conceded" ONLY if you are genuinely convinced and wish to stop debating.
+      Otherwise set status to "continue".
     frontmatter:
       type: object
       properties:
+        $status:
+          enum: ["continue", "conceded"]
         argument:
           type: string
-        conceded:
-          type: boolean
-      required: [argument, conceded]
+      required: [$status, argument]
   for:
     description: "Argues for the proposition"
     goal: |
@@ -40,38 +41,22 @@ roles:
       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.
+      Set status to "conceded" ONLY if you are genuinely convinced and wish to stop debating.
+      Otherwise set status to "continue".
     frontmatter:
       type: object
       properties:
+        $status:
+          enum: ["continue", "conceded"]
         argument:
           type: string
-        conceded:
-          type: boolean
-      required: [argument, conceded]
-conditions:
-  againstConceded:
-    description: "The against side conceded"
-    expression: "$last('against').conceded = true"
-  forConceded:
-    description: "The for side conceded"
-    expression: "$last('for').conceded = true"
+      required: [$status, argument]
 graph:
   $START:
-    - role: "against"
-      condition: null
-      prompt: "Present your opening argument against the proposition."
+    _: { role: "against", prompt: "Present your opening argument against the proposition." }
   against:
-    - role: "$END"
-      condition: "againstConceded"
-      prompt: "The against side conceded. Debate over."
-    - role: "for"
-      condition: null
-      prompt: "Counter the opposing argument. Address their points directly."
+    conceded: { role: "$END", prompt: "The against side conceded. Debate over." }
+    continue: { role: "for", prompt: "Counter the opposing argument: {{{argument}}}" }
   for:
-    - role: "$END"
-      condition: "forConceded"
-      prompt: "The for side conceded. Debate over."
-    - role: "against"
-      condition: null
-      prompt: "Counter the opposing argument. Address their points directly."
+    conceded: { role: "$END", prompt: "The for side conceded. Debate over." }
+    continue: { role: "against", prompt: "Counter the opposing argument: {{{argument}}}" }

examples/solve-issue.yaml

@@ -27,11 +27,13 @@ roles:
     frontmatter:
       type: object
       properties:
+        $status:
+          enum: ["_"]
         repoPath:
           type: string
         plan:
           type: string
-      required: [repoPath, plan]
+      required: [$status, repoPath, plan]
   developer:
     description: "Implements code changes"
     goal: "You are a developer agent. You implement code changes according to plans."
@@ -44,55 +46,47 @@ roles:
       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. Commit your changes with a descriptive message referencing the issue.
+      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:
+        $status:
+          enum: ["_"]
         filesChanged:
           type: array
           items:
             type: string
         summary:
           type: string
-      required: [filesChanged, summary]
+      required: [$status, filesChanged, summary]
   reviewer:
     description: "Reviews code changes"
     goal: "You are a code reviewer. You review implementations for correctness and quality."
     capabilities:
       - code-review
       - static-analysis
-    procedure: "Review the implementation against the plan. Check for bugs, edge cases, and style."
+    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:
-          type: boolean
+        $status:
+          enum: ["approved", "rejected"]
         comments:
           type: string
-      required: [approved, comments]
-conditions:
-  notApproved:
-    description: "Reviewer rejected the implementation"
-    expression: "$last('reviewer').approved = false"
+      required: [$status, comments]
 graph:
   $START:
-    - role: "planner"
-      condition: null
-      prompt: "Analyze the issue described in the task and produce a detailed implementation plan."
+    _: { role: "planner", prompt: "Analyze the issue described in the task and produce a detailed implementation plan." }
   planner:
-    - role: "developer"
-      condition: null
-      prompt: "Implement the plan from the planner. Write code, tests, and ensure existing tests pass."
+    _: { role: "developer", prompt: "Implement the plan from the planner. Write code, tests, and ensure existing tests pass." }
   developer:
-    - role: "reviewer"
-      condition: null
-      prompt: "Review the developer's implementation against the plan for correctness and quality."
+    _: { role: "reviewer", prompt: "Review the developer's implementation against the plan for correctness and quality." }
   reviewer:
-    - role: "developer"
-      condition: "notApproved"
-      prompt: "The reviewer rejected your implementation. Read their feedback and fix the issues."
-    - role: "$END"
-      condition: null
-      prompt: "The review passed. Complete the workflow."
+    approved: { role: "$END", prompt: "The review passed. Complete the workflow." }
+    rejected: { role: "developer", prompt: "The reviewer rejected your implementation. Read their feedback and fix the issues: {{{comments}}}" }

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-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

@@ -5,6 +5,7 @@
     "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",

packages/cli-workflow/README.md

@@ -6,6 +6,18 @@
 
 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`
@@ -30,34 +42,58 @@ bun link packages/cli-workflow
 -h, --help             Show help
 ```
 
-### Thread
+### Thread (Layer 2: Execution Instances)
 
 | Command | Description |
 |---------|-------------|
 | `uwf thread start <workflow> -p <prompt>` | Create a thread without executing |
-| `uwf thread step <thread-id> [--agent <cmd>] [-c <count>]` | Execute one or more moderator→agent→extract cycles |
+| `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 [--all]` | List active threads (`--all` includes archived) |
-| `uwf thread steps <thread-id>` | List all steps chronologically |
+| `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 |
-| `uwf thread fork <step-hash>` | Fork from a specific step |
-| `uwf thread step-details <step-hash>` | Dump full detail node as YAML |
-| `uwf thread kill <thread-id>` | Terminate and archive |
+
+`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 step 01ARZ3NDEKTSV4RRFFQ69G5FAV
-uwf thread step 01ARZ3NDEKTSV4RRFFQ69G5FAV -c 3 --agent uwf-builtin
+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
 ```
 
-### Workflow
+### Step (Layer 3: Single Cycle Results)
 
 | Command | Description |
 |---------|-------------|
-| `uwf workflow put <file.yaml>` | Register a workflow from YAML |
+| `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 |
 
