Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 xingyue
|
842e479784 | ||
|
xingyue
|
f63c670cd9 | ||
|
xingyue
|
64c5122453 |
@@ -1,67 +0,0 @@
|
||||
# Sync README
|
||||
|
||||
When updating README.md files in this monorepo, follow these conventions.
|
||||
|
||||
## Scope
|
||||
|
||||
- Root `README.md` — project overview and navigation hub
|
||||
- Per-package `packages/*/README.md` — each package self-contained
|
||||
|
||||
## Root README Structure
|
||||
|
||||
The root README should have these sections in order:
|
||||
|
||||
1. **Title and one-liner** — stateless workflow engine driven by single-step CLI
|
||||
2. **Overview** — 2-3 paragraphs explaining what it does and key concepts
|
||||
3. **Architecture** — dependency layer diagram (text-based)
|
||||
4. **Packages** — table with ALL packages from packages/ directory, columns: Package, Description, Type (cli/lib/agent/app)
|
||||
5. **Quick Start** — install, build, register workflow, start thread, run step
|
||||
6. **CLI Reference** — brief command list, detailed usage in cli-workflow README
|
||||
7. **Development** — bun install / build / check / test
|
||||
|
||||
## Per-Package README Structure
|
||||
|
||||
Each package README should have:
|
||||
|
||||
1. **Title** — package name
|
||||
2. **One-line description** — matching package.json
|
||||
3. **Overview** — what it does, where it sits in the architecture, dependencies
|
||||
4. **Installation** — bun add (for libs) or "included as binary" (for cli/agents)
|
||||
5. **API** (lib packages) — all exports from src/index.ts with type signatures, grouped by category, minimal usage examples
|
||||
6. **CLI Usage** (cli/agent packages) — command reference with examples
|
||||
7. **Internal Structure** — brief src/ file organization
|
||||
8. **Configuration** (if applicable)
|
||||
|
||||
## Execution Steps
|
||||
|
||||
### Step 1: Gather current state
|
||||
For each package read:
|
||||
- package.json (name, version, description, dependencies, bin)
|
||||
- src/index.ts (public API exports)
|
||||
- Existing README.md (preserve hand-written content worth keeping)
|
||||
|
||||
### Step 2: Update root README
|
||||
- Ensure ALL packages in packages/ directory are listed in the table
|
||||
- Update CLI command reference from uwf --help output
|
||||
- Keep Quick Start examples valid
|
||||
|
||||
### Step 3: Write/update each package README
|
||||
- Follow the per-package structure
|
||||
- API section MUST match actual src/index.ts exports — never invent
|
||||
- For agent packages: document CLI binary name, how it is invoked
|
||||
- For lib packages: document exported types and functions
|
||||
- Internal structure: list actual files in src/
|
||||
|
||||
### Step 4: Verify
|
||||
- All relative links work
|
||||
- Package names match package.json
|
||||
- No references to removed/renamed packages
|
||||
- bun run build still passes
|
||||
|
||||
## Guidelines
|
||||
|
||||
- Only document what src/index.ts actually exports
|
||||
- Root README summarizes, package READMEs go into detail
|
||||
- Verify CLI examples against actual commands
|
||||
- Preserve existing good prose when updating
|
||||
- English for all README content
|
||||
+12
-31
@@ -38,26 +38,19 @@ roles:
|
||||
capabilities:
|
||||
- coding
|
||||
procedure: |
|
||||
IMPORTANT: Always work in a git worktree, NEVER modify the main working directory directly.
|
||||
|
||||
Before starting any work, set up an isolated worktree:
|
||||
1. `cd ~/repos/workflow && git fetch origin` to get latest refs
|
||||
2. First time (no existing branch):
|
||||
- `git worktree add ~/repos/workflow-worktrees/fix/<issue-number>-<short-slug> -b fix/<issue-number>-<short-slug> origin/main`
|
||||
- `cd ~/repos/workflow-worktrees/fix/<issue-number>-<short-slug> && bun install`
|
||||
3. If bounced back from reviewer or tester (branch already exists):
|
||||
- The worktree should already exist at `~/repos/workflow-worktrees/fix/<issue-number>-<short-slug>`
|
||||
- `cd ~/repos/workflow-worktrees/fix/<issue-number>-<short-slug>`
|
||||
- `git fetch origin && git rebase origin/main`
|
||||
4. ALL subsequent work must happen inside the worktree directory.
|
||||
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`
|
||||
|
||||
Then implement TDD:
|
||||
5. Read the test spec from CAS: `uwf cas get <plan hash>` (find the hash from the latest planner step's frontmatter.plan)
|
||||
6. If bounced back from reviewer or tester: read the previous role's output to understand what needs fixing
|
||||
7. Write tests first based on the spec
|
||||
8. Implement the code to make tests pass
|
||||
9. Ensure `bun run build` passes with no errors
|
||||
10. Run `bun test` to verify all tests pass
|
||||
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)."
|
||||
frontmatter:
|
||||
type: object
|
||||
@@ -73,8 +66,6 @@ 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
|
||||
@@ -108,8 +99,6 @@ roles:
|
||||
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
|
||||
@@ -130,21 +119,13 @@ roles:
|
||||
goal: "You are a committer agent. You create a clean commit and push a PR linking the original issue."
|
||||
capabilities: []
|
||||
procedure: |
|
||||
First, cd into the worktree: `cd ~/repos/workflow-worktrees/fix/<issue-number>-*` (find the exact directory)
|
||||
|
||||
Note: You inherit the developer's worktree and branch. Do NOT create a new branch.
|
||||
1. Stage all changes: `git add -A`
|
||||
2. Commit with a descriptive message referencing the issue: `git commit -m "type: description\n\nFixes #N"`
|
||||
3. Push the branch: `git push -u origin <branch-name>`
|
||||
- If push hook fails: capture the error log in your output, mark hook_failed
|
||||
4. On push success: create a PR via `tea pr create --repo uncaged/workflow --title "..." --description "..."`
|
||||
- The `--repo` flag is required to work in worktree directories (fixes #474 "path segment [0] is empty" error)
|
||||
- If working on a different repo, extract owner/repo from: `git remote get-url origin | sed 's/.*[:/]\([^/]*\/[^.]*\).*/\1/'`
|
||||
4. On push success: create a PR via `tea pr create --title "..." --description "..."`
|
||||
- PR description must follow the project template: What / Why / Changes / Ref sections, with `Fixes #N` in Ref
|
||||
- On tea failure: capture stderr/stdout, log the error clearly, include PR details (title, description, branch) for manual creation, and mark success=false
|
||||
5. After PR creation, clean up the worktree:
|
||||
- `cd ~/repos/workflow`
|
||||
- `git worktree remove ~/repos/workflow-worktrees/fix/<issue-number>-<slug>`
|
||||
output: "Include PR URL on success or error log on failure. Frontmatter must include: success (true or false)."
|
||||
frontmatter:
|
||||
type: object
|
||||
|
||||
@@ -2,103 +2,92 @@
|
||||
|
||||
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.
|
||||
|
||||
## Overview
|
||||
## Package Map
|
||||
|
||||
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 `$END`. Each step is a complete process: the moderator evaluates JSONata conditions to pick the next role, an external agent CLI produces frontmatter markdown output, and an extract pipeline validates or structures that output against the role's JSON Schema.
|
||||
| Package | npm | Role |
|
||||
|---------|-----|------|
|
||||
| `cli-workflow` | `@uncaged/cli-workflow` | `uwf` CLI binary — thread lifecycle, workflow registry, CAS inspection, setup |
|
||||
| `workflow-protocol` | `@uncaged/workflow-protocol` | Shared TypeScript types (`WorkflowPayload`, `StepNodePayload`, `WorkflowConfig`, etc.) |
|
||||
| `workflow-moderator` | `@uncaged/workflow-moderator` | JSONata graph evaluator — determines next role or `$END` |
|
||||
| `workflow-agent-kit` | `@uncaged/workflow-agent-kit` | `createAgent` factory, context builder, two-layer extract pipeline |
|
||||
| `workflow-agent-hermes` | `@uncaged/workflow-agent-hermes` | `uwf-hermes` agent — spawns Hermes chat, captures session |
|
||||
| `workflow-util` | `@uncaged/workflow-util` | Crockford Base32, ULID, logger, frontmatter parsing |
|
||||
|
||||
Workflow state lives entirely on disk under `~/.uncaged/workflow/`: CAS nodes for definitions and step payloads, `registry.yaml` for workflow name→hash mappings, and `threads.yaml` for active thread head pointers. Completed threads are archived to `history.jsonl`. Because there is no server process, workflows are easy to debug, fork, and inspect with ordinary CLI tools.
|
||||
|
||||
Agents are pluggable CLI binaries (`uwf-hermes`, `uwf-builtin`, `uwf-claude-code`, or custom commands). The engine spawns the configured agent with `<thread-id>` and `<role>`, sets `UWF_EDGE_PROMPT` from the graph transition, and captures both the agent's markdown output and a detail CAS node for session replay.
|
||||
|
||||
## Architecture
|
||||
|
||||
Dependency layers (lower layers have no dependency on higher layers):
|
||||
|
||||
```
|
||||
Layer 0 — Contract
|
||||
workflow-protocol Shared types and JSON Schema definitions
|
||||
|
||||
Layer 1 — Shared infra
|
||||
workflow-util Encoding, IDs, logging, frontmatter, paths
|
||||
workflow-moderator JSONata graph evaluator
|
||||
|
||||
Layer 2 — Agent framework
|
||||
workflow-agent-kit createAgent factory, context builder, extract pipeline
|
||||
|
||||
Layer 3 — Agent implementations
|
||||
workflow-agent-hermes Hermes ACP agent (uwf-hermes)
|
||||
workflow-agent-builtin Built-in LLM + tools agent (uwf-builtin)
|
||||
workflow-agent-claude-code Claude Code agent (uwf-claude-code)
|
||||
|
||||
Layer 4 — CLI
|
||||
cli-workflow uwf binary — thread lifecycle, registry, CAS, setup
|
||||
|
||||
App (uses protocol; not in the runtime engine stack)
|
||||
workflow-dashboard Web UI for visual workflow editing
|
||||
```
|
||||
|
||||
External CAS: [`@uncaged/json-cas`](https://www.npmjs.com/package/@uncaged/json-cas) (store API, hashing, schema validation) + `@uncaged/json-cas-fs` (filesystem backend).
|
||||
|
||||
See [docs/architecture.md](docs/architecture.md) for the full design — three-phase engine loop, CAS node types, storage layout, agent CLI protocol, and design decisions.
|
||||
|
||||
## Packages
|
||||
|
||||
| Package | npm | Description | Type | README |
|
||||
|---------|-----|-------------|------|--------|
|
||||
| `cli-workflow` | `@uncaged/cli-workflow` | `uwf` CLI — thread lifecycle, workflow registry, CAS inspection, setup | cli | [README](packages/cli-workflow/README.md) |
|
||||
| `workflow-protocol` | `@uncaged/workflow-protocol` | Shared TypeScript types and JSON Schema constants | lib | [README](packages/workflow-protocol/README.md) |
|
||||
| `workflow-moderator` | `@uncaged/workflow-moderator` | JSONata graph evaluator — next role or `$END` | lib | [README](packages/workflow-moderator/README.md) |
|
||||
| `workflow-agent-kit` | `@uncaged/workflow-agent-kit` | `createAgent` factory, context builder, extract pipeline | lib | [README](packages/workflow-agent-kit/README.md) |
|
||||
| `workflow-util` | `@uncaged/workflow-util` | Crockford Base32, ULID, logger, frontmatter parsing, storage paths | lib | [README](packages/workflow-util/README.md) |
|
||||
| `workflow-agent-hermes` | `@uncaged/workflow-agent-hermes` | `uwf-hermes` — spawns Hermes chat via ACP | agent | [README](packages/workflow-agent-hermes/README.md) |
|
||||
| `workflow-agent-builtin` | `@uncaged/workflow-agent-builtin` | `uwf-builtin` — built-in LLM agent with file/shell tools | agent | [README](packages/workflow-agent-builtin/README.md) |
|
||||
| `workflow-agent-claude-code` | `@uncaged/workflow-agent-claude-code` | `uwf-claude-code` — spawns Claude Code CLI | agent | [README](packages/workflow-agent-claude-code/README.md) |
|
||||
| `workflow-dashboard` | `@uncaged/workflow-dashboard` | Web graph editor for workflow YAML (private, alpha) | app | [README](packages/workflow-dashboard/README.md) |
|
||||
External: [`@uncaged/json-cas`](https://www.npmjs.com/package/@uncaged/json-cas) (CAS store + JSON Schema validation) + `@uncaged/json-cas-fs` (filesystem backend).
|
||||
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
# 1. Configure provider, model, and default agent
|
||||
# 1. Configure provider and model
|
||||
uwf setup
|
||||
|
||||
# 2. Register a workflow from YAML
|
||||
uwf workflow add examples/solve-issue.yaml
|
||||
uwf workflow put examples/solve-issue.yaml
|
||||
|
||||
# 3. Start a thread (creates head pointer; does not execute)
|
||||
# 3. Start a thread
|
||||
uwf thread start solve-issue -p "Fix the login redirect bug"
|
||||
|
||||
# 4. Execute steps (one at a time, until done)
|
||||
uwf thread exec <thread-id>
|
||||
uwf thread step <thread-id>
|
||||
```
|
||||
|
||||
Use `-c, --count <number>` on `thread exec` to run multiple steps in one invocation. Override the agent with `--agent <cmd>`.
|
||||
## CLI Commands
|
||||
|
||||
## CLI Reference
|
||||
### Thread
|
||||
|
||||
Global options: `-V, --version`, `--format <json|yaml>`, `-h, --help`.
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf thread start <workflow> -p <prompt>` | Create a thread (no execution) |
|
||||
| `uwf thread step <thread-id> [--agent <cmd>]` | Execute one moderator→agent→extract cycle |
|
||||
| `uwf thread show <thread-id>` | Show head pointer and done status |
|
||||
| `uwf thread list [--all]` | List threads (`--all` includes archived) |
|
||||
| `uwf thread steps <thread-id>` | List all steps chronologically |
|
||||
| `uwf thread read <thread-id> [--quota N]` | 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 |
|
||||
| `uwf thread kill <thread-id>` | Terminate and archive |
|
||||
|
||||
| Group | Commands |
|
||||
|-------|----------|
|
||||
| **thread** | `start`, `exec`, `show`, `list`, `stop`, `cancel`, `read` |
|
||||
| **step** | `list`, `show`, `read`, `fork` |
|
||||
| **workflow** | `add`, `show`, `list` |
|
||||
| **cas** | `get`, `put`, `put-text`, `has`, `refs`, `walk`, `reindex`, `schema list`, `schema get` |
|
||||
| **setup** | Interactive or `--provider`, `--base-url`, `--api-key`, `--model`, `--agent` |
|
||||
| **skill** | `cli` — print markdown reference of all uwf commands |
|
||||
| **log** | `list`, `show`, `clean` — process-level debug logs |
|
||||
### Workflow
|
||||
|
||||
Config is stored in `~/.uncaged/workflow/config.yaml`. API keys go in `~/.uncaged/workflow/.env`.
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf workflow put <file.yaml>` | Register a workflow from YAML |
|
||||
| `uwf workflow show <name-or-hash>` | Show workflow definition |
|
||||
| `uwf workflow list` | List registered workflows |
|
||||
|
||||
Detailed command usage, options, and examples: [packages/cli-workflow/README.md](packages/cli-workflow/README.md).
|
||||
### CAS
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf cas get <hash>` | Read a CAS node |
|
||||
| `uwf cas put <type-hash> <data>` | Store a node |
|
||||
| `uwf cas has <hash>` | Check existence |
|
||||
| `uwf cas refs <hash>` | List direct references |
|
||||
| `uwf cas walk <hash>` | Recursive traversal |
|
||||
| `uwf cas reindex` | Rebuild type index |
|
||||
| `uwf cas schema list` | List schemas |
|
||||
| `uwf cas schema get <hash>` | Show a schema |
|
||||
|
||||
### Setup
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf setup` | Interactive provider/model/agent configuration |
|
||||
| `uwf setup --provider ... --base-url ... --api-key ... --model ...` | Non-interactive setup |
|
||||
|
||||
Config stored in `~/.uncaged/workflow/config.yaml`. API keys in `~/.uncaged/workflow/.env`.
|
||||
|
||||
## Development
|
||||
|
||||
```bash
|
||||
bun install --no-cache # Install dependencies
|
||||
bun run build # tsc --build (all packages)
|
||||
bun run check # tsc + biome + lint-log-tags
|
||||
bun run format # Auto-format with Biome
|
||||
bun test # Run all tests
|
||||
```
|
||||
|
||||
Managed with **bun workspace**. See [CLAUDE.md](CLAUDE.md) for coding conventions.
|
||||
|
||||
## Architecture
|
||||
|
||||
See [docs/architecture.md](docs/architecture.md) for the full design — three-phase engine loop, CAS node types, storage layout, agent CLI protocol, and design decisions.
|
||||
|
||||
@@ -44,8 +44,7 @@ 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. 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.
|
||||
5. 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
|
||||
@@ -63,10 +62,7 @@ roles:
|
||||
capabilities:
|
||||
- code-review
|
||||
- static-analysis
|
||||
procedure: |
|
||||
1. Run hard checks first — build (`bun run build` or equivalent) and lint (`bunx biome check .` or equivalent) MUST pass with zero errors. If they fail, reject immediately.
|
||||
2. Then review code quality: correctness, edge cases, naming, project conventions (CLAUDE.md), and test coverage.
|
||||
3. Only reject for hard check failures or genuine correctness/security issues. Style suggestions alone should not block approval.
|
||||
procedure: "Review the implementation against the plan. Check for bugs, edge cases, and style."
|
||||
output: "Approve or reject with detailed comments explaining your decision."
|
||||
frontmatter:
|
||||
type: object
|
||||
|
||||
@@ -531,25 +531,13 @@ export async function executeThread(
|
||||
timestamp: nowMs,
|
||||
parentState: options.parentStateHash,
|
||||
},
|
||||
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,
|
||||
};
|
||||
}),
|
||||
),
|
||||
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,
|
||||
})),
|
||||
};
|
||||
|
||||
const runtime: WorkflowRuntime = {
|
||||
|
||||
@@ -71,7 +71,6 @@ export type RoleStep<M extends RoleMeta> = {
|
||||
role: K;
|
||||
meta: M[K];
|
||||
contentHash: string;
|
||||
content: string | null;
|
||||
refs: string[];
|
||||
timestamp: number;
|
||||
};
|
||||
|
||||
@@ -71,8 +71,7 @@ async function buildRoleStepsFromStates<M extends RoleMeta>(
|
||||
cas: CasStore,
|
||||
): Promise<RoleStep<M>[]> {
|
||||
const steps: RoleStep<M>[] = [];
|
||||
for (let idx = 0; idx < chronologicalStates.length; idx++) {
|
||||
const st = chronologicalStates[idx];
|
||||
for (const st of chronologicalStates) {
|
||||
if (st.payload.role === END) {
|
||||
continue;
|
||||
}
|
||||
@@ -80,13 +79,10 @@ 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>);
|
||||
|
||||
@@ -88,7 +88,6 @@ async function advanceOneRound<M extends RoleMeta>(
|
||||
const step = {
|
||||
role: next,
|
||||
contentHash,
|
||||
content: contentPayload,
|
||||
meta,
|
||||
refs,
|
||||
timestamp: Date.now(),
|
||||
|
||||
@@ -30,7 +30,7 @@ describe("buildAgentPrompt", () => {
|
||||
expect(text).not.toContain("## Tools");
|
||||
});
|
||||
|
||||
test("single step shows meta and content, and includes tools", async () => {
|
||||
test("single step shows hash and meta, and includes tools", async () => {
|
||||
const onlyHash = "01HASHSINGLESTEP0000000001";
|
||||
const ctx: AgentContext = {
|
||||
start: startTask("user task"),
|
||||
@@ -42,7 +42,6 @@ describe("buildAgentPrompt", () => {
|
||||
{
|
||||
role: "coder",
|
||||
contentHash: onlyHash,
|
||||
content: "Here is my implementation of the feature.",
|
||||
meta: { files: ["a.ts"] },
|
||||
refs: [onlyHash],
|
||||
timestamp: 2,
|
||||
@@ -53,39 +52,13 @@ 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("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 () => {
|
||||
test("two or more steps: previous steps are meta-only; latest step includes hash", async () => {
|
||||
const plannerHash = "01HASHPLANNER0000000000001";
|
||||
const coderHash = "01HASHCODER0000000000000001";
|
||||
const ctx: AgentContext = {
|
||||
@@ -98,7 +71,6 @@ describe("buildAgentPrompt", () => {
|
||||
{
|
||||
role: "planner",
|
||||
contentHash: plannerHash,
|
||||
content: null,
|
||||
meta: { plan: "short" },
|
||||
refs: [plannerHash],
|
||||
timestamp: 2,
|
||||
@@ -106,7 +78,6 @@ 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,
|
||||
@@ -119,11 +90,10 @@ 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 () => {
|
||||
@@ -155,7 +125,7 @@ describe("buildAgentPrompt", () => {
|
||||
expect(text).toContain(`uncaged-workflow cas get ${parentHash}`);
|
||||
});
|
||||
|
||||
test("middle steps show meta summary only and latest shows content", async () => {
|
||||
test("middle steps show meta summary only and latest shows hash", async () => {
|
||||
const ha = "01HASHA00000000000000000001";
|
||||
const hb = "01HASHB00000000000000000001";
|
||||
const hc = "01HASHC00000000000000000001";
|
||||
@@ -169,7 +139,6 @@ describe("buildAgentPrompt", () => {
|
||||
{
|
||||
role: "a",
|
||||
contentHash: ha,
|
||||
content: null,
|
||||
meta: { n: 1 },
|
||||
refs: [ha],
|
||||
timestamp: 2,
|
||||
@@ -177,7 +146,6 @@ describe("buildAgentPrompt", () => {
|
||||
{
|
||||
role: "b",
|
||||
contentHash: hb,
|
||||
content: null,
|
||||
meta: { n: 2 },
|
||||
refs: [hb],
|
||||
timestamp: 3,
|
||||
@@ -185,7 +153,6 @@ describe("buildAgentPrompt", () => {
|
||||
{
|
||||
role: "c",
|
||||
contentHash: hc,
|
||||
content: "Final output from role c",
|
||||
meta: { n: 3 },
|
||||
refs: [hc],
|
||||
timestamp: 4,
|
||||
@@ -195,35 +162,7 @@ describe("buildAgentPrompt", () => {
|
||||
const text = await buildAgentPrompt(ctx);
|
||||
expect(text).toContain('Summary: {"n":1}');
|
||||
expect(text).toContain('Summary: {"n":2}');
|
||||
expect(text).toContain(`ContentHash: ${hc}`);
|
||||
expect(text).toContain("## Latest Step: c");
|
||||
expect(text).toContain("<output>");
|
||||
expect(text).toContain("Final output from role c");
|
||||
expect(text).toContain("</output>");
|
||||
});
|
||||
|
||||
test("content is truncated when exceeding quota", async () => {
|
||||
const longContent = "x".repeat(20_000);
|
||||
const hash = "01HASHLONG000000000000000001";
|
||||
const ctx: AgentContext = {
|
||||
start: startTask("task"),
|
||||
depth: 0,
|
||||
bundleHash: "TESTHASH00001",
|
||||
threadId: "01TEST000000000000000000TR",
|
||||
currentRole: { name: "r", systemPrompt: "S" },
|
||||
steps: [
|
||||
{
|
||||
role: "r",
|
||||
contentHash: hash,
|
||||
content: longContent,
|
||||
meta: {},
|
||||
refs: [],
|
||||
timestamp: 2,
|
||||
},
|
||||
],
|
||||
};
|
||||
const text = await buildAgentPrompt(ctx);
|
||||
expect(text).toContain("<output>");
|
||||
expect(text).toContain("... (truncated)");
|
||||
expect(text.length).toBeLessThan(20_000);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -5,7 +5,6 @@
|
||||
"packages/*"
|
||||
],
|
||||
"scripts": {
|
||||
"uwf": "bun packages/cli-workflow/src/cli.ts",
|
||||
"build": "bunx tsc --build",
|
||||
"check": "bunx tsc --build && biome check . && bash scripts/lint-log-tags.sh",
|
||||
"typecheck": "bunx tsc --build",
|
||||
|
||||
@@ -1,211 +0,0 @@
|
||||
# @uncaged/cli-workflow
|
||||
|
||||
`uwf` CLI — thread lifecycle, workflow registry, CAS inspection, and setup.
