chore: clean up workflow YAML — bun→pnpm, enum→const, deduplicate
CI / check (push) Failing after 3m6s
CI / check (push) Failing after 3m6s
- solve-issue.yaml: bun→pnpm (5 refs), examples/ is now canonical - Delete redundant workflows/solve-issue.yaml and .workflows/solve-issue.yaml - analyze-topic.yaml + eval-simple.yaml: enum→const for $status - Archive normalize-bun-monorepo.yaml and e2e-walkthrough.yaml to legacy-packages/ Closes #137 小橘 🍊
This commit is contained in:
@@ -0,0 +1,286 @@
|
||||
name: "e2e-walkthrough"
|
||||
description: "End-to-end walkthrough of uwf CLI. Dogfooding: uwf tests uwf. Each role validates a phase of the CLI surface inside an isolated Docker container."
|
||||
roles:
|
||||
bootstrap:
|
||||
description: "Start Docker container with isolated storage, verify uwf is runnable"
|
||||
goal: "You are an E2E test runner. Set up an isolated Docker environment and verify basic uwf functionality."
|
||||
capabilities:
|
||||
- docker
|
||||
- shell
|
||||
procedure: |
|
||||
1. Start a Docker container with isolated storage.
|
||||
IMPORTANT: Mount the source code READ-ONLY to prevent the container
|
||||
from overwriting host files (e.g. bun install would replace macOS bun with Linux bun).
|
||||
Use a container-local HOME so bun/npm installs stay inside the container.
|
||||
Add host.docker.internal mapping for LLM API access from inside the container.
|
||||
```
|
||||
docker run -d --name uwf-e2e-$$ \
|
||||
-v "$(pwd):/workspace:ro" \
|
||||
-e HOME=/root \
|
||||
-e UWF_HOME=/tmp/uwf-e2e-storage \
|
||||
--add-host=host.docker.internal:host-gateway \
|
||||
-w /workspace \
|
||||
node:22-bookworm \
|
||||
sleep infinity
|
||||
```
|
||||
NOTE: Run this from the workflow monorepo root directory.
|
||||
On macOS Docker Desktop, host.docker.internal is already available;
|
||||
--add-host ensures it also works on Linux Docker.
|
||||
|
||||
2. Inside the container, copy source to a writable location, install bun, install deps,
|
||||
then `bun link` all packages so that `uwf`, `uwf-hermes`, `uwf-builtin` are on PATH:
|
||||
```
|
||||
docker exec uwf-e2e-$$ bash -c '
|
||||
# Copy source to writable location (mount is read-only)
|
||||
cp -r /workspace /root/workflow
|
||||
|
||||
# Install bun
|
||||
curl -fsSL https://bun.sh/install | bash
|
||||
export PATH="$HOME/.bun/bin:$PATH"
|
||||
|
||||
# Isolated storage
|
||||
mkdir -p $UWF_HOME
|
||||
|
||||
# Install workspace deps
|
||||
cd /root/workflow && bun install
|
||||
|
||||
# bun link each package that has a bin entry
|
||||
cd packages/cli && bun link && cd ../..
|
||||
cd packages/agent-hermes && bun link && cd ../..
|
||||
cd packages/agent-builtin && bun link && cd ../..
|
||||
'
|
||||
```
|
||||
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-$$ bash -c 'export PATH="$HOME/.bun/bin:$PATH" && uwf-builtin --help'
|
||||
```
|
||||
4. Copy host uwf config into the container's isolated storage.
|
||||
The host config contains provider credentials and model settings needed for LLM calls.
|
||||
Also rewrite any localhost URLs to host.docker.internal so the container can reach host services.
|
||||
```
|
||||
docker cp ~/.uwf/config.yaml uwf-e2e-$$:/tmp/uwf-e2e-storage/config.yaml 2>/dev/null || true
|
||||
docker exec uwf-e2e-$$ bash -c '
|
||||
if [ -f $UWF_HOME/config.yaml ]; then
|
||||
sed -i "s|localhost|host.docker.internal|g; s|127\.0\.0\.1|host.docker.internal|g" \
|
||||
$UWF_HOME/config.yaml
|
||||
fi
|
||||
'
|
||||
```
|
||||
|
||||
Report the container name and confirm uwf + agents are working.
|
||||
Set containerName to the Docker container name for subsequent roles.
|
||||
output: "Report uwf version and container readiness. Set $status to pass with containerName, or fail with error."
|
||||
frontmatter:
|
||||
oneOf:
|
||||
- properties:
|
||||
$status: { const: "pass" }
|
||||
containerName: { type: string }
|
||||
required: [$status, containerName]
|
||||
- properties:
|
||||
$status: { const: "fail" }
|
||||
error: { type: string }
|
||||
required: [$status, error]
|
||||
|
||||
config-and-registry:
|
||||
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
|
||||
- shell
|
||||
procedure: |
|
||||
Use the container from the previous step (containerName is in your prompt).
|
||||
All commands run via: `docker exec <containerName> bash -c '...'`
|
||||
All commands use `uwf` (installed via `bun link` inside the container).
|
||||
Remember to set env vars in each exec:
|
||||
export PATH="$HOME/.bun/bin:$PATH"
|
||||
export UWF_HOME=/tmp/uwf-e2e-storage
|
||||
|
||||
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"
|
||||
|
||||
Workflow registration tests:
|
||||
4. `uwf workflow add /root/workflow/examples/debate.yaml` — register a workflow (use debate.yaml as it has no $SUSPEND dependency)
|
||||
5. Verify the output contains a hash
|
||||
6. `uwf workflow list` — verify non-empty array
|
||||
7. Capture the workflow name from the list
|
||||
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."