@@ -99,6 +135,52 @@ Config: `~/.uncaged/workflow/config.yaml`. API keys: `~/.uncaged/workflow/.env`.
 | `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
 
 ```
@@ -109,8 +191,9 @@ src/
 ├── validate.ts         Workflow YAML validation
 ├── schemas.ts          CLI-local schema registration
 └── commands/
-    ├── thread.ts       Thread lifecycle and step execution
-    ├── workflow.ts     Workflow registry (put/show/list)
+    ├── 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

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__/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__/solve-issue-tea-worktree.test.ts

@@ -0,0 +1,97 @@
+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.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 $status field", async () => {
+    const yamlContent = await readFile(workflowPath, "utf-8");
+    // Parse as any to access the raw YAML structure (frontmatter is inline JSON Schema in YAML)
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    const workflow = parse(yamlContent) as any;
+
+    const frontmatter = workflow.roles.committer?.frontmatter;
+    expect(frontmatter).toBeDefined();
+    expect(frontmatter?.type).toBe("object");
+    expect(frontmatter?.properties?.["$status"]).toBeDefined();
+    expect(frontmatter?.properties?.["$status"]?.enum).toContain("committed");
+    expect(frontmatter?.required).toContain("$status");
+  });
+});

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-step-count.test.ts

@@ -22,48 +22,48 @@ function runCli(args: string[]): { stdout: string; stderr: string; exitCode: num
   }
 }
 
-describe("thread step --count CLI parsing", () => {
+describe("thread exec --count CLI parsing", () => {
   test("--help shows -c/--count option", () => {
-    const result = runCli(["thread", "step", "--help"]);
+    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", "step", "--help"]);
+    const result = runCli(["thread", "exec", "--help"]);
     expect(result.stdout).toContain("one or more steps");
   });
 });
 
-describe("cmdThreadStep count logic", () => {
+describe("cmdThreadExec count logic", () => {
   test("count=0 fails with validation error", () => {
-    const result = runCli(["thread", "step", "FAKE_THREAD_ID", "-c", "0"]);
+    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", "step", "FAKE_THREAD_ID", "-c", "-1"]);
+    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", "step", "FAKE_THREAD_ID", "-c", "1.5"]);
+    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", "step", "FAKE_THREAD_ID"]);
+    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", "step", "FAKE_THREAD_ID", "-c", "3"]);
+    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__/thread.test.ts

@@ -5,15 +5,15 @@ 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 { cmdStepList, cmdStepShow } from "../commands/step.js";
 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";
+import { appendThreadHistory, saveThreadsIndex } from "../store.js";
 
 // ── schemas used in tests ────────────────────────────────────────────────────
 
@@ -315,9 +315,9 @@ describe("cmdThreadRead <output> section", () => {
   });
 });
 
-// ── cmdThreadStepDetails ──────────────────────────────────────────────────────
+// ── cmdStepShow ───────────────────────────────────────────────────────────────
 
-describe("cmdThreadStepDetails", () => {
+describe("cmdStepShow", () => {
   test("returns expanded detail node with turns inlined", async () => {
     const uwf = await makeUwfStore(tmpDir);
     const detailSchemas = await registerDetailSchemas(uwf.store);
@@ -365,7 +365,7 @@ describe("cmdThreadStepDetails", () => {
       agent: "uwf-hermes",
     });
 
-    const result = await cmdThreadStepDetails(tmpDir, stepHash);
+    const result = await cmdStepShow(tmpDir, stepHash);
 
     expect(result).toMatchObject({
       sessionId: "sess42",
@@ -586,9 +586,9 @@ describe("cmdThreadRead start section / before / quota", () => {
 
 // ── Tests that call process.exit must be last ─────────────────────────────────
 
-describe("cmdThreadStepDetails (process.exit tests - must be last)", () => {
+describe("cmdStepShow (process.exit tests - must be last)", () => {
   test("throws when step hash does not exist", async () => {
-    await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
+    await expect(cmdStepShow(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
   });
 
   test("before with unknown hash rejects", async () => {
@@ -647,3 +647,383 @@ describe("cmdThreadStepDetails (process.exit tests - must be last)", () => {
     ).rejects.toThrow();
   });
 });
+
+// ── cmdStepList / cmdStepShow: completed threads ──────────────────────────────
+
+describe("cmdStepList with completed threads", () => {
+  test("lists steps from active thread", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf-active",
+      description: "desc",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Start prompt",
+    });
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const step1Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "role1",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+    const step2Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step1Hash,
+      role: "role2",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+    const step3Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step2Hash,
+      role: "role3",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000000A1" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: step3Hash });
+
+    const result = await cmdStepList(tmpDir, threadId);
+
+    expect(result.thread).toBe(threadId);
+    expect(result.steps).toHaveLength(4); // start + 3 steps
+    expect(result.steps[1].role).toBe("role1");
+    expect(result.steps[2].role).toBe("role2");
+    expect(result.steps[3].role).toBe("role3");
+  });
+
+  test("lists steps from completed thread", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf-completed",
+      description: "desc",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Start prompt",
+    });
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const step1Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "roleA",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+    const step2Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step1Hash,
+      role: "roleB",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000000A2" as ThreadId;
+    // Thread is NOT in threads.yaml (simulating completed thread)
+    await saveThreadsIndex(tmpDir, {});
+    // But it IS in history.jsonl
+    await appendThreadHistory(tmpDir, {
+      thread: threadId,
+      workflow: workflowHash,
+      head: step2Hash,
+      completedAt: Date.now(),
+    });
+
+    const result = await cmdStepList(tmpDir, threadId);
+
+    expect(result.thread).toBe(threadId);
+    expect(result.steps).toHaveLength(3); // start + 2 steps
+    expect(result.steps[1].role).toBe("roleA");
+    expect(result.steps[2].role).toBe("roleB");
+  });
+});
+
+describe("cmdStepShow with completed threads", () => {
+  test("shows step detail from active thread", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const detailSchemas = await registerDetailSchemas(uwf.store);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf-step-active",
+      description: "desc",
+      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: "Active thread response",
+      toolCalls: null,
+      reasoning: null,
+    });
+    const detailHash = await uwf.store.put(detailSchemas.detail, {
+      sessionId: "sess-active",
+      model: "model-x",
+      duration: 1234,
+      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 threadId = "01JTEST0000000000000000B1" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
+
+    const result = await cmdStepShow(tmpDir, stepHash);
+
+    expect(result).toMatchObject({
+      sessionId: "sess-active",
+      model: "model-x",
+      duration: 1234,
+      turnCount: 1,
+    });
+  });
+
+  test("shows step detail from completed thread", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const detailSchemas = await registerDetailSchemas(uwf.store);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf-step-completed",
+      description: "desc",
+      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: "Completed thread response",
+      toolCalls: null,
+      reasoning: null,
+    });
+    const detailHash = await uwf.store.put(detailSchemas.detail, {
+      sessionId: "sess-completed",
+      model: "model-y",
+      duration: 5678,
+      turnCount: 1,
+      turns: [turnHash],
+    });
+
+    const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "reviewer",
+      output: outputHash,
+      detail: detailHash,
+      agent: "uwf-hermes",
+    });
+
+    const threadId = "01JTEST0000000000000000B2" as ThreadId;
+    // Thread is NOT in threads.yaml
+    await saveThreadsIndex(tmpDir, {});
+    // But it IS in history.jsonl
+    await appendThreadHistory(tmpDir, {
+      thread: threadId,
+      workflow: workflowHash,
+      head: stepHash,
+      completedAt: Date.now(),
+    });
+
+    const result = await cmdStepShow(tmpDir, stepHash);
+
+    expect(result).toMatchObject({
+      sessionId: "sess-completed",
+      model: "model-y",
+      duration: 5678,
+      turnCount: 1,
+    });
+  });
+});
+
+describe("cmdThreadRead with completed threads", () => {
+  test("reads completed thread context", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf-read-completed",
+      description: "desc",
+      roles: {
+        writer: {
+          description: "Write",
+          goal: "You are a writer.",
+          capabilities: [],
+          procedure: "Write content.",
+          output: "Summary.",
+          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 stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "writer",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-hermes",
+    });
+
+    const threadId = "01JTEST0000000000000000C1" as ThreadId;
+    // Thread is NOT in threads.yaml
+    await saveThreadsIndex(tmpDir, {});
+    // But it IS in history.jsonl
+    await appendThreadHistory(tmpDir, {
+      thread: threadId,
+      workflow: workflowHash,
+      head: stepHash,
+      completedAt: Date.now(),
+    });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+
+    expect(markdown).toContain("writer");
+    expect(markdown).toContain("Write something");
+  });
+
+  test("reads completed thread with before filter", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "test-wf-read-before",
+      description: "desc",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Do task",
+    });
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const step1Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "roleX",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+    const step2Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step1Hash,
+      role: "roleY",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+    const step3Hash = await uwf.store.put(uwf.schemas.stepNode, {
+      start: startHash,
+      prev: step2Hash,
+      role: "roleZ",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+
+    const threadId = "01JTEST0000000000000000C2" as ThreadId;
+    await saveThreadsIndex(tmpDir, {});
+    await appendThreadHistory(tmpDir, {
+      thread: threadId,
+      workflow: workflowHash,
+      head: step3Hash,
+      completedAt: Date.now(),
+    });
+
+    const markdown = await cmdThreadRead(
+      tmpDir,
+      threadId,
+      THREAD_READ_DEFAULT_QUOTA,
+      step2Hash,
+      false,
+    );
+
+    // Should contain step1 (roleX) but not step2 (roleY) or step3 (roleZ)
+    expect(markdown).toContain("roleX");
+    expect(markdown).not.toContain("roleY");
+    expect(markdown).not.toContain("roleZ");
+  });
+});

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

@@ -25,7 +25,6 @@ async function storeWorkflow(uwf: UwfStore, name: string): Promise<CasRef> {
     name,
     description: "Test workflow",
     roles: {},
-    conditions: {},
     graph: {},
   };
   return await uwf.store.put(uwf.schemas.workflow, payload);
@@ -36,7 +35,6 @@ async function createWorkflowYaml(name: string, version: string | null = null):
     name,
     description: version !== null ? `Test workflow (${version})` : "Test workflow",
     roles: {},
-    conditions: {},
     graph: {},
   };
   const yaml = stringify(payload);
@@ -145,7 +143,7 @@ describe("Strategy 2: File Path Resolution", () => {
   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 writeFile(yamlPath, "name: test\n# missing roles and graph");
 
     await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
   });

packages/cli-workflow/src/cli.ts

@@ -1,8 +1,7 @@
 #!/usr/bin/env bun
 
-import type { ThreadId } from "@uncaged/workflow-protocol";
+import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
 import { Command } from "commander";
-import { stringify as yamlStringify } from "yaml";
 import {
   cmdCasGet,
   cmdCasHas,
@@ -17,20 +16,20 @@ import {
 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 {
-  cmdThreadFork,
-  cmdThreadKill,
+  cmdThreadCancel,
+  cmdThreadExec,
   cmdThreadList,
   cmdThreadRead,
-  cmdThreadRunning,
   cmdThreadShow,
   cmdThreadStart,
-  cmdThreadStep,
-  cmdThreadStepDetails,
-  cmdThreadSteps,
+  cmdThreadStop,
   THREAD_READ_DEFAULT_QUOTA,
+  type ThreadStatus,
 } from "./commands/thread.js";
-import { cmdWorkflowList, cmdWorkflowPut, cmdWorkflowShow } from "./commands/workflow.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";
 
@@ -53,20 +52,27 @@ const program = new Command();
 const pkg = await import("../package.json", { with: { type: "json" } });
 program
   .name("uwf")
-  .description("Stateless workflow CLI")
+  .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 registry and CAS");
+const workflow = program
+  .command("workflow")
+  .description("Workflow definitions (layer 1: templates)");
 
 workflow
-  .command("put")
+  .command("add")
   .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);
+      const result = await cmdWorkflowAdd(storageRoot, file);
       writeOutput(result);
     });
   });
@@ -94,7 +100,7 @@ workflow
     });
   });
 
-const thread = program.command("thread").description("Thread lifecycle and execution");
+const thread = program.command("thread").description("Thread execution (layer 2: instances)");
 
 thread
   .command("start")
@@ -110,7 +116,7 @@ thread
   });
 
 thread
-  .command("step")
+  .command("exec")
   .description("Execute one or more steps")
   .argument("<thread-id>", "Thread ULID")
   .option("--agent <cmd>", "Override agent command")
@@ -134,7 +140,7 @@ thread
         const background = opts.background ?? false;
         const backgroundWorker = opts._backgroundWorker ?? false;
 
-        const results = await cmdThreadStep(
+        const results = await cmdThreadExec(
           storageRoot,
           threadId,
           agentOverride,
@@ -163,49 +169,124 @@ thread
     });
   });
 
+// 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 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);
-    });
-  });
+  .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("running")
-  .description("List threads currently executing in the background")
-  .action(() => {
-    const storageRoot = resolveStorageRoot();
-    runAction(async () => {
-      const result = await cmdThreadRunning(storageRoot);
-      writeOutput(result);
-    });
-  });
-
-thread
-  .command("kill")
-  .description("Terminate and archive a 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 cmdThreadKill(storageRoot, threadId);
+      const result = await cmdThreadStop(storageRoot, threadId);
       writeOutput(result);
     });
   });
 
 thread
-  .command("steps")
-  .description("List all steps in a 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 cmdThreadSteps(storageRoot, threadId);
+      const result = await cmdThreadCancel(storageRoot, threadId);
       writeOutput(result);
     });
   });
@@ -239,28 +320,157 @@ thread
     },
   );
 
-thread
+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 cmdThreadFork(storageRoot, stepHash);
+      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("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));
-    });
+  .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");
@@ -355,7 +565,11 @@ cas
   .action((hash: string) => {
     const storageRoot = resolveStorageRoot();
     runAction(async () => {
-      writeOutput(await cmdCasHas(storageRoot, hash));
+      const result = await cmdCasHas(storageRoot, hash);
+      writeOutput(result);
+      if (!result.exists) {
+        process.exit(1);
+      }
     });
   });
 

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/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/thread.ts

@@ -1,39 +1,32 @@
 import { execFileSync, spawn } from "node:child_process";
 import { access, readFile } from "node:fs/promises";
 import { dirname, isAbsolute, resolve as resolvePath } from "node:path";
-import type { Store as CasStore, JSONSchema } from "@uncaged/json-cas";
-import { getSchema, validate } from "@uncaged/json-cas";
+import { validate } from "@uncaged/json-cas";
 import { getEnvPath, loadWorkflowConfig } from "@uncaged/workflow-agent-kit";
 import { evaluate } from "@uncaged/workflow-moderator";
 import type {
   AgentAlias,
   AgentConfig,
   CasRef,
-  ModeratorContext,
-  RunningThreadsOutput,
-  StartEntry,
   StartNodePayload,
   StartOutput,
-  StepContext,
-  StepEntry,
   StepNodePayload,
   StepOutput,
-  ThreadForkOutput,
   ThreadId,
   ThreadListItem,
-  ThreadStepsOutput,
+  ThreadsIndex,
   WorkflowConfig,
   WorkflowPayload,
 } from "@uncaged/workflow-protocol";
-import { createProcessLogger, generateUlid, type ProcessLogger } from "@uncaged/workflow-util";
-import { config as loadDotenv } from "dotenv";
-import { parse, stringify } from "yaml";
 import {
-  createMarker,
-  deleteMarker,
-  isThreadRunning,
-  listRunningThreads,
-} from "../background/index.js";
+  createProcessLogger,
+  extractUlidTimestamp,
+  generateUlid,
+  type ProcessLogger,
+} from "@uncaged/workflow-util";
+import { config as loadDotenv } from "dotenv";
+import { parse } from "yaml";
+import { createMarker, deleteMarker, isThreadRunning } from "../background/index.js";
 import {
   appendThreadHistory,
   createUwfStore,
@@ -47,9 +40,18 @@ import {
   type UwfStore,
 } from "../store.js";
 import { checkWorkflowFilenameConsistency, isCasRef, parseWorkflowPayload } from "../validate.js";
+import {
+  type ChainState,
+  collectOrderedSteps,
+  expandOutput,
+  fail,
+  type OrderedStepItem,
+  walkChain,
+} from "./shared.js";
 import { materializeWorkflowPayload } from "./workflow.js";
 
 const END_ROLE = "$END";
+const START_ROLE = "$START";
 export const THREAD_READ_DEFAULT_QUOTA = 4000;
 
 const PL_THREAD_START = "7HNQ4B2X";
@@ -65,29 +67,6 @@ function failStep(plog: ProcessLogger, message: string): never {
   fail(message);
 }
 
-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);
-}
-
 /**
  * Check if a string looks like a file path (contains path separators or has .yaml/.yml extension).
  */
@@ -346,243 +325,139 @@ export async function cmdThreadShow(storageRoot: string, threadId: ThreadId): Pr
   fail(`thread not found: ${threadId}`);
 }
 
+export type ThreadStatus = "idle" | "running" | "completed";
+
+export type ThreadListItemWithStatus = ThreadListItem & {
+  status: ThreadStatus;
+};
+
 async function threadListItemFromActive(
+  storageRoot: string,
   uwf: UwfStore,
   threadId: ThreadId,
   head: CasRef,
-): Promise<ThreadListItem | null> {
+): Promise<ThreadListItemWithStatus | null> {
   const workflow = resolveWorkflowFromHead(uwf, head);
   if (workflow === null) {
     return null;
   }
-  return { thread: threadId, workflow, head };
+
+  // Check if thread is currently running in background
+  const runningMarker = await isThreadRunning(storageRoot, threadId);
+  const status: ThreadStatus = runningMarker !== null ? "running" : "idle";
+
+  return { thread: threadId, workflow, head, status };
 }
 
-export async function cmdThreadList(
+async function collectActiveThreads(
   storageRoot: string,
-  includeAll: boolean,
-): Promise<ThreadListItem[]> {
-  const uwf = await createUwfStore(storageRoot);
-  const index = await loadThreadsIndex(storageRoot);
-  const items: ThreadListItem[] = [];
-
+  uwf: UwfStore,
+  index: ThreadsIndex,
+): Promise<ThreadListItemWithStatus[]> {
+  const items: ThreadListItemWithStatus[] = [];
   for (const [threadId, head] of Object.entries(index)) {
-    const item = await threadListItemFromActive(uwf, threadId as ThreadId, head);
+    const item = await threadListItemFromActive(
+      storageRoot,
+      uwf,
+      threadId as ThreadId,
+      head as CasRef,
+    );
     if (item !== null) {
       items.push(item);
     }
   }
+  return items;
+}
 
-  if (!includeAll) {
-    return items;
-  }
-
-  const activeIds = new Set(items.map((i) => i.thread));
+async function collectCompletedThreads(
+  storageRoot: string,
+  activeIds: Set<ThreadId>,
+): Promise<ThreadListItemWithStatus[]> {
+  const items: ThreadListItemWithStatus[] = [];
   const history = await loadThreadHistory(storageRoot);
+  const seen = new Set<ThreadId>(); // Deduplication (issue #470)
   for (const entry of history) {
-    if (!activeIds.has(entry.thread)) {
+    if (!activeIds.has(entry.thread) && !seen.has(entry.thread)) {
+      seen.add(entry.thread);
       items.push({
         thread: entry.thread,
         workflow: entry.workflow,
         head: entry.head,
+        status: "completed",
       });
     }
   }
-
   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 applyTimeFilters(
+  items: ThreadListItemWithStatus[],
+  afterMs: number | null,
+  beforeMs: number | null,
+): ThreadListItemWithStatus[] {
+  if (afterMs === null && beforeMs === null) return items;
+  return items.filter((item) => {
+    const ts = extractUlidTimestamp(item.thread);
+    if (ts === null) return false;
+    if (afterMs !== null && ts <= afterMs) return false;
+    if (beforeMs !== null && ts >= beforeMs) return false;
+    return true;
+  });
 }
 
-function expandOutput(uwf: UwfStore, outputRef: CasRef): unknown {
-  const node = uwf.store.get(outputRef);
-  if (node === null) {
-    return {};
-  }
-  return node.payload;
+function sortByNewestFirst(items: ThreadListItemWithStatus[]): ThreadListItemWithStatus[] {
+  return items.sort((a, b) => {
+    const tsA = extractUlidTimestamp(a.thread) ?? 0;
+    const tsB = extractUlidTimestamp(b.thread) ?? 0;
+    return tsB - tsA;
+  });
 }
 
-/**
- * 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 applyPagination(
+  items: ThreadListItemWithStatus[],
+  skip: number | null,
+  take: number | null,
+): ThreadListItemWithStatus[] {
+  const skipCount = skip ?? 0;
+  const takeCount = take ?? items.length;
+  return items.slice(skipCount, skipCount + takeCount);
 }
 
-function expandCasRefField(store: CasStore, value: unknown, visited: Set<string>): unknown {
-  if (typeof value === "string") {
-    return expandDeep(store, value as CasRef, visited);
-  }
-  return value;
-}
+export async function cmdThreadList(
+  storageRoot: string,
+  statusFilter: ThreadStatus[] | null,
+  afterMs: number | null,
+  beforeMs: number | null,
+  skip: number | null,
+  take: number | null,
+): Promise<ThreadListItemWithStatus[]> {
+  const uwf = await createUwfStore(storageRoot);
+  const index = await loadThreadsIndex(storageRoot);
 
-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;
-}
+  // Collect active threads
+  let items = await collectActiveThreads(storageRoot, uwf, index);
 
-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;
+  // Collect completed threads (if relevant for status filter)
+  const includeCompleted = statusFilter === null || statusFilter.includes("completed");
+  if (includeCompleted) {
+    const activeIds = new Set(items.map((i) => i.thread));
+    const completedItems = await collectCompletedThreads(storageRoot, activeIds);
+    items = items.concat(completedItems);
   }
 
-  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;
+  // Apply status filter
+  if (statusFilter !== null) {
+    items = items.filter((item) => statusFilter.includes(item.status));
   }
-  ordered.reverse();
-  return ordered;
-}
 
-function formatYaml(value: unknown): string {
-  return stringify(value, { aliasDuplicateObjects: false }).trimEnd();
-}
+  // Apply time range filters
+  items = applyTimeFilters(items, afterMs, beforeMs);
 
-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");
+  // Sort by timestamp descending (newest first)
+  items = sortByNewestFirst(items);
+
+  // Apply pagination
+  return applyPagination(items, skip, take);
 }
 