|
||||
|
||||
## Overview
|
||||
|
||||
Layer 4 entry point for the workflow engine. The `uwf` binary orchestrates one step per invocation: load thread head from `threads.yaml`, run the moderator, spawn the configured agent CLI, run extract, append a CAS step node, and update the head pointer (or archive when `$END`).
|
||||
|
||||
### Four-Layer Architecture
|
||||
|
||||
```
|
||||
workflow → thread → step → turn
|
||||
模板定义 执行实例 单步结果 agent内部交互
|
||||
```
|
||||
|
||||
- **Workflow** (layer 1): YAML template with roles and routing graph
|
||||
- **Thread** (layer 2): Single workflow execution instance
|
||||
- **Step** (layer 3): One moderator→agent→extract cycle
|
||||
- **Turn** (layer 4): Agent-internal interactions (use `step show` or CAS to inspect)
|
||||
|
||||
This package has no library `src/index.ts` — it is consumed as a CLI binary only.
|
||||
|
||||
**Dependencies:** `@uncaged/json-cas`, `@uncaged/json-cas-fs`, `@uncaged/workflow-agent-kit`, `@uncaged/workflow-moderator`, `@uncaged/workflow-protocol`, `@uncaged/workflow-util`, `commander`, `dotenv`, `yaml`
|
||||
|
||||
## Installation
|
||||
|
||||
Included as the `uwf` binary when you install `@uncaged/cli-workflow`:
|
||||
|
||||
```bash
|
||||
bun add -g @uncaged/cli-workflow
|
||||
# or from the monorepo:
|
||||
bun link packages/cli-workflow
|
||||
```
|
||||
|
||||
## CLI Usage
|
||||
|
||||
### Global options
|
||||
|
||||
```
|
||||
-V, --version Show version
|
||||
--format <json|yaml> Output format (default: json)
|
||||
-h, --help Show help
|
||||
```
|
||||
|
||||
### Thread (Layer 2: Execution Instances)
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf thread start <workflow> -p <prompt>` | Create a thread without executing |
|
||||
| `uwf thread exec <thread-id> [--agent <cmd>] [-c <count>] [--background]` | Execute one or more moderator→agent→extract cycles |
|
||||
| `uwf thread show <thread-id>` | Show thread head pointer |
|
||||
| `uwf thread list [--status <status>] [--after <date>] [--before <date>] [--skip <n>] [--take <n>]` | List threads filtered by status (idle, running, completed, active, or comma-separated), time range (ISO or relative like '7d'), with pagination |
|
||||
| `uwf thread read <thread-id> [--quota N] [--before <hash>] [--start]` | Render thread as readable markdown |
|
||||
|
||||
`thread read`, `step list`, and `step show` work on both active and completed threads.
|
||||
| `uwf thread stop <thread-id>` | Stop background execution (keep thread active) |
|
||||
| `uwf thread cancel <thread-id>` | Cancel thread (stop + archive to history) |
|
||||
|
||||
Examples:
|
||||
|
||||
```bash
|
||||
uwf thread start solve-issue -p "Fix the login redirect bug"
|
||||
uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV
|
||||
uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV -c 3 --agent uwf-builtin
|
||||
uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV --background
|
||||
uwf thread list --status running
|
||||
uwf thread list --status active
|
||||
uwf thread list --status idle,completed
|
||||
uwf thread list --after 7d --take 10
|
||||
uwf thread read 01ARZ3NDEKTSV4RRFFQ69G5FAV --quota 8000
|
||||
uwf thread stop 01ARZ3NDEKTSV4RRFFQ69G5FAV
|
||||
```
|
||||
|
||||
### Step (Layer 3: Single Cycle Results)
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf step list <thread-id>` | List all steps in a thread chronologically |
|
||||
| `uwf step show <step-hash>` | Show step metadata and frontmatter |
|
||||
| `uwf step read <step-hash> [--quota <chars>]` | Read a step's turns as human-readable markdown |
|
||||
| `uwf step fork <step-hash>` | Fork a thread from a specific step |
|
||||
|
||||
Examples:
|
||||
|
||||
```bash
|
||||
uwf step list 01ARZ3NDEKTSV4RRFFQ69G5FAV
|
||||
uwf step show 32GCDE899RRQ3
|
||||
uwf step read 32GCDE899RRQ3 --quota 2000
|
||||
uwf step fork 32GCDE899RRQ3
|
||||
```
|
||||
|
||||
### Workflow (Layer 1: Templates)
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf workflow add <file.yaml>` | Register a workflow from YAML |
|
||||
| `uwf workflow show <name-or-hash>` | Show workflow definition |
|
||||
| `uwf workflow list` | List registered workflows |
|
||||
|
||||
### CAS
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf cas get <hash> [--timestamp]` | Read a CAS node |
|
||||
| `uwf cas put <type-hash> <data>` | Store a node, print hash |
|
||||
| `uwf cas put-text <text>` | Store plain text, print hash |
|
||||
| `uwf cas has <hash>` | Check existence |
|
||||
| `uwf cas refs <hash>` | List direct references |
|
||||
| `uwf cas walk <hash>` | Recursive traversal |
|
||||
| `uwf cas reindex` | Rebuild type index |
|
||||
| `uwf cas schema list` | List registered schemas |
|
||||
| `uwf cas schema get <hash>` | Show a schema |
|
||||
|
||||
### Setup
|
||||
|
||||
```bash
|
||||
uwf setup
|
||||
uwf setup --provider openai --base-url https://api.openai.com/v1 \
|
||||
--api-key sk-... --model gpt-4o --agent hermes
|
||||
```
|
||||
|
||||
Config: `~/.uncaged/workflow/config.yaml`. API keys: `~/.uncaged/workflow/.env`.
|
||||
|
||||
### Skill
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf skill cli` | Print markdown reference of all uwf commands (for agent skills) |
|
||||
|
||||
### Log
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf log list` | List log files with sizes |
|
||||
| `uwf log show [--thread <id>] [--process <pid>] [--date YYYY-MM-DD]` | Show filtered log entries |
|
||||
| `uwf log clean [--before YYYY-MM-DD]` | Delete old log files |
|
||||
|
||||
## Migration Guide
|
||||
|
||||
### Breaking Changes (v0.x → v1.x)
|
||||
|
||||
The CLI was reorganized to clarify the four-layer architecture. **No backward compatibility** — old commands have been removed.
|
||||
|
||||
#### Renamed Commands
|
||||
|
||||
| Old Command | New Command | Notes |
|
||||
|------------|-------------|-------|
|
||||
| `workflow put` | `workflow add` | More intuitive verb |
|
||||
| `thread step` | `thread exec` | Eliminates ambiguity with "step" noun |
|
||||
| `thread list --all` | `thread list --status completed` | Unified status filtering |
|
||||
|
||||
#### Removed Commands (Merged)
|
||||
|
||||
| Old Command | New Command | Notes |
|
||||
|------------|-------------|-------|
|
||||
| `thread running` | `thread list --status running` | Merged into unified list |
|
||||
|
||||
#### Removed Commands (Split)
|
||||
|
||||
| Old Command | New Commands | Notes |
|
||||
|------------|-------------|-------|
|
||||
| `thread kill` | `thread stop` or `thread cancel` | `stop` keeps thread active, `cancel` archives it |
|
||||
|
||||
#### Moved Commands
|
||||
|
||||
| Old Command | New Command | Notes |
|
||||
|------------|-------------|-------|
|
||||
| `thread steps` | `step list` | Moved to step layer |
|
||||
| `thread step-details` | `step show` | Moved to step layer |
|
||||
| `thread fork` | `step fork` | Moved to step layer (forks are step-based) |
|
||||
|
||||
#### Deprecation Errors
|
||||
|
||||
Old commands now show helpful error messages:
|
||||
|
||||
```bash
|
||||
$ uwf thread step 01ARZ3NDEKTSV4RRFFQ69G5FAV
|
||||
Error: Command 'thread step' has been removed.
|
||||
Use 'thread exec' instead.
|
||||
|
||||
For more information, see: uwf help thread exec
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── cli.ts Commander entrypoint, command registration
|
||||
├── format.ts JSON/YAML output formatting
|
||||
├── store.ts CAS store + registry initialization
|
||||
├── validate.ts Workflow YAML validation
|
||||
├── schemas.ts CLI-local schema registration
|
||||
└── commands/
|
||||
├── thread.ts Thread lifecycle and exec
|
||||
├── step.ts Step operations (list/show/read/fork)
|
||||
├── workflow.ts Workflow registry (add/show/list)
|
||||
├── cas.ts CAS inspection and schema ops
|
||||
├── setup.ts Interactive/non-interactive setup
|
||||
├── skill.ts Built-in skill references
|
||||
└── log.ts Process debug log management
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `~/.uncaged/workflow/config.yaml` | Providers, models, default agent |
|
||||
| `~/.uncaged/workflow/.env` | API keys (referenced by `apiKeyEnv` in config) |
|
||||
| `~/.uncaged/workflow/registry.yaml` | Workflow name → CAS hash |
|
||||
| `~/.uncaged/workflow/threads.yaml` | Active thread head pointers |
|
||||
| `~/.uncaged/workflow/cas/` | Content-addressed node storage |
|
||||
@@ -1,152 +0,0 @@
|
||||
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
|
||||
});
|
||||
});
|
||||
@@ -1,74 +0,0 @@
|
||||
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 });
|
||||
});
|
||||
});
|
||||
@@ -1,108 +0,0 @@
|
||||
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);
|
||||
});
|
||||
});
|
||||
@@ -1,381 +0,0 @@
|
||||
import { mkdirSync, writeFileSync } from "node:fs";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { afterEach, describe, expect, test, vi } from "vitest";
|
||||
import {
|
||||
_discoverAgents,
|
||||
_isBackspace,
|
||||
_isTerminator,
|
||||
_parseWhichOutput,
|
||||
_printModelMenu,
|
||||
_printProviderMenu,
|
||||
_printValidationResult,
|
||||
_resolveModelChoice,
|
||||
_resolveProviderChoice,
|
||||
_searchPathDirs,
|
||||
} from "../commands/setup.js";
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 1a. _searchPathDirs
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_searchPathDirs", () => {
|
||||
test("returns empty array for empty PATH", async () => {
|
||||
const result = await _searchPathDirs("");
|
||||
expect(result).toEqual([]);
|
||||
});
|
||||
|
||||
test("finds uwf-hermes in a single dir", async () => {
|
||||
const dir = mkdirSync(join(tmpdir(), `uwf-test-${Date.now()}`), { recursive: true }) as
|
||||
| string
|
||||
| undefined;
|
||||
const actualDir = dir ?? join(tmpdir(), `uwf-test-${Date.now()}`);
|
||||
mkdirSync(actualDir, { recursive: true });
|
||||
const filePath = join(actualDir, "uwf-hermes");
|
||||
writeFileSync(filePath, "#!/bin/sh\n", { mode: 0o755 });
|
||||
const result = await _searchPathDirs(actualDir);
|
||||
expect(result).toContain("uwf-hermes");
|
||||
});
|
||||
|
||||
test("skips non-uwf- prefixed binaries", async () => {
|
||||
const dir = join(tmpdir(), `uwf-test-${Date.now()}-2`);
|
||||
mkdirSync(dir, { recursive: true });
|
||||
writeFileSync(join(dir, "hermes"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
writeFileSync(join(dir, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
const result = await _searchPathDirs(dir);
|
||||
expect(result).toEqual(["uwf-hermes"]);
|
||||
});
|
||||
|
||||
test("skips entry named exactly 'uwf'", async () => {
|
||||
const dir = join(tmpdir(), `uwf-test-${Date.now()}-3`);
|
||||
mkdirSync(dir, { recursive: true });
|
||||
writeFileSync(join(dir, "uwf"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
writeFileSync(join(dir, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
const result = await _searchPathDirs(dir);
|
||||
expect(result).toEqual(["uwf-hermes"]);
|
||||
});
|
||||
|
||||
test("skips non-executable files", async () => {
|
||||
const dir = join(tmpdir(), `uwf-test-${Date.now()}-4`);
|
||||
mkdirSync(dir, { recursive: true });
|
||||
writeFileSync(join(dir, "uwf-foo"), "#!/bin/sh\n", { mode: 0o644 });
|
||||
const result = await _searchPathDirs(dir);
|
||||
expect(result).toEqual([]);
|
||||
});
|
||||
|
||||
test("deduplicates across PATH dirs", async () => {
|
||||
const dir1 = join(tmpdir(), `uwf-test-${Date.now()}-5a`);
|
||||
const dir2 = join(tmpdir(), `uwf-test-${Date.now()}-5b`);
|
||||
mkdirSync(dir1, { recursive: true });
|
||||
mkdirSync(dir2, { recursive: true });
|
||||
writeFileSync(join(dir1, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
writeFileSync(join(dir2, "uwf-hermes"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
const result = await _searchPathDirs(`${dir1}:${dir2}`);
|
||||
expect(result).toEqual(["uwf-hermes"]);
|
||||
});
|
||||
|
||||
test("returns sorted array", async () => {
|
||||
const dir = join(tmpdir(), `uwf-test-${Date.now()}-6`);
|
||||
mkdirSync(dir, { recursive: true });
|
||||
writeFileSync(join(dir, "uwf-zoo"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
writeFileSync(join(dir, "uwf-alpha"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
writeFileSync(join(dir, "uwf-mid"), "#!/bin/sh\n", { mode: 0o755 });
|
||||
const result = await _searchPathDirs(dir);
|
||||
expect(result).toEqual(["uwf-alpha", "uwf-mid", "uwf-zoo"]);
|
||||
});
|
||||
|
||||
test("skips inaccessible/nonexistent directories silently", async () => {
|
||||
const result = await _searchPathDirs("/nonexistent-dir-xyz-abc-12345");
|
||||
expect(result).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 1b. _parseWhichOutput
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_parseWhichOutput", () => {
|
||||
test("returns empty array for empty string", () => {
|
||||
expect(_parseWhichOutput("")).toEqual([]);
|
||||
});
|
||||
|
||||
test("parses single path", () => {
|
||||
expect(_parseWhichOutput("/usr/local/bin/uwf-hermes")).toEqual(["uwf-hermes"]);
|
||||
});
|
||||
|
||||
test("parses multiple paths", () => {
|
||||
expect(_parseWhichOutput("/usr/local/bin/uwf-hermes\n/usr/bin/uwf-claude-code")).toEqual([
|
||||
"uwf-claude-code",
|
||||
"uwf-hermes",
|
||||
]);
|
||||
});
|
||||
|
||||
test("deduplicates identical basenames from different dirs", () => {
|
||||
expect(_parseWhichOutput("/a/uwf-hermes\n/b/uwf-hermes")).toEqual(["uwf-hermes"]);
|
||||
});
|
||||
|
||||
test("skips blank lines", () => {
|
||||
expect(_parseWhichOutput("/a/uwf-hermes\n\n/b/uwf-cursor")).toEqual([
|
||||
"uwf-cursor",
|
||||
"uwf-hermes",
|
||||
]);
|
||||
});
|
||||
|
||||
test("skips entry named exactly 'uwf'", () => {
|
||||
expect(_parseWhichOutput("/usr/bin/uwf")).toEqual([]);
|
||||
});
|
||||
|
||||
test("skips basenames not starting with uwf-", () => {
|
||||
expect(_parseWhichOutput("/usr/bin/node")).toEqual([]);
|
||||
});
|
||||
|
||||
test("returns sorted array", () => {
|
||||
expect(_parseWhichOutput("/a/uwf-zoo\n/a/uwf-alpha")).toEqual(["uwf-alpha", "uwf-zoo"]);
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 2a. _isTerminator
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_isTerminator", () => {
|
||||
test("\\n is a terminator", () => {
|
||||
expect(_isTerminator("\n")).toBe(true);
|
||||
});
|
||||
test("\\r is a terminator", () => {
|
||||
expect(_isTerminator("\r")).toBe(true);
|
||||
});
|
||||
test("\\u0004 (EOT) is a terminator", () => {
|
||||
expect(_isTerminator("")).toBe(true);
|
||||
});
|
||||
test("regular char is not a terminator", () => {
|
||||
expect(_isTerminator("a")).toBe(false);
|
||||
});
|
||||
test("empty string is not a terminator", () => {
|
||||
expect(_isTerminator("")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 2b. _isBackspace
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_isBackspace", () => {
|
||||
test("\\u007F is a backspace", () => {
|
||||
expect(_isBackspace("")).toBe(true);
|
||||
});
|
||||
test("\\b is a backspace", () => {
|
||||
expect(_isBackspace("\b")).toBe(true);
|
||||
});
|
||||
test("regular char is not a backspace", () => {
|
||||
expect(_isBackspace("x")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 3a. _printProviderMenu
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_printProviderMenu", () => {
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
const providers = [
|
||||
{ name: "openai", label: "OpenAI", baseUrl: "https://api.openai.com/v1" },
|
||||
{ name: "xai", label: "xAI", baseUrl: "https://api.x.ai/v1" },
|
||||
] as const;
|
||||
|
||||
test("prints correct number of lines (one per provider + custom)", () => {
|
||||
const lines: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
lines.push(msg);
|
||||
});
|
||||
_printProviderMenu(providers);
|
||||
// 2 providers + 1 custom = 3 lines
|
||||
expect(lines.length).toBe(3);
|
||||
});
|
||||
|
||||
test("custom option number = providers.length + 1", () => {
|
||||
const lines: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
lines.push(msg);
|
||||
});
|
||||
_printProviderMenu(providers);
|
||||
const lastLine = lines[lines.length - 1] ?? "";
|
||||
expect(lastLine).toMatch(/3\)/);
|
||||
});
|
||||
|
||||
test("each provider line contains its label and baseUrl", () => {
|
||||
const lines: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
lines.push(msg);
|
||||
});
|
||||
_printProviderMenu(providers);
|
||||
expect(lines[0]).toContain("OpenAI");
|
||||
expect(lines[0]).toContain("https://api.openai.com/v1");
|
||||
expect(lines[1]).toContain("xAI");
|
||||
expect(lines[1]).toContain("https://api.x.ai/v1");
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 3b. _resolveProviderChoice
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_resolveProviderChoice", () => {
|
||||
const providers = [
|
||||
{ name: "openai", label: "OpenAI", baseUrl: "https://api.openai.com/v1" },
|
||||
{ name: "xai", label: "xAI", baseUrl: "https://api.x.ai/v1" },
|
||||
{ name: "deepseek", label: "DeepSeek", baseUrl: "https://api.deepseek.com/v1" },
|
||||
] as const;
|
||||
|
||||
test("valid index 1 returns first provider", () => {
|
||||
const result = _resolveProviderChoice("1", providers);
|
||||
expect(result).toEqual({ providerName: "openai", baseUrl: "https://api.openai.com/v1" });
|
||||
});
|
||||
|
||||
test("valid index N (last preset) returns last provider", () => {
|
||||
const result = _resolveProviderChoice("3", providers);
|
||||
expect(result).toEqual({ providerName: "deepseek", baseUrl: "https://api.deepseek.com/v1" });
|
||||
});
|
||||
|
||||
test("index providers.length+1 (custom) returns null", () => {
|
||||
const result = _resolveProviderChoice("4", providers);
|
||||
expect(result).toBeNull();
|
||||
});
|
||||
|
||||
test("non-numeric string returns null", () => {
|
||||
expect(_resolveProviderChoice("abc", providers)).toBeNull();
|
||||
});
|
||||
|
||||
test("0 returns null (out of range)", () => {
|
||||
expect(_resolveProviderChoice("0", providers)).toBeNull();
|
||||
});
|
||||
|
||||
test("N+2 returns null (out of range)", () => {
|
||||
expect(_resolveProviderChoice("5", providers)).toBeNull();
|
||||
});
|
||||
|
||||
test("negative number returns null", () => {
|
||||
expect(_resolveProviderChoice("-1", providers)).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 3c. _resolveModelChoice
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_resolveModelChoice", () => {
|
||||
test("numeric input within range returns model at that index", () => {
|
||||
expect(_resolveModelChoice("2", ["a", "b", "c"])).toBe("b");
|
||||
});
|
||||
|
||||
test("numeric input out of range returns input as-is", () => {
|
||||
expect(_resolveModelChoice("5", ["a"])).toBe("5");
|
||||
});
|
||||
|
||||
test("non-numeric input returns input as-is", () => {
|
||||
expect(_resolveModelChoice("gpt-4o", ["a", "b"])).toBe("gpt-4o");
|
||||
});
|
||||
|
||||
test("numeric input 1 returns first model", () => {
|
||||
expect(_resolveModelChoice("1", ["alpha", "beta"])).toBe("alpha");
|
||||
});
|
||||
|
||||
test("empty models list with numeric input returns input as-is", () => {
|
||||
expect(_resolveModelChoice("1", [])).toBe("1");
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 3d. _printModelMenu
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_printModelMenu", () => {
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
test("prints all models — each model name appears in output", () => {
|
||||
const output: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
output.push(msg);
|
||||
});
|
||||
const models = ["model-a", "model-b", "model-c"];
|
||||
_printModelMenu(models, 100);
|
||||
const combined = output.join("\n");
|
||||
for (const m of models) {
|
||||
expect(combined).toContain(m);
|
||||
}
|
||||
});
|
||||
|
||||
test("single column when termCols is very small", () => {
|
||||
const output: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
output.push(msg);
|
||||
});
|
||||
_printModelMenu(["a", "b", "c"], 1);
|
||||
// Each model on its own row → 3 lines
|
||||
expect(output.length).toBe(3);
|
||||
});
|
||||
|
||||
test("wide terminal fits multiple columns", () => {
|
||||
const output: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
output.push(msg);
|
||||
});
|
||||
const models = Array.from({ length: 6 }, (_, i) => `m${i}`);
|
||||
_printModelMenu(models, 200);
|
||||
// With wide terminal and short names, should fit in fewer than 6 rows
|
||||
expect(output.length).toBeLessThan(6);
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 3e. _printValidationResult
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_printValidationResult", () => {
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
test("ok=true prints success message containing '✓'", () => {
|
||||
const lines: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
lines.push(msg);
|
||||
});
|
||||
_printValidationResult({ ok: true, error: null });
|
||||
expect(lines.join("\n")).toContain("✓");
|
||||
});
|
||||
|
||||
test("ok=false prints warning message containing '⚠'", () => {
|
||||
const lines: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
lines.push(msg);
|
||||
});
|
||||
_printValidationResult({ ok: false, error: "HTTP 401" });
|
||||
expect(lines.join("\n")).toContain("⚠");
|
||||
});
|
||||
|
||||
test("ok=false includes the error string in output", () => {
|
||||
const lines: string[] = [];
|
||||
vi.spyOn(console, "log").mockImplementation((msg: string) => {
|
||||
lines.push(msg);
|
||||
});
|
||||
_printValidationResult({ ok: false, error: "HTTP 401" });
|
||||
expect(lines.join("\n")).toContain("HTTP 401");
|
||||
});
|
||||
});
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// 4. Regression
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("_discoverAgents regression", () => {
|
||||
test("returns an array (may be empty) — never throws", async () => {
|
||||
const result = await _discoverAgents();
|
||||
expect(Array.isArray(result)).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -1,97 +0,0 @@
|
||||
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 success field", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
// Parse as any to access the raw YAML structure (frontmatter is inline JSON Schema in YAML)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const workflow = parse(yamlContent) as any;
|
||||
|
||||
const frontmatter = workflow.roles.committer?.frontmatter;
|
||||
expect(frontmatter).toBeDefined();
|
||||
expect(frontmatter?.type).toBe("object");
|
||||
expect(frontmatter?.properties?.success).toBeDefined();
|
||||
expect(frontmatter?.properties?.success?.type).toBe("boolean");
|
||||
expect(frontmatter?.required).toContain("success");
|
||||
});
|
||||
});
|
||||
@@ -1,519 +0,0 @@
|
||||
import { mkdir, mkdtemp, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { bootstrap, putSchema } from "@uncaged/json-cas";
|
||||
import { createFsStore } from "@uncaged/json-cas-fs";
|
||||
import type { CasRef } 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)");
|
||||
});
|
||||
});
|
||||
@@ -1,550 +0,0 @@
|
||||
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();
|
||||
});
|
||||
});
|
||||
@@ -1,583 +0,0 @@
|
||||
import { mkdir, mkdtemp, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { bootstrap, putSchema } from "@uncaged/json-cas";
|
||||
import { createFsStore } from "@uncaged/json-cas-fs";
|
||||
import type { CasRef, ThreadId } from "@uncaged/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);
|
||||
});
|
||||
});
|
||||
@@ -1,683 +0,0 @@
|
||||
import { mkdir, mkdtemp, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { bootstrap, putSchema } from "@uncaged/json-cas";
|
||||
import { createFsStore } from "@uncaged/json-cas-fs";
|
||||
import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
|
||||
import { afterEach, beforeEach, describe, expect, test } from "vitest";
|
||||
import { cmdThreadRead, THREAD_READ_DEFAULT_QUOTA } from "../commands/thread.js";
|
||||
import { registerUwfSchemas } from "../schemas.js";
|
||||
import type { UwfStore } from "../store.js";
|
||||
import { saveThreadsIndex } from "../store.js";
|
||||
|
||||
// ── schemas used in tests ────────────────────────────────────────────────────
|
||||
|
||||
const TURN_SCHEMA = {
|
||||
title: "hermes-turn",
|
||||
type: "object" as const,
|
||||
required: ["index", "role", "content"],
|
||||
properties: {
|
||||
index: { type: "integer" as const },
|
||||
role: { type: "string" as const },
|
||||
content: { type: "string" as const },
|
||||
toolCalls: {
|
||||
anyOf: [
|
||||
{ type: "array" as const, items: { type: "object" as const } },
|
||||
{ type: "null" as const },
|
||||
],
|
||||
},
|
||||
reasoning: { anyOf: [{ type: "string" as const }, { type: "null" as const }] },
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
const DETAIL_SCHEMA = {
|
||||
title: "hermes-detail",
|
||||
type: "object" as const,
|
||||
required: ["sessionId", "model", "duration", "turnCount", "turns"],
|
||||
properties: {
|
||||
sessionId: { type: "string" as const },
|
||||
model: { type: "string" as const },
|
||||
duration: { type: "integer" as const },
|
||||
turnCount: { type: "integer" as const },
|
||||
turns: {
|
||||
type: "array" as const,
|
||||
items: { type: "string" as const, format: "cas_ref" },
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
// ── helpers ───────────────────────────────────────────────────────────────────
|
||||
|
||||
async function makeUwfStore(storageRoot: string): Promise<UwfStore> {
|
||||
const casDir = join(storageRoot, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
return { storageRoot, store, schemas };
|
||||
}
|
||||
|
||||
async function registerDetailSchemas(store: ReturnType<typeof createFsStore>) {