|
||||
frontmatter:
|
||||
oneOf:
|
||||
- properties:
|
||||
$status: { const: "pass" }
|
||||
workflowName: { type: string }
|
||||
containerName: { type: string }
|
||||
required: [$status, workflowName, containerName]
|
||||
- properties:
|
||||
$status: { const: "fail" }
|
||||
error: { type: string }
|
||||
containerName: { type: string }
|
||||
required: [$status, error, containerName]
|
||||
|
||||
thread-ops:
|
||||
description: "Test thread start, list, show, and exec"
|
||||
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="$HOME/.bun/bin:$PATH" UWF_HOME=/tmp/uwf-e2e-storage
|
||||
|
||||
1. `uwf thread start <workflowName> -p 'E2E test: what is 2+2?'` — capture thread ID from JSON output
|
||||
2. `uwf thread list` — verify the thread appears in the list
|
||||
3. `uwf thread show <threadId>` — verify head pointer exists
|
||||
4. `uwf thread exec <threadId> --agent uwf-builtin` — execute one step
|
||||
5. Verify exec returns JSON with a head field
|
||||
|
||||
Report results. Pass threadId and containerName forward.
|
||||
output: "Report test results. Set $status to pass (with threadId, workflowName, containerName) or fail."
|
||||
frontmatter:
|
||||
oneOf:
|
||||
- properties:
|
||||
$status: { const: "pass" }
|
||||
threadId: { type: string }
|
||||
workflowName: { type: string }
|
||||
containerName: { type: string }
|
||||
required: [$status, threadId, workflowName, containerName]
|
||||
- properties:
|
||||
$status: { const: "fail" }
|
||||
error: { type: string }
|
||||
containerName: { type: string }
|
||||
required: [$status, error, containerName]
|
||||
|
||||
inspect:
|
||||
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" UWF_HOME=/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. `ocas get <lastStepHash>` — verify returns a type field
|
||||
6. `ocas has <lastStepHash>` — verify exits 0
|
||||
7. `ocas refs <lastStepHash>` — list refs (may be empty)
|
||||
8. `ocas 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:
|
||||
$status: { const: "pass" }
|
||||
threadId: { type: string }
|
||||
lastStepHash: { type: string }
|
||||
workflowName: { type: string }
|
||||
containerName: { type: string }
|
||||
required: [$status, threadId, lastStepHash, workflowName, containerName]
|
||||
- properties:
|
||||
$status: { const: "fail" }
|
||||
error: { type: string }
|
||||
containerName: { type: string }
|
||||
required: [$status, error, containerName]
|
||||
|
||||
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 inside the Docker container."
|
||||
capabilities:
|
||||
- docker
|
||||
- shell
|
||||
procedure: |
|
||||
Use containerName, threadId, lastStepHash, and workflowName from your prompt.
|
||||
All commands via: `docker exec <containerName> bash -c '...'`
|
||||
Set env: PATH="$HOME/.bun/bin:$PATH" UWF_HOME=/tmp/uwf-e2e-storage
|
||||
|
||||
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 cancelled list: `uwf thread list --status cancelled`
|
||||
|
||||
Fork:
|
||||
4. Fork from the first thread's last step: `uwf step fork <lastStepHash>`
|
||||
5. Verify fork creates a new thread with a different ID
|
||||
|
||||
Logs:
|
||||
6. `uwf log list` — verify output (may be empty)
|
||||
7. `uwf log show --thread <threadId>` — verify runs without error
|
||||
|
||||
Report results with summary.
|
||||
output: "Report test results with summary. Set $status to pass or fail."
|
||||
frontmatter:
|
||||
oneOf:
|
||||
- properties:
|
||||
$status: { const: "pass" }
|
||||
containerName: { type: string }
|
||||
summary: { type: string }
|
||||
required: [$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:
|
||||
$status: { const: "fail" }
|
||||
error: { type: string }
|
||||
required: [$status, error]
|
||||
|
||||
graph:
|
||||
$START:
|
||||
new: { role: "bootstrap", prompt: "Set up the Docker container and verify uwf is runnable." }
|
||||
resume: { role: "bootstrap", prompt: "Review the previous run output and continue the walkthrough." }
|
||||
bootstrap:
|
||||
pass: { role: "config-and-registry", prompt: "Container {{{containerName}}} is ready. Validate config and workflow registration." }
|
||||
fail: { role: "$END", prompt: "Bootstrap failed: {{{error}}}. No container was created." }
|
||||
config-and-registry:
|
||||
pass: { role: "thread-ops", prompt: "Config and registry OK. Workflow '{{{workflowName}}}' registered. Container: {{{containerName}}}. Now test thread operations." }
|
||||
fail: { role: "cleanup", prompt: "Config/registry failed: {{{error}}}. Clean up container {{{containerName}}}." }
|
||||
thread-ops:
|
||||
pass: { role: "inspect", prompt: "Thread ops OK. threadId={{{threadId}}}, workflowName={{{workflowName}}}, containerName={{{containerName}}}. Now test inspect operations." }
|
||||
fail: { role: "cleanup", prompt: "Thread ops failed: {{{error}}}. Clean up container {{{containerName}}}." }
|
||||
inspect:
|
||||
pass: { role: "cancel-and-fork", prompt: "Inspect OK. threadId={{{threadId}}}, lastStepHash={{{lastStepHash}}}, workflowName={{{workflowName}}}, containerName={{{containerName}}}. Now test cancel, fork, and logs." }
|
||||
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." }
|
||||
Reference in New Issue
Block a user