 export function extractLastAssistantContent(uwf: UwfStore, detailRef: CasRef): string | null {
@@ -628,22 +503,60 @@ function sliceBeforeHash(
   return candidates.slice(0, idx);
 }
 
+function calculateFormattedStepLength(
+  stepNum: number,
+  item: OrderedStepItem,
+  uwf: UwfStore,
+  workflow: WorkflowPayload,
+): number {
+  // Calculate using the same format as formatStepHeader, formatStepPrompt, formatStepContent
+  // Use a temporary set to avoid mutating the actual shownPromptRoles during calculation
+  const tempShownRoles = new Set<string>();
+  const header = formatStepHeader(stepNum, item);
+  const roleDef = workflow.roles[item.payload.role];
+  const prompt = formatStepPrompt(roleDef, item.payload.role, tempShownRoles);
+  const content = formatStepContent(uwf, item);
+
+  const stepBlock = [header, prompt, content].filter((s) => s !== "").join("");
+
+  // Don't add separator here - it will be counted when we know the final structure
+  return stepBlock.length;
+}
+
 function selectByQuota(
   candidates: OrderedStepItem[],
   uwf: UwfStore,
+  workflow: WorkflowPayload,
   quota: number,
+  startSectionLength: number,
 ): { selected: OrderedStepItem[]; skippedCount: number } {
   const selected: OrderedStepItem[] = [];
-  let totalChars = 0;
+
+  // Start with start section length
+  let totalChars = startSectionLength;
+
   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;
+
+    // Calculate the actual formatted length using the same format as final output
+    const blockLen = calculateFormattedStepLength(i + 1, item, uwf, workflow);
+
+    // Calculate cost of adding this step:
+    // - blockLen: the step content
+    // - 6: separator before this step (if there are already parts)
+    const separatorCost = totalChars > 0 || selected.length > 0 ? 6 : 0;
+    const addCost = blockLen + separatorCost;
+
+    // Check quota BEFORE adding - but always include at least one step
+    if (totalChars + addCost > quota && selected.length > 0) {
+      break;
+    }
+
     selected.unshift(item);
-    totalChars += blockLen;
-    if (totalChars > quota) break;
+    totalChars += addCost;
   }
+
   return { selected, skippedCount: candidates.length - selected.length };
 }
 
@@ -710,11 +623,21 @@ function formatThreadReadMarkdown(options: {
   const { ordered, uwf, workflow, quota, before } = options;
 
   const candidates = before !== null ? sliceBeforeHash(ordered, before, options.threadId) : ordered;
-  const { selected, skippedCount } = selectByQuota(candidates, uwf, quota);
+
+  // Calculate start section length for quota accounting
+  const startSection = formatStartSection(options);
+  const startSectionLength = startSection !== "" ? startSection.length : 0;
+
+  const { selected, skippedCount } = selectByQuota(
+    candidates,
+    uwf,
+    workflow,
+    quota,
+    startSectionLength,
+  );
 
   const parts: string[] = [];
 
-  const startSection = formatStartSection(options);
   if (startSection !== "") parts.push(startSection);
 
   if (skippedCount > 0 && selected.length > 0) {
@@ -746,16 +669,33 @@ function formatThreadReadMarkdown(options: {
   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,
-    edgePrompt: step.edgePrompt ?? "",
-  }));
-  return { start: chain.start, steps };
+type EvaluateLastOutput = Record<string, unknown>;
+
+const STATUS_KEY = "$status";
+
+function resolveEvaluateArgs(
+  uwf: UwfStore,
+  chain: ChainState,
+): { lastRole: string; lastOutput: EvaluateLastOutput } {
+  if (chain.headIsStart) {
+    return { lastRole: START_ROLE, lastOutput: { [STATUS_KEY]: "_" } };
+  }
+
+  const lastStep = chain.stepsNewestFirst[0];
+  if (lastStep === undefined) {
+    fail("empty step chain");
+  }
+
+  const raw = expandOutput(uwf, lastStep.output);
+  const base =
+    typeof raw === "object" && raw !== null && !Array.isArray(raw)
+      ? (raw as Record<string, unknown>)
+      : {};
+
+  return {
+    lastRole: lastStep.role,
+    lastOutput: base,
+  };
 }
 
 function loadWorkflowPayload(uwf: UwfStore, workflowRef: CasRef): WorkflowPayload {
@@ -857,7 +797,7 @@ async function archiveThread(
   });
 }
 
-export async function cmdThreadStep(
+export async function cmdThreadExec(
   storageRoot: string,
   threadId: ThreadId,
   agentOverride: string | null,
@@ -953,7 +893,7 @@ async function cmdThreadStepBackground(
     failStep(plog, "unable to determine script path for background execution");
   }
 
-  const args = ["thread", "step", threadId, "--count", String(count)];
+  const args = ["thread", "exec", threadId, "--count", String(count)];
 
   if (agentOverride !== null) {
     args.push("--agent", agentOverride);
@@ -999,9 +939,9 @@ async function cmdThreadStepOnce(
   const chain = walkChain(uwf, headHash);
   const workflowHash = chain.start.workflow;
   const workflow = loadWorkflowPayload(uwf, workflowHash);
-  const context = buildModeratorContext(uwf, chain);
+  const { lastRole, lastOutput } = resolveEvaluateArgs(uwf, chain);
 
-  const nextResult = await evaluate(workflow, context);
+  const nextResult = evaluate(workflow.graph, lastRole, lastOutput);
   if (!nextResult.ok) {
     failStep(plog, `moderator evaluate failed: ${nextResult.error.message}`);
   }
@@ -1051,8 +991,11 @@ async function cmdThreadStepOnce(
   await saveThreadsIndex(storageRoot, freshIndex);
 
   const chainAfter = walkChain(uwfAfter, newHead);
-  const contextAfter = buildModeratorContext(uwfAfter, chainAfter);
-  const afterResult = await evaluate(workflow, contextAfter);
+  const { lastRole: lastRoleAfter, lastOutput: lastOutputAfter } = resolveEvaluateArgs(
+    uwfAfter,
+    chainAfter,
+  );
+  const afterResult = evaluate(workflow.graph, lastRoleAfter, lastOutputAfter);
   if (!afterResult.ok) {
     failStep(plog, `post-step moderator evaluate failed: ${afterResult.error.message}`);
   }
@@ -1085,47 +1028,6 @@ async function resolveHeadHash(storageRoot: string, threadId: ThreadId): Promise
   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,
@@ -1153,52 +1055,50 @@ export async function cmdThreadRead(
   });
 }
 
-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`);
-  }
+export type StopOutput = {
+  thread: ThreadId;
+  stopped: boolean;
+};
 
-  const newThreadId = generateUlid(Date.now()) as ThreadId;
+export type CancelOutput = {
+  thread: ThreadId;
+  cancelled: boolean;
+};
+
+/**
+ * Stop background execution of a thread (but keep thread active)
+ */
+export async function cmdThreadStop(storageRoot: string, threadId: ThreadId): Promise<StopOutput> {
   const index = await loadThreadsIndex(storageRoot);
-  index[newThreadId] = stepHash;
-  await saveThreadsIndex(storageRoot, index);
+  const head = index[threadId];
+  if (head === undefined) {
+    fail(`thread not active: ${threadId}`);
+  }
 
-  return {
-    thread: newThreadId,
-    forkedFrom: {
-      step: stepHash,
-    },
-  };
+  // Check if thread is running in background and terminate it
+  const runningMarker = await isThreadRunning(storageRoot, threadId);
+  if (runningMarker === null) {
+    process.stderr.write(`Warning: thread ${threadId} is not currently running\n`);
+    return { thread: threadId, stopped: false };
+  }
+
+  try {
+    process.kill(runningMarker.pid, "SIGTERM");
+  } catch {
+    // Process may have already exited, ignore error
+  }
+  await deleteMarker(storageRoot, threadId);
+
+  return { thread: threadId, stopped: true };
 }
 
-export async function cmdThreadStepDetails(
+/**
+ * Cancel a thread (stop execution + move to history)
+ */
+export async function cmdThreadCancel(
   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> {
+  threadId: ThreadId,
+): Promise<CancelOutput> {
   const index = await loadThreadsIndex(storageRoot);
   const head = index[threadId];
   if (head === undefined) {
@@ -1233,10 +1133,5 @@ export async function cmdThreadKill(storageRoot: string, threadId: ThreadId): Pr
   };
   await appendThreadHistory(storageRoot, historyEntry);
 
-  return { thread: threadId, archived: true };
-}
-
-export async function cmdThreadRunning(storageRoot: string): Promise<RunningThreadsOutput> {
-  const threads = await listRunningThreads(storageRoot);
-  return { threads };
+  return { thread: threadId, cancelled: true };
 }

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

@@ -2,12 +2,7 @@ import { readFile } from "node:fs/promises";
 
 import type { JSONSchema } from "@uncaged/json-cas";
 import { putSchema, validate } from "@uncaged/json-cas";
-import type {
-  CasRef,
-  RoleDefinition,
-  Transition,
-  WorkflowPayload,
-} from "@uncaged/workflow-protocol";
+import type { CasRef, RoleDefinition, Target, WorkflowPayload } from "@uncaged/workflow-protocol";
 import { parse } from "yaml";
 
 import {
@@ -29,7 +24,7 @@ export type WorkflowListEntry = {
   origin: WorkflowOrigin;
 };
 
-export type WorkflowPutOutput = {
+export type WorkflowAddOutput = {
   name: string;
   hash: CasRef;
 };
@@ -51,20 +46,23 @@ function isJsonSchema(value: unknown): value is JSONSchema {
   return typeof value === "object" && value !== null && !Array.isArray(value);
 }
 
-/** 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)`);
+/** Normalize graph: validate each status → target mapping. */
+function normalizeGraph(
+  graph: Record<string, Record<string, Target>>,
+): Record<string, Record<string, Target>> {
+  const result: Record<string, Record<string, Target>> = {};
+  for (const [node, statusMap] of Object.entries(graph)) {
+    const normalized: Record<string, Target> = {};
+    for (const [status, target] of Object.entries(statusMap)) {
+      if (typeof target.prompt !== "string" || target.prompt.trim() === "") {
+        fail(`graph[${node}][${status}] → "${target.role}": prompt is required (non-empty string)`);
       }
-      return {
-        role: t.role,
-        condition: t.condition ?? null,
-        prompt: t.prompt,
+      normalized[status] = {
+        role: target.role,
+        prompt: target.prompt,
       };
-    });
+    }
+    result[node] = normalized;
   }
   return result;
 }
@@ -106,15 +104,14 @@ export async function materializeWorkflowPayload(
     name: raw.name,
     description: raw.description,
     roles,
-    conditions: raw.conditions,
     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");

packages/cli-workflow/src/validate.ts

@@ -30,23 +30,12 @@ function isRoleDefinition(value: unknown): boolean {
   );
 }
 
-function isConditionDefinition(value: unknown): boolean {
+function isTarget(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")
+    typeof value.role === "string" && typeof value.prompt === "string" && value.prompt.trim() !== ""
   );
 }
 
@@ -62,7 +51,7 @@ function isGraph(value: unknown): boolean {
     return false;
   }
   return Object.values(value).every(
-    (transitions) => Array.isArray(transitions) && transitions.every((t) => isTransition(t)),
+    (statusMap) => isRecord(statusMap) && Object.values(statusMap).every((t) => isTarget(t)),
   );
 }
 
@@ -101,11 +90,7 @@ export function parseWorkflowPayload(raw: unknown): WorkflowPayload | null {
   if (typeof raw.name !== "string" || typeof raw.description !== "string") {
     return null;
   }
-  if (
-    !isStringRecord(raw.roles, isRoleDefinition) ||
-    !isStringRecord(raw.conditions, isConditionDefinition) ||
-    !isGraph(raw.graph)
-  ) {
+  if (!isStringRecord(raw.roles, isRoleDefinition) || !isGraph(raw.graph)) {
     return null;
   }
   return raw as WorkflowPayload;

packages/workflow-agent-claude-code/__tests__/claude-code.test.ts

@@ -39,7 +39,7 @@ describe("buildClaudeCodePrompt", () => {
     expect(result).toContain("## Task\nFix the bug");
   });
 
-  test("includes previous steps as history summary", () => {
+  test("includes previous steps with content on first visit", () => {
     const ctx = makeCtx({
       steps: [
         {
@@ -48,18 +48,50 @@ describe("buildClaudeCodePrompt", () => {
           agent: "hermes",
           detail: "detail-1",
           edgePrompt: "Create a plan.",
+          content: "Here is my detailed plan for doing X.",
         },
       ],
     });
     const result = buildClaudeCodePrompt(ctx);
-    expect(result).toContain("## Previous Steps");
+    expect(result).toContain("## What Happened Since Your Last Turn");
     expect(result).toContain("Step 1: planner");
     expect(result).toContain("do X");
+    // First visit should include step content
+    expect(result).toContain("Here is my detailed plan for doing X.");
+  });
+
+  test("re-entry shows steps since last visit without content", () => {
+    const ctx = makeCtx({
+      isFirstVisit: false,
+      steps: [
+        {
+          role: "developer",
+          output: '{"status":"done"}',
+          agent: "claude-code",
+          detail: "detail-1",
+          edgePrompt: "Implement.",
+          content: "I implemented everything.",
+        },
+        {
+          role: "reviewer",
+          output: '{"approved":false}',
+          agent: "claude-code",
+          detail: "detail-2",
+          edgePrompt: "Review.",
+          content: "Rejected: complexity too high, refactor cmdStepRead.",
+        },
+      ],
+    });
+    const result = buildClaudeCodePrompt(ctx);
+    expect(result).toContain("## What Happened Since Your Last Turn");
+    expect(result).toContain("reviewer");
+    expect(result).toContain("approved");
   });
 
   test("omits history section when steps array is empty", () => {
     const result = buildClaudeCodePrompt(makeCtx({ steps: [] }));
-    expect(result).not.toContain("## Previous Steps");
+    expect(result).not.toContain("## What Happened Since Your Last Turn");
+    expect(result).toContain("## Current Instruction");
   });
 
   test("works without outputFormatInstruction", () => {

packages/workflow-agent-claude-code/package.json

@@ -22,7 +22,8 @@
   },
   "dependencies": {
     "@uncaged/json-cas": "^0.4.0",
-    "@uncaged/workflow-agent-kit": "workspace:^"
+    "@uncaged/workflow-agent-kit": "workspace:^",
+    "@uncaged/workflow-util": "workspace:^"
   },
   "devDependencies": {
     "typescript": "^5.8.3"

packages/workflow-agent-claude-code/src/claude-code.ts

@@ -3,6 +3,7 @@ import type { Store } from "@uncaged/json-cas";
 import {
   type AgentContext,
   type AgentRunResult,
+  buildContinuationPrompt,
   buildRolePrompt,
   createAgent,
   getCachedSessionId,
@@ -18,25 +19,6 @@ const CLAUDE_COMMAND = "claude";
 const CLAUDE_MAX_TURNS = 90;
 const CLAUDE_MODEL = process.env.CLAUDE_MODEL ?? null;
 
-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 Claude Code. */
 export function buildClaudeCodePrompt(ctx: AgentContext): string {
   const roleDef = ctx.workflow.roles[ctx.role];
@@ -46,11 +28,23 @@ export function buildClaudeCodePrompt(ctx: AgentContext): string {
     parts.push(ctx.outputFormatInstruction, "");
   }
   parts.push(rolePrompt, "", "## Task", ctx.start.prompt);
-  const historyBlock = buildHistorySummary(ctx.steps);
-  if (historyBlock !== "") {
-    parts.push("", historyBlock);
+
+  if (!ctx.isFirstVisit) {
+    // Re-entry (session will be resumed): show only steps since last visit, meta only
+    parts.push("", buildContinuationPrompt(ctx.steps, ctx.role, ctx.edgePrompt));
+  } else if (ctx.steps.length > 0) {
+    // First visit: show all steps with content for recent ones
+    parts.push(
+      "",
+      buildContinuationPrompt(ctx.steps, ctx.role, ctx.edgePrompt, {
+        includeContent: true,
+        quota: 32000,
+      }),
+    );
+  } else {
+    parts.push("", "## Current Instruction", "", ctx.edgePrompt);
   }
-  parts.push("", "## Current Instruction", "", ctx.edgePrompt);
+
   return parts.join("\n");
 }
 
@@ -146,13 +140,13 @@ async function runClaudeCode(ctx: AgentContext): Promise<AgentRunResult> {
 
   // Try resuming a cached session for re-entry scenarios (e.g. reviewer reject → developer re-entry).
   if (!ctx.isFirstVisit) {
-    const cachedSessionId = await getCachedSessionId(ctx.threadId, ctx.role);
+    const cachedSessionId = await getCachedSessionId("claude-code", ctx.threadId, ctx.role);
     if (cachedSessionId !== null) {
       try {
         const { stdout } = await spawnClaudeResume(cachedSessionId, fullPrompt);
         const result = await processClaudeOutput(stdout, ctx.store);
         if (result.sessionId !== undefined && result.sessionId !== "") {
-          await setCachedSessionId(ctx.threadId, ctx.role, result.sessionId);
+          await setCachedSessionId("claude-code", ctx.threadId, ctx.role, result.sessionId);
         }
         return result;
       } catch (err) {
@@ -169,7 +163,7 @@ async function runClaudeCode(ctx: AgentContext): Promise<AgentRunResult> {
   const { stdout } = await spawnClaudeRun(fullPrompt);
   const result = await processClaudeOutput(stdout, ctx.store);
   if (result.sessionId !== undefined && result.sessionId !== "") {
-    await setCachedSessionId(ctx.threadId, ctx.role, result.sessionId);
+    await setCachedSessionId("claude-code", ctx.threadId, ctx.role, result.sessionId);
   }
   return result;
 }

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

@@ -23,7 +23,7 @@ function makeCtx(overrides: Partial<AgentContext> = {}): AgentContext {
       graph: {},
     },
     role: "developer",
-    start: { prompt: "Fix the bug", workflowHash: "abc123", threadId: "t1" },
+    start: { prompt: "Fix the bug", workflow: "abc123" },
     steps: [],
     store: {} as AgentContext["store"],
     outputFormatInstruction: "Use YAML frontmatter",
@@ -55,6 +55,7 @@ describe("buildHermesPrompt", () => {
           agent: "uwf-hermes",
           detail: "detail-1",
           edgePrompt: "Implement the fix.",
+          content: null,
         },
         {
           role: "reviewer",
@@ -62,6 +63,7 @@ describe("buildHermesPrompt", () => {
           agent: "uwf-hermes",
           detail: "detail-2",
           edgePrompt: "Review the code.",
+          content: null,
         },
       ],
     });
@@ -85,6 +87,7 @@ describe("buildHermesPrompt", () => {
             agent: "uwf-hermes",
             detail: "detail-1",
             edgePrompt: "First attempt.",
+            content: null,
           },
         ],
         edgePrompt: "Retry with a fresh approach.",
@@ -95,4 +98,90 @@ describe("buildHermesPrompt", () => {
     expect(result).toContain("Retry with a fresh approach.");
     expect(result).not.toContain("## What Happened Since Your Last Turn");
   });
+
+  test("first visit includes content from previous steps", () => {
+    const ctx = makeCtx({
+      isFirstVisit: true,
+      steps: [
+        {
+          role: "planner",
+          output: { plan: "hash1" },
+          agent: "uwf-hermes",
+          detail: "detail-1",
+          edgePrompt: "Create the plan.",
+          content: "# Plan\nDetailed plan markdown...",
+        },
+        {
+          role: "developer",
+          output: { files: ["app.ts"] },
+          agent: "uwf-hermes",
+          detail: "detail-2",
+          edgePrompt: "Implement the code.",
+          content: "# Implementation\nCode changes...",
+        },
+        {
+          role: "reviewer",
+          output: { approved: true },
+          agent: "uwf-hermes",
+          detail: "detail-3",
+          edgePrompt: "Review the work.",
+          content: "# Review\nApproved!",
+        },
+      ],
+      role: "committer",
+      edgePrompt: "Commit the reviewed code.",
+    });
+
+    const result = buildHermesPrompt(ctx);
+
+    expect(result).toContain("Use YAML frontmatter");
+    expect(result).toContain("## Task");
+    expect(result).toContain("Fix the bug");
+    expect(result).toContain("## What Happened Since Your Last Turn");
+    expect(result).toContain("### Step 1: planner");
+    expect(result).toContain("#### Step Content");
+    expect(result).toContain("# Plan");
+    expect(result).toContain("Detailed plan markdown");
+    expect(result).toContain("### Step 2: developer");
+    expect(result).toContain("# Implementation");
+    expect(result).toContain("### Step 3: reviewer");
+    expect(result).toContain("# Review");
+    expect(result).toContain("## Moderator Instruction");
+    expect(result).toContain("Commit the reviewed code.");
+  });
+
+  test("re-entry omits content from previous steps", () => {
+    const ctx = makeCtx({
+      isFirstVisit: false,
+      steps: [
+        {
+          role: "developer",
+          output: { files: ["app.ts"] },
+          agent: "uwf-hermes",
+          detail: "detail-1",
+          edgePrompt: "Implement the code.",
+          content: "# Implementation\nCode changes...",
+        },
+        {
+          role: "reviewer",
+          output: { approved: false },
+          agent: "uwf-hermes",
+          detail: "detail-2",
+          edgePrompt: "Review the work.",
+          content: "# Review\nNot approved!",
+        },
+      ],
+      role: "developer",
+      edgePrompt: "Fix the issues.",
+    });
+
+    const result = buildHermesPrompt(ctx);
+
+    expect(result).toContain("## What Happened Since Your Last Turn");
+    expect(result).toContain("### Step 2: reviewer");
+    expect(result).toContain(JSON.stringify({ approved: false }));
+    expect(result).not.toContain("#### Step Content");
+    expect(result).not.toContain("# Review");
+    expect(result).not.toContain("Not approved!");
+  });
 });

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

@@ -14,53 +14,39 @@ import { storeHermesSessionDetail } from "./session-detail.js";
 
 const log = createLogger({ sink: { kind: "stderr" } });
 
-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");
-}
-
-function buildInitialPrompt(ctx: AgentContext): string {
-  const roleDef = ctx.workflow.roles[ctx.role];
-  const rolePrompt = roleDef !== undefined ? buildRolePrompt(roleDef) : "";
+/** Assemble system prompt, task, and prior step outputs for Hermes. */
+export function buildHermesPrompt(ctx: AgentContext): string {
   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);
-  }
-  parts.push("", "## Moderator Instruction", "", ctx.edgePrompt);
-  return parts.join("\n");
-}
 
-/** Assemble system prompt, task, and prior step outputs for Hermes. */
-export function buildHermesPrompt(ctx: AgentContext): string {
   if (!ctx.isFirstVisit) {
-    const parts: string[] = [];
-    if (ctx.outputFormatInstruction !== "") {
-      parts.push(ctx.outputFormatInstruction, "");
-    }
+    // Re-entry: show only steps since last visit, meta only
     parts.push(buildContinuationPrompt(ctx.steps, ctx.role, ctx.edgePrompt));
     return parts.join("\n");
   }
 
-  return buildInitialPrompt(ctx);
+  // First visit: show initial context with content for recent steps
+  const roleDef = ctx.workflow.roles[ctx.role];
+  const rolePrompt = roleDef !== undefined ? buildRolePrompt(roleDef) : "";
+  parts.push(rolePrompt, "", "## Task", ctx.start.prompt);
+
+  // Add history with content (last 2-3 steps within quota)
+  if (ctx.steps.length > 0) {
+    parts.push(
+      "",
+      buildContinuationPrompt(ctx.steps, ctx.role, ctx.edgePrompt, {
+        includeContent: true,
+        quota: 32000, // Use THREAD_READ_DEFAULT_QUOTA equivalent
+      }),
+    );
+  } else {
+    parts.push("", "## Moderator Instruction", "", ctx.edgePrompt);
+  }
+
+  return parts.join("\n");
 }
 
 async function storePromptResult(

packages/workflow-agent-hermes/src/session-cache.ts

@@ -1,5 +1,22 @@
-// Re-export session cache from the shared agent-kit package.
-export { getCachedSessionId, setCachedSessionId } from "@uncaged/workflow-agent-kit";
+// Re-export session cache from the shared agent-kit package with agent name injected.
+
+import {
+  getCachedSessionId as getCachedSessionIdBase,
+  setCachedSessionId as setCachedSessionIdBase,
+} from "@uncaged/workflow-agent-kit";
+import type { ThreadId } from "@uncaged/workflow-protocol";
+
+export async function getCachedSessionId(threadId: ThreadId, role: string): Promise<string | null> {
+  return getCachedSessionIdBase("hermes", threadId, role);
+}
+
+export async function setCachedSessionId(
+  threadId: ThreadId,
+  role: string,
+  sessionId: string,
+): Promise<void> {
+  return setCachedSessionIdBase("hermes", threadId, role, sessionId);
+}
 
 export function isResumeDisabled(): boolean {
   // Hermes ACP session/resume is broken: _restore fails for custom providers

packages/workflow-agent-kit/README.md

@@ -83,9 +83,10 @@ Requires `UWF_EDGE_PROMPT` in the environment (set by `uwf thread step`).
 function buildRolePrompt(role: RoleDefinition): string
 function buildOutputFormatInstruction(schema: JSONSchema): string
 function buildContinuationPrompt(
-  ctx: AgentContext,
-  priorOutput: string,
-  instruction: string,
+  steps: StepContext[],
+  role: string,
+  edgePrompt: string,
+  options?: { includeContent?: boolean; quota?: number },
 ): string
 ```
 