|
||||
await bootstrap(store);
|
||||
const [turn, detail] = await Promise.all([
|
||||
putSchema(store, TURN_SCHEMA),
|
||||
putSchema(store, DETAIL_SCHEMA),
|
||||
]);
|
||||
return { turn, detail };
|
||||
}
|
||||
|
||||
// ── fixture ───────────────────────────────────────────────────────────────────
|
||||
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-test-"));
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
// ── thread read XML tag isolation ─────────────────────────────────────────────
|
||||
|
||||
describe("thread read XML tag isolation", () => {
|
||||
test("scenario 1: wraps output in XML tags instead of heading", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const detailSchemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
planner: {
|
||||
description: "Planner",
|
||||
goal: "You are a planning agent. Your task is to...",
|
||||
capabilities: [],
|
||||
procedure: "Plan the work.",
|
||||
output: "Summarize the plan.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Fix issue #459",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const turnHash = await uwf.store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content:
|
||||
"---\nstatus: ready\nplan: CMWGHQKT58RY4\n---\n\n# Analysis Complete\n## Issue Summary\nThe issue requires XML tag isolation.",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await uwf.store.put(detailSchemas.detail, {
|
||||
sessionId: "sx",
|
||||
model: "mx",
|
||||
duration: 500,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "planner",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-claude-code",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000001" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
// Should wrap output in XML tags
|
||||
expect(markdown).toContain("<output>");
|
||||
expect(markdown).toContain("</output>");
|
||||
|
||||
// Should not have ### Content heading
|
||||
expect(markdown).not.toContain("### Content");
|
||||
|
||||
// Should preserve markdown headings inside output tags
|
||||
expect(markdown).toContain("# Analysis Complete");
|
||||
expect(markdown).toContain("## Issue Summary");
|
||||
});
|
||||
|
||||
test("scenario 2: wraps prompt in XML tags", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const detailSchemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
planner: {
|
||||
description: "Planner",
|
||||
goal: "You are a planning agent. Your task is to analyze and plan.",
|
||||
capabilities: [],
|
||||
procedure: "Plan the work.",
|
||||
output: "Summarize the plan.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Fix issue",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const turnHash = await uwf.store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "---\nstatus: ready\n---\n\nContent here...",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await uwf.store.put(detailSchemas.detail, {
|
||||
sessionId: "sx",
|
||||
model: "mx",
|
||||
duration: 500,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "planner",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-claude-code",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000002" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
// Should wrap prompt in XML tags
|
||||
expect(markdown).toContain("<prompt>");
|
||||
expect(markdown).toContain("</prompt>");
|
||||
expect(markdown).toContain("You are a planning agent. Your task is to analyze and plan.");
|
||||
|
||||
// Should not have ### Prompt heading
|
||||
expect(markdown).not.toContain("### Prompt");
|
||||
|
||||
// Should wrap output in XML tags
|
||||
expect(markdown).toContain("<output>");
|
||||
expect(markdown).toContain("</output>");
|
||||
});
|
||||
|
||||
test("scenario 3: same role repeated does not show prompt twice", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
writer: {
|
||||
description: "Writer",
|
||||
goal: "You are a writer agent.",
|
||||
capabilities: [],
|
||||
procedure: "Write content.",
|
||||
output: "Summarize writing.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Write something",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const step1 = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "writer",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const step2 = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: step1 as CasRef,
|
||||
role: "writer",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000003" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: step2 });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
// Should only show prompt tags once
|
||||
const promptCount = (markdown.match(/<prompt>/g) ?? []).length;
|
||||
expect(promptCount).toBe(1);
|
||||
});
|
||||
|
||||
test("scenario 4: step with no detail shows no output tags", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
worker: {
|
||||
description: "Worker",
|
||||
goal: "You are a worker agent.",
|
||||
capabilities: [],
|
||||
procedure: "Do work.",
|
||||
output: "Summarize work.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Do stuff",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000004" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
// Should not have output tags
|
||||
expect(markdown).not.toContain("<output>");
|
||||
expect(markdown).not.toContain("</output>");
|
||||
|
||||
// Step header should still be displayed
|
||||
expect(markdown).toContain("## Step 1: worker");
|
||||
|
||||
// Prompt should still be shown
|
||||
expect(markdown).toContain("<prompt>");
|
||||
});
|
||||
|
||||
test("scenario 5: empty content shows no output tags", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Do stuff",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
// A detail ref that doesn't exist → extractLastAssistantContent returns null
|
||||
const missingDetailRef = "missingdetail0" as CasRef;
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: missingDetailRef,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000005" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
// Should not have output tags
|
||||
expect(markdown).not.toContain("<output>");
|
||||
expect(markdown).not.toContain("</output>");
|
||||
});
|
||||
|
||||
test("scenario 6: thread read with --start flag shows task section", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
roleA: {
|
||||
description: "Role A",
|
||||
goal: "Goal for roleA",
|
||||
capabilities: [],
|
||||
procedure: "Do stuff.",
|
||||
output: "Output.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Initial prompt",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "roleA",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000006" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, true);
|
||||
|
||||
// Should include task section
|
||||
expect(markdown).toContain("# Thread");
|
||||
expect(markdown).toContain("## Task");
|
||||
expect(markdown).toContain("Initial prompt");
|
||||
|
||||
// Prompts should use XML tags
|
||||
expect(markdown).toContain("<prompt>");
|
||||
});
|
||||
|
||||
test("scenario 7: thread read with --before parameter", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
roleA: {
|
||||
description: "Role A",
|
||||
goal: "Goal for roleA",
|
||||
capabilities: [],
|
||||
procedure: "Do stuff.",
|
||||
output: "Output.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
roleB: {
|
||||
description: "Role B",
|
||||
goal: "Goal for roleB",
|
||||
capabilities: [],
|
||||
procedure: "Do stuff.",
|
||||
output: "Output.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
roleC: {
|
||||
description: "Role C",
|
||||
goal: "Goal for roleC",
|
||||
capabilities: [],
|
||||
procedure: "Do stuff.",
|
||||
output: "Output.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Initial prompt",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const step1 = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "roleA",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const step2 = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: step1 as CasRef,
|
||||
role: "roleB",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const step3 = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: step2 as CasRef,
|
||||
role: "roleC",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000007" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: step3 });
|
||||
|
||||
const markdown = await cmdThreadRead(
|
||||
tmpDir,
|
||||
threadId,
|
||||
THREAD_READ_DEFAULT_QUOTA,
|
||||
step2 as CasRef,
|
||||
false,
|
||||
);
|
||||
|
||||
// Should only show roleA
|
||||
expect(markdown).toContain("roleA");
|
||||
expect(markdown).not.toContain("roleB");
|
||||
expect(markdown).not.toContain("roleC");
|
||||
|
||||
// Should use XML tags
|
||||
expect(markdown).toContain("<prompt>");
|
||||
});
|
||||
|
||||
test("scenario 9: special characters in content are preserved", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const detailSchemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
writer: {
|
||||
description: "Writer",
|
||||
goal: "You are a writer.",
|
||||
capabilities: [],
|
||||
procedure: "Write content.",
|
||||
output: "Summarize.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Write something",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const turnHash = await uwf.store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "Content with <special> & characters > like <this>",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await uwf.store.put(detailSchemas.detail, {
|
||||
sessionId: "sx",
|
||||
model: "mx",
|
||||
duration: 500,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "writer",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000008" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
// Special characters should be preserved as-is
|
||||
expect(markdown).toContain("Content with <special> & characters > like <this>");
|
||||
});
|
||||
|
||||
test("scenario 10: quota limit with XML tags", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
roleA: {
|
||||
description: "Role A",
|
||||
goal: "Goal for roleA",
|
||||
capabilities: [],
|
||||
procedure: "Do stuff.",
|
||||
output: "Output.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Initial prompt",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const steps: CasRef[] = [];
|
||||
let prev: CasRef | null = null;
|
||||
for (let i = 0; i < 5; i++) {
|
||||
const step = (await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev,
|
||||
role: "roleA",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
})) as CasRef;
|
||||
steps.push(step);
|
||||
prev = step;
|
||||
}
|
||||
|
||||
const threadId = "01JTEST0000000000000009" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: steps[steps.length - 1]! });
|
||||
|
||||
// Use very small quota
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 1, null, false);
|
||||
|
||||
// Should have skip hint
|
||||
expect(markdown).toContain("earlier step");
|
||||
|
||||
// Should have XML tags for displayed steps
|
||||
if (markdown.includes("<prompt>")) {
|
||||
expect(markdown).toContain("</prompt>");
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -22,48 +22,48 @@ function runCli(args: string[]): { stdout: string; stderr: string; exitCode: num
|
||||
}
|
||||
}
|
||||
|
||||
describe("thread exec --count CLI parsing", () => {
|
||||
describe("thread step --count CLI parsing", () => {
|
||||
test("--help shows -c/--count option", () => {
|
||||
const result = runCli(["thread", "exec", "--help"]);
|
||||
const result = runCli(["thread", "step", "--help"]);
|
||||
expect(result.stdout).toContain("--count");
|
||||
expect(result.stdout).toContain("-c");
|
||||
});
|
||||
|
||||
test("description says 'one or more steps'", () => {
|
||||
const result = runCli(["thread", "exec", "--help"]);
|
||||
const result = runCli(["thread", "step", "--help"]);
|
||||
expect(result.stdout).toContain("one or more steps");
|
||||
});
|
||||
});
|
||||
|
||||
describe("cmdThreadExec count logic", () => {
|
||||
describe("cmdThreadStep count logic", () => {
|
||||
test("count=0 fails with validation error", () => {
|
||||
const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "0"]);
|
||||
const result = runCli(["thread", "step", "FAKE_THREAD_ID", "-c", "0"]);
|
||||
expect(result.exitCode).not.toBe(0);
|
||||
expect(result.stderr).toContain("positive integer");
|
||||
});
|
||||
|
||||
test("negative count fails with validation error", () => {
|
||||
const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "-1"]);
|
||||
const result = runCli(["thread", "step", "FAKE_THREAD_ID", "-c", "-1"]);
|
||||
expect(result.exitCode).not.toBe(0);
|
||||
expect(result.stderr).toContain("positive integer");
|
||||
});
|
||||
|
||||
test("non-integer count fails with validation error", () => {
|
||||
const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "1.5"]);
|
||||
const result = runCli(["thread", "step", "FAKE_THREAD_ID", "-c", "1.5"]);
|
||||
expect(result.exitCode).not.toBe(0);
|
||||
expect(result.stderr).toContain("positive integer");
|
||||
});
|
||||
|
||||
test("count=1 is the default (no -c flag)", () => {
|
||||
// Without -c, it should attempt to run 1 step (failing on missing thread, not on count validation)
|
||||
const result = runCli(["thread", "exec", "FAKE_THREAD_ID"]);
|
||||
const result = runCli(["thread", "step", "FAKE_THREAD_ID"]);
|
||||
expect(result.exitCode).not.toBe(0);
|
||||
// Should NOT contain "positive integer" error — should fail on thread lookup instead
|
||||
expect(result.stderr).not.toContain("positive integer");
|
||||
});
|
||||
|
||||
test("count=3 passes validation (fails on thread lookup)", () => {
|
||||
const result = runCli(["thread", "exec", "FAKE_THREAD_ID", "-c", "3"]);
|
||||
const result = runCli(["thread", "step", "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");
|
||||
|
||||
@@ -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 { appendThreadHistory, saveThreadsIndex } from "../store.js";
|
||||
import { saveThreadsIndex } from "../store.js";
|
||||
|
||||
// ── schemas used in tests ────────────────────────────────────────────────────
|
||||
|
||||
@@ -198,10 +198,10 @@ describe("extractLastAssistantContent", () => {
|
||||
});
|
||||
});
|
||||
|
||||
// ── cmdThreadRead: <output> section ──────────────────────────────────────────
|
||||
// ── cmdThreadRead: ### Content section ───────────────────────────────────────
|
||||
|
||||
describe("cmdThreadRead <output> section", () => {
|
||||
test("includes <output> tags when detail has assistant turns", async () => {
|
||||
describe("cmdThreadRead ### Content section", () => {
|
||||
test("includes ### Content before ### Output when detail has assistant turns", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const detailSchemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
@@ -264,13 +264,12 @@ describe("cmdThreadRead <output> section", () => {
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
expect(markdown).toContain("<output>");
|
||||
expect(markdown).toContain("</output>");
|
||||
expect(markdown).toContain("### Content");
|
||||
expect(markdown).toContain("The assistant response text");
|
||||
expect(markdown).not.toContain("### Content");
|
||||
expect(markdown).not.toContain("### Output");
|
||||
});
|
||||
|
||||
test("omits <output> tags when detail has no matching assistant turns", async () => {
|
||||
test("omits ### Content when detail has no matching assistant turns", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
@@ -309,15 +308,14 @@ describe("cmdThreadRead <output> section", () => {
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
expect(markdown).not.toContain("<output>");
|
||||
expect(markdown).not.toContain("</output>");
|
||||
expect(markdown).not.toContain("### Content");
|
||||
expect(markdown).not.toContain("### Output");
|
||||
});
|
||||
});
|
||||
|
||||
// ── cmdStepShow ───────────────────────────────────────────────────────────────
|
||||
// ── cmdThreadStepDetails ──────────────────────────────────────────────────────
|
||||
|
||||
describe("cmdStepShow", () => {
|
||||
describe("cmdThreadStepDetails", () => {
|
||||
test("returns expanded detail node with turns inlined", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const detailSchemas = await registerDetailSchemas(uwf.store);
|
||||
@@ -365,7 +363,7 @@ describe("cmdStepShow", () => {
|
||||
agent: "uwf-hermes",
|
||||
});
|
||||
|
||||
const result = await cmdStepShow(tmpDir, stepHash);
|
||||
const result = await cmdThreadStepDetails(tmpDir, stepHash);
|
||||
|
||||
expect(result).toMatchObject({
|
||||
sessionId: "sess42",
|
||||
@@ -384,11 +382,15 @@ describe("cmdStepShow", () => {
|
||||
content: "done",
|
||||
});
|
||||
});
|
||||
|
||||
test("throws when step hash does not exist", async () => {
|
||||
await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
// ── cmdThreadRead: <prompt> deduplication ────────────────────────────────────
|
||||
// ── cmdThreadRead: ### Prompt deduplication ───────────────────────────────────
|
||||
|
||||
describe("cmdThreadRead <prompt> deduplication", () => {
|
||||
describe("cmdThreadRead ### Prompt deduplication", () => {
|
||||
async function makeThreadWithRoles(uwf: UwfStore, roles: string[]): Promise<string> {
|
||||
const roleMap: Record<string, unknown> = {};
|
||||
for (const r of [...new Set(roles)]) {
|
||||
@@ -436,594 +438,36 @@ describe("cmdThreadRead <prompt> deduplication", () => {
|
||||
return stepHash;
|
||||
}
|
||||
|
||||
test("same consecutive role shows <prompt> once", async () => {
|
||||
test("same consecutive role shows ### Prompt once", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const headHash = await makeThreadWithRoles(uwf, ["writer", "writer"]);
|
||||
const threadId = "01JTEST0000000000000003" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: headHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
const count = (markdown.match(/<prompt>/g) ?? []).length;
|
||||
const count = (markdown.match(/### Prompt/g) ?? []).length;
|
||||
expect(count).toBe(1);
|
||||
});
|
||||
|
||||
test("different consecutive roles each show <prompt>", async () => {
|
||||
test("different consecutive roles each show ### Prompt", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const headHash = await makeThreadWithRoles(uwf, ["planner", "coder"]);
|
||||
const threadId = "01JTEST0000000000000004" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: headHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
const count = (markdown.match(/<prompt>/g) ?? []).length;
|
||||
const count = (markdown.match(/### Prompt/g) ?? []).length;
|
||||
expect(count).toBe(2);
|
||||
});
|
||||
|
||||
test("non-consecutive same role shows <prompt> twice", async () => {
|
||||
test("non-consecutive same role shows ### Prompt twice", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const headHash = await makeThreadWithRoles(uwf, ["roleA", "roleB", "roleA"]);
|
||||
const threadId = "01JTEST0000000000000005" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: headHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
const count = (markdown.match(/<prompt>/g) ?? []).length;
|
||||
const count = (markdown.match(/### Prompt/g) ?? []).length;
|
||||
expect(count).toBe(2);
|
||||
});
|
||||
});
|
||||
|
||||
// ── cmdThreadRead: showStart / before / quota ─────────────────────────────────
|
||||
|
||||
describe("cmdThreadRead start section / before / quota", () => {
|
||||
async function makeSimpleThread(
|
||||
uwf: UwfStore,
|
||||
roles: string[],
|
||||
): Promise<{ startHash: CasRef; stepHashes: CasRef[] }> {
|
||||
const uniqueRoles = [...new Set(roles)];
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "simple-wf",
|
||||
description: "desc",
|
||||
roles: Object.fromEntries(
|
||||
uniqueRoles.map((r) => [
|
||||
r,
|
||||
{
|
||||
description: r,
|
||||
goal: `Goal for ${r}`,
|
||||
capabilities: [],
|
||||
procedure: "Do stuff.",
|
||||
output: "Output.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
]),
|
||||
),
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
const startHash = (await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Initial prompt",
|
||||
})) as CasRef;
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const stepHashes: CasRef[] = [];
|
||||
let prev: CasRef | null = null;
|
||||
for (const role of roles) {
|
||||
const stepHash = (await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev,
|
||||
role,
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
})) as CasRef;
|
||||
stepHashes.push(stepHash);
|
||||
prev = stepHash;
|
||||
}
|
||||
return { startHash, stepHashes };
|
||||
}
|
||||
|
||||
test("showStart=true includes # Thread header and ## Task section", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const { stepHashes } = await makeSimpleThread(uwf, ["roleA"]);
|
||||
const threadId = "01JTEST0000000000000006" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[stepHashes.length - 1]! });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, true);
|
||||
expect(markdown).toContain("# Thread");
|
||||
expect(markdown).toContain("## Task");
|
||||
expect(markdown).toContain("Initial prompt");
|
||||
});
|
||||
|
||||
test("showStart=false with before=null still shows # Thread header (default behavior)", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const { stepHashes } = await makeSimpleThread(uwf, ["roleA"]);
|
||||
const threadId = "01JTEST0000000000000007" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[stepHashes.length - 1]! });
|
||||
|
||||
// When before=null, the start section is always shown regardless of showStart
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
expect(markdown).toContain("# Thread");
|
||||
expect(markdown).toContain("## Task");
|
||||
});
|
||||
|
||||
test("before filter: only steps before the given hash appear", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const { stepHashes } = await makeSimpleThread(uwf, ["roleA", "roleB", "roleC"]);
|
||||
const [_hashA, hashB, hashC] = stepHashes as [CasRef, CasRef, CasRef];
|
||||
const threadId = "01JTEST0000000000000008" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: hashC });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, hashB, false);
|
||||
expect(markdown).toContain("roleA");
|
||||
expect(markdown).not.toContain("roleB");
|
||||
expect(markdown).not.toContain("roleC");
|
||||
});
|
||||
|
||||
test("quota=1 limits output and includes skip hint", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const { stepHashes } = await makeSimpleThread(uwf, ["roleA", "roleB", "roleC"]);
|
||||
const threadId = "01JTEST000000000000000A" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[stepHashes.length - 1]! });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 1, null, false);
|
||||
expect(markdown).toContain("earlier step");
|
||||
});
|
||||
|
||||
test("all steps fit in quota: no skip hint", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const { stepHashes } = await makeSimpleThread(uwf, ["roleA"]);
|
||||
const threadId = "01JTEST000000000000000B" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[0]! });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
expect(markdown).not.toContain("earlier step");
|
||||
});
|
||||
});
|
||||
|
||||
// ── Tests that call process.exit must be last ─────────────────────────────────
|
||||
|
||||
describe("cmdStepShow (process.exit tests - must be last)", () => {
|
||||
test("throws when step hash does not exist", async () => {
|
||||
await expect(cmdStepShow(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("before with unknown hash rejects", async () => {
|
||||
const _uwf = await makeUwfStore(tmpDir);
|
||||
const casDir = join(tmpDir, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
const uwfStore: UwfStore = { storageRoot: tmpDir, store, schemas };
|
||||
|
||||
const workflowHash = await uwfStore.store.put(uwfStore.schemas.workflow, {
|
||||
name: "wf2",
|
||||
description: "",
|
||||
roles: {
|
||||
roleA: {
|
||||
description: "r",
|
||||
goal: "g",
|
||||
capabilities: [],
|
||||
procedure: "p",
|
||||
output: "o",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
const startHash = await uwfStore.store.put(uwfStore.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "p",
|
||||
});
|
||||
const outputHash = await uwfStore.store.put(uwfStore.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
const stepHash = await uwfStore.store.put(uwfStore.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "roleA",
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
await saveThreadsIndex(tmpDir, { ["01JTEST000000000000000C" as ThreadId]: stepHash as CasRef });
|
||||
|
||||
await expect(
|
||||
cmdThreadRead(
|
||||
tmpDir,
|
||||
"01JTEST000000000000000C" as ThreadId,
|
||||
THREAD_READ_DEFAULT_QUOTA,
|
||||
"unknownhash0" as CasRef,
|
||||
false,
|
||||
),
|
||||
).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");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -25,6 +25,7 @@ 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);
|
||||
@@ -35,6 +36,7 @@ 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);
|
||||
@@ -143,7 +145,7 @@ 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 and graph");
|
||||
await writeFile(yamlPath, "name: test\n# missing roles, conditions, and graph");
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
|
||||
@@ -1,147 +0,0 @@
|
||||
import { mkdir, readdir, readFile, rename, rm, writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import type { RunningThreadItem, ThreadId } from "@uncaged/workflow-protocol";
|
||||
|
||||
import type { RunningMarker } from "./types.js";
|
||||
|
||||
/**
|
||||
* Get the path to the running markers directory.
