refactor: split e2e-walkthrough into 6 roles with dedicated cleanup

- bootstrap: Docker + bun install + bun link + verify
- config-and-registry: config get/set/list + workflow add/show/list
- thread-ops: thread start/list/show/exec
- inspect: step list/show + thread read + CAS get/has/refs/walk
- cancel-and-fork: cancel + fork + logs
- cleanup: docker rm -f (all fail paths route here)

小橘 🍊

.workflows/e2e-walkthrough.yaml

@@ -8,8 +8,7 @@ roles:
       - docker
       - shell
     procedure: |
-      1. Create a temp dir for this E2E run: `E2E_DIR=$(mktemp -d /tmp/uwf-e2e-XXXXXX)`
+      1. Start a Docker container with isolated storage:
-      2. Start a Docker container with isolated storage:
          ```
          docker run -d --name uwf-e2e-$$ \
            -v $HOME:$HOME \
@@ -19,7 +18,7 @@ roles:
            node:22-bookworm \
            sleep infinity
          ```
-      3. Inside the container, install bun, install deps, then `bun link` all packages
+      2. Inside the container, install bun, install deps, then `bun link` all packages
          so that `uwf`, `uwf-hermes`, `uwf-builtin` are on PATH (from source):
          ```
          docker exec uwf-e2e-$$ bash -c '
@@ -39,13 +38,13 @@ roles:
            cd packages/workflow-agent-builtin && bun link && cd ../..
          '
          ```
-      4. Verify all three commands are available inside the container:
+      3. Verify all three commands are available inside the container:
          ```
          docker exec uwf-e2e-$$ bash -c 'export PATH="$HOME/.bun/bin:$PATH" && uwf --version'
          docker exec uwf-e2e-$$ bash -c 'export PATH="$HOME/.bun/bin:$PATH" && uwf-hermes --help'
          docker exec uwf-e2e-$$ bash -c 'export PATH="$HOME/.bun/bin:$PATH" && uwf-builtin --help'
          ```
-      5. Copy host config if it exists:
+      4. Copy host config if it exists:
          ```
          docker exec uwf-e2e-$$ bash -c '
            if [ -f $HOME/.uncaged/workflow/config.yaml ]; then
@@ -68,8 +67,8 @@ roles:
             error: { type: string }
           required: [$status, error]
 
-  setup-and-registry:
+  config-and-registry:
-    description: "Validate uwf setup, config commands, and workflow registration"
+    description: "Validate uwf config commands and workflow registration"
     goal: "You are an E2E test runner. Validate uwf config operations and workflow registration inside the Docker container."
     capabilities:
       - docker
@@ -82,12 +81,12 @@ roles:
         export PATH="$HOME/.bun/bin:$PATH"
         export UNCAGED_WORKFLOW_STORAGE_ROOT=/tmp/uwf-e2e-storage
 
-      Phase 2 — Config:
+      Config tests:
       1. `uwf config list` — verify it returns valid JSON
       2. `uwf config set models.test.name test-model` — set a test key
       3. `uwf config get models.test.name` — verify it returns "test-model"
 
-      Phase 3 — Workflow registration:
+      Workflow registration tests:
       4. `uwf workflow add ~/repos/workflow/examples/solve-issue.yaml` — register workflow
       5. Verify the output contains a hash
       6. `uwf workflow list` — verify non-empty array
@@ -95,116 +94,176 @@ roles:
       8. `uwf workflow show <name>` — verify it returns roles
 
       Report all test results with pass/fail counts.
-    output: "Report test results. Set $status to pass (with workflowName and containerName) or fail (with error and partial results)."
+    output: "Report test results. Set $status to pass (with workflowName and containerName) or fail."
     frontmatter:
       oneOf:
         - properties:
             $status: { const: "pass" }
             workflowName: { type: string }
             containerName: { type: string }
-            testsPassed: { type: number }
           required: [$status, workflowName, containerName]
         - properties:
             $status: { const: "fail" }
             error: { type: string }
-          required: [$status, error]
+            containerName: { type: string }
+          required: [$status, error, containerName]
 
-  thread-lifecycle:
+  thread-ops:
-    description: "Test thread start, exec, read, step list/show, and CAS operations"
+    description: "Test thread start, list, show, and exec"
-    goal: "You are an E2E test runner. Validate the full thread lifecycle and CAS operations."
+    goal: "You are an E2E test runner. Validate thread creation and execution inside the Docker container."
     capabilities:
       - docker
       - shell
     procedure: |
       Use the container (containerName) and workflow (workflowName) from your prompt.
       All commands via: `docker exec <containerName> bash -c '...'`
-      Set env: PATH, UNCAGED_WORKFLOW_STORAGE_ROOT=/tmp/uwf-e2e-storage
+      Set env: PATH="$HOME/.bun/bin:$PATH" UNCAGED_WORKFLOW_STORAGE_ROOT=/tmp/uwf-e2e-storage
 