packages/workflow-agent-kit/__tests__/build-continuation-prompt.test.ts

@@ -8,6 +8,7 @@ const reviewerStep: StepContext = {
   detail: "2MXBG6PN4A8JR",
   agent: "uwf-hermes",
   edgePrompt: "Review the developer's work.",
+  content: null,
 };
 
 const developerStep: StepContext = {
@@ -16,6 +17,7 @@ const developerStep: StepContext = {
   detail: "1VPBG9SM5E7WK",
   agent: "uwf-hermes",
   edgePrompt: "Implement the fix.",
+  content: null,
 };
 
 describe("buildContinuationPrompt", () => {
@@ -29,6 +31,7 @@ describe("buildContinuationPrompt", () => {
         detail: "7BQST3VW9F2MA",
         agent: "uwf-hermes",
         edgePrompt: "Revise the plan.",
+        content: null,
       },
     ];
 
@@ -70,4 +73,162 @@ describe("buildContinuationPrompt", () => {
     expect(result).toContain("## Moderator Instruction");
     expect(result).toContain("Please revise your work.");
   });
+
+  test("includes step content when includeContent option is true", () => {
+    const stepsWithContent: StepContext[] = [
+      {
+        role: "planner",
+        output: { plan: "hash123" },
+        detail: "detail1",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Plan\nDetailed plan markdown...",
+      },
+      {
+        role: "developer",
+        output: { filesChanged: ["app.ts"] },
+        detail: "detail2",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Implementation\nCode changes...",
+      },
+      {
+        role: "reviewer",
+        output: { approved: false },
+        detail: "detail3",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Review\nFeedback...",
+      },
+    ];
+
+    const result = buildContinuationPrompt(stepsWithContent, "committer", "Commit the changes.", {
+      includeContent: true,
+    });
+
+    expect(result).toContain("## What Happened Since Your Last Turn");
+    expect(result).toContain("### Step 1: planner");
+    expect(result).toContain("#### Step Content");
+    expect(result).toContain("# Plan");
+    expect(result).toContain("Detailed plan markdown");
+    expect(result).toContain("### Step 2: developer");
+    expect(result).toContain("# Implementation");
+    expect(result).toContain("### Step 3: reviewer");
+    expect(result).toContain("# Review");
+    expect(result).toContain("## Moderator Instruction");
+    expect(result).toContain("Commit the changes.");
+  });
+
+  test("omits step content when includeContent is false (default)", () => {
+    const stepsWithContent: StepContext[] = [
+      {
+        role: "developer",
+        output: { filesChanged: ["app.ts"] },
+        detail: "detail1",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Implementation\nCode changes...",
+      },
+      {
+        role: "reviewer",
+        output: { approved: false },
+        detail: "detail2",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Review\nFeedback...",
+      },
+    ];
+
+    const result = buildContinuationPrompt(stepsWithContent, "developer", "Fix the issues.");
+
+    expect(result).toContain("## What Happened Since Your Last Turn");
+    expect(result).toContain("### Step 2: reviewer");
+    expect(result).toContain(JSON.stringify(stepsWithContent[1]?.output));
+    expect(result).not.toContain("#### Step Content");
+    expect(result).not.toContain("# Review");
+  });
+
+  test("respects quota when includeContent is true", () => {
+    const largeContent = "x".repeat(5000);
+    const stepsWithContent: StepContext[] = [
+      {
+        role: "planner",
+        output: { plan: "hash1" },
+        detail: "detail1",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: largeContent,
+      },
+      {
+        role: "developer",
+        output: { files: ["app.ts"] },
+        detail: "detail2",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: largeContent,
+      },
+      {
+        role: "reviewer",
+        output: { approved: true },
+        detail: "detail3",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Review\nLooks good!",
+      },
+    ];
+
+    const result = buildContinuationPrompt(stepsWithContent, "committer", "Commit the changes.", {
+      includeContent: true,
+      quota: 1000,
+    });
+
+    // Should include most recent step(s) within quota
+    expect(result).toContain("### Step 1: reviewer"); // Showing 1 of 3, so step 3 becomes step 1
+    expect(result).toContain("#### Step Content");
+    expect(result).toContain("## Moderator Instruction");
+    expect(result).toContain("Showing 1 of 3 steps (2 omitted due to quota)");
+  });
+
+  test("handles null content gracefully when includeContent is true", () => {
+    const stepsWithMixedContent: StepContext[] = [
+      {
+        role: "planner",
+        output: { plan: "hash1" },
+        detail: "detail1",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Plan\nDetails...",
+      },
+      {
+        role: "developer",
+        output: { files: ["app.ts"] },
+        detail: "detail2",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: null, // No content available
+      },
+      {
+        role: "reviewer",
+        output: { approved: true },
+        detail: "detail3",
+        agent: "uwf-hermes",
+        edgePrompt: "",
+        content: "# Review\nApproved!",
+      },
+    ];
+
+    const result = buildContinuationPrompt(
+      stepsWithMixedContent,
+      "committer",
+      "Commit the changes.",
+      { includeContent: true },
+    );
+
+    expect(result).toContain("### Step 1: planner");
+    expect(result).toContain("# Plan");
+    expect(result).toContain("### Step 2: developer");
+    // Step 2 should not have content section since content is null
+    expect(result).toContain("### Step 3: reviewer");
+    expect(result).toContain("# Review");
+  });
 });

packages/workflow-agent-kit/__tests__/context.test.ts

@@ -0,0 +1,14 @@
+import { describe, expect, test } from "vitest";
+
+// We need to test buildHistory indirectly through buildContext
+// since buildHistory is not exported. For now, we'll test the integration
+// through the public API in a separate integration test.
+
+describe("context module - content extraction", () => {
+  test("placeholder - content extraction will be tested via integration tests", () => {
+    // This test is a placeholder. The actual testing of content extraction
+    // will be done through integration tests in build-continuation-prompt.test.ts
+    // where we can verify that StepContext objects have the correct content field.
+    expect(true).toBe(true);
+  });
+});

packages/workflow-agent-kit/__tests__/session-cache.test.ts

@@ -0,0 +1,247 @@
+import { mkdir, readdir, readFile, rm, stat, writeFile } from "node:fs/promises";
+import { dirname, join } from "node:path";
+import type { ThreadId } from "@uncaged/workflow-protocol";
+import { afterEach, beforeEach, describe, expect, test } from "vitest";
+
+import { getCachedSessionId, getCachePath, setCachedSessionId } from "../src/session-cache.js";
+import { resolveStorageRoot } from "../src/storage.js";
+
+describe("session-cache", () => {
+  let originalStorageRoot: string;
+  let testStorageRoot: string;
+
+  beforeEach(async () => {
+    // Create a temporary test storage root
+    originalStorageRoot = resolveStorageRoot();
+    testStorageRoot = join(originalStorageRoot, "test-cache", `test-${Date.now()}`);
+    await mkdir(testStorageRoot, { recursive: true });
+
+    // Override the storage root for testing
+    process.env.WORKFLOW_STORAGE_ROOT = testStorageRoot;
+  });
+
+  afterEach(async () => {
+    // Clean up test storage root
+    await rm(testStorageRoot, { recursive: true, force: true });
+    delete process.env.WORKFLOW_STORAGE_ROOT;
+  });
+
+  describe("getCachePath", () => {
+    test("returns agent-specific file path", () => {
+      const path = getCachePath("claude-code");
+      expect(path).toMatch(/\/cache\/claude-code-sessions\.json$/);
+    });
+
+    test("returns different paths for different agents", () => {
+      const pathClaudeCode = getCachePath("claude-code");
+      const pathHermes = getCachePath("hermes");
+
+      expect(pathClaudeCode).not.toBe(pathHermes);
+      expect(pathClaudeCode).toMatch(/claude-code-sessions\.json$/);
+      expect(pathHermes).toMatch(/hermes-sessions\.json$/);
+    });
+
+    test("handles agent names with special characters", () => {
+      const path1 = getCachePath("my-agent");
+      const path2 = getCachePath("my_agent");
+
+      expect(path1).toMatch(/my-agent-sessions\.json$/);
+      expect(path2).toMatch(/my_agent-sessions\.json$/);
+    });
+  });
+
+  describe("session isolation", () => {
+    const threadId = "01234567890123456789012345" as ThreadId;
+    const role = "developer";
+
+    test("sessions are isolated per agent", async () => {
+      // Cache different session IDs for each agent
+      await setCachedSessionId("claude-code", threadId, role, "session-cc-001");
+      await setCachedSessionId("hermes", threadId, role, "session-hermes-001");
+
+      // Each agent should retrieve its own session ID
+      const sessionCC = await getCachedSessionId("claude-code", threadId, role);
+      const sessionHermes = await getCachedSessionId("hermes", threadId, role);
+
+      expect(sessionCC).toBe("session-cc-001");
+      expect(sessionHermes).toBe("session-hermes-001");
+    });
+
+    test("updating one agent's cache does not affect another", async () => {
+      // Set initial sessions for both agents
+      await setCachedSessionId("claude-code", threadId, role, "session-cc-001");
+      await setCachedSessionId("hermes", threadId, role, "session-hermes-001");
+
+      // Update claude-code's session
+      await setCachedSessionId("claude-code", threadId, role, "session-cc-002");
+
+      // Hermes's session should remain unchanged
+      const sessionHermes = await getCachedSessionId("hermes", threadId, role);
+      expect(sessionHermes).toBe("session-hermes-001");
+
+      // Claude-code should have the new session
+      const sessionCC = await getCachedSessionId("claude-code", threadId, role);
+      expect(sessionCC).toBe("session-cc-002");
+    });
+
+    test("missing session returns null for specific agent", async () => {
+      const session = await getCachedSessionId("claude-code", threadId, role);
+      expect(session).toBeNull();
+    });
+
+    test("empty session ID is treated as missing", async () => {
+      await setCachedSessionId("claude-code", threadId, role, "");
+
+      const session = await getCachedSessionId("claude-code", threadId, role);
+      expect(session).toBeNull();
+    });
+  });
+
+  describe("file system operations", () => {
+    const threadId = "01234567890123456789012345" as ThreadId;
+    const role = "developer";
+
+    test("cache directory is created if missing", async () => {
+      const cachePath = getCachePath("claude-code");
+      const cacheDir = dirname(cachePath);
+
+      // Ensure cache dir doesn't exist
+      await rm(cacheDir, { recursive: true, force: true });
+
+      // Write a session
+      await setCachedSessionId("claude-code", threadId, role, "session-001");
+
+      // Cache directory should be created
+      const stats = await stat(cacheDir);
+      expect(stats.isDirectory()).toBe(true);
+    });
+
+    test("multiple agents create separate cache files", async () => {
+      // Cache sessions for multiple agents
+      await setCachedSessionId("claude-code", threadId, role, "session-cc-001");
+      await setCachedSessionId("hermes", threadId, role, "session-hermes-001");
+
+      // Separate cache files should exist
+      const pathCC = getCachePath("claude-code");
+      const pathHermes = getCachePath("hermes");
+
+      const contentCC = JSON.parse(await readFile(pathCC, "utf8")) as Record<string, string>;
+      const contentHermes = JSON.parse(await readFile(pathHermes, "utf8")) as Record<
+        string,
+        string
+      >;
+
+      expect(contentCC).toHaveProperty(`${threadId}:${role}`, "session-cc-001");
+      expect(contentHermes).toHaveProperty(`${threadId}:${role}`, "session-hermes-001");
+    });
+
+    test("atomic writes prevent partial reads", async () => {
+      // Write a session
+      await setCachedSessionId("claude-code", threadId, role, "session-001");
+
+      // The final file should exist (no .tmp files left behind)
+      const cachePath = getCachePath("claude-code");
+      const dir = dirname(cachePath);
+      const files = await readdir(dir);
+
+      expect(files).toContain("claude-code-sessions.json");
+      expect(files.every((f) => !f.endsWith(".tmp"))).toBe(true);
+    });
+  });
+
+  describe("legacy migration", () => {
+    const threadId = "01234567890123456789012345" as ThreadId;
+    const role = "developer";
+
+    test("old agent-sessions.json is ignored", async () => {
+      // Create old agent-sessions.json file
+      const oldCachePath = join(resolveStorageRoot(), "cache", "agent-sessions.json");
+      await mkdir(dirname(oldCachePath), { recursive: true });
+      await writeFile(
+        oldCachePath,
+        JSON.stringify({
+          "01234567890123456789012345:developer": "old-session-001",
+        }),
+        "utf8",
+      );
+
+      // Query with the new per-agent cache
+      const session = await getCachedSessionId("claude-code", threadId, role);
+
+      // Should return null (old cache is ignored)
+      expect(session).toBeNull();
+    });
+
+    test("new per-agent cache takes precedence", async () => {
+      // Create both old and new cache files
+      const oldPath = join(resolveStorageRoot(), "cache", "agent-sessions.json");
+      await mkdir(dirname(oldPath), { recursive: true });
+      await writeFile(
+        oldPath,
+        JSON.stringify({
+          [`${threadId}:${role}`]: "old-session",
+        }),
+        "utf8",
+      );
+
+      await setCachedSessionId("claude-code", threadId, role, "new-session");
+
+      // The new per-agent cache value should be returned
+      const session = await getCachedSessionId("claude-code", threadId, role);
+      expect(session).toBe("new-session");
+    });
+  });
+
+  describe("error handling", () => {
+    const threadId = "01234567890123456789012345" as ThreadId;
+    const role = "developer";
+
+    test("invalid JSON in cache file returns empty cache", async () => {
+      // Create a corrupted cache file
+      const cachePath = getCachePath("claude-code");
+      await mkdir(dirname(cachePath), { recursive: true });
+      await writeFile(cachePath, "{ invalid json }", "utf8");
+
+      // Should return null (treating corrupted cache as empty)
+      const session = await getCachedSessionId("claude-code", threadId, role);
+      expect(session).toBeNull();
+    });
+
+    test("non-object JSON in cache file returns empty cache", async () => {
+      // Create a cache file with non-object JSON
+      const cachePath = getCachePath("claude-code");
+      await mkdir(dirname(cachePath), { recursive: true });
+      await writeFile(cachePath, JSON.stringify(["not", "an", "object"]), "utf8");
+
+      // Should return null
+      const session = await getCachedSessionId("claude-code", threadId, role);
+      expect(session).toBeNull();
+    });
+
+    test("cache entries with non-string values are ignored", async () => {
+      // Create a cache file with mixed types
+      const cachePath = getCachePath("claude-code");
+      const cacheData = {
+        "thread1:role1": "valid-session",
+        "thread2:role2": 12345, // number
+        "thread3:role3": null, // null
+        "thread4:role4": "", // empty string
+      };
+      await mkdir(dirname(cachePath), { recursive: true });
+      await writeFile(cachePath, JSON.stringify(cacheData), "utf8");
+
+      // Valid string entries should be returned
+      const session1 = await getCachedSessionId("claude-code", "thread1" as ThreadId, "role1");
+      expect(session1).toBe("valid-session");
+
+      // Invalid entries should return null
+      const session2 = await getCachedSessionId("claude-code", "thread2" as ThreadId, "role2");
+      const session3 = await getCachedSessionId("claude-code", "thread3" as ThreadId, "role3");
+      const session4 = await getCachedSessionId("claude-code", "thread4" as ThreadId, "role4");
+
+      expect(session2).toBeNull();
+      expect(session3).toBeNull();
+      expect(session4).toBeNull(); // empty string is treated as missing
+    });
+  });
+});

packages/workflow-agent-kit/src/build-continuation-prompt.ts

@@ -1,11 +1,20 @@
 import type { StepContext } from "@uncaged/workflow-protocol";
 
-function formatStep(step: StepContext, stepNumber: number): string {
-  return [
+function formatStep(step: StepContext, stepNumber: number, includeContent: boolean): string {
+  const lines = [
     `### Step ${stepNumber}: ${step.role}`,
     `Output: ${JSON.stringify(step.output)}`,
     `Agent: ${step.agent}`,
-  ].join("\n");
+  ];
+
+  if (includeContent && step.content !== null) {
+    lines.push("");
+    lines.push("#### Step Content");
+    lines.push("");
+    lines.push(step.content);
+  }
+
+  return lines.join("\n");
 }
 
 function findLastRoleIndex(steps: StepContext[], role: string): number {
@@ -18,6 +27,45 @@ function findLastRoleIndex(steps: StepContext[], role: string): number {
   return -1;
 }
 
+function selectStepsWithinQuota(steps: StepContext[], quota: number): StepContext[] {
+  const selected: StepContext[] = [];
+  let totalChars = 0;
+
+  // Work backwards (newest first)
+  for (let i = steps.length - 1; i >= 0; i--) {
+    const step = steps[i];
+    if (step === undefined) continue;
+
+    // Estimate size: meta + content
+    const metaSize = JSON.stringify({
+      role: step.role,
+      output: step.output,
+      agent: step.agent,
+    }).length;
+    const contentSize = step.content?.length ?? 0;
+    const stepSize = metaSize + contentSize;
+
+    if (totalChars + stepSize > quota && selected.length > 0) {
+      // Stop adding steps but keep at least 1
+      break;
+    }
+
+    selected.unshift(step); // Keep chronological order
+    totalChars += stepSize;
+
+    if (totalChars >= quota) {
+      break;
+    }
+  }
+
+  return selected;
+}
+
+type BuildContinuationPromptOptions = {
+  includeContent?: boolean;
+  quota?: number;
+};
+
 /**
  * Build a continuation prompt for a role re-entry.
  *
@@ -28,7 +76,11 @@ export function buildContinuationPrompt(
   steps: StepContext[],
   role: string,
   edgePrompt: string,
+  options?: BuildContinuationPromptOptions,
 ): string {
+  const includeContent = options?.includeContent ?? false;
+  const quota = options?.quota ?? Number.POSITIVE_INFINITY;
+
   const lastIndex = findLastRoleIndex(steps, role);
   const sinceSteps = lastIndex >= 0 ? steps.slice(lastIndex + 1) : steps;
 
@@ -37,13 +89,25 @@ export function buildContinuationPrompt(
   if (sinceSteps.length > 0) {
     parts.push("## What Happened Since Your Last Turn");
     const baseStepNumber = lastIndex >= 0 ? lastIndex + 2 : 1;
-    for (let i = 0; i < sinceSteps.length; i++) {
-      const step = sinceSteps[i];
+
+    // Select steps within quota (newest-first if includeContent = true)
+    const selectedSteps = includeContent ? selectStepsWithinQuota(sinceSteps, quota) : sinceSteps;
+
+    const skippedCount = sinceSteps.length - selectedSteps.length;
+    if (skippedCount > 0) {
+      parts.push("");
+      parts.push(
+        `_Showing ${selectedSteps.length} of ${sinceSteps.length} steps (${skippedCount} omitted due to quota)_`,
+      );
+    }
+
+    for (let i = 0; i < selectedSteps.length; i++) {
+      const step = selectedSteps[i];
       if (step === undefined) {
         continue;
       }
       parts.push("");
-      parts.push(formatStep(step, baseStepNumber + i));
+      parts.push(formatStep(step, baseStepNumber + i, includeContent));
     }
     parts.push("");
   }

packages/workflow-agent-kit/src/context.ts

@@ -82,6 +82,38 @@ function expandOutput(store: Store, outputRef: CasRef): unknown {
   return node.payload;
 }
 