|
||||
*/
|
||||
export function getRunningDir(storageRoot: string): string {
|
||||
return join(storageRoot, "running");
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the path to a specific thread's marker file.
|
||||
*/
|
||||
export function getMarkerPath(storageRoot: string, threadId: ThreadId): string {
|
||||
return join(getRunningDir(storageRoot), `${threadId}.json`);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a PID is still running.
|
||||
* Returns true if the process exists, false otherwise.
|
||||
*/
|
||||
export function isPidAlive(pid: number): boolean {
|
||||
try {
|
||||
// process.kill with signal 0 checks existence without killing
|
||||
process.kill(pid, 0);
|
||||
return true;
|
||||
} catch {
|
||||
// ESRCH means process doesn't exist
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Create a marker file for a running thread.
|
||||
* Writes to a temp file in the same directory, then atomically renames.
|
||||
*/
|
||||
export async function createMarker(storageRoot: string, marker: RunningMarker): Promise<void> {
|
||||
const runningDir = getRunningDir(storageRoot);
|
||||
await mkdir(runningDir, { recursive: true });
|
||||
|
||||
const markerPath = getMarkerPath(storageRoot, marker.thread);
|
||||
const tempPath = join(runningDir, `.${marker.thread}-${process.pid}.tmp`);
|
||||
|
||||
const content = JSON.stringify(marker, null, 2);
|
||||
await writeFile(tempPath, content, "utf8");
|
||||
await rename(tempPath, markerPath);
|
||||
}
|
||||
|
||||
/**
|
||||
* Delete a marker file for a thread.
|
||||
*/
|
||||
export async function deleteMarker(storageRoot: string, threadId: ThreadId): Promise<void> {
|
||||
const markerPath = getMarkerPath(storageRoot, threadId);
|
||||
try {
|
||||
await rm(markerPath);
|
||||
} catch {
|
||||
// Ignore errors if file doesn't exist
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Read a marker file. Returns null if file doesn't exist or is invalid.
|
||||
*/
|
||||
export async function readMarker(
|
||||
storageRoot: string,
|
||||
threadId: ThreadId,
|
||||
): Promise<RunningMarker | null> {
|
||||
const markerPath = getMarkerPath(storageRoot, threadId);
|
||||
try {
|
||||
const content = await readFile(markerPath, "utf8");
|
||||
const marker = JSON.parse(content) as RunningMarker;
|
||||
return marker;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* List all running threads, filtering out stale markers.
|
||||
*/
|
||||
export async function listRunningThreads(storageRoot: string): Promise<RunningThreadItem[]> {
|
||||
const runningDir = getRunningDir(storageRoot);
|
||||
|
||||
let files: string[];
|
||||
try {
|
||||
files = await readdir(runningDir);
|
||||
} catch {
|
||||
// Directory doesn't exist or can't be read
|
||||
return [];
|
||||
}
|
||||
|
||||
const results: RunningThreadItem[] = [];
|
||||
|
||||
for (const filename of files) {
|
||||
if (!filename.endsWith(".json")) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const threadId = filename.slice(0, -5) as ThreadId;
|
||||
const marker = await readMarker(storageRoot, threadId);
|
||||
|
||||
if (marker === null) {
|
||||
// Invalid marker file
|
||||
continue;
|
||||
}
|
||||
|
||||
if (!isPidAlive(marker.pid)) {
|
||||
// Stale marker - process no longer exists
|
||||
await deleteMarker(storageRoot, threadId);
|
||||
continue;
|
||||
}
|
||||
|
||||
results.push({
|
||||
thread: marker.thread,
|
||||
workflow: marker.workflow,
|
||||
pid: marker.pid,
|
||||
startedAt: marker.startedAt,
|
||||
});
|
||||
}
|
||||
|
||||
return results;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a thread is currently executing in the background.
|
||||
* Returns the marker if running, null otherwise.
|
||||
*/
|
||||
export async function isThreadRunning(
|
||||
storageRoot: string,
|
||||
threadId: ThreadId,
|
||||
): Promise<RunningMarker | null> {
|
||||
const marker = await readMarker(storageRoot, threadId);
|
||||
if (marker === null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
if (!isPidAlive(marker.pid)) {
|
||||
// Stale marker
|
||||
await deleteMarker(storageRoot, threadId);
|
||||
return null;
|
||||
}
|
||||
|
||||
return marker;
|
||||
}
|
||||
@@ -1,11 +0,0 @@
|
||||
export {
|
||||
createMarker,
|
||||
deleteMarker,
|
||||
getMarkerPath,
|
||||
getRunningDir,
|
||||
isPidAlive,
|
||||
isThreadRunning,
|
||||
listRunningThreads,
|
||||
readMarker,
|
||||
} from "./background.js";
|
||||
export type { RunningMarker } from "./types.js";
|
||||
@@ -1,9 +0,0 @@
|
||||
import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
|
||||
|
||||
/** Marker file stored at ~/.uncaged/workflow/running/<thread-id>.json */
|
||||
export type RunningMarker = {
|
||||
thread: ThreadId;
|
||||
workflow: CasRef;
|
||||
pid: number;
|
||||
startedAt: number;
|
||||
};
|
||||
@@ -1,7 +1,8 @@
|
||||
#!/usr/bin/env bun
|
||||
|
||||
import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
|
||||
import type { ThreadId } from "@uncaged/workflow-protocol";
|
||||
import { Command } from "commander";
|
||||
import { stringify as yamlStringify } from "yaml";
|
||||
import {
|
||||
cmdCasGet,
|
||||
cmdCasHas,
|
||||
@@ -16,20 +17,19 @@ 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 {
|
||||
cmdThreadCancel,
|
||||
cmdThreadExec,
|
||||
cmdThreadFork,
|
||||
cmdThreadKill,
|
||||
cmdThreadList,
|
||||
cmdThreadRead,
|
||||
cmdThreadShow,
|
||||
cmdThreadStart,
|
||||
cmdThreadStop,
|
||||
cmdThreadStep,
|
||||
cmdThreadStepDetails,
|
||||
cmdThreadSteps,
|
||||
THREAD_READ_DEFAULT_QUOTA,
|
||||
type ThreadStatus,
|
||||
} from "./commands/thread.js";
|
||||
import { parseTimeInput } from "./commands/thread-time-parser.js";
|
||||
import { cmdWorkflowAdd, cmdWorkflowList, cmdWorkflowShow } from "./commands/workflow.js";
|
||||
import { cmdWorkflowList, cmdWorkflowPut, cmdWorkflowShow } from "./commands/workflow.js";
|
||||
import { formatOutput, type OutputFormat } from "./format.js";
|
||||
import { resolveStorageRoot } from "./store.js";
|
||||
|
||||
@@ -52,27 +52,20 @@ const program = new Command();
|
||||
const pkg = await import("../package.json", { with: { type: "json" } });
|
||||
program
|
||||
.name("uwf")
|
||||
.description(
|
||||
"Stateless workflow CLI\n\n" +
|
||||
"Four-layer architecture:\n" +
|
||||
" workflow → thread → step → turn\n" +
|
||||
" 模板定义 执行实例 单步结果 agent内部交互",
|
||||
)
|
||||
.description("Stateless workflow CLI")
|
||||
.version(pkg.default.version, "-V, --version");
|
||||
program.option("--format <fmt>", "Output format: json or yaml", "json");
|
||||
|
||||
const workflow = program
|
||||
.command("workflow")
|
||||
.description("Workflow definitions (layer 1: templates)");
|
||||
const workflow = program.command("workflow").description("Workflow registry and CAS");
|
||||
|
||||
workflow
|
||||
.command("add")
|
||||
.command("put")
|
||||
.description("Register a workflow from YAML")
|
||||
.argument("<file>", "Workflow YAML file")
|
||||
.action((file: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdWorkflowAdd(storageRoot, file);
|
||||
const result = await cmdWorkflowPut(storageRoot, file);
|
||||
writeOutput(result);
|
||||
});
|
||||
});
|
||||
@@ -100,7 +93,7 @@ workflow
|
||||
});
|
||||
});
|
||||
|
||||
const thread = program.command("thread").description("Thread execution (layer 2: instances)");
|
||||
const thread = program.command("thread").description("Thread lifecycle and execution");
|
||||
|
||||
thread
|
||||
.command("start")
|
||||
@@ -116,46 +109,24 @@ thread
|
||||
});
|
||||
|
||||
thread
|
||||
.command("exec")
|
||||
.command("step")
|
||||
.description("Execute one or more steps")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.option("--agent <cmd>", "Override agent command")
|
||||
.option("-c, --count <number>", "Number of steps to run (default: 1)")
|
||||
.option("--background", "Run in background and return immediately")
|
||||
.option("--_background-worker", "Internal flag for background worker process", false)
|
||||
.action(
|
||||
(
|
||||
threadId: string,
|
||||
opts: {
|
||||
agent: string | undefined;
|
||||
count: string | undefined;
|
||||
background: boolean;
|
||||
_backgroundWorker: boolean;
|
||||
},
|
||||
) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const agentOverride = opts.agent ?? null;
|
||||
const count = opts.count !== undefined ? Number(opts.count) : 1;
|
||||
const background = opts.background ?? false;
|
||||
const backgroundWorker = opts._backgroundWorker ?? false;
|
||||
|
||||
const results = await cmdThreadExec(
|
||||
storageRoot,
|
||||
threadId,
|
||||
agentOverride,
|
||||
count,
|
||||
background,
|
||||
backgroundWorker,
|
||||
);
|
||||
if (results.length === 1) {
|
||||
writeOutput(results[0]);
|
||||
} else {
|
||||
writeOutput(results);
|
||||
}
|
||||
});
|
||||
},
|
||||
);
|
||||
.action((threadId: string, opts: { agent: string | undefined; count: string | undefined }) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const agentOverride = opts.agent ?? null;
|
||||
const count = opts.count !== undefined ? Number(opts.count) : 1;
|
||||
const results = await cmdThreadStep(storageRoot, threadId, agentOverride, count);
|
||||
if (results.length === 1) {
|
||||
writeOutput(results[0]);
|
||||
} else {
|
||||
writeOutput(results);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
thread
|
||||
.command("show")
|
||||
@@ -169,124 +140,38 @@ 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 threads")
|
||||
.option(
|
||||
"--status <status>",
|
||||
"Filter by status: idle, running, completed, active (idle+running), or comma-separated values",
|
||||
)
|
||||
.option("--after <date>", "Filter threads created after this date (ISO or relative like '7d')")
|
||||
.option("--before <date>", "Filter threads created before this date (ISO or relative like '7d')")
|
||||
.option("--skip <n>", "Skip first n threads")
|
||||
.option("--take <n>", "Return at most n threads")
|
||||
.action(
|
||||
(opts: {
|
||||
status: string | undefined;
|
||||
after: string | undefined;
|
||||
before: string | undefined;
|
||||
skip: string | undefined;
|
||||
take: string | undefined;
|
||||
}) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const statusFilter = parseStatusFilter(opts.status);
|
||||
const nowMs = Date.now();
|
||||
const { afterMs, beforeMs } = parseTimeFilters(opts.after, opts.before, nowMs);
|
||||
const { skip, take } = parsePaginationOptions(opts.skip, opts.take);
|
||||
|
||||
const result = await cmdThreadList(
|
||||
storageRoot,
|
||||
statusFilter,
|
||||
afterMs,
|
||||
beforeMs,
|
||||
skip,
|
||||
take,
|
||||
);
|
||||
writeOutput(result);
|
||||
});
|
||||
},
|
||||
);
|
||||
|
||||
thread
|
||||
.command("stop")
|
||||
.description("Stop background execution of a thread (keep thread active)")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.action((threadId: string) => {
|
||||
.description("List active threads")
|
||||
.option("--all", "Include archived threads")
|
||||
.action((opts: { all: boolean }) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdThreadStop(storageRoot, threadId);
|
||||
const result = await cmdThreadList(storageRoot, opts.all);
|
||||
writeOutput(result);
|
||||
});
|
||||
});
|
||||
|
||||
thread
|
||||
.command("cancel")
|
||||
.description("Cancel a thread (stop execution and move to history)")
|
||||
.command("kill")
|
||||
.description("Terminate and archive a thread")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.action((threadId: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdThreadCancel(storageRoot, threadId);
|
||||
const result = await cmdThreadKill(storageRoot, threadId);
|
||||
writeOutput(result);
|
||||
});
|
||||
});
|
||||
|
||||
thread
|
||||
.command("steps")
|
||||
.description("List all steps in a thread")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.action((threadId: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdThreadSteps(storageRoot, threadId);
|
||||
writeOutput(result);
|
||||
});
|
||||
});
|
||||
@@ -320,157 +205,28 @@ 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
|
||||
thread
|
||||
.command("fork")
|
||||
.description("Fork a thread from a specific step")
|
||||
.argument("<step-hash>", "CAS hash of the StartNode or StepNode to fork from")
|
||||
.action((stepHash: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdStepFork(storageRoot, stepHash as CasRef);
|
||||
const result = await cmdThreadFork(storageRoot, stepHash);
|
||||
writeOutput(result);
|
||||
});
|
||||
});
|
||||
|
||||
// ── Deprecation Handlers ──────────────────────────────────────────────────────
|
||||
// These commands have been removed. Show helpful error messages.
|
||||
|
||||
workflow
|
||||
.command("put")
|
||||
.description("[DEPRECATED] Use 'workflow add' instead")
|
||||
.argument("<file>", "Workflow YAML file")
|
||||
.action(() => {
|
||||
process.stderr.write(`Error: Command 'workflow put' has been removed.
|
||||
Use 'workflow add' instead.
|
||||
|
||||
For more information, see: uwf help workflow add
|
||||
`);
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
thread
|
||||
.command("step")
|
||||
.description("[DEPRECATED] Use 'thread exec' instead")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.allowUnknownOption()
|
||||
.action(() => {
|
||||
process.stderr.write(`Error: Command 'thread step' has been removed.
|
||||
Use 'thread exec' instead.
|
||||
|
||||
For more information, see: uwf help thread exec
|
||||
`);
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
thread
|
||||
.command("steps")
|
||||
.description("[DEPRECATED] Use 'step list' instead")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.action(() => {
|
||||
process.stderr.write(`Error: Command 'thread steps' has been removed.
|
||||
Use 'step list' instead.
|
||||
|
||||
For more information, see: uwf help step list
|
||||
`);
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
thread
|
||||
.command("step-details")
|
||||
.description("[DEPRECATED] Use 'step show' instead")
|
||||
.argument("<step-hash>", "Step hash")
|
||||
.action(() => {
|
||||
process.stderr.write(`Error: Command 'thread step-details' has been removed.
|
||||
Use 'step show' instead.
|
||||
|
||||
For more information, see: uwf help step show
|
||||
`);
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
thread
|
||||
.command("fork")
|
||||
.description("[DEPRECATED] Use 'step fork' instead")
|
||||
.argument("<step-hash>", "Step hash")
|
||||
.action(() => {
|
||||
process.stderr.write(`Error: Command 'thread fork' has been removed.
|
||||
Use 'step fork' instead.
|
||||
|
||||
For more information, see: uwf help step fork
|
||||
`);
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
thread
|
||||
.command("kill")
|
||||
.description("[DEPRECATED] Use 'thread stop' or 'thread cancel' instead")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.action(() => {
|
||||
process.stderr.write(`Error: Command 'thread kill' has been removed.
|
||||
Use 'thread stop' to stop background execution (keep thread active),
|
||||
or 'thread cancel' to cancel and archive the thread.
|
||||
|
||||
For more information, see:
|
||||
uwf help thread stop
|
||||
uwf help thread cancel
|
||||
`);
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
thread
|
||||
.command("running")
|
||||
.description("[DEPRECATED] Use 'thread list --status running' instead")
|
||||
.action(() => {
|
||||
process.stderr.write(`Error: Command 'thread running' has been removed.
|
||||
Use 'thread list --status running' instead.
|
||||
|
||||
For more information, see: uwf help thread list
|
||||
`);
|
||||
process.exit(1);
|
||||
.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));
|
||||
});
|
||||
});
|
||||
|
||||
const skill = program.command("skill").description("Built-in skill references for agents");
|
||||
@@ -565,11 +321,7 @@ cas
|
||||
.action((hash: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdCasHas(storageRoot, hash);
|
||||
writeOutput(result);
|
||||
if (!result.exists) {
|
||||
process.exit(1);
|
||||
}
|
||||
writeOutput(await cmdCasHas(storageRoot, hash));
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { existsSync, mkdirSync, readdirSync, readFileSync, statSync, writeFileSync } from "node:fs";
|
||||
import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
|
||||
import { join } from "node:path";
|
||||
import { stdin as input, stdout as output } from "node:process";
|
||||
import { createInterface } from "node:readline/promises";
|
||||
@@ -137,182 +137,75 @@ function apiKeyEnvName(providerName: string): string {
|
||||
return `${providerName.toUpperCase().replace(/[^A-Z0-9]/g, "_")}_API_KEY`;
|
||||
}
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// Extracted helpers — _discoverAgents
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Scans directories from a PATH string for uwf-* executables.