-      Phase 4 — Thread lifecycle:
+      1. `uwf thread start <workflowName> -p 'E2E test: what is 2+2?'` — capture thread ID from JSON output
-      1. `uwf thread start <workflowName> -p 'E2E test: what is 2+2?'` — capture thread ID
+      2. `uwf thread list` — verify the thread appears in the list
-      2. `uwf thread list` — verify thread appears
       3. `uwf thread show <threadId>` — verify head pointer exists
       4. `uwf thread exec <threadId> --agent uwf-builtin` — execute one step
-      5. Verify exec returns step info with head
+      5. Verify exec returns JSON with a head field
 
-      Phase 5 — Read & Inspect:
+      Report results. Pass threadId and containerName forward.
-      6. `uwf step list <threadId>` — verify steps exist (length > 1)
+    output: "Report test results. Set $status to pass (with threadId, workflowName, containerName) or fail."
-      7. Capture last step hash
+    frontmatter:
-      8. `uwf step show <lastStepHash>` — verify it returns role
+      oneOf:
-      9. `uwf thread read <threadId>` — verify non-empty output
+        - properties:
-      10. `uwf cas get <lastStepHash>` — verify returns type
+            $status: { const: "pass" }
-      11. `uwf cas has <lastStepHash>` — verify exists
+            threadId: { type: string }
-      12. `uwf cas refs <lastStepHash>` — list refs
+            workflowName: { type: string }
-      13. `uwf cas walk <lastStepHash>` — verify returns nodes
+            containerName: { type: string }
+          required: [$status, threadId, workflowName, containerName]
+        - properties:
+            $status: { const: "fail" }
+            error: { type: string }
+            containerName: { type: string }
+          required: [$status, error, containerName]
 
-      Report all results. Pass the threadId and lastStepHash forward.
+  inspect:
-    output: "Report test results. Set $status to pass (with threadId, lastStepHash, containerName) or fail."
+    description: "Test step list/show, thread read, and CAS operations"
+    goal: "You are an E2E test runner. Validate read and inspect operations inside the Docker container."
+    capabilities:
+      - docker
+      - shell
+    procedure: |
+      Use the container (containerName) and threadId from your prompt.
+      All commands via: `docker exec <containerName> bash -c '...'`
+      Set env: PATH="$HOME/.bun/bin:$PATH" UNCAGED_WORKFLOW_STORAGE_ROOT=/tmp/uwf-e2e-storage
+
+      Step inspection:
+      1. `uwf step list <threadId>` — verify steps array has length > 1
+      2. Capture the last step hash from the output
+      3. `uwf step show <lastStepHash>` — verify it returns a role field
+
+      Thread read:
+      4. `uwf thread read <threadId>` — verify non-empty output
+
+      CAS operations:
+      5. `uwf cas get <lastStepHash>` — verify returns a type field
+      6. `uwf cas has <lastStepHash>` — verify exits 0
+      7. `uwf cas refs <lastStepHash>` — list refs (may be empty)
+      8. `uwf cas walk <lastStepHash>` — verify returns non-empty array
+
+      Report results. Pass threadId, lastStepHash, workflowName, containerName forward.
+    output: "Report test results. Set $status to pass (with threadId, lastStepHash, workflowName, containerName) or fail."
     frontmatter:
       oneOf:
         - properties:
             $status: { const: "pass" }
             threadId: { type: string }
             lastStepHash: { type: string }
+            workflowName: { type: string }
             containerName: { type: string }
-            testsPassed: { type: number }
+          required: [$status, threadId, lastStepHash, workflowName, containerName]
-          required: [$status, threadId, lastStepHash, containerName]
         - properties:
             $status: { const: "fail" }
             error: { type: string }
-          required: [$status, error]
+            containerName: { type: string }
+          required: [$status, error, containerName]
 
-  cancel-fork-and-logs:
+  cancel-and-fork:
     description: "Test thread cancel, step fork, and log inspection"
-    goal: "You are an E2E test runner. Validate cancel, fork, and log operations."
+    goal: "You are an E2E test runner. Validate cancel, fork, and log operations inside the Docker container."
     capabilities:
       - docker
       - shell
     procedure: |
-      Use containerName, threadId (first thread), lastStepHash, and workflowName from your prompt.
+      Use containerName, threadId, lastStepHash, and workflowName from your prompt.
       All commands via: `docker exec <containerName> bash -c '...'`
-      Set env: PATH, UNCAGED_WORKFLOW_STORAGE_ROOT=/tmp/uwf-e2e-storage
+      Set env: PATH="$HOME/.bun/bin:$PATH" UNCAGED_WORKFLOW_STORAGE_ROOT=/tmp/uwf-e2e-storage
 
-      Phase 6 — Cancel & Fork:
+      Cancel:
       1. Start a second thread: `uwf thread start <workflowName> -p 'E2E cancel test'`
       2. Cancel it: `uwf thread cancel <secondThreadId>`
       3. Verify it appears in completed list: `uwf thread list --status completed`
+
+      Fork:
       4. Fork from the first thread's last step: `uwf step fork <lastStepHash>`
-      5. Verify fork creates a new thread with different ID
+      5. Verify fork creates a new thread with a different ID
 