+function extractStepContent(store: Store, detailRef: CasRef): string | null {
+  const detailNode = 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;
+  }
+  // Find last assistant content (same logic as extractLastAssistantContent in cli-workflow)
+  for (let i = turns.length - 1; i >= 0; i--) {
+    const turnRef = turns[i];
+    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 (
+      turn.role === "assistant" &&
+      typeof turn.content === "string" &&
+      turn.content.trim() !== ""
+    ) {
+      return turn.content;
+    }
+  }
+  return null;
+}
+
 async function buildHistory(
   store: Store,
   stepsNewestFirst: StepNodePayload[],
@@ -89,12 +121,14 @@ async function buildHistory(
   const chronological = [...stepsNewestFirst].reverse();
   const history: StepContext[] = [];
   for (const step of chronological) {
+    const content = extractStepContent(store, step.detail);
     history.push({
       role: step.role,
       output: expandOutput(store, step.output),
       detail: step.detail,
       agent: step.agent,
       edgePrompt: step.edgePrompt ?? "",
+      content,
     });
   }
   return history;

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

@@ -12,7 +12,7 @@ export {
 export type { FrontmatterFastPathResult } from "./frontmatter.js";
 export { tryFrontmatterFastPath } from "./frontmatter.js";
 export { createAgent } from "./run.js";
-export { getCachedSessionId, setCachedSessionId } from "./session-cache.js";
+export { getCachedSessionId, getCachePath, setCachedSessionId } from "./session-cache.js";
 export { getConfigPath, getEnvPath, loadWorkflowConfig, resolveStorageRoot } from "./storage.js";
 export type {
   AgentContext,

packages/workflow-agent-kit/src/session-cache.ts

@@ -8,8 +8,8 @@ import { resolveStorageRoot } from "./storage.js";
 
 type SessionCache = Record<string, string>;
 
-function getCachePath(): string {
-  return join(resolveStorageRoot(), "cache", "agent-sessions.json");
+export function getCachePath(agentName: string): string {
+  return join(resolveStorageRoot(), "cache", `${agentName}-sessions.json`);
 }
 
 function cacheKey(threadId: ThreadId, role: string): string {
@@ -20,8 +20,8 @@ function isRecord(value: unknown): value is Record<string, unknown> {
   return typeof value === "object" && value !== null && !Array.isArray(value);
 }
 
-async function readCache(): Promise<SessionCache> {
-  const path = getCachePath();
+async function readCache(agentName: string): Promise<SessionCache> {
+  const path = getCachePath(agentName);
   try {
     const text = await readFile(path, "utf8");
     const raw = JSON.parse(text) as unknown;
@@ -40,36 +40,45 @@ async function readCache(): Promise<SessionCache> {
     if (err.code === "ENOENT") {
       return {};
     }
+    // Treat JSON parse errors as empty cache
+    if (err.name === "SyntaxError") {
+      return {};
+    }
     throw e;
   }
 }
 
-async function writeCache(cache: SessionCache): Promise<void> {
-  const path = getCachePath();
+async function writeCache(agentName: string, cache: SessionCache): Promise<void> {
+  const path = getCachePath(agentName);
   const dir = dirname(path);
   await mkdir(dir, { recursive: true });
   // Atomic write: write to temp file then rename to avoid partial reads on concurrent access.
   // NOTE: Current workflow execution is serial (execFileSync), so true concurrency doesn't occur.
   // This is a safety net for future parallel execution.
-  const tmpPath = join(dir, `.agent-sessions.${randomBytes(4).toString("hex")}.tmp`);
+  const tmpPath = join(dir, `.${agentName}-sessions.${randomBytes(4).toString("hex")}.tmp`);
   await writeFile(tmpPath, `${JSON.stringify(cache, null, 2)}\n`, "utf8");
   await rename(tmpPath, path);
 }
 
 /** Read the cached session ID for a thread+role pair. */
-export async function getCachedSessionId(threadId: ThreadId, role: string): Promise<string | null> {
-  const cache = await readCache();
+export async function getCachedSessionId(
+  agentName: string,
+  threadId: ThreadId,
+  role: string,
+): Promise<string | null> {
+  const cache = await readCache(agentName);
   const sessionId = cache[cacheKey(threadId, role)];
   return sessionId ?? null;
 }
 
 /** Write the session ID for a thread+role pair into the cache. */
 export async function setCachedSessionId(
+  agentName: string,
   threadId: ThreadId,
   role: string,
   sessionId: string,
 ): Promise<void> {
-  const cache = await readCache();
+  const cache = await readCache(agentName);
   cache[cacheKey(threadId, role)] = sessionId;
-  await writeCache(cache);
+  await writeCache(agentName, cache);
 }

packages/workflow-dashboard/context.md

@@ -123,7 +123,7 @@ type RoleNodeData = {
 
 **边类型**：
 - `default`（GradientEdge）→ 渐变色边（绿→蓝），节点仅有一条出边时使用
-- `conditional`（ConditionalEdge）→ 带条件标签的渐变色边，节点有多条出边时使用
+- `status`（StatusEdge）→ 带 status 标签的渐变色边，节点有多条出边时使用
 
 **边渲染特性**：
 - 渐变色：SVG linearGradient，从 source 端绿色（#10b981）到 target 端蓝色（#3b82f6）
@@ -234,7 +234,7 @@ Model 提供事务机制：
 ```
 ReactFlow
   ├─ nodeTypes: { start: NodeStart, end: NodeEnd, role: NodeRole }
-  └─ edgeTypes: { default: GradientEdge, conditional: ConditionalEdge }
+  └─ edgeTypes: { default: GradientEdge, status: StatusEdge }
 ```
 