|
||||
*/
|
||||
export async function _searchPathDirs(pathEnv: string): Promise<string[]> {
|
||||
if (!pathEnv) return [];
|
||||
const dirs = pathEnv.split(":").filter((d) => d.length > 0);
|
||||
const agents = new Set<string>();
|
||||
for (const dir of dirs) {
|
||||
_scanDirForAgents(dir, agents);
|
||||
}
|
||||
return Array.from(agents).sort();
|
||||
}
|
||||
|
||||
function _scanDirForAgents(dir: string, agents: Set<string>): void {
|
||||
try {
|
||||
if (!existsSync(dir)) return;
|
||||
const entries = readdirSync(dir);
|
||||
for (const entry of entries) {
|
||||
if (!entry.startsWith("uwf-") || entry === "uwf") continue;
|
||||
if (_isExecutableFile(join(dir, entry))) {
|
||||
agents.add(entry);
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
// Skip inaccessible directories
|
||||
}
|
||||
}
|
||||
|
||||
function _isExecutableFile(fullPath: string): boolean {
|
||||
try {
|
||||
const s = statSync(fullPath);
|
||||
return s.isFile() && (s.mode & 0o111) !== 0;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Parses the stdout of `which -a` into sorted unique basenames.
|
||||
*/
|
||||
export function _parseWhichOutput(text: string): string[] {
|
||||
if (!text) return [];
|
||||
const agents = new Set<string>();
|
||||
for (const line of text.trim().split("\n")) {
|
||||
if (!line) continue;
|
||||
const basename = line.split("/").pop() ?? "";
|
||||
if (basename.startsWith("uwf-") && basename !== "uwf") {
|
||||
agents.add(basename);
|
||||
}
|
||||
}
|
||||
return Array.from(agents).sort();
|
||||
}
|
||||
|
||||
/**
|
||||
* Discover uwf-* agent binaries in PATH.
|
||||
* Returns sorted list of binary names (e.g., ["uwf-hermes", "uwf-claude-code"]).
|
||||
*/
|
||||
export async function _discoverAgents(): Promise<string[]> {
|
||||
try {
|
||||
const agents = await _tryWhichDiscovery();
|
||||
if (agents !== null) return agents;
|
||||
return await _searchPathDirs(process.env.PATH ?? "");
|
||||
} catch {
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
async function _tryWhichDiscovery(): Promise<string[] | null> {
|
||||
async function _discoverAgents(): Promise<string[]> {
|
||||
try {
|
||||
// Use which -a to find all uwf-* binaries in PATH
|
||||
const proc = Bun.spawn(["which", "-a", "uwf-hermes", "uwf-claude-code", "uwf-cursor"], {
|
||||
stdout: "pipe",
|
||||
stderr: "pipe",
|
||||
});
|
||||
|
||||
const text = await new Response(proc.stdout).text();
|
||||
await proc.exited;
|
||||
if (proc.exitCode !== 0) return null;
|
||||
return _parseWhichOutput(text);
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// Extracted helpers — onData closure (promptSecret)
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
if (proc.exitCode !== 0) {
|
||||
// Try alternative approach: search PATH directories manually
|
||||
const pathEnv = process.env.PATH || "";
|
||||
const pathDirs = pathEnv.split(":").filter((d) => d.length > 0);
|
||||
const agents = new Set<string>();
|
||||
|
||||
/** Returns true for newline, carriage return, or EOF (EOT). */
|
||||
export function _isTerminator(c: string): boolean {
|
||||
return c === "\n" || c === "\r" || c === "";
|
||||
}
|
||||
for (const dir of pathDirs) {
|
||||
try {
|
||||
if (!existsSync(dir)) continue;
|
||||
const { readdirSync, statSync } = await import("node:fs");
|
||||
const entries = readdirSync(dir);
|
||||
|
||||
/** Returns true for DEL or backspace. */
|
||||
export function _isBackspace(c: string): boolean {
|
||||
return c === "" || c === "\b";
|
||||
}
|
||||
for (const entry of entries) {
|
||||
if (!entry.startsWith("uwf-") || entry === "uwf") continue;
|
||||
const fullPath = join(dir, entry);
|
||||
try {
|
||||
const stat = statSync(fullPath);
|
||||
// Check if executable (owner, group, or other has execute bit)
|
||||
if (stat.isFile() && (stat.mode & 0o111) !== 0) {
|
||||
agents.add(entry);
|
||||
}
|
||||
} catch {
|
||||
// Skip if can't stat
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
// Skip inaccessible directories
|
||||
}
|
||||
}
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
// Extracted helpers — cmdSetupInteractive
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
type ProviderEntry = { name: string; label: string; baseUrl: string };
|
||||
|
||||
/** Prints the numbered provider list and custom option to stdout. */
|
||||
export function _printProviderMenu(providers: readonly ProviderEntry[]): void {
|
||||
const numWidth = String(providers.length + 1).length;
|
||||
for (let i = 0; i < providers.length; i++) {
|
||||
const p = providers[i];
|
||||
if (!p) continue;
|
||||
const num = String(i + 1).padStart(numWidth);
|
||||
console.log(` ${num}) ${p.label.padEnd(28)} ${p.baseUrl}`);
|
||||
}
|
||||
const customNum = String(providers.length + 1).padStart(numWidth);
|
||||
console.log(` ${customNum}) Custom (enter name and URL manually)\n`);
|
||||
}
|
||||
|
||||
/** Resolves a numeric choice string to a preset provider, or null for custom/invalid. */
|
||||
export function _resolveProviderChoice(
|
||||
choice: string,
|
||||
providers: readonly ProviderEntry[],
|
||||
): { providerName: string; baseUrl: string } | null {
|
||||
const n = Number.parseInt(choice, 10);
|
||||
if (Number.isNaN(n) || n < 1 || n > providers.length) return null;
|
||||
const p = providers[n - 1];
|
||||
if (!p) return null;
|
||||
return { providerName: p.name, baseUrl: p.baseUrl };
|
||||
}
|
||||
|
||||
/** Resolves numeric index or literal model name to a model string. */
|
||||
export function _resolveModelChoice(input: string, models: string[]): string {
|
||||
const n = Number.parseInt(input, 10);
|
||||
if (!Number.isNaN(n) && n >= 1 && n <= models.length) {
|
||||
return models[n - 1] ?? input;
|
||||
}
|
||||
return input;
|
||||
}
|
||||
|
||||
/** Prints the multi-column model list to stdout. */
|
||||
export function _printModelMenu(models: string[], termCols: number): void {
|
||||
const nw = String(models.length).length;
|
||||
const maxLen = models.reduce((m, s) => Math.max(m, s.length), 0);
|
||||
const colWidth = nw + 2 + maxLen + 4;
|
||||
const cols = Math.max(1, Math.floor(termCols / colWidth));
|
||||
const rows = Math.ceil(models.length / cols);
|
||||
for (let r = 0; r < rows; r++) {
|
||||
let line = "";
|
||||
for (let c = 0; c < cols; c++) {
|
||||
const idx = c * rows + r;
|
||||
if (idx >= models.length) break;
|
||||
const num = String(idx + 1).padStart(nw);
|
||||
const name = (models[idx] ?? "").padEnd(maxLen);
|
||||
line += ` ${num}) ${name} `;
|
||||
return Array.from(agents).sort();
|
||||
}
|
||||
console.log(line.trimEnd());
|
||||
|
||||
// Parse which output - each line is a path to a binary
|
||||
const paths = text
|
||||
.trim()
|
||||
.split("\n")
|
||||
.filter((line) => line.length > 0);
|
||||
const agents = new Set<string>();
|
||||
|
||||
for (const path of paths) {
|
||||
const basename = path.split("/").pop();
|
||||
if (basename?.startsWith("uwf-") && basename !== "uwf") {
|
||||
agents.add(basename);
|
||||
}
|
||||
}
|
||||
|
||||
return Array.from(agents).sort();
|
||||
} catch {
|
||||
// If all fails, return empty array
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
type ValidationResult = { ok: boolean; error: string | null };
|
||||
|
||||
/** Prints the model validation result to stdout. */
|
||||
export function _printValidationResult(validation: ValidationResult): void {
|
||||
if (validation.ok) {
|
||||
console.log("✓ Model verified — connection successful.\n");
|
||||
} else {
|
||||
console.log(`\n⚠ Warning: Could not reach model — ${validation.error}`);
|
||||
console.log(
|
||||
" Config saved, but you may want to try a different model or check your API key.\n",
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// ──────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Merge setup args into config.yaml structure. Non-destructive — preserves existing entries.
|
||||
*/
|
||||
@@ -388,46 +281,6 @@ export async function cmdSetup(args: SetupArgs): Promise<Record<string, unknown>
|
||||
};
|
||||
}
|
||||
|
||||
type SecretState = {
|
||||
buf: string;
|
||||
rawWasSet: boolean;
|
||||
resolve: (value: string) => void;
|
||||
onData: (chunk: string) => void;
|
||||
};
|
||||
|
||||
function _handleSecretTerminator(state: SecretState): void {
|
||||
if (process.stdin.isTTY) process.stdin.setRawMode(state.rawWasSet);
|
||||
process.stdin.pause();
|
||||
process.stdin.removeListener("data", state.onData);
|
||||
process.stdout.write("\n");
|
||||
state.resolve(state.buf.trim());
|
||||
}
|
||||
|
||||
function _handleSecretBackspace(state: SecretState): void {
|
||||
if (state.buf.length > 0) {
|
||||
state.buf = state.buf.slice(0, -1);
|
||||
process.stdout.write("\b \b");
|
||||
}
|
||||
}
|
||||
|
||||
function _handleSecretChar(c: string, state: SecretState): boolean {
|
||||
if (_isTerminator(c)) {
|
||||
_handleSecretTerminator(state);
|
||||
return true;
|
||||
}
|
||||
if (_isBackspace(c)) {
|
||||
_handleSecretBackspace(state);
|
||||
return false;
|
||||
}
|
||||
if (c === "") {
|
||||
if (process.stdin.isTTY) process.stdin.setRawMode(state.rawWasSet);
|
||||
process.exit(130);
|
||||
}
|
||||
state.buf += c;
|
||||
process.stdout.write("*");
|
||||
return false;
|
||||
}
|
||||
|
||||
/** Read a line with terminal echo disabled (for secrets). */
|
||||
async function promptSecret(label: string): Promise<string> {
|
||||
process.stdout.write(label);
|
||||
@@ -439,13 +292,33 @@ async function promptSecret(label: string): Promise<string> {
|
||||
process.stdin.resume();
|
||||
process.stdin.setEncoding("utf8");
|
||||
|
||||
const state: SecretState = { buf: "", rawWasSet, resolve, onData: () => {} };
|
||||
state.onData = (chunk: string) => {
|
||||
let buf = "";
|
||||
const onData = (chunk: string) => {
|
||||
for (const c of chunk.toString()) {
|
||||
if (_handleSecretChar(c, state)) return;
|
||||
if (c === "\n" || c === "\r" || c === "\u0004") {
|
||||
if (process.stdin.isTTY) process.stdin.setRawMode(rawWasSet);
|
||||
process.stdin.pause();
|
||||
process.stdin.removeListener("data", onData);
|
||||
process.stdout.write("\n");
|
||||
resolve(buf.trim());
|
||||
return;
|
||||
}
|
||||
if (c === "\u007F" || c === "\b") {
|
||||
if (buf.length > 0) {
|
||||
buf = buf.slice(0, -1);
|
||||
process.stdout.write("\b \b");
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if (c === "\u0003") {
|
||||
if (process.stdin.isTTY) process.stdin.setRawMode(rawWasSet);
|
||||
process.exit(130);
|
||||
}
|
||||
buf += c;
|
||||
process.stdout.write("*");
|
||||
}
|
||||
};
|
||||
process.stdin.on("data", state.onData);
|
||||
process.stdin.on("data", onData);
|
||||
});
|
||||
}
|
||||
|
||||
@@ -471,56 +344,6 @@ async function fetchModels(baseUrl: string, apiKey: string): Promise<string[]> {
|
||||
}
|
||||
}
|
||||
|
||||
async function _promptProviderSelection(
|
||||
rl: ReturnType<typeof createInterface>,
|
||||
): Promise<{ providerName: string; baseUrl: string }> {
|
||||
console.log("Select a provider:\n");
|
||||
_printProviderMenu(PRESET_PROVIDERS);
|
||||
|
||||
const choice = (await rl.question(`Choose [1-${PRESET_PROVIDERS.length + 1}]: `)).trim();
|
||||
const choiceNum = Number.parseInt(choice, 10);
|
||||
if (Number.isNaN(choiceNum) || choiceNum < 1 || choiceNum > PRESET_PROVIDERS.length + 1) {
|
||||
throw new Error(`Invalid choice: ${choice}`);
|
||||
}
|
||||
|
||||
const preset = _resolveProviderChoice(choice, PRESET_PROVIDERS);
|
||||
if (preset) {
|
||||
const selected = PRESET_PROVIDERS[choiceNum - 1];
|
||||
if (selected) {
|
||||
console.log(`\n → ${selected.label} (${selected.baseUrl})\n`);
|
||||
}
|
||||
return preset;
|
||||
}
|
||||
|
||||
const providerName = (await rl.question("Provider name (e.g. my-proxy): ")).trim();
|
||||
if (!providerName) throw new Error("Provider name required");
|
||||
const baseUrl = (await rl.question("OpenAI-compatible API base URL: ")).trim();
|
||||
if (!baseUrl) throw new Error("Base URL required");
|
||||
return { providerName, baseUrl };
|
||||
}
|
||||
|
||||
async function _promptModelSelection(
|
||||
rl: ReturnType<typeof createInterface>,
|
||||
baseUrl: string,
|
||||
apiKey: string,
|
||||
): Promise<string> {
|
||||
console.log("\nFetching available models...");
|
||||
const models = await fetchModels(baseUrl, apiKey);
|
||||
|
||||
if (models.length === 0) {
|
||||
console.log("Could not fetch models. Enter model name manually.");
|
||||
const model = (await rl.question("Default model (e.g. qwen-plus, gpt-4o): ")).trim();
|
||||
if (!model) throw new Error("Model required");
|
||||
return model;
|
||||
}
|
||||
console.log(`\nAvailable models (${models.length}):\n`);
|
||||
_printModelMenu(models, process.stdout.columns || 100);
|
||||
console.log(`\nChoose a number, or type a model name directly.`);
|
||||
const modelInput = (await rl.question(`Default model [1-${models.length}]: `)).trim();
|
||||
if (!modelInput) throw new Error("Model required");
|
||||
return _resolveModelChoice(modelInput, models);
|
||||
}
|
||||
|
||||
/**
|
||||
* Interactive setup — prompts user for provider, API key, model.
|
||||
*/
|
||||
@@ -530,7 +353,39 @@ export async function cmdSetupInteractive(storageRoot: string): Promise<Record<s
|
||||
try {
|
||||
console.log("Configure LLM provider for uwf workflow agents.\n");
|
||||
|
||||
const { providerName, baseUrl } = await _promptProviderSelection(rl);
|
||||
// 1. Provider selection
|
||||
const numWidth = String(PRESET_PROVIDERS.length + 1).length;
|
||||
console.log("Select a provider:\n");
|
||||
for (let i = 0; i < PRESET_PROVIDERS.length; i++) {
|
||||
const p = PRESET_PROVIDERS[i];
|
||||
if (!p) continue;
|
||||
const num = String(i + 1).padStart(numWidth);
|
||||
console.log(` ${num}) ${p.label.padEnd(28)} ${p.baseUrl}`);
|
||||
}
|
||||
const customNum = String(PRESET_PROVIDERS.length + 1).padStart(numWidth);
|
||||
console.log(` ${customNum}) Custom (enter name and URL manually)\n`);
|
||||
|
||||
const choice = (await rl.question(`Choose [1-${PRESET_PROVIDERS.length + 1}]: `)).trim();
|
||||
const choiceNum = Number.parseInt(choice, 10);
|
||||
if (Number.isNaN(choiceNum) || choiceNum < 1 || choiceNum > PRESET_PROVIDERS.length + 1) {
|
||||
throw new Error(`Invalid choice: ${choice}`);
|
||||
}
|
||||
|
||||
let providerName: string;
|
||||
let baseUrl: string;
|
||||
|
||||
if (choiceNum <= PRESET_PROVIDERS.length) {
|
||||
const selected = PRESET_PROVIDERS[choiceNum - 1];
|
||||
if (!selected) throw new Error("Invalid selection");
|
||||
providerName = selected.name;
|
||||
baseUrl = selected.baseUrl;
|
||||
console.log(`\n → ${selected.label} (${selected.baseUrl})\n`);
|
||||
} else {
|
||||
providerName = (await rl.question("Provider name (e.g. my-proxy): ")).trim();
|
||||
if (!providerName) throw new Error("Provider name required");
|
||||
baseUrl = (await rl.question("OpenAI-compatible API base URL: ")).trim();
|
||||
if (!baseUrl) throw new Error("Base URL required");
|
||||
}
|
||||
|
||||
// 2. API key
|
||||
rl.close();
|
||||
@@ -539,8 +394,47 @@ export async function cmdSetupInteractive(storageRoot: string): Promise<Record<s
|
||||
|
||||
// 3. Model selection
|
||||
const rl2 = createInterface({ input, output });
|
||||
const model = await _promptModelSelection(rl2, baseUrl, apiKey);
|
||||
console.log("\nFetching available models...");
|
||||
const models = await fetchModels(baseUrl, apiKey);
|
||||
|
||||
let model: string;
|
||||
if (models.length > 0) {
|
||||
console.log(`\nAvailable models (${models.length}):\n`);
|
||||
const nw = String(models.length).length;
|
||||
// Multi-column layout
|
||||
const maxLen = models.reduce((m, s) => Math.max(m, s.length), 0);
|
||||
const colWidth = nw + 2 + maxLen + 4; // " N) name "
|
||||
const termCols = process.stdout.columns || 100;
|
||||
const cols = Math.max(1, Math.floor(termCols / colWidth));
|
||||
const rows = Math.ceil(models.length / cols);
|
||||
for (let r = 0; r < rows; r++) {
|
||||
let line = "";
|
||||
for (let c = 0; c < cols; c++) {
|
||||
const idx = c * rows + r;
|
||||
if (idx >= models.length) break;
|
||||
const num = String(idx + 1).padStart(nw);
|
||||
const name = (models[idx] ?? "").padEnd(maxLen);
|
||||
line += ` ${num}) ${name} `;
|
||||
}
|
||||
console.log(line.trimEnd());
|
||||
}
|
||||
console.log(`\nChoose a number, or type a model name directly.`);
|
||||
const modelInput = (await rl2.question(`Default model [1-${models.length}]: `)).trim();
|
||||
if (!modelInput) throw new Error("Model required");
|
||||
const modelNum = Number.parseInt(modelInput, 10);
|
||||
if (!Number.isNaN(modelNum) && modelNum >= 1 && modelNum <= models.length) {
|
||||
model = models[modelNum - 1] ?? modelInput;
|
||||
} else {
|
||||
model = modelInput;
|
||||
}
|
||||
} else {
|
||||
console.log("Could not fetch models. Enter model name manually.");
|
||||
model = (await rl2.question("Default model (e.g. qwen-plus, gpt-4o): ")).trim();
|
||||
if (!model) throw new Error("Model required");
|
||||
}
|
||||
|
||||
rl2.close();
|
||||
|
||||
console.log(` → ${providerName}/${model}\n`);
|
||||
|
||||
const setupResult = await cmdSetup({
|
||||
@@ -553,8 +447,17 @@ export async function cmdSetupInteractive(storageRoot: string): Promise<Record<s
|
||||
|
||||
// Show validation result
|
||||
if (setupResult.validation && typeof setupResult.validation === "object") {
|
||||
_printValidationResult(setupResult.validation as ValidationResult);
|
||||
const v = setupResult.validation as { ok: boolean; error?: string };
|
||||
if (v.ok) {
|
||||
console.log("✓ Model verified — connection successful.\n");
|
||||
} else {
|
||||
console.log(`\n⚠ Warning: Could not reach model — ${v.error}`);
|
||||
console.log(
|
||||
" Config saved, but you may want to try a different model or check your API key.\n",
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
console.log("Setup complete! Get started:\n");
|
||||
console.log(" uwf workflow put <workflow.yaml> Register a workflow");
|
||||
console.log(' uwf thread start <name> -p "..." Start a thread');
|
||||
|
||||
@@ -1,231 +0,0 @@
|
||||
import type { Store as CasStore, JSONSchema } from "@uncaged/json-cas";
|
||||
import { getSchema } from "@uncaged/json-cas";
|
||||
import type {
|
||||
CasRef,
|
||||
StartNodePayload,
|
||||
StepNodePayload,
|
||||
ThreadId,
|
||||
} from "@uncaged/workflow-protocol";
|
||||
import { findThreadInHistory, loadThreadsIndex, type UwfStore } from "../store.js";
|
||||
|
||||
type ChainState = {
|
||||
startHash: CasRef;
|
||||
start: StartNodePayload;
|
||||
stepsNewestFirst: StepNodePayload[];
|
||||
headIsStart: boolean;
|
||||
};
|
||||
|
||||
type OrderedStepItem = {
|
||||
hash: CasRef;
|
||||
payload: StepNodePayload;
|
||||
timestamp: number;
|
||||
};
|
||||
|
||||
function fail(message: string): never {
|
||||
process.stderr.write(`${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,
|
||||
};
|
||||
@@ -1,230 +0,0 @@
|
||||
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";
|
||||
|
||||
/**
|
||||
* 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,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* 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;
|
||||
|
||||
// Build header section
|
||||
const parts: string[] = [];
|
||||
parts.push(`# Step ${stepHash}`);
|
||||
parts.push("");
|
||||
parts.push(`**Role:** ${payload.role}`);
|
||||
parts.push(`**Agent:** ${payload.agent}`);
|
||||
|
||||
// If no detail, return metadata only
|
||||
if (payload.detail === null) {
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
// Load detail node
|
||||
const detailNode = uwf.store.get(payload.detail);
|
||||
if (detailNode === null) {
|
||||
fail(`detail node not found: ${payload.detail}`);
|
||||
}
|
||||
|
||||
const detail = detailNode.payload as Record<string, unknown>;
|
||||
const turns = detail.turns;
|
||||
|
||||
// If no turns array, return metadata only
|
||||
if (!Array.isArray(turns) || turns.length === 0) {
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
// Load all turn nodes
|
||||
type TurnData = {
|
||||
index: number;
|
||||
content: string;
|
||||
};
|
||||
const turnData: TurnData[] = [];
|
||||
for (const turnRef of turns) {
|
||||
if (typeof turnRef !== "string") {
|
||||
continue;
|
||||
}
|
||||
const turnNode = uwf.store.get(turnRef as CasRef);
|
||||
if (turnNode === null) {
|
||||
continue;
|
||||
}
|
||||
const turn = turnNode.payload as Record<string, unknown>;
|
||||
if (typeof turn.content === "string") {
|
||||
turnData.push({
|
||||
index: typeof turn.index === "number" ? turn.index : turnData.length,
|
||||
content: turn.content,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
if (turnData.length === 0) {
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
// Calculate header length for quota accounting
|
||||
const headerSection = parts.join("\n");
|
||||
const headerLength = headerSection.length;
|
||||
|
||||
// Select turns that fit within quota (working backwards from most recent)
|
||||
const BUFFER = 200; // Conservative buffer for structural overhead
|
||||
const availableQuota = quota - headerLength - BUFFER;
|
||||
|
||||
const selectedTurns: TurnData[] = [];
|
||||
let totalChars = 0;
|
||||
|
||||
for (let i = turnData.length - 1; i >= 0; i--) {
|
||||
const turn = turnData[i];
|
||||
if (turn === undefined) continue;
|
||||
|
||||
// Calculate formatted turn length
|
||||
const turnHeader = `## Turn ${turn.index + 1}\n\n`;
|
||||
const turnBlock = turnHeader + turn.content;
|
||||
const separatorCost = selectedTurns.length > 0 ? 2 : 0; // "\n\n" between turns
|
||||
const addCost = turnBlock.length + separatorCost;
|
||||
|
||||
// Check quota - but always include at least one turn
|
||||
if (totalChars + addCost > availableQuota && selectedTurns.length > 0) {
|
||||
break;
|
||||
}
|
||||
|
||||
selectedTurns.unshift(turn);
|
||||
totalChars += addCost;
|
||||
}
|
||||
|
||||
// Add skip hint if not all turns fit
|
||||
const skippedCount = turnData.length - selectedTurns.length;
|
||||
if (skippedCount > 0) {
|
||||
parts.push("");
|
||||
parts.push(`_[Earlier turns omitted due to quota. Use --quota to increase.]_`);
|
||||
}
|
||||
|
||||
// Add selected turns
|
||||
for (const turn of selectedTurns) {
|
||||
parts.push("");
|
||||
parts.push(`## Turn ${turn.index + 1}`);
|
||||
parts.push("");
|
||||
parts.push(turn.content);
|
||||
}
|
||||
|
||||
return parts.join("\n");
|
||||
}
|
||||
@@ -1,23 +0,0 @@
|
||||
/**
|
||||
* Parse time input: ISO date (YYYY-MM-DD, YYYY-MM-DDTHH:MM:SS) or relative (7d, 24h, 30m)
|
||||
* Returns Unix timestamp in milliseconds.