-      Phase 7 — Logs:
+      Logs:
-      6. `uwf log list` — check log files exist
+      6. `uwf log list` — verify output (may be empty)
-      7. `uwf log show --thread <threadId>` — verify log output (may be empty, that's ok)
+      7. `uwf log show --thread <threadId>` — verify runs without error
 
-      Phase 8 — Cleanup:
+      Report results with summary.
-      8. Stop and remove the Docker container: `docker rm -f <containerName>`
+    output: "Report test results with summary. Set $status to pass or fail."
-
-      Report final results with full summary of all phases.
-    output: "Report final test results with pass/fail counts. Set $status to pass or fail."
     frontmatter:
       oneOf:
         - properties:
             $status: { const: "pass" }
-            totalPassed: { type: number }
+            containerName: { type: string }
             summary: { type: string }
-          required: [$status, totalPassed, summary]
+          required: [$status, containerName, summary]
+        - properties:
+            $status: { const: "fail" }
+            error: { type: string }
+            containerName: { type: string }
+          required: [$status, error, containerName]
+
+  cleanup:
+    description: "Remove Docker container"
+    goal: "You are an E2E test runner. Clean up the Docker container used for testing."
+    capabilities:
+      - docker
+      - shell
+    procedure: |
+      Remove the Docker container (containerName is in your prompt):
+      1. `docker rm -f <containerName>`
+      2. Verify the container is gone: `docker ps -a --filter name=<containerName> --format '{{.Names}}'` should return empty
+
+      Report cleanup result.
+    output: "Report cleanup result. Set $status to pass or fail."
+    frontmatter:
+      oneOf:
+        - properties:
+            $status: { const: "pass" }
+            summary: { type: string }
+          required: [$status, summary]
         - properties:
             $status: { const: "fail" }
             error: { type: string }
-            totalPassed: { type: number }
           required: [$status, error]
 
 graph:
   $START:
     _: { role: "bootstrap", prompt: "Set up the Docker container and verify uwf is runnable." }
   bootstrap:
-    pass: { role: "setup-and-registry", prompt: "Container {{{containerName}}} is ready. Validate config and workflow registration." }
+    pass: { role: "config-and-registry", prompt: "Container {{{containerName}}} is ready. Validate config and workflow registration." }
-    fail: { role: "$END", prompt: "Bootstrap failed: {{{error}}}" }
+    fail: { role: "$END", prompt: "Bootstrap failed: {{{error}}}. No container was created." }
-  setup-and-registry:
+  config-and-registry:
-    pass: { role: "thread-lifecycle", prompt: "Config and registry OK. Workflow '{{{workflowName}}}' registered. Container: {{{containerName}}}. Now test thread lifecycle." }
+    pass: { role: "thread-ops", prompt: "Config and registry OK. Workflow '{{{workflowName}}}' registered. Container: {{{containerName}}}. Now test thread operations." }
-    fail: { role: "$END", prompt: "Setup/registry failed: {{{error}}}" }
+    fail: { role: "cleanup", prompt: "Config/registry failed: {{{error}}}. Clean up container {{{containerName}}}." }
-  thread-lifecycle:
+  thread-ops:
-    pass: { role: "cancel-fork-and-logs", prompt: "Thread lifecycle OK. threadId={{{threadId}}}, lastStepHash={{{lastStepHash}}}, containerName={{{containerName}}}. Now test cancel, fork, logs, and cleanup." }
+    pass: { role: "inspect", prompt: "Thread ops OK. threadId={{{threadId}}}, workflowName={{{workflowName}}}, containerName={{{containerName}}}. Now test inspect operations." }
-    fail: { role: "$END", prompt: "Thread lifecycle failed: {{{error}}}" }
+    fail: { role: "cleanup", prompt: "Thread ops failed: {{{error}}}. Clean up container {{{containerName}}}." }
-  cancel-fork-and-logs:
+  inspect:
-    pass: { role: "$END", prompt: "All E2E tests passed! {{{summary}}}" }
+    pass: { role: "cancel-and-fork", prompt: "Inspect OK. threadId={{{threadId}}}, lastStepHash={{{lastStepHash}}}, workflowName={{{workflowName}}}, containerName={{{containerName}}}. Now test cancel, fork, and logs." }
-    fail: { role: "$END", prompt: "Cancel/fork/logs phase failed: {{{error}}}. Passed: {{{totalPassed}}}" }
+    fail: { role: "cleanup", prompt: "Inspect failed: {{{error}}}. Clean up container {{{containerName}}}." }
+  cancel-and-fork:
+    pass: { role: "cleanup", prompt: "All tests passed! {{{summary}}}. Clean up container {{{containerName}}}." }
+    fail: { role: "cleanup", prompt: "Cancel/fork failed: {{{error}}}. Clean up container {{{containerName}}}." }
+  cleanup:
+    pass: { role: "$END", prompt: "E2E walkthrough complete. {{{summary}}}" }
+    fail: { role: "$END", prompt: "Cleanup failed: {{{error}}}. Manual cleanup may be needed." }