 `NodeRole` 显示角色名（data.name），使用 teal 色系图标和标签。Handle 分蓝色（in）和绿色（out）两种颜色。
@@ -324,12 +324,11 @@ type WorkflowPayload = {
   name: string;
   description: string;
   roles: Record<string, RoleDefinition>;       // 角色定义（4 段式：identity/prepare/execute/report）
-  conditions: Record<string, ConditionDefinition>; // JSONata 条件表达式
-  graph: Record<string, Transition[]>;          // 角色间的转移图
+  graph: Record<string, Record<string, Target>>;   // status-based 路由图
 };
 ```
 
-workflow-dashboard 使用 `WorkFlowSteps` 格式作为交换数据，其中 `WorkFlowRole` 的字段与 `RoleDefinition` 对齐（description/identity/prepare/execute/report），`WorkFlowTransition` 对应 graph 中的 `Transition`。外部（CLI/server）负责 `WorkflowPayload` ↔ `WorkFlowSteps` 的转换。
+workflow-dashboard 使用 `WorkFlowSteps` 格式作为交换数据，其中 `WorkFlowRole` 的字段与 `RoleDefinition` 对齐（description/identity/prepare/execute/report），`WorkFlowTransition` 对应 graph 中的 `Target`。外部（CLI/server）负责 `WorkflowPayload` ↔ `WorkFlowSteps` 的转换。
 
 ## 11. 当前状态与待完善项
 

packages/workflow-dashboard/server/api.ts

@@ -57,7 +57,7 @@ export function createApi() {
             transitions: t.Array(
               t.Object({
                 target: t.String(),
-                condition: t.Union([t.String(), t.Null()]),
+                status: t.String(),
               }),
             ),
           }),

packages/workflow-dashboard/server/workflow.ts

@@ -1,6 +1,6 @@
 import { mkdir, readdir, readFile, unlink, writeFile } from "node:fs/promises";
 import { join } from "node:path";
-import type { RoleDefinition, Transition, WorkflowPayload } from "@uncaged/workflow-protocol";
+import type { RoleDefinition, Target, WorkflowPayload } from "@uncaged/workflow-protocol";
 import YAML from "yaml";
 import type { WorkFlowSteps, WorkFlowTransition, WorkflowSummary } from "../shared/types.ts";
 
@@ -11,17 +11,12 @@ async function ensureDir() {
 }
 
 function payloadToSteps(payload: WorkflowPayload): WorkFlowSteps {
-  const conditionMap = new Map<string, string>();
-  for (const [name, def] of Object.entries(payload.conditions)) {
-    conditionMap.set(name, def.expression);
-  }
-
   const steps: WorkFlowSteps = [];
   for (const [roleName, roleDef] of Object.entries(payload.roles)) {
-    const graphTransitions = payload.graph[roleName] ?? [];
-    const transitions: WorkFlowTransition[] = graphTransitions.map((t) => ({
-      target: t.role === "$END" ? "END" : t.role,
-      condition: t.condition ? (conditionMap.get(t.condition) ?? t.condition) : null,
+    const statusMap = payload.graph[roleName] ?? {};
+    const transitions: WorkFlowTransition[] = Object.entries(statusMap).map(([status, target]) => ({
+      target: target.role === "$END" ? "END" : target.role,
+      status,
     }));
 
     steps.push({
@@ -42,11 +37,7 @@ function payloadToSteps(payload: WorkflowPayload): WorkFlowSteps {
 
 function stepsToPayload(name: string, description: string, steps: WorkFlowSteps): WorkflowPayload {
   const roles: Record<string, RoleDefinition> = {};
-  const conditions: WorkflowPayload["conditions"] = {};
-  const graph: Record<string, Transition[]> = {};
-
-  const expressionToName = new Map<string, string>();
-  let condIdx = 0;
+  const graph: Record<string, Record<string, Target>> = {};
 
   for (const step of steps) {
     const r = step.role;
@@ -59,43 +50,28 @@ function stepsToPayload(name: string, description: string, steps: WorkFlowSteps)
       frontmatter: "",
     };
 
-    const transitions: Transition[] = step.transitions.map((t) => {
-      let condName: string | null = null;
-      if (t.condition) {
-        if (expressionToName.has(t.condition)) {
-          condName = expressionToName.get(t.condition) ?? null;
-        } else {
-          condName = `cond${condIdx++}`;
-          expressionToName.set(t.condition, condName);
-          conditions[condName] = {
-            description: "",
-            expression: t.condition,
-          };
-        }
-      }
+    const statusMap: Record<string, Target> = {};
+    for (const t of step.transitions) {
       const targetRole = t.target === "END" ? "$END" : t.target;
-      return {
+      statusMap[t.status] = {
         role: targetRole,
-        condition: condName,
         prompt: `Transition to ${targetRole}.`,
       };
-    });
-
-    graph[r.name] = transitions;
+    }
+    graph[r.name] = statusMap;
   }
 
   if (steps.length > 0) {
     const firstRole = steps[0].role.name;
-    graph.$START = [
-      {
+    graph.$START = {
+      _: {
         role: firstRole,
-        condition: null,
         prompt: `Begin workflow at role ${firstRole}.`,
       },
-    ];
+    };
   }
 
-  return { name, description, roles, conditions, graph };
+  return { name, description, roles, graph };
 }
 
 export async function listWorkflows(): Promise<WorkflowSummary[]> {
@@ -125,7 +101,6 @@ export async function createWorkflow(name: string, description: string): Promise
     name,
     description,
     roles: {},
-    conditions: {},
     graph: {},
   };
   await writeFile(join(WORKFLOW_DIR, `${name}.yaml`), YAML.stringify(payload), "utf-8");

packages/workflow-dashboard/shared/types.ts

@@ -9,7 +9,7 @@ export type WorkFlowRole = {
 
 export type WorkFlowTransition = {
   target: string;
-  condition: string | null;
+  status: string;
 };
 
 export type WorkFlowStep = {

packages/workflow-dashboard/src/editor/edges/index.tsx

@@ -1,6 +1,6 @@
-import { ConditionalEdge, GradientEdge } from "./conditional";
+import { GradientEdge, StatusEdge } from "./status";
 
 export const edgeTypes = {
-  conditional: ConditionalEdge,
+  status: StatusEdge,
   default: GradientEdge,
 };

packages/workflow-dashboard/src/editor/edges/status.tsx

@@ -6,10 +6,10 @@ import {
   useReactFlow,
 } from "@xyflow/react";
 import { Check } from "lucide-react";
-import { type ReactNode, useEffect, useMemo, useRef, useState } from "react";
+import { type ReactNode, useEffect, useRef, useState } from "react";
 import { cn } from "../../lib/utils.ts";
 import { useModel } from "../context.tsx";
-import type { ConditionalEdge as ConditionalEdgeType } from "../type.ts";
+import type { StatusEdge as StatusEdgeType } from "../type.ts";
 
 const SOURCE_COLOR = "#10b981";
 const TARGET_COLOR = "#3b82f6";
@@ -23,7 +23,7 @@ function GradientPath({
   sourceY,
   targetX,
   targetY,
-  hasCondition,
+  hasStatus,
   selected,
 }: {
   id: string;
@@ -32,11 +32,11 @@ function GradientPath({
   sourceY: number;
   targetX: number;
   targetY: number;
-  hasCondition: boolean | null;
+  hasStatus: boolean;
   selected: boolean;
 }) {
   const gradientId = `gradient-${id}`;
-  const showLack = hasCondition === false;
+  const showLack = !hasStatus;
   const strokeStyle = selected
     ? { stroke: "#f59e0b", strokeWidth: 2 }
     : { stroke: `url(#${gradientId})`, strokeWidth: 1.5 };
@@ -68,35 +68,20 @@ function GradientPath({
   );
 }
 
-function ElseBadge({ labelX, labelY }: { labelX: number; labelY: number }): ReactNode {
-  return (
-    <div
-      className="absolute pointer-events-none"
-      style={{
-        transform: `translate(-50%, -50%) translate(${labelX}px,${labelY}px)`,
-      }}
-    >
-      <span className="inline-block px-1 bg-white rounded text-[10px] border border-gray-300 text-gray-500">
-        else
-      </span>
-    </div>
-  );
-}
-
-type ConditionLabelProps = {
-  condition: string | undefined;
+type StatusLabelProps = {
+  status: string | undefined;
   labelX: number;
   labelY: number;
   onSave: (value: string) => void;
 };
 
-function ConditionLabel({ condition, labelX, labelY, onSave }: ConditionLabelProps): ReactNode {
+function StatusLabel({ status, labelX, labelY, onSave }: StatusLabelProps): ReactNode {
   const [isOpen, setIsOpen] = useState(false);
   const [inputValue, setInputValue] = useState("");
   const containerRef = useRef<HTMLDivElement>(null);
 
   function handleBadgeClick() {
-    setInputValue(condition || "");
+    setInputValue(status || "");
     setIsOpen(true);
   }
 
@@ -127,6 +112,8 @@ function ConditionLabel({ condition, labelX, labelY, onSave }: ConditionLabelPro
     return () => document.removeEventListener("pointerdown", handleClickOutside, true);
   }, [isOpen]);
 
+  const displayStatus = status?.trim() || null;
+
   return (
     <div
       ref={containerRef}
@@ -142,11 +129,13 @@ function ConditionLabel({ condition, labelX, labelY, onSave }: ConditionLabelPro
         <span
           className={cn(
             "inline-block px-1 bg-white rounded text-[10px]",
-            condition ? "border border-gray-300 text-black" : "border border-dashed text-red-500",
+            displayStatus
+              ? "border border-gray-300 text-black"
+              : "border border-dashed text-red-500",
           )}
-          style={condition ? undefined : { borderColor: LACK_COLOR }}
+          style={displayStatus ? undefined : { borderColor: LACK_COLOR }}
         >
-          if
+          {displayStatus ?? "status"}
         </span>
       </div>
       {isOpen && (
@@ -155,7 +144,7 @@ function ConditionLabel({ condition, labelX, labelY, onSave }: ConditionLabelPro
             <input
               type="text"
               className="w-32 rounded border border-gray-300 px-1 py-0.5 text-[10px] focus:border-blue-500 focus:outline-none"
-              placeholder="输入条件"
+              placeholder="输入状态"
               value={inputValue}
               onChange={(e) => setInputValue(e.target.value)}
               onKeyDown={handleKeyDown}
@@ -174,14 +163,8 @@ function ConditionLabel({ condition, labelX, labelY, onSave }: ConditionLabelPro
   );
 }
 
-export function isElseEdge(edgeId: string, source: string, allEdges: Edge[]): boolean {
-  const siblings = allEdges.filter((e) => e.source === source && e.type === "conditional");
-  return siblings.length >= 2 && siblings[0].id === edgeId;
-}
-
-export function ConditionalEdge({
+export function StatusEdge({
   id,
-  source,
   sourceX,
   sourceY,
   targetX,
@@ -190,7 +173,7 @@ export function ConditionalEdge({
   targetPosition,
   selected,
   data,
-}: EdgeProps<ConditionalEdgeType>): ReactNode {
+}: EdgeProps<StatusEdgeType>): ReactNode {
   const [edgePath, labelX, labelY] = getSmoothStepPath({
     sourceX,
     sourceY,
@@ -203,13 +186,11 @@ export function ConditionalEdge({
   const flow = useReactFlow();
   const model = useModel();
 
-  const allEdges = flow.getEdges();
-  const isElse = useMemo(() => isElseEdge(id, source, allEdges), [id, source, allEdges]);
+  const status = data?.status;
 
-  const condition = data?.condition;
   function handleSave(value: string) {
     model.startTransaction();
-    flow.updateEdgeData(id, { condition: value });
+    flow.updateEdgeData(id, { status: value });
     requestAnimationFrame(model.endTransaction);
   }
 
@@ -222,20 +203,11 @@ export function ConditionalEdge({
         sourceY={sourceY}
         targetX={targetX}
         targetY={targetY}
-        hasCondition={isElse ? null : !!condition}
+        hasStatus={!!status?.trim()}
         selected={!!selected}
       />
       <EdgeLabelRenderer>
-        {isElse ? (
-          <ElseBadge labelX={labelX} labelY={labelY} />
-        ) : (
-          <ConditionLabel
-            condition={condition}
-            labelX={labelX}
-            labelY={labelY}
-            onSave={handleSave}
-          />
-        )}
+        <StatusLabel status={status} labelX={labelX} labelY={labelY} onSave={handleSave} />
       </EdgeLabelRenderer>
     </>
   );
@@ -269,7 +241,7 @@ export function GradientEdge({
       sourceY={sourceY}
       targetX={targetX}
       targetY={targetY}
-      hasCondition={null}
+      hasStatus={true}
       selected={!!selected}
     />
   );

packages/workflow-dashboard/src/editor/model/edges.ts

@@ -65,12 +65,12 @@ export const edgesModel = define.model("edges", makeEdges, (set, get, model) =>
     const existingFromSource = currentEdges.filter((e) => e.source === normalized.source);
 
     if (existingFromSource.length > 0) {
-      edge.type = "conditional";
-      edge.data = { condition: "" };
+      edge.type = "status";
+      edge.data = { status: "" };
 
       const promoted = currentEdges.map((e) => {
-        if (e.source === normalized.source && e.type !== "conditional") {
-          return { ...e, type: "conditional" as const, data: { condition: "" } };
+        if (e.source === normalized.source && e.type !== "status") {
+          return { ...e, type: "status" as const, data: { status: "_" } };
         }
         return e;
       });

packages/workflow-dashboard/src/editor/model/handlers.ts

@@ -34,21 +34,8 @@ export const handlers = define.memoize((use, model) => {
     return node.type === "start" || node.type === "end";
   }
 
-  function isFirstConditionalSibling(
-    edge: { id: string; source: string; type: string | null },
-    allEdges: { id: string; source: string; type: string | null }[],
-  ): boolean {
-    if (edge.type !== "conditional") return false;
-    const siblings = allEdges.filter((e) => e.source === edge.source && e.type === "conditional");
-    return siblings.length >= 2 && siblings[0].id === edge.id;
-  }
-
-  const onBeforeDelete: OnBeforeDelete<AnyWorkNode> = async ({ nodes, edges }) => {
+  const onBeforeDelete: OnBeforeDelete<AnyWorkNode> = async ({ nodes }) => {
     if (nodes.some(isProtectedNode)) return false;
-    if (edges.length > 0) {
-      const allEdges = use(edgesModel)[0];
-      if (edges.some((e) => isFirstConditionalSibling(e, allEdges))) return false;
-    }
     model.startTransaction();
     return true;
   };
@@ -56,16 +43,14 @@ export const handlers = define.memoize((use, model) => {
     if (deletedEdges.length > 0) {
       const currentEdges = use(edgesModel)[0];
       const sourcesToCheck = new Set(
-        deletedEdges.filter((e) => e.type === "conditional").map((e) => e.source),
+        deletedEdges.filter((e) => e.type === "status").map((e) => e.source),
       );
 
       if (sourcesToCheck.size > 0) {
         let needsDowngrade = false;
         const updatedEdges = currentEdges.map((e) => {
-          if (!sourcesToCheck.has(e.source) || e.type !== "conditional") return e;
-          const siblings = currentEdges.filter(
-            (s) => s.source === e.source && s.type === "conditional",
-          );
+          if (!sourcesToCheck.has(e.source) || e.type !== "status") return e;
+          const siblings = currentEdges.filter((s) => s.source === e.source && s.type === "status");
           if (siblings.length === 1) {
             needsDowngrade = true;
             const { data: _, ...rest } = e;

packages/workflow-dashboard/src/editor/trans/__tests__/trans-in.test.ts

@@ -36,7 +36,7 @@ describe("transIn", () => {
   });
 
   it("4.3 Single step with END transition → edge to end node exists", () => {
-    const steps = [makeStep("A", [{ condition: null, target: "END" }])];
+    const steps = [makeStep("A", [{ status: "_", target: "END" }])];
     const { edges } = transIn(steps);
     const endEdge = edges.find((e) => e.target === "end");
     expect(endEdge).toBeDefined();
@@ -44,8 +44,8 @@ describe("transIn", () => {
 
   it("4.4 Two steps with default transitions chain", () => {
     const steps = [
-      makeStep("A", [{ condition: null, target: "B" }]),
-      makeStep("B", [{ condition: null, target: "END" }]),
+      makeStep("A", [{ status: "_", target: "B" }]),
+      makeStep("B", [{ status: "_", target: "END" }]),
     ];
     const { edges } = transIn(steps);
     // Should have start→A, A→B, B→end
@@ -53,15 +53,15 @@ describe("transIn", () => {
     const nodeAId = edges.find((e) => e.source === "start")?.target;
     expect(edges.find((e) => e.source === nodeAId && e.target !== "end")).toBeDefined();
     expect(edges.find((e) => e.target === "end")).toBeDefined();
-    // No conditional edges
-    expect(edges.every((e) => e.type !== "conditional")).toBe(true);
+    // No status edges for single default transitions
+    expect(edges.every((e) => e.type !== "status")).toBe(true);
   });
 
-  it("4.5 Step with multiple transitions → conditional edges", () => {
+  it("4.5 Step with multiple transitions → status edges", () => {
     const steps = [
       makeStep("A", [
-        { condition: null, target: "B" },
-        { condition: "x>0", target: "C" },
+        { status: "_", target: "B" },
+        { status: "approved", target: "C" },
       ]),
       makeStep("B", []),
       makeStep("C", []),
@@ -69,23 +69,35 @@ describe("transIn", () => {
     const { edges } = transIn(steps);
     const nodeAId = edges.find((e) => e.source === "start")?.target;
     const outEdges = edges.filter((e) => e.source === nodeAId);
-    expect(outEdges.every((e) => e.type === "conditional")).toBe(true);
-    // else-branch has empty condition
-    const elseEdge = outEdges.find(
-      (e) => (e as { data?: { condition?: string } }).data?.condition === "",
+    expect(outEdges.every((e) => e.type === "status")).toBe(true);
+  });
+
+  it("4.5b Multiple transitions include expected status values", () => {
+    const steps = [
+      makeStep("A", [
+        { status: "_", target: "B" },
+        { status: "approved", target: "C" },
+      ]),
+      makeStep("B", []),
+      makeStep("C", []),
+    ];
+    const { edges } = transIn(steps);
+    const nodeAId = edges.find((e) => e.source === "start")?.target;
+    const outEdges = edges.filter((e) => e.source === nodeAId);
+    const defaultEdge = outEdges.find(
+      (e) => (e as { data?: { status?: string } }).data?.status === "_",
     );
-    expect(elseEdge).toBeDefined();
-    // if-branch has condition
-    const ifEdge = outEdges.find(
-      (e) => (e as { data?: { condition?: string } }).data?.condition === "x>0",
+    expect(defaultEdge).toBeDefined();
+    const approvedEdge = outEdges.find(
+      (e) => (e as { data?: { status?: string } }).data?.status === "approved",
     );
-    expect(ifEdge).toBeDefined();
+    expect(approvedEdge).toBeDefined();
   });
 
   it("4.6 With 1 incoming edge: targetHandle = 'input'; with 2: first gets 'input'", () => {
     const steps = [
-      makeStep("A", [{ condition: null, target: "END" }]),
-      makeStep("B", [{ condition: null, target: "END" }]),
+      makeStep("A", [{ status: "_", target: "END" }]),
+      makeStep("B", [{ status: "_", target: "END" }]),
     ];
     const { edges } = transIn(steps);
     // start→A and start→B; end has 2 incoming edges
@@ -95,8 +107,8 @@ describe("transIn", () => {
 
   it("4.7 Same role name maps to same node id across steps", () => {
     const steps = [
-      makeStep("A", [{ condition: null, target: "B" }]),
-      makeStep("B", [{ condition: null, target: "A" }]),
+      makeStep("A", [{ status: "_", target: "B" }]),
+      makeStep("B", [{ status: "_", target: "A" }]),
     ];
     const { edges } = transIn(steps);
     const aId = edges.find((e) => e.source === "start")?.target;

packages/workflow-dashboard/src/editor/trans/__tests__/validate.test.ts

@@ -33,13 +33,13 @@ function defaultEdge(source: string, target: string): AnyWorkEdge {
   return { id: `${source}-${target}`, source, target, animated: true } as AnyWorkEdge;
 }
 
-function conditionalEdge(source: string, target: string, condition: string): AnyWorkEdge {
+function statusEdge(source: string, target: string, status: string): AnyWorkEdge {
   return {
-    id: `${source}-${target}-cond`,
+    id: `${source}-${target}-status`,
     source,
     target,
-    type: "conditional" as const,
-    data: { condition },
+    type: "status" as const,
+    data: { status },
     animated: true,
   } as AnyWorkEdge;
 }
@@ -76,36 +76,36 @@ describe("validateRoleNodes (via validate)", () => {
     expect(nodeErrors.some((e) => e.message.includes("缺少输出连接"))).toBe(true);
   });
 
-  it("5.3 Empty condition on non-first conditional edge → error", () => {
+  it("5.3 Empty status on status edge → error", () => {
     const n1 = roleNode("n1");
     const n2 = roleNode("n2");
     const n3 = roleNode("n3");
     const nodes = baseNodes(n1, n2, n3);
     const edges = [
       defaultEdge("start", "n1"),
-      conditionalEdge("n1", "n2", ""), // else-branch (index 0) - exempt
-      conditionalEdge("n1", "n3", ""), // if-branch (index 1) - empty condition → error
+      statusEdge("n1", "n2", "_"),
+      statusEdge("n1", "n3", ""), // empty status → error
       defaultEdge("n2", "end"),
       defaultEdge("n3", "end"),
     ];
     const result = validate(nodes, edges);
-    expect(result.errors.some((e) => e.message.includes("条件表达式不能为空"))).toBe(true);
+    expect(result.errors.some((e) => e.message.includes("状态值不能为空"))).toBe(true);
   });
 
-  it("5.4 Mix of conditional and non-conditional outgoing → error", () => {
+  it("5.4 Mix of status and non-status outgoing → error", () => {
     const n1 = roleNode("n1");
     const n2 = roleNode("n2");
     const n3 = roleNode("n3");
     const nodes = baseNodes(n1, n2, n3);
     const edges = [
       defaultEdge("start", "n1"),
-      conditionalEdge("n1", "n2", "x>0"),
+      statusEdge("n1", "n2", "approved"),
       defaultEdge("n1", "n3"), // mix → error
       defaultEdge("n2", "end"),
       defaultEdge("n3", "end"),
     ];
     const result = validate(nodes, edges);
-    expect(result.errors.some((e) => e.message.includes("所有出边必须附带条件"))).toBe(true);
+    expect(result.errors.some((e) => e.message.includes("所有出边必须附带状态"))).toBe(true);
   });
 
   it("5.5 Valid role node (1 in, 1 out default) → no errors for that node", () => {
@@ -118,15 +118,15 @@ describe("validateRoleNodes (via validate)", () => {
     expect(roleErrors).toHaveLength(0);
   });
 
-  it("5.6 Valid role node (1 in, 2 conditional out with conditions) → no errors", () => {
+  it("5.6 Valid role node (1 in, 2 status out with statuses) → no errors", () => {
     const n1 = roleNode("n1");
     const n2 = roleNode("n2");
     const n3 = roleNode("n3");
     const nodes = baseNodes(n1, n2, n3);
     const edges = [
       defaultEdge("start", "n1"),
-      conditionalEdge("n1", "n2", ""), // else-branch
-      conditionalEdge("n1", "n3", "x>0"), // if-branch
+      statusEdge("n1", "n2", "_"),
+      statusEdge("n1", "n3", "approved"),
       defaultEdge("n2", "end"),
       defaultEdge("n3", "end"),
     ];

packages/workflow-dashboard/src/editor/trans/trans-in.ts

@@ -1,4 +1,4 @@
-import type { AnyWorkEdge, AnyWorkNode, ConditionalEdge } from "../type";
+import type { AnyWorkEdge, AnyWorkNode, StatusEdge } from "../type";
 import { uuid } from "../utils";
 import type { WorkFlowStep } from "./type";
 
@@ -9,6 +9,7 @@ type Result = {
 
 const _OUT_HANDLES = ["output-top", "output", "output-bottom"] as const;
 const IN_HANDLES = ["input-top", "input", "input-bottom"] as const;
+const DEFAULT_STATUS = "_";
 
 function assignHandles(
   indices: number[],
@@ -50,8 +51,8 @@ function buildNodeMap(
 function sortTransitions(step: WorkFlowStep): WorkFlowStep["transitions"] {
   if (step.transitions.length <= 1) return step.transitions;
   return [...step.transitions].sort((a, b) => {
-    if (a.condition === null && b.condition !== null) return -1;
-    if (a.condition !== null && b.condition === null) return 1;
+    if (a.status === DEFAULT_STATUS && b.status !== DEFAULT_STATUS) return -1;
+    if (a.status !== DEFAULT_STATUS && b.status === DEFAULT_STATUS) return 1;
     return 0;
   });
 }
@@ -60,32 +61,32 @@ function buildStepEdges(
   sourceId: string,
   step: WorkFlowStep,
   nameToId: Map<string, string>,
-): { elseEdges: AnyWorkEdge[]; ifEdges: AnyWorkEdge[] } {
+): { primaryEdges: AnyWorkEdge[]; statusEdges: AnyWorkEdge[] } {
   const hasMultiple = step.transitions.length > 1;
   const sorted = sortTransitions(step);
-  const elseEdges: AnyWorkEdge[] = [];
-  const ifEdges: AnyWorkEdge[] = [];
+  const primaryEdges: AnyWorkEdge[] = [];
+  const statusEdges: AnyWorkEdge[] = [];
 
   for (let i = 0; i < sorted.length; i++) {
     const t = sorted[i];
     const targetId = nameToId.get(t.target);
     if (!targetId) continue;
     const edgeId = `e-${sourceId}-${targetId}-${i}`;
-    if (hasMultiple || t.condition !== null) {
-      const edge: ConditionalEdge = {
+    if (hasMultiple || t.status !== DEFAULT_STATUS) {
+      const edge: StatusEdge = {
         id: edgeId,
         source: sourceId,
         target: targetId,
         sourceHandle: "output",
         targetHandle: "input",
-        type: "conditional",
-        data: { condition: t.condition ?? "" },
+        type: "status",
+        data: { status: t.status },
         animated: true,
       };
-      if (hasMultiple && i === 0) elseEdges.push(edge);
-      else ifEdges.push(edge);
+      if (hasMultiple && t.status === DEFAULT_STATUS) primaryEdges.push(edge);
+      else statusEdges.push(edge);
     } else {
-      elseEdges.push({
+      primaryEdges.push({
         id: edgeId,
         source: sourceId,
         target: targetId,
@@ -95,23 +96,23 @@ function buildStepEdges(
       });
     }
   }
-  return { elseEdges, ifEdges };
+  return { primaryEdges, statusEdges };
 }
 
 function pushStepEdges(
   edges: AnyWorkEdge[],
-  elseEdges: AnyWorkEdge[],
-  ifEdges: AnyWorkEdge[],
+  primaryEdges: AnyWorkEdge[],
+  statusEdges: AnyWorkEdge[],
   idToOrder: Map<string, number>,
 ): void {
-  for (const e of elseEdges) edges.push({ ...e, sourceHandle: "output" });
-  if (ifEdges.length > 0) {
-    const ifHandles = ["output-top", "output-bottom"] as const;
-    const sorted = [...ifEdges].sort(
+  for (const e of primaryEdges) edges.push({ ...e, sourceHandle: "output" });
+  if (statusEdges.length > 0) {
+    const statusHandles = ["output-top", "output-bottom"] as const;
+    const sorted = [...statusEdges].sort(
       (a, b) => (idToOrder.get(b.target) ?? 0) - (idToOrder.get(a.target) ?? 0),
     );
     for (let i = 0; i < sorted.length; i++) {
-      edges.push({ ...sorted[i], sourceHandle: ifHandles[i % ifHandles.length] });
+      edges.push({ ...sorted[i], sourceHandle: statusHandles[i % statusHandles.length] });
     }
   }
 }
@@ -164,8 +165,8 @@ export function transIn(steps: WorkFlowStep[]): Result {
 
   for (const step of steps) {
     const sourceId = nameToId.get(step.role.name) ?? "";
-    const { elseEdges, ifEdges } = buildStepEdges(sourceId, step, nameToId);
-    pushStepEdges(edges, elseEdges, ifEdges, idToOrder);
+    const { primaryEdges, statusEdges } = buildStepEdges(sourceId, step, nameToId);
+    pushStepEdges(edges, primaryEdges, statusEdges, idToOrder);
   }
 
   assignTargetHandles(edges, idToOrder);

packages/workflow-dashboard/src/editor/trans/trans-out.ts

@@ -1,6 +1,8 @@
-import type { AnyWorkEdge, AnyWorkNode, ConditionalEdge, WorkNode } from "../type";
+import type { AnyWorkEdge, AnyWorkNode, StatusEdge, WorkNode } from "../type";
 import type { WorkFlowStep, WorkFlowTransition } from "./type";
 
+const DEFAULT_STATUS = "_";
+
 export function transOut(nodes: AnyWorkNode[], edges: AnyWorkEdge[]): WorkFlowStep[] {
   const nodeMap = new Map<string, AnyWorkNode>();
   for (const node of nodes) {
@@ -43,7 +45,7 @@ function traverse(
   const roleNode = node as WorkNode<"role">;
   const outEdges = outgoingEdges.get(nodeId) ?? [];
 
-  const transitions: WorkFlowTransition[] = outEdges.map((edge, index) => {
+  const transitions: WorkFlowTransition[] = outEdges.map((edge) => {
     const targetNode = nodeMap.get(edge.target);
     const target =
       edge.target === "end"
@@ -52,13 +54,12 @@ function traverse(
           ? (targetNode as WorkNode<"role">).data.name
           : edge.target;
 
-    let condition: string | null = null;
-    if (edge.type === "conditional") {
-      const isElse = outEdges.length >= 2 && index === 0;
-      condition = isElse ? null : ((edge as ConditionalEdge).data?.condition ?? null);
-    }
+    const status =
+      edge.type === "status"
+        ? ((edge as StatusEdge).data?.status ?? DEFAULT_STATUS)
+        : DEFAULT_STATUS;
 
-    return { target, condition };
+    return { target, status };
   });
 
   const { name, description, identity, prepare, execute, report } = roleNode.data;

packages/workflow-dashboard/src/editor/trans/validate.ts

@@ -1,4 +1,4 @@
-import type { AnyWorkEdge, AnyWorkNode, ConditionalEdge } from "../type";
+import type { AnyWorkEdge, AnyWorkNode, StatusEdge } from "../type";
 
 export type ValidationError = {
   nodeId: string | null;
@@ -91,10 +91,10 @@ function validateEndNode(
   }
 }
 
-function hasEmptyConditionOnIfEdge(conditionalEdges: AnyWorkEdge[]): boolean {
-  return conditionalEdges.slice(1).some((edge) => {
-    const cond = (edge as ConditionalEdge).data?.condition?.trim();
-    return !cond;
+function hasEmptyStatusOnEdge(statusEdges: AnyWorkEdge[]): boolean {
+  return statusEdges.some((edge) => {
+    const status = (edge as StatusEdge).data?.status?.trim();
+    return !status;
   });
 }
 
@@ -113,11 +113,11 @@ function validateRoleNodeEdges(
   }
   if (outEdges.length <= 1) return;
 
-  const conditionalEdges = outEdges.filter((e) => e.type === "conditional");
-  if (conditionalEdges.length !== outEdges.length) {
-    errors.push({ nodeId: node.id, message: "多输出节点的所有出边必须附带条件" });
-  } else if (hasEmptyConditionOnIfEdge(conditionalEdges)) {
-    errors.push({ nodeId: node.id, message: "条件边的条件表达式不能为空" });
+  const statusEdges = outEdges.filter((e) => e.type === "status");
+  if (statusEdges.length !== outEdges.length) {
+    errors.push({ nodeId: node.id, message: "多输出节点的所有出边必须附带状态" });
+  } else if (hasEmptyStatusOnEdge(statusEdges)) {
+    errors.push({ nodeId: node.id, message: "状态边的状态值不能为空" });
   }
 }
 

packages/workflow-dashboard/src/editor/type.ts

@@ -21,9 +21,9 @@ export type WorkNodeType = keyof NodeMap;
 export type WorkNode<T extends WorkNodeType> = Node<NodeMap[T], T>;
 export type AnyWorkNode = WorkNode<"start"> | WorkNode<"end"> | WorkNode<"role">;
 
-export type ConditionalEdgeData = AnyKeyBase & {
-  condition: string;
+export type StatusEdgeData = AnyKeyBase & {
+  status: string;
 };
 
-export type ConditionalEdge = Edge<ConditionalEdgeData, "conditional">;
-export type AnyWorkEdge = ConditionalEdge | Edge;
+export type StatusEdge = Edge<StatusEdgeData, "status">;
+export type AnyWorkEdge = StatusEdge | Edge;

packages/workflow-dashboard/src/pages/editor.tsx

@@ -11,7 +11,7 @@ const DEFAULT_STEPS: WorkFlowSteps = [
       execute: "制定详细的实施计划和步骤分解",
       report: "输出结构化的计划文档，包含步骤列表和预期产出",
     },
-    transitions: [{ target: "developer", condition: null }],
+    transitions: [{ target: "developer", status: "_" }],
   },
   {
     role: {
@@ -22,7 +22,7 @@ const DEFAULT_STEPS: WorkFlowSteps = [
       execute: "编写高质量的代码实现",
       report: "输出变更文件列表和实现摘要",
     },
-    transitions: [{ target: "reviewer", condition: null }],
+    transitions: [{ target: "reviewer", status: "_" }],
   },
   {
     role: {
@@ -34,8 +34,8 @@ const DEFAULT_STEPS: WorkFlowSteps = [
       report: "输出审查结果，包含 approved 状态和评审意见",
     },
     transitions: [
-      { target: "END", condition: null },
-      { target: "developer", condition: "steps[-1].output.approved = false" },
+      { target: "END", status: "approved" },
+      { target: "developer", status: "rejected" },
     ],
   },
 ];

packages/workflow-dashboard/vitest.config.ts

@@ -1,7 +1,6 @@
 import path from "node:path";
 import { defineConfig } from "vitest/config";
 
-// biome-ignore lint/style/noDefaultExport: Vitest loads config from default export.
 export default defineConfig({
   test: {
     environment: "node",

packages/workflow-moderator/README.md

@@ -1,12 +1,12 @@
 # @uncaged/workflow-moderator
 
-JSONata-based graph evaluator — determines the next role or `$END` with zero LLM cost.
+Status-based graph evaluator — determines the next role or `$END` with zero LLM cost.
 
 ## Overview
 
-The moderator (Layer 1) walks the workflow graph from the current role. For each outgoing transition it evaluates an optional JSONata condition against `ModeratorContext` (start prompt + prior step outputs). The first truthy transition wins; its target role and edge prompt are returned. When no transition matches, the workflow ends (`$END`).
+The moderator (Layer 1) performs a status-based map lookup on the workflow graph. Given the last role and its output, it looks up `graph[lastRole][lastOutput.status]` to find the next `Target` (role + prompt template). The prompt is rendered via Mustache with `lastOutput` as the template context. For `$START`, the unit status `_` is used.
 
-**Dependencies:** `@uncaged/workflow-protocol`, `jsonata`
+**Dependencies:** `@uncaged/workflow-protocol`, `mustache`
 
 ## Installation
 
@@ -20,12 +20,13 @@ bun add @uncaged/workflow-moderator
 