|
||||
*/
|
||||
export function parseTimeInput(input: string, nowMs: number): number {
|
||||
const trimmed = input.trim();
|
||||
|
||||
// Relative time: 7d, 24h, 30m
|
||||
const relativeMatch = /^(\d+)(d|h|m)$/.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: ${trimmed} (expected ISO date or relative like '7d')`);
|
||||
}
|
||||
return parsed;
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -2,7 +2,12 @@ import { readFile } from "node:fs/promises";
|
||||
|
||||
import type { JSONSchema } from "@uncaged/json-cas";
|
||||
import { putSchema, validate } from "@uncaged/json-cas";
|
||||
import type { CasRef, RoleDefinition, Target, WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
import type {
|
||||
CasRef,
|
||||
RoleDefinition,
|
||||
Transition,
|
||||
WorkflowPayload,
|
||||
} from "@uncaged/workflow-protocol";
|
||||
import { parse } from "yaml";
|
||||
|
||||
import {
|
||||
@@ -24,7 +29,7 @@ export type WorkflowListEntry = {
|
||||
origin: WorkflowOrigin;
|
||||
};
|
||||
|
||||
export type WorkflowAddOutput = {
|
||||
export type WorkflowPutOutput = {
|
||||
name: string;
|
||||
hash: CasRef;
|
||||
};
|
||||
@@ -46,23 +51,20 @@ function isJsonSchema(value: unknown): value is JSONSchema {
|
||||
return typeof value === "object" && value !== null && !Array.isArray(value);
|
||||
}
|
||||
|
||||
/** Normalize graph: validate each status → target mapping. */
|
||||
function normalizeGraph(
|
||||
graph: Record<string, Record<string, Target>>,
|
||||
): Record<string, Record<string, Target>> {
|
||||
const result: Record<string, Record<string, Target>> = {};
|
||||
for (const [node, statusMap] of Object.entries(graph)) {
|
||||
const normalized: Record<string, Target> = {};
|
||||
for (const [status, target] of Object.entries(statusMap)) {
|
||||
if (typeof target.prompt !== "string" || target.prompt.trim() === "") {
|
||||
fail(`graph[${node}][${status}] → "${target.role}": prompt is required (non-empty string)`);
|
||||
/** 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)`);
|
||||
}
|
||||
normalized[status] = {
|
||||
role: target.role,
|
||||
prompt: target.prompt,
|
||||
return {
|
||||
role: t.role,
|
||||
condition: t.condition ?? null,
|
||||
prompt: t.prompt,
|
||||
};
|
||||
}
|
||||
result[node] = normalized;
|
||||
});
|
||||
}
|
||||
return result;
|
||||
}
|
||||
@@ -104,14 +106,15 @@ export async function materializeWorkflowPayload(
|
||||
name: raw.name,
|
||||
description: raw.description,
|
||||
roles,
|
||||
conditions: raw.conditions,
|
||||
graph: normalizeGraph(raw.graph),
|
||||
};
|
||||
}
|
||||
|
||||
export async function cmdWorkflowAdd(
|
||||
export async function cmdWorkflowPut(
|
||||
storageRoot: string,
|
||||
filePath: string,
|
||||
): Promise<WorkflowAddOutput> {
|
||||
): Promise<WorkflowPutOutput> {
|
||||
let text: string;
|
||||
try {
|
||||
text = await readFile(filePath, "utf8");
|
||||
|
||||
@@ -30,12 +30,23 @@ function isRoleDefinition(value: unknown): boolean {
|
||||
);
|
||||
}
|
||||
|
||||
function isTarget(value: unknown): boolean {
|
||||
function isConditionDefinition(value: unknown): boolean {
|
||||
if (!isRecord(value)) {
|
||||
return false;
|
||||
}
|
||||
return typeof value.description === "string" && typeof value.expression === "string";
|
||||
}
|
||||
|
||||
function isTransition(value: unknown): boolean {
|
||||
if (!isRecord(value)) {
|
||||
return false;
|
||||
}
|
||||
const condition = value.condition;
|
||||
return (
|
||||
typeof value.role === "string" && typeof value.prompt === "string" && value.prompt.trim() !== ""
|
||||
typeof value.role === "string" &&
|
||||
typeof value.prompt === "string" &&
|
||||
value.prompt.trim() !== "" &&
|
||||
(condition === null || condition === undefined || typeof condition === "string")
|
||||
);
|
||||
}
|
||||
|
||||
@@ -51,7 +62,7 @@ function isGraph(value: unknown): boolean {
|
||||
return false;
|
||||
}
|
||||
return Object.values(value).every(
|
||||
(statusMap) => isRecord(statusMap) && Object.values(statusMap).every((t) => isTarget(t)),
|
||||
(transitions) => Array.isArray(transitions) && transitions.every((t) => isTransition(t)),
|
||||
);
|
||||
}
|
||||
|
||||
@@ -90,7 +101,11 @@ export function parseWorkflowPayload(raw: unknown): WorkflowPayload | null {
|
||||
if (typeof raw.name !== "string" || typeof raw.description !== "string") {
|
||||
return null;
|
||||
}
|
||||
if (!isStringRecord(raw.roles, isRoleDefinition) || !isGraph(raw.graph)) {
|
||||
if (
|
||||
!isStringRecord(raw.roles, isRoleDefinition) ||
|
||||
!isStringRecord(raw.conditions, isConditionDefinition) ||
|
||||
!isGraph(raw.graph)
|
||||
) {
|
||||
return null;
|
||||
}
|
||||
return raw as WorkflowPayload;
|
||||
|
||||
@@ -1,141 +0,0 @@
|
||||
# @uncaged/workflow-agent-builtin
|
||||
|
||||
`uwf-builtin` agent — built-in LLM agent with file read/write and shell tools.
|
||||
|
||||
## Overview
|
||||
|
||||
Layer 3 agent implementation. Runs an OpenAI-compatible chat completion loop with built-in tools (`read_file`, `write_file`, `run_command`). Uses the configured provider/model from `config.yaml`. Produces frontmatter markdown output and stores turn-by-turn session detail in CAS.
|
||||
|
||||
Useful when you want a self-contained agent without an external CLI like Hermes or Claude Code.
|
||||
|
||||
**Dependencies:** `@uncaged/json-cas`, `@uncaged/workflow-agent-kit`, `@uncaged/workflow-util`
|
||||
|
||||
## Installation
|
||||
|
||||
Included as the `uwf-builtin` binary when you install `@uncaged/workflow-agent-builtin`:
|
||||
|
||||
```bash
|
||||
bun add -g @uncaged/workflow-agent-builtin
|
||||
```
|
||||
|
||||
## CLI Usage
|
||||
|
||||
Invoked by `uwf thread step`:
|
||||
|
||||
```bash
|
||||
uwf-builtin <thread-id> <role>
|
||||
```
|
||||
|
||||
Configure as default agent:
|
||||
|
||||
```bash
|
||||
uwf setup --agent builtin
|
||||
```
|
||||
|
||||
Override per step:
|
||||
|
||||
```bash
|
||||
uwf thread step <thread-id> --agent uwf-builtin
|
||||
```
|
||||
|
||||
Environment variables set by the engine:
|
||||
|
||||
| Variable | Purpose |
|
||||
|----------|---------|
|
||||
| `UWF_EDGE_PROMPT` | Moderator edge instruction for this step |
|
||||
|
||||
## API
|
||||
|
||||
All exports come from `src/index.ts`.
|
||||
|
||||
### Agent factory
|
||||
|
||||
```typescript
|
||||
function createBuiltinAgent(): () => Promise<void>
|
||||
function buildBuiltinMessages(ctx: AgentContext): ChatMessage[]
|
||||
```
|
||||
|
||||
### LLM loop
|
||||
|
||||
```typescript
|
||||
const BUILTIN_MAX_TURNS = 30;
|
||||
const BUILTIN_CONTINUE_MAX_TURNS = 5;
|
||||
|
||||
function runBuiltinLoop(/* options: RunBuiltinLoopOptions */): Promise<RunBuiltinLoopResult>
|
||||
function chatCompletionWithTools(
|
||||
provider: ResolvedLlmProvider,
|
||||
messages: ChatMessage[],
|
||||
tools: OpenAiToolDefinition[],
|
||||
): Promise<LlmAssistantResponse>
|
||||
```
|
||||
|
||||
`RunBuiltinLoopOptions` and `RunBuiltinLoopResult` are internal to `loop.ts` and not re-exported from `index.ts`.
|
||||
|
||||
### Tools
|
||||
|
||||
```typescript
|
||||
function getBuiltinTools(): readonly BuiltinTool[]
|
||||
function executeBuiltinTool(
|
||||
name: string,
|
||||
args: Record<string, unknown>,
|
||||
ctx: ToolContext,
|
||||
): Promise<string>
|
||||
```
|
||||
|
||||
### Session and detail
|
||||
|
||||
```typescript
|
||||
function initSessionDir(storageRoot: string): Promise<void>
|
||||
function appendSessionTurn(storageRoot: string, sessionId: string, turn: BuiltinTurnPayload): Promise<void>
|
||||
function readSessionTurns(storageRoot: string, sessionId: string): Promise<BuiltinTurnPayload[]>
|
||||
function removeSession(storageRoot: string, sessionId: string): Promise<void>
|
||||
function registerBuiltinSchemas(store: Store): Promise<BuiltinSchemaHashes>
|
||||
function storeBuiltinDetail(store: Store, payload: BuiltinDetailPayload): Promise<string>
|
||||
```
|
||||
|
||||
### Types
|
||||
|
||||
```typescript
|
||||
type ChatMessage = /* system | user | assistant | tool */;
|
||||
type LlmAssistantResponse = { content: string | null; toolCalls: LlmToolCall[] | null };
|
||||
type LlmToolCall = { id: string; name: string; arguments: string };
|
||||
type BuiltinTool = { name: string; description: string; parameters: Record<string, unknown> };
|
||||
type ToolContext = { cwd: string; storageRoot: string };
|
||||
type BuiltinDetailPayload = { /* session turns, model, timestamps */ };
|
||||
type BuiltinLoopTurn = { /* single loop iteration record */ };
|
||||
type BuiltinToolCallRecord = { /* tool call audit */ };
|
||||
type BuiltinToolResultRecord = { /* tool result audit */ };
|
||||
type BuiltinTurnPayload = { /* persisted turn */ };
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts
|
||||
├── cli.ts Binary entrypoint
|
||||
├── agent.ts createBuiltinAgent
|
||||
├── loop.ts Multi-turn LLM + tool loop
|
||||
├── prompt.ts buildBuiltinMessages
|
||||
├── session.ts Session directory persistence
|
||||
├── detail.ts CAS detail node storage
|
||||
├── schemas.ts Builtin CAS schemas
|
||||
├── types.ts Detail and turn payload types
|
||||
├── llm/
|
||||
│ ├── index.ts
|
||||
│ ├── llm.ts chatCompletionWithTools
|
||||
│ └── types.ts ChatMessage, LlmToolCall, etc.
|
||||
└── tools/
|
||||
├── index.ts getBuiltinTools, executeBuiltinTool
|
||||
├── read-file.ts
|
||||
├── write-file.ts
|
||||
├── run-command.ts
|
||||
├── path.ts
|
||||
└── types.ts
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Requires a configured OpenAI-compatible provider and model in `~/.uncaged/workflow/config.yaml` (via `uwf setup`). API keys are loaded from `~/.uncaged/workflow/.env`.
|
||||
|
||||
Tools run with the current working directory as `ToolContext.cwd` (typically the directory where `uwf thread step` was invoked).
|
||||
@@ -19,14 +19,7 @@ mock.module("../src/tools/index.js", () => ({
|
||||
getBuiltinTools: () => [],
|
||||
}));
|
||||
|
||||
import {
|
||||
executeTurnTools,
|
||||
extractFinalText,
|
||||
runBuiltinLoop,
|
||||
shouldInjectDeadlineWarning,
|
||||
shouldNudge,
|
||||
shouldProcessToolCalls,
|
||||
} from "../src/loop.js";
|
||||
import { executeTurnTools, runBuiltinLoop, shouldNudge } from "../src/loop.js";
|
||||
|
||||
const fakeProvider = {} as any;
|
||||
const fakeToolCtx = {} as any;
|
||||
@@ -161,96 +154,3 @@ describe("runBuiltinLoop integration", () => {
|
||||
expect(original.length).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe("shouldInjectDeadlineWarning", () => {
|
||||
test("5.1 returns true when turn count reaches warning threshold and not yet warned", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, false, false)).toBe(true);
|
||||
});
|
||||
test("5.2 returns false when already warned", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, true, false)).toBe(false);
|
||||
});
|
||||
test("5.3 returns false when noTools is true", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, false, true)).toBe(false);
|
||||
});
|
||||
test("5.4 returns false when turns remaining > DEADLINE_WARNING_TURNS", () => {
|
||||
expect(shouldInjectDeadlineWarning(5, 10, false, false)).toBe(false);
|
||||
});
|
||||
test("5.5 returns true when exactly at warning threshold", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, false, false)).toBe(true);
|
||||
});
|
||||
test("5.6 returns false when turns remaining is 0", () => {
|
||||
expect(shouldInjectDeadlineWarning(10, 10, false, false)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("shouldProcessToolCalls", () => {
|
||||
test("6.1 returns true when toolCalls present and noTools=false", () => {
|
||||
expect(shouldProcessToolCalls([{ id: "x", name: "read", arguments: "{}" }], false)).toBe(true);
|
||||
});
|
||||
test("6.2 returns false when toolCalls is null", () => {
|
||||
expect(shouldProcessToolCalls(null, false)).toBe(false);
|
||||
});
|
||||
test("6.3 returns false when toolCalls is empty array", () => {
|
||||
expect(shouldProcessToolCalls([], false)).toBe(false);
|
||||
});
|
||||
test("6.4 returns false when noTools=true", () => {
|
||||
expect(shouldProcessToolCalls([{ id: "x", name: "read", arguments: "{}" }], true)).toBe(false);
|
||||
});
|
||||
test("6.5 returns true when multiple tool calls present", () => {
|
||||
expect(
|
||||
shouldProcessToolCalls(
|
||||
[
|
||||
{ id: "x1", name: "read", arguments: "{}" },
|
||||
{ id: "x2", name: "write", arguments: "{}" },
|
||||
],
|
||||
false,
|
||||
),
|
||||
).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe("extractFinalText", () => {
|
||||
test("7.1 returns last assistant message content", () => {
|
||||
const messages = [
|
||||
{ role: "system" as const, content: "sys", tool_calls: null },
|
||||
{ role: "assistant" as const, content: "first", tool_calls: null },
|
||||
{ role: "assistant" as const, content: "last", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("last");
|
||||
});
|
||||
test("7.2 returns empty string when no assistant messages", () => {
|
||||
expect(extractFinalText([{ role: "system" as const, content: "sys", tool_calls: null }])).toBe(
|
||||
"",
|
||||
);
|
||||
});
|
||||
test("7.3 skips assistant messages with null content", () => {
|
||||
const messages = [
|
||||
{ role: "assistant" as const, content: "first", tool_calls: null },
|
||||
{
|
||||
role: "assistant" as const,
|
||||
content: null,
|
||||
tool_calls: [{ id: "x", name: "t", arguments: "{}" }],
|
||||
},
|
||||
{ role: "assistant" as const, content: "second", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("second");
|
||||
});
|
||||
test("7.4 skips assistant messages with empty content", () => {
|
||||
const messages = [
|
||||
{ role: "assistant" as const, content: "first", tool_calls: null },
|
||||
{ role: "assistant" as const, content: "", tool_calls: null },
|
||||
{ role: "user" as const, content: "nudge", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("first");
|
||||
});
|
||||
test("7.5 handles empty messages array", () => {
|
||||
expect(extractFinalText([])).toBe("");
|
||||
});
|
||||
test("7.6 handles messages with only user and system roles", () => {
|
||||
const messages = [
|
||||
{ role: "system" as const, content: "sys", tool_calls: null },
|
||||
{ role: "user" as const, content: "query", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,12 +1,7 @@
|
||||
import type { ResolvedLlmProvider } from "@uncaged/workflow-agent-kit";
|
||||
import { createLogger } from "@uncaged/workflow-util";
|
||||
|
||||
import {
|
||||
type ChatMessage,
|
||||
chatCompletionWithTools,
|
||||
type LlmToolCall,
|
||||
type OpenAiToolDefinition,
|
||||
} from "./llm/index.js";
|
||||
import { type ChatMessage, chatCompletionWithTools, type LlmToolCall } from "./llm/index.js";
|
||||
import { appendSessionTurn } from "./session.js";
|
||||
import {
|
||||
builtinToolsToOpenAi,
|
||||
@@ -82,23 +77,53 @@ export type ShouldNudgeOptions = {
|
||||
maxTurns: number;
|
||||
};
|
||||
|
||||
const MAX_NUDGES = 3;
|
||||
const DEADLINE_WARNING_TURNS = 3;
|
||||
|
||||
export function shouldInjectDeadlineWarning(
|
||||
turn: number,
|
||||
maxTurns: number,
|
||||
alreadyWarned: boolean,
|
||||
noTools: boolean,
|
||||
): boolean {
|
||||
const turnsRemaining = maxTurns - turn;
|
||||
return (
|
||||
!noTools && !alreadyWarned && turnsRemaining > 0 && turnsRemaining <= DEADLINE_WARNING_TURNS
|
||||
);
|
||||
export function shouldNudge({ noTools, text, turn, maxTurns }: ShouldNudgeOptions): boolean {
|
||||
return !noTools && !text.trimStart().startsWith("---") && turn < maxTurns - 1;
|
||||
}
|
||||
|
||||
export function shouldProcessToolCalls(toolCalls: LlmToolCall[] | null, noTools: boolean): boolean {
|
||||
return !noTools && toolCalls !== null && toolCalls.length > 0;
|
||||
async function handleTextTurn(
|
||||
text: string,
|
||||
turn: number,
|
||||
noTools: boolean,
|
||||
maxTurns: number,
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
messages: ChatMessage[],
|
||||
): Promise<{ done: boolean; finalText: string }> {
|
||||
await appendTurn(storageRoot, sessionId, {
|
||||
role: "assistant",
|
||||
content: text,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
|
||||
if (shouldNudge({ noTools, text, turn, maxTurns })) {
|
||||
log("7FXQM2KN", "text-only turn without frontmatter, nudging LLM to continue");
|
||||
const nudge =
|
||||
"You stopped calling tools but your response does not start with the required `---` YAML frontmatter. " +
|
||||
"Either continue using tools to complete your work, or output your final response starting with `---`.";
|
||||
messages.push({ role: "user", content: nudge });
|
||||
return { done: false, finalText: "" };
|
||||
}
|
||||
|
||||
return { done: true, finalText: text };
|
||||
}
|
||||
|
||||
async function handleToolTurn(
|
||||
content: string,
|
||||
toolCalls: LlmToolCall[],
|
||||
toolCtx: ToolContext,
|
||||
messages: ChatMessage[],
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
): Promise<number> {
|
||||
await appendTurn(storageRoot, sessionId, {
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: mapToolCallsForPayload(toolCalls),
|
||||
reasoning: null,
|
||||
});
|
||||
return executeTurnTools(toolCalls, toolCtx, messages, storageRoot, sessionId);
|
||||
}
|
||||
|
||||
export function extractFinalText(messages: ChatMessage[]): string {
|
||||
@@ -116,151 +141,47 @@ export function extractFinalText(messages: ChatMessage[]): string {
|
||||
return "";
|
||||
}
|
||||
|
||||
function injectDeadlineWarning(messages: ChatMessage[], turnsRemaining: number): void {
|
||||
log("4NRXW6KT", `${turnsRemaining} turns remaining, injecting deadline warning`);
|
||||
messages.push({
|
||||
role: "user",
|
||||
content:
|
||||
`⚠️ You have ${turnsRemaining} turns remaining. ` +
|
||||
"Wrap up your work and output the YAML frontmatter starting with `---`. " +
|
||||
"If you cannot finish in time, output frontmatter with `status: failed` and describe what remains.",
|
||||
});
|
||||
}
|
||||
type LoopTurnResult = { done: boolean; finalText: string; extraTurns: number };
|
||||
|
||||
type HandleTextOnlyTurnResult = {
|
||||
shouldBreak: boolean;
|
||||
finalText: string;
|
||||
turnCount: number;
|
||||
nudgeCount: number;
|
||||
turnAdjustment: number;
|
||||
};
|
||||
|
||||
async function handleTextOnlyTurn(
|
||||
text: string,
|
||||
messages: ChatMessage[],
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
noTools: boolean,
|
||||
async function runLoopTurn(
|
||||
turn: number,
|
||||
maxTurns: number,
|
||||
currentNudgeCount: number,
|
||||
): Promise<HandleTextOnlyTurnResult> {
|
||||
await appendTurn(storageRoot, sessionId, {
|
||||
role: "assistant",
|
||||
content: text,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const turnCount = 1;
|
||||
let nudgeCount = currentNudgeCount;
|
||||
let turnAdjustment = 0;
|
||||
|
||||
if (shouldNudge({ noTools, text, turn, maxTurns })) {
|
||||
nudgeCount += 1;
|
||||
log("7FXQM2KN", `text-only turn without frontmatter, nudge ${nudgeCount}/${MAX_NUDGES}`);
|
||||
const nudge =
|
||||
"You stopped calling tools but your response does not start with the required `---` YAML frontmatter. " +
|
||||
"Either continue using tools to complete your work, or output your final response starting with `---`.";
|
||||
messages.push({ role: "user", content: nudge });
|
||||
// Nudge doesn't consume turn budget (up to MAX_NUDGES)
|
||||
if (nudgeCount <= MAX_NUDGES) {
|
||||
turnAdjustment = -1;
|
||||
}
|
||||
return { shouldBreak: false, finalText: "", turnCount, nudgeCount, turnAdjustment };
|
||||
}
|
||||
|
||||
return { shouldBreak: true, finalText: text, turnCount, nudgeCount, turnAdjustment };
|
||||
}
|
||||
|
||||
async function handleToolCallTurn(
|
||||
content: string,
|
||||
toolCalls: LlmToolCall[],
|
||||
messages: ChatMessage[],
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
toolCtx: ToolContext,
|
||||
): Promise<number> {
|
||||
await appendTurn(storageRoot, sessionId, {
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: mapToolCallsForPayload(toolCalls),
|
||||
reasoning: null,
|
||||
});
|
||||
let turnCount = 1;
|
||||
|
||||
// Execute tools
|
||||
turnCount += await executeTurnTools(toolCalls, toolCtx, messages, storageRoot, sessionId);
|
||||
|
||||
return turnCount;
|
||||
}
|
||||
|
||||
export function shouldNudge({ noTools, text, turn, maxTurns }: ShouldNudgeOptions): boolean {
|
||||
return !noTools && !text.trimStart().startsWith("---") && turn < maxTurns - 1;
|
||||
}
|
||||
|
||||
type ProcessLoopIterationResult = {
|
||||
shouldBreak: boolean;
|
||||
finalText: string;
|
||||
turnCount: number;
|
||||
nudgeCount: number;
|
||||
turnAdjustment: number;
|
||||
};
|
||||
|
||||
async function processLoopIteration(
|
||||
options: RunBuiltinLoopOptions,
|
||||
messages: ChatMessage[],
|
||||
openAiTools: OpenAiToolDefinition[],
|
||||
turn: number,
|
||||
nudgeCount: number,
|
||||
): Promise<ProcessLoopIterationResult> {
|
||||
openAiTools: ReturnType<typeof builtinToolsToOpenAi>,
|
||||
): Promise<LoopTurnResult> {
|
||||
log("8K2M4N7P", `builtin loop turn ${turn + 1}/${options.maxTurns}`);
|
||||
const response = await chatCompletionWithTools(
|
||||
options.provider,
|
||||
messages,
|
||||
openAiTools.length > 0 ? openAiTools : null,
|
||||
);
|
||||
|
||||
// When noTools is set, ignore any tool_calls the LLM might still return
|
||||
const effectiveToolCalls = options.noTools ? null : (response.toolCalls ?? null);
|
||||
messages.push({ role: "assistant", content: response.content, tool_calls: effectiveToolCalls });
|
||||
|
||||
const assistantMessage: ChatMessage = {
|
||||
role: "assistant",
|
||||
content: response.content,
|
||||
tool_calls: effectiveToolCalls,
|
||||
};
|
||||
messages.push(assistantMessage);
|
||||
|
||||
if (!shouldProcessToolCalls(effectiveToolCalls, options.noTools)) {
|
||||
if (effectiveToolCalls === null || effectiveToolCalls.length === 0) {
|
||||
const text = response.content ?? "";
|
||||
const result = await handleTextOnlyTurn(
|
||||
const result = await handleTextTurn(
|
||||
text,
|
||||
messages,
|
||||
turn,
|
||||
options.noTools,
|
||||
options.maxTurns,
|
||||
options.storageRoot,
|
||||
options.sessionId,
|
||||
options.noTools,
|
||||
turn,
|
||||
options.maxTurns,
|
||||
nudgeCount,
|
||||
messages,
|
||||
);
|
||||
return result;
|
||||
return { done: result.done, finalText: result.finalText, extraTurns: 0 };
|
||||
}
|
||||
|
||||
// At this point, effectiveToolCalls is guaranteed to be non-null and non-empty
|
||||
const turnCount = await handleToolCallTurn(
|
||||
const extra = await handleToolTurn(
|
||||
response.content ?? "",
|
||||
effectiveToolCalls as LlmToolCall[],
|
||||
effectiveToolCalls,
|
||||
options.toolCtx,
|
||||
messages,
|
||||
options.storageRoot,
|
||||
options.sessionId,
|
||||
options.toolCtx,
|
||||
);
|
||||
|
||||
return {
|
||||
shouldBreak: false,
|
||||
finalText: "",
|
||||
turnCount,
|
||||
nudgeCount,
|
||||
turnAdjustment: 0,
|
||||
};
|
||||
return { done: false, finalText: "", extraTurns: extra };
|
||||
}
|
||||
|
||||
/** Agent run loop: LLM ↔ tools until no tool_calls or maxTurns. */
|
||||
@@ -271,31 +192,17 @@ export async function runBuiltinLoop(
|
||||
const openAiTools = options.noTools ? [] : builtinToolsToOpenAi(getBuiltinTools());
|
||||
let finalText = "";
|
||||
let turnCount = 0;
|
||||
let nudgeCount = 0;
|
||||
let deadlineWarned = false;
|
||||
|
||||
for (let turn = 0; turn < options.maxTurns; turn++) {
|
||||
log("8K2M4N7P", `builtin loop turn ${turn + 1}/${options.maxTurns}`);
|
||||
|
||||
// Warn agent when approaching turn limit
|
||||
if (shouldInjectDeadlineWarning(turn, options.maxTurns, deadlineWarned, options.noTools)) {
|
||||
deadlineWarned = true;
|
||||
const turnsRemaining = options.maxTurns - turn;
|
||||
injectDeadlineWarning(messages, turnsRemaining);
|
||||
}
|
||||
|
||||
const result = await processLoopIteration(options, messages, openAiTools, turn, nudgeCount);
|
||||
turnCount += result.turnCount;
|
||||
nudgeCount = result.nudgeCount;
|
||||
turn += result.turnAdjustment;
|
||||
|
||||
if (result.shouldBreak) {
|
||||
const result = await runLoopTurn(turn, options, messages, openAiTools);
|
||||
turnCount += 1 + result.extraTurns;
|
||||
if (result.done) {
|
||||
finalText = result.finalText;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (finalText === "") {
|
||||
if (finalText === "" && messages.length > 0) {
|
||||
finalText = extractFinalText(messages);
|
||||
}
|
||||
|
||||
|
||||
@@ -1,91 +0,0 @@
|
||||
# @uncaged/workflow-agent-claude-code
|
||||
|
||||
`uwf-claude-code` agent — spawns the Claude Code CLI and captures session detail.
|
||||
|
||||
## Overview
|
||||
|
||||
Layer 3 agent implementation. Spawns the `claude` CLI with a composed system prompt (role definition, task, prior steps, edge prompt). Parses stream or JSON stdout, caches session IDs for multi-turn continuation, and stores raw output plus structured detail in CAS.
|
||||
|
||||
**Dependencies:** `@uncaged/json-cas`, `@uncaged/workflow-agent-kit`
|
||||
|
||||
## Installation
|
||||
|
||||
Included as the `uwf-claude-code` binary when you install `@uncaged/workflow-agent-claude-code`:
|
||||
|
||||
```bash
|
||||
bun add -g @uncaged/workflow-agent-claude-code
|
||||
```
|
||||
|
||||
Requires the `claude` CLI on `PATH`.
|
||||
|
||||
## CLI Usage
|
||||
|
||||
Invoked by `uwf thread step`:
|
||||
|
||||
```bash
|
||||
uwf-claude-code <thread-id> <role>
|
||||
```
|
||||
|
||||
Configure or override the agent:
|
||||
|
||||
```bash
|
||||
uwf setup --agent claude-code
|
||||
uwf thread step <thread-id> --agent uwf-claude-code
|
||||
```
|
||||
|
||||
Environment variables set by the engine:
|
||||
|
||||
| Variable | Purpose |
|
||||
|----------|---------|
|
||||
| `UWF_EDGE_PROMPT` | Moderator edge instruction for this step |
|
||||
|
||||
## API
|
||||
|
||||
All exports come from `src/index.ts`.
|
||||
|
||||
### Agent factory
|
||||
|
||||
```typescript
|
||||
function createClaudeCodeAgent(): () => Promise<void>
|
||||
function buildClaudeCodePrompt(ctx: AgentContext): string
|
||||
```
|
||||
|
||||
### Session detail
|
||||
|
||||
```typescript
|
||||
function parseClaudeCodeStreamOutput(stdout: string): ClaudeCodeParsedResult | null
|
||||
function parseClaudeCodeJsonOutput(stdout: string): ClaudeCodeParsedResult | null
|
||||
function storeClaudeCodeDetail(
|
||||
store: Store,
|
||||
parsed: ClaudeCodeParsedResult,
|
||||
sessionId: string,
|
||||
): Promise<string>
|
||||
function storeClaudeCodeRawOutput(store: Store, rawOutput: string): Promise<string>
|
||||
```
|
||||
|
||||
## Usage (library)
|
||||
|
||||
```typescript
|
||||
import { createClaudeCodeAgent, buildClaudeCodePrompt } from "@uncaged/workflow-agent-claude-code";
|
||||
|
||||
const main = createClaudeCodeAgent();
|
||||
void main();
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts
|
||||
├── cli.ts Binary entrypoint
|
||||
├── claude-code.ts createClaudeCodeAgent, buildClaudeCodePrompt, spawn logic
|
||||
├── session-detail.ts Parse stdout, store CAS detail nodes
|
||||
├── schemas.ts Claude Code detail CAS schemas
|
||||
└── types.ts ClaudeCodeParsedResult, message shapes
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Uses session caching from `@uncaged/workflow-agent-kit` (`getCachedSessionId` / `setCachedSessionId`). No separate config file — relies on the Claude Code CLI's own authentication.
|
||||
|
||||
Maximum turns per invocation: 90 (constant in `claude-code.ts`).
|
||||
@@ -39,7 +39,7 @@ describe("buildClaudeCodePrompt", () => {
|
||||
expect(result).toContain("## Task\nFix the bug");
|
||||
});
|
||||
|
||||
test("includes previous steps with content on first visit", () => {
|
||||
test("includes previous steps as history summary", () => {
|
||||
const ctx = makeCtx({
|
||||
steps: [
|
||||
{
|
||||
@@ -48,50 +48,18 @@ 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("## What Happened Since Your Last Turn");
|
||||
expect(result).toContain("## Previous Steps");
|
||||
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("## What Happened Since Your Last Turn");
|
||||
expect(result).toContain("## Current Instruction");
|
||||
expect(result).not.toContain("## Previous Steps");
|
||||
});
|
||||
|
||||
test("works without outputFormatInstruction", () => {
|
||||
|
||||
@@ -154,99 +154,6 @@ describe("parseClaudeCodeStreamOutput", () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe("parseClaudeCodeStreamOutput — helper extraction", () => {
|
||||
test("processSystemLine sets model from system message", () => {
|
||||
const lines = [
|
||||
JSON.stringify({ type: "system", model: "claude-opus-4" }),
|
||||
JSON.stringify({
|
||||
type: "result",
|
||||
subtype: "success",
|
||||
result: "ok",
|
||||
session_id: "s1",
|
||||
num_turns: 0,
|
||||
total_cost_usd: 0,
|
||||
duration_ms: 0,
|
||||
stop_reason: "end_turn",
|
||||
}),
|
||||
];
|
||||
const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
|
||||
expect(parsed).not.toBeNull();
|
||||
expect(parsed!.model).toBe("claude-opus-4");
|
||||
});
|
||||
|
||||
test("processAssistantLine skips empty content", () => {
|
||||
const lines = [
|
||||
JSON.stringify({ type: "assistant", message: { role: "assistant", content: [] } }),
|
||||
JSON.stringify({
|
||||
type: "result",
|
||||
subtype: "success",
|
||||
result: "ok",
|
||||
session_id: "s1",
|
||||
num_turns: 0,
|
||||
total_cost_usd: 0,
|
||||
duration_ms: 0,
|
||||
stop_reason: "end_turn",
|
||||
}),
|
||||
];
|
||||
const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
|
||||
expect(parsed).not.toBeNull();
|
||||
expect(parsed!.turns).toHaveLength(0);
|
||||
});
|
||||
|
||||
test("processUserLine skips when no tool_result items", () => {
|
||||
const lines = [
|
||||
JSON.stringify({
|
||||
type: "user",
|
||||
message: { role: "user", content: [{ type: "text", text: "hi" }] },
|
||||
}),
|
||||
JSON.stringify({
|
||||
type: "result",
|
||||
subtype: "success",
|
||||
result: "ok",
|
||||
session_id: "s1",
|
||||
num_turns: 0,
|
||||
total_cost_usd: 0,
|
||||
duration_ms: 0,
|
||||
stop_reason: "end_turn",
|
||||
}),
|
||||
];
|
||||
const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
|
||||
expect(parsed).not.toBeNull();
|
||||
expect(parsed!.turns).toHaveLength(0);
|
||||
});
|
||||
|
||||
test("turn indices are sequential across mixed assistant and user lines", () => {
|
||||
const lines = [
|
||||
JSON.stringify({
|
||||
type: "assistant",
|
||||
message: { role: "assistant", content: [{ type: "text", text: "A" }] },
|
||||
}),
|
||||
JSON.stringify({
|
||||
type: "user",
|
||||
message: { role: "user", content: [{ type: "tool_result", content: "R" }] },
|
||||
}),
|
||||
JSON.stringify({
|
||||
type: "assistant",
|
||||
message: { role: "assistant", content: [{ type: "text", text: "B" }] },
|
||||
}),
|
||||
JSON.stringify({
|
||||
type: "result",
|
||||
subtype: "success",
|
||||
result: "ok",
|
||||
session_id: "s1",
|
||||
num_turns: 3,
|
||||
total_cost_usd: 0,
|
||||
duration_ms: 0,
|
||||
stop_reason: "end_turn",
|
||||
}),
|
||||
];
|
||||
const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
|
||||
expect(parsed).not.toBeNull();
|
||||
expect(parsed!.turns).toHaveLength(3);
|
||||
expect(parsed!.turns.map((t) => t.index)).toEqual([0, 1, 2]);
|
||||
});
|
||||
});
|
||||
|
||||
describe("storeClaudeCodeDetail", () => {
|
||||
const baseParsed: ClaudeCodeParsedResult = {
|
||||
type: "result",
|
||||
|
||||
@@ -22,8 +22,7 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/json-cas": "^0.4.0",
|
||||
"@uncaged/workflow-agent-kit": "workspace:^",
|
||||
"@uncaged/workflow-util": "workspace:^"
|
||||
"@uncaged/workflow-agent-kit": "workspace:^"
|
||||
},
|
||||
"devDependencies": {
|
||||
"typescript": "^5.8.3"
|
||||
|
||||
@@ -3,7 +3,6 @@ import type { Store } from "@uncaged/json-cas";
|
||||
import {
|
||||
type AgentContext,
|
||||
type AgentRunResult,
|
||||
buildContinuationPrompt,
|
||||
buildRolePrompt,
|
||||
createAgent,
|
||||
getCachedSessionId,
|
||||
@@ -17,7 +16,25 @@ const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
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 {
|
||||
@@ -28,23 +45,11 @@ export function buildClaudeCodePrompt(ctx: AgentContext): string {
|
||||
parts.push(ctx.outputFormatInstruction, "");
|
||||
}
|
||||
parts.push(rolePrompt, "", "## Task", ctx.start.prompt);
|
||||
|
||||
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);
|
||||
const historyBlock = buildHistorySummary(ctx.steps);
|
||||
if (historyBlock !== "") {
|
||||
parts.push("", historyBlock);
|
||||
}
|
||||
|
||||
parts.push("", "## Current Instruction", "", ctx.edgePrompt);
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
@@ -82,7 +87,7 @@ function spawnClaude(args: string[]): Promise<{ stdout: string; stderr: string }
|
||||
}
|
||||
|
||||
function spawnClaudeRun(prompt: string): Promise<{ stdout: string; stderr: string }> {
|
||||
const args = [
|
||||
return spawnClaude([
|
||||
"-p",
|
||||
prompt,
|
||||
"--output-format",
|
||||
@@ -91,18 +96,14 @@ function spawnClaudeRun(prompt: string): Promise<{ stdout: string; stderr: strin
|
||||
"--dangerously-skip-permissions",
|
||||
"--max-turns",
|
||||
String(CLAUDE_MAX_TURNS),
|
||||
];
|
||||
if (CLAUDE_MODEL !== null) {
|
||||
args.push("--model", CLAUDE_MODEL);
|
||||
}
|
||||
return spawnClaude(args);
|
||||
]);
|
||||
}
|
||||
|
||||
function spawnClaudeResume(
|
||||
sessionId: string,
|
||||
message: string,
|
||||
): Promise<{ stdout: string; stderr: string }> {
|
||||
const args = [
|
||||
return spawnClaude([
|
||||
"-p",
|
||||
message,
|
||||
"--resume",
|
||||
@@ -113,11 +114,7 @@ function spawnClaudeResume(
|
||||
"--dangerously-skip-permissions",
|
||||
"--max-turns",
|
||||
String(CLAUDE_MAX_TURNS),
|
||||
];
|
||||
if (CLAUDE_MODEL !== null) {
|
||||
args.push("--model", CLAUDE_MODEL);
|
||||
}
|
||||
return spawnClaude(args);
|
||||
]);
|
||||
}
|
||||
|
||||
async function processClaudeOutput(stdout: string, store: Store): Promise<AgentRunResult> {
|
||||
@@ -140,13 +137,13 @@ 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("claude-code", ctx.threadId, ctx.role);
|
||||
const cachedSessionId = await getCachedSessionId(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("claude-code", ctx.threadId, ctx.role, result.sessionId);
|
||||
await setCachedSessionId(ctx.threadId, ctx.role, result.sessionId);
|
||||
}
|
||||
return result;
|
||||
} catch (err) {
|
||||
@@ -163,7 +160,7 @@ 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("claude-code", ctx.threadId, ctx.role, result.sessionId);
|
||||
await setCachedSessionId(ctx.threadId, ctx.role, result.sessionId);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
@@ -34,7 +34,7 @@ export const CLAUDE_CODE_DETAIL_SCHEMA: JSONSchema = {
|
||||
},
|
||||
turns: {
|
||||
type: "array",
|
||||
items: { type: "string", format: "cas_ref" },
|
||||
items: { type: "string" },
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
|
||||
@@ -67,103 +67,99 @@ function extractToolResultContent(content: unknown[]): string {
|
||||
return results.join("\n");
|
||||
}
|
||||
|
||||
type ParseState = {
|
||||
turns: ClaudeCodeTurnPayload[];
|
||||
resultLine: Record<string, unknown> | null;
|
||||
model: string;
|
||||
turnIndex: number;
|
||||
};
|
||||
|
||||
function processSystemLine(parsed: Record<string, unknown>, state: ParseState): void {
|
||||
if (typeof parsed.model === "string") {
|
||||
state.model = parsed.model;
|
||||
}
|
||||
}
|
||||
|
||||
function processAssistantLine(parsed: Record<string, unknown>, state: ParseState): void {
|
||||
if (!isRecord(parsed.message)) return;
|
||||
const content = Array.isArray(parsed.message.content) ? parsed.message.content : [];
|
||||
const textContent = extractTextContent(content as unknown[]);
|
||||
const toolCalls = extractToolCalls(content as unknown[]);
|
||||
if (textContent !== "" || toolCalls.length > 0) {
|
||||
state.turns.push({
|
||||
index: state.turnIndex++,
|
||||
role: "assistant",
|
||||
content: textContent,
|
||||
toolCalls: toolCalls.length > 0 ? toolCalls : null,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
function processUserLine(parsed: Record<string, unknown>, state: ParseState): void {
|
||||
if (!isRecord(parsed.message)) return;
|
||||
const content = Array.isArray(parsed.message.content) ? parsed.message.content : [];
|
||||
const resultContent = extractToolResultContent(content as unknown[]);
|
||||
if (resultContent !== "") {
|
||||
state.turns.push({
|
||||
index: state.turnIndex++,
|
||||
role: "tool_result",
|
||||
content: resultContent,
|
||||
toolCalls: null,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
function processLine(line: string, state: ParseState): void {
|
||||
let parsed: unknown;
|
||||
try {
|
||||
parsed = JSON.parse(line);
|
||||
} catch {
|
||||
return;
|
||||
}
|
||||
if (!isRecord(parsed)) return;
|
||||
const type = parsed.type;
|
||||
if (type === "system") processSystemLine(parsed, state);
|
||||
else if (type === "assistant") processAssistantLine(parsed, state);
|
||||
else if (type === "user") processUserLine(parsed, state);
|
||||
else if (type === "result") state.resultLine = parsed;
|
||||
}
|
||||
|
||||
function assembleResult(state: ParseState): ClaudeCodeParsedResult | null {
|
||||
if (state.resultLine === null) return null;
|
||||
const sessionId = state.resultLine.session_id;
|
||||
const result = state.resultLine.result;
|
||||
const subtype = state.resultLine.subtype;
|
||||
if (typeof sessionId !== "string" || typeof result !== "string" || typeof subtype !== "string") {
|
||||
return null;
|
||||
}
|
||||
const usage = isRecord(state.resultLine.usage) ? state.resultLine.usage : {};
|
||||
return {
|
||||
type: safeString(state.resultLine.type, "result"),
|
||||
subtype: subtype as ClaudeCodeParsedResult["subtype"],
|
||||
result,
|
||||
sessionId,
|
||||
numTurns: safeNumber(state.resultLine.num_turns),
|
||||
totalCostUsd: safeNumber(state.resultLine.total_cost_usd),
|
||||
durationMs: safeNumber(state.resultLine.duration_ms),
|
||||
model: state.model,
|
||||
stopReason: safeString(state.resultLine.stop_reason),
|
||||
usage: {
|
||||
inputTokens: safeNumber(usage.input_tokens),
|
||||
outputTokens: safeNumber(usage.output_tokens),
|
||||
cacheReadInputTokens: safeNumber(usage.cache_read_input_tokens),
|
||||
cacheCreationInputTokens: safeNumber(usage.cache_creation_input_tokens),
|
||||
},
|
||||
turns: state.turns,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse Claude Code stream-json (NDJSON) output.