 ```typescript
 function evaluate(
-  workflow: WorkflowPayload,
-  context: ModeratorContext,
-): Promise<Result<EvaluateResult, Error>>
+  graph: Record<string, Record<string, Target>>,
+  lastRole: string,
+  lastOutput: Record<string, unknown> & { status: string },
+): Result<EvaluateResult, Error>
 ```
 
-Returns `{ ok: true, value: { role, prompt } }` where `role` is the next role name or `"$END"`, and `prompt` is the edge instruction for the agent.
+Returns `{ ok: true, value: { role, prompt } }` where `role` is the next role name or `"$END"`, and `prompt` is the rendered edge instruction for the agent.
 
 ### Types
 
@@ -42,9 +43,9 @@ The `Result<T, E>` type is local to this package (`{ ok: true; value: T } | { ok
 
 ```typescript
 import { evaluate } from "@uncaged/workflow-moderator";
-import type { ModeratorContext, WorkflowPayload } from "@uncaged/workflow-protocol";
+import type { Target } from "@uncaged/workflow-protocol";
 
-const result = await evaluate(workflow, context);
+const result = evaluate(graph, lastRole, lastOutput);
 if (result.ok && result.value.role !== "$END") {
   console.log(`Next role: ${result.value.role}, prompt: ${result.value.prompt}`);
 }
@@ -55,6 +56,6 @@ if (result.ok && result.value.role !== "$END") {
 ```
 src/
 ├── index.ts      Public exports
-├── evaluate.ts   Graph walk + JSONata condition evaluation
+├── evaluate.ts   Status-based map lookup + Mustache prompt rendering
 └── types.ts      EvaluateResult, Result
 ```

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

@@ -1,312 +1,132 @@
 import { describe, expect, test } from "bun:test";
-import type { ModeratorContext, WorkflowPayload } from "@uncaged/workflow-protocol";
+import type { Target, WorkflowPayload } from "@uncaged/workflow-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",
-      goal: "You are a planning agent.",
-      capabilities: ["planning"],
-      procedure: "Create a step-by-step plan.",
-      output: "Output the plan and steps.",
-      frontmatter: "5GWKR8TN1V3JA",
-    },
-    developer: {
-      description: "Implements code changes",
-      goal: "You are a developer agent.",
-      capabilities: ["coding"],
-      procedure: "Implement the plan.",
-      output: "List files changed and summary.",
-      frontmatter: "8CNWT4KR6D1HV",
-    },
-    reviewer: {
-      description: "Reviews code changes",
-      goal: "You are a code reviewer.",
-      capabilities: ["code-review"],
-      procedure: "Review the implementation.",
-      output: "Approve or reject with comments.",
-      frontmatter: "1VPBG9SM5E7WK",
-    },
+const solveIssueGraph: WorkflowPayload["graph"] = {
+  $START: {
+    _: { role: "planner", prompt: "Start planning from the issue in the task." },
   },
-  conditions: {
-    needsClarification: {
-      description: "Planner requests clarification from user",
-      expression: "$exists($last('planner').needsClarification)",
-    },
-    rejected: {
-      description: "Reviewer rejected the implementation",
-      expression: "$last('reviewer').approved = false",
-    },
+  planner: {
+    _: { role: "developer", prompt: "Implement the plan: {{plan}}" },
   },
-  graph: {
-    $START: [
-      {
-        role: "planner",
-        condition: null,
-        prompt: "Start planning from the issue in the task.",
-      },
-    ],
-    planner: [
-      {
-        role: "developer",
-        condition: "needsClarification",
-        prompt: "Clarification is needed; hand off to developer.",
-      },
-      { role: "$END", condition: null, prompt: "Planning complete; end workflow." },
-    ],
-    developer: [
-      {
-        role: "reviewer",
-        condition: null,
-        prompt: "Implementation done; send to reviewer.",
-      },
-    ],
-    reviewer: [
-      {
-        role: "developer",
-        condition: "rejected",
-        prompt: "Reviewer rejected; return to developer.",
-      },
-      { role: "$END", condition: null, prompt: "Review passed; end workflow." },
-    ],
+  developer: {
+    _: { role: "reviewer", prompt: "Review the changes: {{summary}}" },
+  },
+  reviewer: {
+    approved: { role: "$END", prompt: "Done." },
+    rejected: { role: "developer", prompt: "Fix: {{comments}}" },
   },
 };
 
-function makeContext(steps: ModeratorContext["steps"]): ModeratorContext {
-  return {
-    start: {
-      workflow: "4KNM2PXR3B1QW",
-      prompt: "Fix the login bug",
-    },
-    steps,
-  };
-}
-
 describe("evaluate", () => {
-  test("$START → first role (fallback)", async () => {
-    const result = await evaluate(solveIssueWorkflow, makeContext([]));
+  test("$START → first role (unit status _)", () => {
+    const result = evaluate(solveIssueGraph, "$START", { $status: "_" });
     expect(result).toEqual({
       ok: true,
       value: { role: "planner", prompt: "Start planning from the issue in the task." },
     });
   });
 
-  test("condition match (rejected → developer)", async () => {
-    const context = makeContext([
-      {
-        role: "reviewer",
-        output: { approved: false },
-        detail: "2MXBG6PN4A8JR",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(solveIssueWorkflow, context);
+  test("status-based routing (reviewer rejected → developer)", () => {
+    const result = evaluate(solveIssueGraph, "reviewer", {
+      $status: "rejected",
+      comments: "missing tests",
+    });
     expect(result).toEqual({
       ok: true,
-      value: { role: "developer", prompt: "Reviewer rejected; return to developer." },
+      value: { role: "developer", prompt: "Fix: missing tests" },
     });
   });
 
-  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);
+  test("status-based routing (reviewer approved → $END)", () => {
+    const result = evaluate(solveIssueGraph, "reviewer", { $status: "approved" });
     expect(result).toEqual({
       ok: true,
-      value: { role: "$END", prompt: "Review passed; end workflow." },
+      value: { role: "$END", prompt: "Done." },
     });
   });
 
-  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);
+  test("missing role in graph → error", () => {
+    const result = evaluate(solveIssueGraph, "unknown-role", { $status: "_" });
     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);
+  test("missing status in graph → error", () => {
+    const result = evaluate(solveIssueGraph, "reviewer", { $status: "pending" });
+    expect(result.ok).toBe(false);
+    if (!result.ok) {
+      expect(result.error.message).toBe('no transition for role "reviewer" with status "pending"');
+    }
+  });
+
+  test("mustache template rendering with simple fields", () => {
+    const result = evaluate(solveIssueGraph, "planner", {
+      $status: "_",
+      plan: "Add auth middleware",
+    });
     expect(result).toEqual({
       ok: true,
-      value: { role: "developer", prompt: "Clarification is needed; hand off to developer." },
+      value: { role: "developer", prompt: "Implement the plan: Add auth middleware" },
     });
   });
 
-  test("$last returns most recent matching role's frontmatter", async () => {
-    const workflow: WorkflowPayload = {
-      ...solveIssueWorkflow,
-      conditions: {
-        devFailed: {
-          description: "Developer failed",
-          expression: "$last('developer').status = 'failed'",
-        },
-      },
-      graph: {
-        $START: [
-          {
-            role: "developer",
-            condition: null,
-            prompt: "Begin development.",
-          },
-        ],
-        developer: [
-          { role: "$END", condition: "devFailed", prompt: "Development failed; end." },
-          {
-            role: "reviewer",
-            condition: null,
-            prompt: "Development succeeded; review.",
-          },
-        ],
-      },
-    };
-    const context = makeContext([
-      {
-        role: "developer",
-        output: { status: "done" },
-        detail: "1VPBG9SM5E7WK",
-        agent: "uwf-hermes",
-      },
-      {
-        role: "reviewer",
-        output: { approved: false },
-        detail: "2MXBG6PN4A8JR",
-        agent: "uwf-hermes",
-      },
-      {
-        role: "developer",
-        output: { status: "failed" },
-        detail: "3QNTH7WK8D2PA",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(workflow, context);
+  test("mustache does not HTML-escape prompt content", () => {
+    const result = evaluate(solveIssueGraph, "reviewer", {
+      $status: "rejected",
+      comments: 'use <T> & "Result<T, E>" types',
+    });
     expect(result).toEqual({
       ok: true,
-      value: { role: "$END", prompt: "Development failed; end." },
+      value: { role: "developer", prompt: 'Fix: use <T> & "Result<T, E>" types' },
     });
   });
 
-  test("$first returns earliest matching role's frontmatter", async () => {
-    const workflow: WorkflowPayload = {
-      ...solveIssueWorkflow,
-      conditions: {
-        firstPlanReady: {
-          description: "First planner run was ready",
-          expression: "$first('planner').status = 'ready'",
-        },
-      },
-      graph: {
-        $START: [
-          {
-            role: "planner",
-            condition: null,
-            prompt: "Begin planning.",
-          },
-        ],
-        planner: [
-          { role: "$END", condition: "firstPlanReady", prompt: "First plan was ready; end." },
-          {
-            role: "developer",
-            condition: null,
-            prompt: "Plan not ready on first pass; implement.",
-          },
-        ],
+  test("triple mustache also works for unescaped output", () => {
+    const graph: Record<string, Record<string, Target>> = {
+      reviewer: {
+        _: { role: "developer", prompt: "Fix: {{{comments}}}" },
       },
     };
-    const context = makeContext([
-      {
-        role: "planner",
-        output: { status: "ready", plan: "ABC123" },
-        detail: "7BQST3VW9F2MA",
-        agent: "uwf-hermes",
-      },
-      {
-        role: "developer",
-        output: { status: "done" },
-        detail: "1VPBG9SM5E7WK",
-        agent: "uwf-hermes",
-      },
-      {
-        role: "planner",
-        output: { status: "revised", plan: "DEF456" },
-        detail: "4RNMK6PX8B3WQ",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(workflow, context);
+    const result = evaluate(graph, "reviewer", {
+      $status: "_",
+      comments: "<script>alert(1)</script>",
+    });
     expect(result).toEqual({
       ok: true,
-      value: { role: "$END", prompt: "First plan was ready; end." },
+      value: { role: "developer", prompt: "Fix: <script>alert(1)</script>" },
     });
   });
 
-  test("$last returns undefined for unmatched role", async () => {
-    const workflow: WorkflowPayload = {
-      ...solveIssueWorkflow,
-      conditions: {
-        hasReviewer: {
-          description: "Reviewer has run",
-          expression: "$exists($last('reviewer'))",
-        },
-      },
-      graph: {
-        $START: [
-          {
-            role: "planner",
-            condition: null,
-            prompt: "Begin planning.",
-          },
-        ],
-        planner: [
-          { role: "$END", condition: "hasReviewer", prompt: "Reviewer already ran; end." },
-          {
-            role: "developer",
-            condition: null,
-            prompt: "No reviewer yet; implement.",
-          },
-        ],
-      },
-    };
-    const context = makeContext([
-      {
-        role: "planner",
-        output: { status: "ready" },
-        detail: "7BQST3VW9F2MA",
-        agent: "uwf-hermes",
-      },
-    ]);
-    const result = await evaluate(workflow, context);
-    // no reviewer step → $exists returns false → fallback to developer
+  test("missing $status defaults to _ (unit routing)", () => {
+    const result = evaluate(solveIssueGraph, "planner", {
+      plan: "Add auth middleware",
+    });
     expect(result).toEqual({
       ok: true,
-      value: { role: "developer", prompt: "No reviewer yet; implement." },
+      value: { role: "developer", prompt: "Implement the plan: Add auth middleware" },
+    });
+  });
+
+  test("mustache template with nested object paths", () => {
+    const graph: Record<string, Record<string, Target>> = {
+      reviewer: {
+        _: {
+          role: "developer",
+          prompt: "Address: {{review.comments}}",
+        },
+      },
+    };
+    const result = evaluate(graph, "reviewer", {
+      $status: "_",
+      review: { comments: "refactor the handler" },
+    });
+    expect(result).toEqual({
+      ok: true,
+      value: { role: "developer", prompt: "Address: refactor the handler" },
     });
   });
 });

packages/workflow-moderator/package.json

@@ -19,9 +19,10 @@
   },
   "dependencies": {
     "@uncaged/workflow-protocol": "workspace:^",
-    "jsonata": "^1.8.7"
+    "mustache": "^4.2.0"
   },
   "devDependencies": {
+    "@types/mustache": "^4.2.6",
     "typescript": "^5.8.3"
   },
   "publishConfig": {

packages/workflow-moderator/src/evaluate.ts

@@ -1,65 +1,49 @@
-import type { ModeratorContext, WorkflowPayload } from "@uncaged/workflow-protocol";
-import jsonata from "jsonata";
+import type { Target } from "@uncaged/workflow-protocol";
+import mustache from "mustache";
 
 import type { EvaluateResult, Result } from "./types.js";
 
+// Disable HTML escaping — prompts are plain text, not HTML.
+mustache.escape = (text: string) => text;
+
 const START_ROLE = "$START";
+const UNIT_STATUS = "_";
 
-function isTruthy(value: unknown): boolean {
-  if (value === null || value === undefined) {
-    return false;
-  }
-  if (typeof value === "boolean") {
-    return value;
-  }
-  if (typeof value === "number") {
-    return value !== 0 && !Number.isNaN(value);
-  }
-  if (typeof value === "string") {
-    return value.length > 0;
-  }
-  return true;
-}
+type LastOutput = Record<string, unknown>;
 
-function findByRole(
-  steps: ModeratorContext["steps"],
-  role: string,
-  direction: "first" | "last",
-): unknown {
-  if (direction === "last") {
-    for (let i = steps.length - 1; i >= 0; i--) {
-      if (steps[i].role === role) {
-        return steps[i].output;
-      }
-    }
-  } else {
-    for (const step of steps) {
-      if (step.role === role) {
-        return step.output;
-      }
-    }
-  }
-  return undefined;
-}
+const STATUS_KEY = "$status";
+
+export function evaluate(
+  graph: Record<string, Record<string, Target>>,
+  lastRole: string,
+  lastOutput: LastOutput,
+): Result<EvaluateResult, Error> {
+  const status =
+    lastRole === START_ROLE
+      ? UNIT_STATUS
+      : typeof lastOutput[STATUS_KEY] === "string"
+        ? (lastOutput[STATUS_KEY] as string)
+        : UNIT_STATUS;
+
+  const roleTargets = graph[lastRole];
+  if (roleTargets === undefined) {
+    return {
+      ok: false,
+      error: new Error(`no transitions defined for role "${lastRole}"`),
+    };
+  }
+
+  const target = roleTargets[status];
+  if (target === undefined) {
+    return {
+      ok: false,
+      error: new Error(`no transition for role "${lastRole}" with status "${status}"`),
+    };
+  }
 
-async function evaluateJsonata(
-  expression: string,
-  context: ModeratorContext,
-): Promise<Result<unknown, Error>> {
   try {
-    const expr = jsonata(expression);
-    expr.registerFunction(
-      "first",
-      (role: string) => findByRole(context.steps, role, "first"),
-      "<s:x>",
-    );
-    expr.registerFunction(
-      "last",
-      (role: string) => findByRole(context.steps, role, "last"),
-      "<s:x>",
-    );
-    const result = await expr.evaluate(context);
-    return { ok: true, value: result };
+    const prompt = mustache.render(target.prompt, lastOutput);
+    return { ok: true, value: { role: target.role, prompt } };
   } catch (error) {
     return {
       ok: false,
@@ -67,51 +51,3 @@ async function evaluateJsonata(
     };
   }
 }
-
-function currentRole(context: ModeratorContext): string {
-  if (context.steps.length === 0) {
-    return START_ROLE;
-  }
-  return context.steps[context.steps.length - 1].role;
-}
-
-export async function evaluate(
-  workflow: WorkflowPayload,
-  context: ModeratorContext,
-): Promise<Result<EvaluateResult, Error>> {
-  const role = currentRole(context);
-  const transitions = workflow.graph[role];
-  if (transitions === undefined) {
-    return {
-      ok: false,
-      error: new Error(`no transitions defined for role "${role}"`),
-    };
-  }
-
-  for (const transition of transitions) {
-    if (transition.condition === null) {
-      return { ok: true, value: { role: transition.role, prompt: transition.prompt } };
-    }
-
-    const conditionDef = workflow.conditions[transition.condition];
-    if (conditionDef === undefined) {
-      return {
-        ok: false,
-        error: new Error(`unknown condition "${transition.condition}"`),
-      };
-    }
-
-    const evalResult = await evaluateJsonata(conditionDef.expression, context);
-    if (!evalResult.ok) {
-      return evalResult;
-    }
-    if (isTruthy(evalResult.value)) {
-      return { ok: true, value: { role: transition.role, prompt: transition.prompt } };
-    }
-  }
-
-  return {
-    ok: false,
-    error: new Error(`no transition matched for role "${role}"`),
-  };
-}

packages/workflow-protocol/README.md

@@ -47,23 +47,16 @@ type RoleDefinition = {
   frontmatter: CasRef;
 };
 
-type Transition = {
+type Target = {
   role: string;
-  condition: string | null;
   prompt: string;
 };
 
-type ConditionDefinition = {
-  description: string;
-  expression: string;
-};
-
 type WorkflowPayload = {
   name: string;
   description: string;
   roles: Record<string, RoleDefinition>;
-  conditions: Record<string, ConditionDefinition>;
-  graph: Record<string, Transition[]>;
+  graph: Record<string, Record<string, Target>>;
 };
 ```
 
@@ -92,7 +85,7 @@ type StepNodePayload = StepRecord & {
 ### Moderator context
 
 ```typescript
-type StepContext = Omit<StepRecord, "output"> & { output: unknown };
+type StepContext = Omit<StepRecord, "output"> & { output: unknown; content: string | null };
 
 type ModeratorContext = {
   start: StartNodePayload;

packages/workflow-protocol/src/index.ts

@@ -7,7 +7,6 @@ export type {
   AgentAlias,
   AgentConfig,
   CasRef,
-  ConditionDefinition,
   ModelAlias,
   ModelConfig,
   ModeratorContext,
@@ -26,12 +25,12 @@ export type {
   StepNodePayload,
   StepOutput,
   StepRecord,
+  Target,
   ThreadForkOutput,
   ThreadId,
   ThreadListItem,
   ThreadStepsOutput,
   ThreadsIndex,
-  Transition,
   WorkflowConfig,
   WorkflowName,
   WorkflowPayload,

packages/workflow-protocol/src/schemas.ts

@@ -14,22 +14,11 @@ const ROLE_DEFINITION: JSONSchema = {
   additionalProperties: false,
 };
 
-const CONDITION_DEFINITION: JSONSchema = {
+const TARGET: JSONSchema = {
   type: "object",
-  required: ["description", "expression"],
-  properties: {
-    description: { type: "string" },
-    expression: { type: "string" },
-  },
-  additionalProperties: false,
-};
-
-const TRANSITION: JSONSchema = {
-  type: "object",
-  required: ["role", "condition", "prompt"],
+  required: ["role", "prompt"],
   properties: {
     role: { type: "string" },
-    condition: { anyOf: [{ type: "string" }, { type: "null" }] },
     prompt: { type: "string" },
   },
   additionalProperties: false,
@@ -38,7 +27,7 @@ const TRANSITION: JSONSchema = {
 export const WORKFLOW_SCHEMA: JSONSchema = {
   title: "Workflow",
   type: "object",
-  required: ["name", "description", "roles", "conditions", "graph"],
+  required: ["name", "description", "roles", "graph"],
   properties: {
     name: { type: "string" },
     description: { type: "string" },
@@ -46,15 +35,11 @@ export const WORKFLOW_SCHEMA: JSONSchema = {
       type: "object",
       additionalProperties: ROLE_DEFINITION,
     },
-    conditions: {
-      type: "object",
-      additionalProperties: CONDITION_DEFINITION,
-    },
     graph: {
       type: "object",
       additionalProperties: {
-        type: "array",
-        items: TRANSITION,
+        type: "object",
+        additionalProperties: TARGET,
       },
     },
   },

packages/workflow-protocol/src/types.ts

@@ -27,23 +27,16 @@ export type RoleDefinition = {
   frontmatter: CasRef;
 };
 
-export type Transition = {
+export type Target = {
   role: string;
-  condition: string | null;
   prompt: string;
 };
 
-export type ConditionDefinition = {
-  description: string;
-  expression: string;
-};
-
 export type WorkflowPayload = {
   name: string;
   description: string;
   roles: Record<string, RoleDefinition>;
-  conditions: Record<string, ConditionDefinition>;
-  graph: Record<string, Transition[]>;
+  graph: Record<string, Record<string, Target>>;
 };
 
 // ── 4.3 Thread 节点 ─────────────────────────────────────────────────
@@ -63,6 +56,7 @@ export type StepNodePayload = StepRecord & {
 /** JSONata 上下文中的 step — output 被展开 */
 export type StepContext = Omit<StepRecord, "output"> & {
   output: unknown;
+  content: string | null;
 };
 
 export type ModeratorContext = {

packages/workflow-util-agent/src/build-agent-prompt.ts

@@ -0,0 +1,64 @@
+import type { AgentContext } from "@uncaged/workflow-runtime";
+
+/** Max characters of step content to include in the prompt. */
+const CONTENT_QUOTA = 16_000;
+
+/** Builds the full agent prompt: system instructions plus summarized thread history. */
+export async function buildAgentPrompt(ctx: AgentContext): Promise<string> {
+  const lines: string[] = [];
+  lines.push(ctx.currentRole.systemPrompt);
+  lines.push("");
+  lines.push("## Task");
+  lines.push(ctx.start.content);
+
+  const { steps } = ctx;
+  if (steps.length === 0) {
+    return lines.join("\n");
+  }
+
+  if (steps.length === 1) {
+    const s = steps[0];
+    lines.push("");
+    lines.push(`## Step: ${s.role}`);
+    lines.push("");
+    lines.push(`Meta: ${JSON.stringify(s.meta)}`);
+    appendContent(lines, s.content);
+  } else {
+    lines.push("");
+    lines.push("## Previous Steps");
+    for (let i = 0; i < steps.length - 1; i++) {
+      const s = steps[i];
+      lines.push("");
+      lines.push(`### Step ${i + 1}: ${s.role}`);
+      lines.push(`Summary: ${JSON.stringify(s.meta)}`);
+    }
+    const last = steps[steps.length - 1];
+    lines.push("");
+    lines.push(`## Latest Step: ${last.role}`);
+    lines.push("");
+    lines.push(`Meta: ${JSON.stringify(last.meta)}`);
+    appendContent(lines, last.content);
+  }
+
+  lines.push("");
+  lines.push("## Tools");
+  lines.push(
+    `Use \`uncaged-workflow thread ${ctx.threadId}\` to read full details of any previous step.`,
+  );
+
+  return lines.join("\n");
+}
+
+function appendContent(lines: string[], content: string | null | undefined): void {
+  if (content === null || content === undefined || content.trim() === "") {
+    return;
+  }
+  const truncated =
+    content.length > CONTENT_QUOTA
+      ? `${content.slice(0, CONTENT_QUOTA)}\n... (truncated)`
+      : content;
+  lines.push("");
+  lines.push("<output>");
+  lines.push(truncated);
+  lines.push("</output>");
+}

packages/workflow-util/README.md

@@ -23,6 +23,7 @@ All exports come from `src/index.ts`.
 ```typescript
 function encodeUint64AsCrockford(value: bigint): string
 function generateUlid(nowMs: number): string
+function extractUlidTimestamp(ulid: string): number | null
 ```
 
 ### Logging

packages/workflow-util/src/__tests__/ulid-timestamp.test.ts

@@ -0,0 +1,55 @@
+import { describe, expect, it } from "bun:test";
+import { extractUlidTimestamp, generateUlid } from "../ulid.js";
+
+describe("extractUlidTimestamp", () => {
+  it("should extract correct timestamp from ULID", () => {
+    const knownTimestamp = Date.UTC(2026, 4, 20, 0, 0, 0);
+    const ulid = generateUlid(knownTimestamp);
+    const extracted = extractUlidTimestamp(ulid);
+    expect(extracted).toBe(knownTimestamp);
+  });
+
+  it("should handle epoch timestamp (timestamp 0)", () => {
+    const ulid = generateUlid(0);
+    const extracted = extractUlidTimestamp(ulid);
+    expect(extracted).toBe(0);
+  });
+
+  it("should handle recent timestamps", () => {
+    const recentTimestamp = Date.now();
+    const ulid = generateUlid(recentTimestamp);
+    const extracted = extractUlidTimestamp(ulid);
+    expect(extracted).toBe(recentTimestamp);
+  });
+
+  it("should handle max 48-bit timestamp", () => {
+    const maxTimestamp = 2 ** 48 - 1;
+    const ulid = generateUlid(maxTimestamp);
+    const extracted = extractUlidTimestamp(ulid);
+    expect(extracted).toBe(maxTimestamp);
+  });
+
+  it("should return null for invalid ULID length", () => {
+    expect(extractUlidTimestamp("")).toBe(null);
+    expect(extractUlidTimestamp("TOOSHORT")).toBe(null);
+    expect(extractUlidTimestamp("TOOLONGAAAAAAAAAAAAAAAAAA")).toBe(null);
+  });
+
+  it("should return null for invalid Crockford Base32 characters", () => {
+    expect(extractUlidTimestamp("INVALID!@#$%^&CHARACTERS")).toBe(null);
+  });
+
+  it("should extract timestamps from multiple ULIDs correctly", () => {
+    const timestamps = [
+      Date.UTC(2020, 0, 1, 0, 0, 0),
+      Date.UTC(2023, 5, 15, 12, 30, 45),
+      Date.UTC(2026, 11, 31, 23, 59, 59),
+    ];
+
+    for (const ts of timestamps) {
+      const ulid = generateUlid(ts);
+      const extracted = extractUlidTimestamp(ulid);
+      expect(extracted).toBe(ts);
+    }
+  });
+});

packages/workflow-util/src/cli-reference.ts

@@ -15,7 +15,7 @@ uwf setup --provider <name> --base-url <url> \\
 ## Workflow Commands
 
 \`\`\`
-uwf workflow put <file>           # register a workflow from YAML file
+uwf workflow add <file>           # register a workflow from YAML file
 uwf workflow show <id>            # show workflow by name or CAS hash
 uwf workflow list                 # list all registered workflows
 \`\`\`
@@ -24,20 +24,27 @@ uwf workflow list                 # list all registered workflows
 
 \`\`\`
 uwf thread start <workflow> -p <prompt>           # create a thread (no execution)
-uwf thread step <thread-id>                       # execute one moderator→agent→extract cycle
+uwf thread exec <thread-id>                       # execute one moderator→agent→extract cycle
                [--agent <cmd>]                    # override agent command
                [-c, --count <number>]             # run multiple steps (default: 1)
+               [--background]                     # run in background
 uwf thread show <thread-id>                       # show thread head pointer
-uwf thread list                                   # list active threads
-               [--all]                            # include archived threads
-uwf thread kill <thread-id>                       # terminate and archive a thread
-uwf thread steps <thread-id>                      # list all steps in a thread
+uwf thread list                                   # list threads
+               [--status <status>]                # filter: idle, running, or completed
 uwf thread read <thread-id>                       # render thread context as markdown
                [--quota <chars>]                  # max output characters (default 32000)
                [--before <step-hash>]             # load steps before this hash (exclusive)
                [--start]                          # include start step in output
-uwf thread fork <step-hash>                       # fork a thread from a specific step
-uwf thread step-details <step-hash>               # dump full detail node of a step as YAML
+uwf thread stop <thread-id>                       # stop background execution (keep thread active)
+uwf thread cancel <thread-id>                     # cancel thread (stop + move to history)
+\`\`\`
+
+## Step Commands
+
+\`\`\`
+uwf step list <thread-id>        # list all steps in a thread
+uwf step show <step-hash>        # show details of a specific step
+uwf step fork <step-hash>        # fork a thread from a specific step
 \`\`\`
 
 ## CAS Commands
@@ -78,10 +85,9 @@ uwf -V, --version                 # print version
 ## Key Concepts
 
 - **Workflow**: YAML definition with roles, conditions, and a routing graph; stored as a CAS node identified by its XXH64 hash.
-- **Thread**: A single workflow execution (ULID). State is an immutable CAS chain; active threads are indexed in \`threads.yaml\`.
-- **Step**: One moderator→agent→extract cycle. Run \`uwf thread step\` repeatedly until \`$END\`.
-- **CAS**: Content-Addressed Storage — all nodes are immutable and identified by hash.
-- **Role**: Named actor with goal, capabilities, procedure, output, and frontmatter schema; the moderator routes between roles.
-- **Edge Prompt**: Required instruction on each graph edge — the moderator's dispatch message to the agent.
+- **Thread**: A running instance of a workflow; points to a chain of CAS step nodes.
+- **Step**: One moderator→agent→extract cycle; stored as a CAS node with output + detail refs.
+- **Turn**: Agent-internal interaction (within a single step); stored per-turn in the detail node.
+- **CAS**: Content-addressable store; every artifact (workflows, steps, details, turns) is hashed.
 `;
 }

packages/workflow-util/src/index.ts

@@ -24,4 +24,4 @@ export { normalizeRefsField } from "./refs-field.js";
 export { err, ok } from "./result.js";
 export { getDefaultWorkflowStorageRoot, getGlobalCasDir } from "./storage-root.js";
 export type { LogFn, Result } from "./types.js";
-export { generateUlid } from "./ulid.js";
+export { extractUlidTimestamp, generateUlid } from "./ulid.js";

packages/workflow-util/src/ulid.ts

@@ -1,4 +1,4 @@
-import { encodeCrockfordBase32Bits } from "./base32.js";
+import { decodeCrockfordBase32Bits, encodeCrockfordBase32Bits } from "./base32.js";
 
 const ULID_TIME_BITS = 48;
 const ULID_RANDOM_BITS = 80;
@@ -26,3 +26,19 @@ export function generateUlid(nowMs: number): string {
   const payload = (time << BigInt(ULID_RANDOM_BITS)) | rand;
   return encodeCrockfordBase32Bits(payload, ULID_TIME_BITS + ULID_RANDOM_BITS);
 }
+
+/**
+ * Extract the timestamp (in milliseconds) from a ULID string.
+ * Returns null if the ULID is invalid.
+ */
+export function extractUlidTimestamp(ulid: string): number | null {
+  if (ulid.length !== 26) {
+    return null;
+  }
+  const timestampPart = ulid.slice(0, 10);
+  const decoded = decodeCrockfordBase32Bits(timestampPart, ULID_TIME_BITS);
+  if (!decoded.ok) {
+    return null;
+  }
+  return Number(decoded.value);
+}