|
||||
* Each line is a JSON object with type: "system" | "assistant" | "user" | "result".
|
||||
*/
|
||||
export function parseClaudeCodeStreamOutput(stdout: string): ClaudeCodeParsedResult | null {
|
||||
const lines = stdout.trim().split("\n");
|
||||
const state: ParseState = { turns: [], resultLine: null, model: "", turnIndex: 0 };
|
||||
const turns: ClaudeCodeTurnPayload[] = [];
|
||||
let resultLine: Record<string, unknown> | null = null;
|
||||
let model = "";
|
||||
let turnIndex = 0;
|
||||
|
||||
for (const line of lines) {
|
||||
processLine(line, state);
|
||||
let parsed: unknown;
|
||||
try {
|
||||
parsed = JSON.parse(line);
|
||||
} catch {
|
||||
continue;
|
||||
}
|
||||
if (!isRecord(parsed)) continue;
|
||||
|
||||
const type = parsed.type;
|
||||
|
||||
if (type === "system" && typeof parsed.model === "string") {
|
||||
model = parsed.model;
|
||||
}
|
||||
|
||||
if (type === "assistant" && isRecord(parsed.message)) {
|
||||
const msg = parsed.message;
|
||||
const content = Array.isArray(msg.content) ? msg.content : [];
|
||||
const textContent = extractTextContent(content as unknown[]);
|
||||
const toolCalls = extractToolCalls(content as unknown[]);
|
||||
|
||||
// Only record turns that have actual content
|
||||
if (textContent !== "" || toolCalls.length > 0) {
|
||||
turns.push({
|
||||
index: turnIndex++,
|
||||
role: "assistant",
|
||||
content: textContent,
|
||||
toolCalls: toolCalls.length > 0 ? toolCalls : null,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
if (type === "user" && isRecord(parsed.message)) {
|
||||
const msg = parsed.message;
|
||||
const content = Array.isArray(msg.content) ? msg.content : [];
|
||||
const resultContent = extractToolResultContent(content as unknown[]);
|
||||
|
||||
if (resultContent !== "") {
|
||||
turns.push({
|
||||
index: turnIndex++,
|
||||
role: "tool_result",
|
||||
content: resultContent,
|
||||
toolCalls: null,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
if (type === "result") {
|
||||
resultLine = parsed;
|
||||
}
|
||||
}
|
||||
return assembleResult(state);
|
||||
|
||||
if (resultLine === null) return null;
|
||||
|
||||
const sessionId = resultLine.session_id;
|
||||
const result = resultLine.result;
|
||||
const subtype = resultLine.subtype;
|
||||
|
||||
if (typeof sessionId !== "string" || typeof result !== "string" || typeof subtype !== "string") {
|
||||
return null;
|
||||
}
|
||||
|
||||
const usage = isRecord(resultLine.usage) ? resultLine.usage : {};
|
||||
|
||||
return {
|
||||
type: safeString(resultLine.type, "result"),
|
||||
subtype: subtype as ClaudeCodeParsedResult["subtype"],
|
||||
result,
|
||||
sessionId,
|
||||
numTurns: safeNumber(resultLine.num_turns),
|
||||
totalCostUsd: safeNumber(resultLine.total_cost_usd),
|
||||
durationMs: safeNumber(resultLine.duration_ms),
|
||||
model,
|
||||
stopReason: safeString(resultLine.stop_reason),
|
||||
usage: {
|
||||
inputTokens: safeNumber(usage.input_tokens),
|
||||
outputTokens: safeNumber(usage.output_tokens),
|
||||
cacheReadInputTokens: safeNumber(usage.cache_read_input_tokens),
|
||||
cacheCreationInputTokens: safeNumber(usage.cache_creation_input_tokens),
|
||||
},
|
||||
turns,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -1,90 +0,0 @@
|
||||
# @uncaged/workflow-agent-hermes
|
||||
|
||||
`uwf-hermes` agent — spawns Hermes chat via ACP and captures session detail.
|
||||
|
||||
## Overview
|
||||
|
||||
Layer 3 agent implementation. Wraps the Hermes CLI using the Agent Client Protocol (ACP). On first visit to a role it sends a composed prompt (role definition, task, history, edge prompt); on continuation it resumes the cached session. Session transcripts and raw output are stored as CAS detail nodes.
|
||||
|
||||
**Dependencies:** `@uncaged/json-cas`, `@uncaged/workflow-agent-kit`, `@uncaged/workflow-protocol`, `@uncaged/workflow-util`
|
||||
|
||||
## Installation
|
||||
|
||||
Included as the `uwf-hermes` binary when you install `@uncaged/workflow-agent-hermes`:
|
||||
|
||||
```bash
|
||||
bun add -g @uncaged/workflow-agent-hermes
|
||||
```
|
||||
|
||||
Requires the `hermes` CLI on `PATH`.
|
||||
|
||||
## CLI Usage
|
||||
|
||||
Invoked by `uwf thread step` (not typically run directly):
|
||||
|
||||
```bash
|
||||
uwf-hermes <thread-id> <role>
|
||||
```
|
||||
|
||||
Environment variables set by the engine:
|
||||
|
||||
| Variable | Purpose |
|
||||
|----------|---------|
|
||||
| `UWF_EDGE_PROMPT` | Moderator edge instruction for this step |
|
||||
|
||||
Configure as the default agent via `uwf setup --agent hermes`.
|
||||
|
||||
Override per step:
|
||||
|
||||
```bash
|
||||
uwf thread step <thread-id> --agent uwf-hermes
|
||||
```
|
||||
|
||||
## API
|
||||
|
||||
All exports come from `src/index.ts`.
|
||||
|
||||
### Agent factory
|
||||
|
||||
```typescript
|
||||
function createHermesAgent(): () => Promise<void>
|
||||
function buildHermesPrompt(ctx: AgentContext): string
|
||||
```
|
||||
|
||||
### ACP client
|
||||
|
||||
```typescript
|
||||
class HermesAcpClient {
|
||||
// Spawns hermes, handles JSON-RPC over stdio
|
||||
}
|
||||
```
|
||||
|
||||
## Usage (library)
|
||||
|
||||
```typescript
|
||||
import { createHermesAgent, buildHermesPrompt } from "@uncaged/workflow-agent-hermes";
|
||||
|
||||
// CLI entry (src/cli.ts):
|
||||
const main = createHermesAgent();
|
||||
void main();
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts
|
||||
├── cli.ts Binary entrypoint
|
||||
├── hermes.ts createHermesAgent, buildHermesPrompt
|
||||
├── acp-client.ts HermesAcpClient — ACP JSON-RPC over stdio
|
||||
├── session-cache.ts Session ID cache (re-exports kit helpers + isResumeDisabled)
|
||||
├── session-detail.ts Parse Hermes session JSON, store CAS detail nodes
|
||||
├── schemas.ts Hermes detail CAS schemas
|
||||
└── types.ts HermesSessionJson, HermesSessionMessage
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Uses workflow config from `~/.uncaged/workflow/config.yaml` (via agent-kit). Hermes session files are stored under the workflow storage root (see `session-detail.ts`).
|
||||
|
||||
Set `UWF_HERMES_NO_RESUME=1` to disable session resume (see `isResumeDisabled` in `session-cache.ts`).
|
||||
@@ -4,96 +4,6 @@ import { HermesAcpClient } from "../src/acp-client.js";
|
||||
|
||||
const UUID_RE = /^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$/i;
|
||||
|
||||
describe("handleSessionUpdate — helper extraction", () => {
|
||||
let client: HermesAcpClient;
|
||||
|
||||
beforeEach(() => {
|
||||
client = new HermesAcpClient();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await client.close();
|
||||
});
|
||||
|
||||
it("agent_message_chunk accumulates text in messageChunks", () => {
|
||||
(client as any).handleSessionUpdate({
|
||||
sessionUpdate: "agent_message_chunk",
|
||||
content: { type: "text", text: "hello" },
|
||||
});
|
||||
(client as any).handleSessionUpdate({
|
||||
sessionUpdate: "agent_message_chunk",
|
||||
content: { type: "text", text: " world" },
|
||||
});
|
||||
expect((client as any).messageChunks).toEqual(["hello", " world"]);
|
||||
});
|
||||
|
||||
it("agent_thought_chunk accumulates reasoning in reasoningChunks", () => {
|
||||
(client as any).handleSessionUpdate({
|
||||
sessionUpdate: "agent_thought_chunk",
|
||||
content: { type: "text", text: "thinking" },
|
||||
});
|
||||
expect((client as any).reasoningChunks).toEqual(["thinking"]);
|
||||
});
|
||||
|
||||
it("tool_call registers a pending tool and flushes message chunks", () => {
|
||||
(client as any).messageChunks = ["pre-tool text"];
|
||||
(client as any).handleSessionUpdate({
|
||||
sessionUpdate: "tool_call",
|
||||
title: "Bash",
|
||||
rawInput: { command: "ls" },
|
||||
toolCallId: "tc-1",
|
||||
});
|
||||
expect((client as any).pendingTools.get("tc-1")).toEqual({
|
||||
name: "Bash",
|
||||
args: JSON.stringify({ command: "ls" }),
|
||||
});
|
||||
expect((client as any).messageChunks).toEqual([]);
|
||||
expect((client as any).messages).toHaveLength(1);
|
||||
expect((client as any).messages[0].role).toBe("assistant");
|
||||
});
|
||||
|
||||
it("tool_call_update completed pushes tool_call and tool messages", () => {
|
||||
(client as any).pendingTools.set("tc-2", { name: "Read", args: '{"path":"/foo"}' });
|
||||
(client as any).handleSessionUpdate({
|
||||
sessionUpdate: "tool_call_update",
|
||||
status: "completed",
|
||||
toolCallId: "tc-2",
|
||||
rawOutput: "file contents",
|
||||
});
|
||||
const msgs = (client as any).messages as Array<{
|
||||
role: string;
|
||||
tool_calls: unknown;
|
||||
content: string | null;
|
||||
}>;
|
||||
expect(msgs).toHaveLength(2);
|
||||
expect(msgs[0].role).toBe("assistant");
|
||||
expect(msgs[0].tool_calls).toEqual([
|
||||
{ function: { name: "Read", arguments: '{"path":"/foo"}' } },
|
||||
]);
|
||||
expect(msgs[1].role).toBe("tool");
|
||||
expect(msgs[1].content).toBe("file contents");
|
||||
expect((client as any).pendingTools.has("tc-2")).toBe(false);
|
||||
});
|
||||
|
||||
it("tool_call_update with non-string rawOutput JSON-stringifies it", () => {
|
||||
(client as any).pendingTools.set("tc-3", { name: "Fetch", args: "" });
|
||||
(client as any).handleSessionUpdate({
|
||||
sessionUpdate: "tool_call_update",
|
||||
status: "completed",
|
||||
toolCallId: "tc-3",
|
||||
rawOutput: { html: "<p>page</p>" },
|
||||
});
|
||||
const msgs = (client as any).messages as Array<{ role: string; content: string | null }>;
|
||||
expect(msgs[1].content).toBe(JSON.stringify({ html: "<p>page</p>" }));
|
||||
});
|
||||
|
||||
it("unknown updateType is a no-op", () => {
|
||||
(client as any).handleSessionUpdate({ sessionUpdate: "unknown_type", data: {} });
|
||||
expect((client as any).messages).toHaveLength(0);
|
||||
expect((client as any).messageChunks).toHaveLength(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe("HermesAcpClient", () => {
|
||||
let client: HermesAcpClient;
|
||||
|
||||
|
||||
@@ -23,7 +23,7 @@ function makeCtx(overrides: Partial<AgentContext> = {}): AgentContext {
|
||||
graph: {},
|
||||
},
|
||||
role: "developer",
|
||||
start: { prompt: "Fix the bug", workflow: "abc123" },
|
||||
start: { prompt: "Fix the bug", workflowHash: "abc123", threadId: "t1" },
|
||||
steps: [],
|
||||
store: {} as AgentContext["store"],
|
||||
outputFormatInstruction: "Use YAML frontmatter",
|
||||
@@ -55,7 +55,6 @@ describe("buildHermesPrompt", () => {
|
||||
agent: "uwf-hermes",
|
||||
detail: "detail-1",
|
||||
edgePrompt: "Implement the fix.",
|
||||
content: null,
|
||||
},
|
||||
{
|
||||
role: "reviewer",
|
||||
@@ -63,7 +62,6 @@ describe("buildHermesPrompt", () => {
|
||||
agent: "uwf-hermes",
|
||||
detail: "detail-2",
|
||||
edgePrompt: "Review the code.",
|
||||
content: null,
|
||||
},
|
||||
],
|
||||
});
|
||||
@@ -87,7 +85,6 @@ describe("buildHermesPrompt", () => {
|
||||
agent: "uwf-hermes",
|
||||
detail: "detail-1",
|
||||
edgePrompt: "First attempt.",
|
||||
content: null,
|
||||
},
|
||||
],
|
||||
edgePrompt: "Retry with a fresh approach.",
|
||||
@@ -98,90 +95,4 @@ 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!");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -245,75 +245,72 @@ export class HermesAcpClient {
|
||||
// ---- Session update → structured messages ----
|
||||
|
||||
private handleSessionUpdate(update: Record<string, unknown>): void {
|
||||
switch (update.sessionUpdate as string) {
|
||||
case "agent_message_chunk":
|
||||
this.handleAgentMessageChunk(update);
|
||||
const updateType = update.sessionUpdate as string;
|
||||
|
||||
switch (updateType) {
|
||||
case "agent_message_chunk": {
|
||||
const content = update.content as { type?: string; text?: string } | undefined;
|
||||
if (content?.type === "text" && typeof content.text === "string") {
|
||||
this.messageChunks.push(content.text);
|
||||
}
|
||||
break;
|
||||
case "agent_thought_chunk":
|
||||
this.handleAgentThoughtChunk(update);
|
||||
}
|
||||
|
||||
case "agent_thought_chunk": {
|
||||
const content = update.content as { type?: string; text?: string } | undefined;
|
||||
if (content?.type === "text" && typeof content.text === "string") {
|
||||
this.reasoningChunks.push(content.text);
|
||||
}
|
||||
break;
|
||||
case "tool_call":
|
||||
this.handleToolCall(update);
|
||||
}
|
||||
|
||||
case "tool_call": {
|
||||
const title = (update.title as string) ?? "";
|
||||
const rawInput = update.rawInput;
|
||||
const args = rawInput !== undefined && rawInput !== null ? JSON.stringify(rawInput) : "";
|
||||
const toolCallId = update.toolCallId as string;
|
||||
this.pendingTools.set(toolCallId, { name: title, args });
|
||||
|
||||
// Flush accumulated assistant text before tool call
|
||||
this.flushAssistantMessage();
|
||||
break;
|
||||
case "tool_call_update":
|
||||
this.handleToolCallUpdate(update);
|
||||
}
|
||||
|
||||
case "tool_call_update": {
|
||||
const status = update.status as string | undefined;
|
||||
if (status === "completed" || status === "failed") {
|
||||
const toolCallId = update.toolCallId as string;
|
||||
const pending = this.pendingTools.get(toolCallId);
|
||||
const toolName = pending?.name ?? toolCallId;
|
||||
const rawOutput = update.rawOutput;
|
||||
const outputStr =
|
||||
rawOutput !== undefined && rawOutput !== null
|
||||
? typeof rawOutput === "string"
|
||||
? rawOutput
|
||||
: JSON.stringify(rawOutput)
|
||||
: "";
|
||||
this.messages.push({
|
||||
role: "assistant",
|
||||
content: null,
|
||||
reasoning: null,
|
||||
tool_calls: [{ function: { name: toolName, arguments: pending?.args ?? "" } }],
|
||||
});
|
||||
this.messages.push({
|
||||
role: "tool",
|
||||
content: outputStr,
|
||||
reasoning: null,
|
||||
tool_calls: null,
|
||||
});
|
||||
this.pendingTools.delete(toolCallId);
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
private handleAgentMessageChunk(update: Record<string, unknown>): void {
|
||||
const content = update.content as { type?: string; text?: string } | undefined;
|
||||
if (content?.type === "text" && typeof content.text === "string") {
|
||||
this.messageChunks.push(content.text);
|
||||
}
|
||||
}
|
||||
|
||||
private handleAgentThoughtChunk(update: Record<string, unknown>): void {
|
||||
const content = update.content as { type?: string; text?: string } | undefined;
|
||||
if (content?.type === "text" && typeof content.text === "string") {
|
||||
this.reasoningChunks.push(content.text);
|
||||
}
|
||||
}
|
||||
|
||||
private handleToolCall(update: Record<string, unknown>): void {
|
||||
const title = (update.title as string) ?? "";
|
||||
const rawInput = update.rawInput;
|
||||
const args = rawInput !== undefined && rawInput !== null ? JSON.stringify(rawInput) : "";
|
||||
const toolCallId = update.toolCallId as string;
|
||||
this.pendingTools.set(toolCallId, { name: title, args });
|
||||
this.flushAssistantMessage();
|
||||
}
|
||||
|
||||
private handleToolCallUpdate(update: Record<string, unknown>): void {
|
||||
const status = update.status as string | undefined;
|
||||
if (status !== "completed" && status !== "failed") return;
|
||||
const toolCallId = update.toolCallId as string;
|
||||
const pending = this.pendingTools.get(toolCallId);
|
||||
const toolName = pending?.name ?? toolCallId;
|
||||
const rawOutput = update.rawOutput;
|
||||
const outputStr =
|
||||
rawOutput !== undefined && rawOutput !== null
|
||||
? typeof rawOutput === "string"
|
||||
? rawOutput
|
||||
: JSON.stringify(rawOutput)
|
||||
: "";
|
||||
this.messages.push({
|
||||
role: "assistant",
|
||||
content: null,
|
||||
reasoning: null,
|
||||
tool_calls: [{ function: { name: toolName, arguments: pending?.args ?? "" } }],
|
||||
});
|
||||
this.messages.push({
|
||||
role: "tool",
|
||||
content: outputStr,
|
||||
reasoning: null,
|
||||
tool_calls: null,
|
||||
});
|
||||
this.pendingTools.delete(toolCallId);
|
||||
}
|
||||
|
||||
/** Flush any accumulated text/reasoning into an assistant message. */
|
||||
private flushAssistantMessage(): void {
|
||||
const text = this.messageChunks.join("");
|
||||
|
||||
@@ -14,39 +14,53 @@ import { storeHermesSessionDetail } from "./session-detail.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
/** Assemble system prompt, task, and prior step outputs for Hermes. */
|
||||
export function buildHermesPrompt(ctx: AgentContext): string {
|
||||
const parts: string[] = [];
|
||||
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) : "";
|
||||
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) {
|
||||
// Re-entry: show only steps since last visit, meta only
|
||||
const parts: string[] = [];
|
||||
if (ctx.outputFormatInstruction !== "") {
|
||||
parts.push(ctx.outputFormatInstruction, "");
|
||||
}
|
||||
parts.push(buildContinuationPrompt(ctx.steps, ctx.role, ctx.edgePrompt));
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
// 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");
|
||||
return buildInitialPrompt(ctx);
|
||||
}
|
||||
|
||||
async function storePromptResult(
|
||||
|
||||
@@ -1,22 +1,5 @@
|
||||
// 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);
|
||||
}
|
||||
// Re-export session cache from the shared agent-kit package.
|
||||
export { getCachedSessionId, setCachedSessionId } from "@uncaged/workflow-agent-kit";
|
||||
|
||||
export function isResumeDisabled(): boolean {
|
||||
// Hermes ACP session/resume is broken: _restore fails for custom providers
|
||||
|
||||
@@ -1,183 +0,0 @@
|
||||
# @uncaged/workflow-agent-kit
|
||||
|
||||
Agent framework — `createAgent` factory, context builder, frontmatter fast-path, and LLM extract pipeline.
|
||||
|
||||
## Overview
|
||||
|
||||
Layer 2 agent framework. Provides the standard entrypoint for all agent CLIs: parse `<thread-id> <role>` from argv, load thread/workflow context from CAS, invoke the agent's `run`/`continue` functions, validate output via frontmatter fast-path or LLM extract, and write a `StepNodePayload` to CAS.
|
||||
|
||||
Also exports prompt builders, config/storage helpers, and session ID caching for multi-turn agents.
|
||||
|
||||
**Dependencies:** `@uncaged/json-cas`, `@uncaged/json-cas-fs`, `@uncaged/workflow-protocol`, `@uncaged/workflow-util`, `dotenv`, `yaml`
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
bun add @uncaged/workflow-agent-kit
|
||||
```
|
||||
|
||||
## API
|
||||
|
||||
All exports come from `src/index.ts`.
|
||||
|
||||
### Agent factory
|
||||
|
||||
```typescript
|
||||
function createAgent(options: AgentOptions): () => Promise<void>
|
||||
|
||||
type AgentOptions = {
|
||||
name: string;
|
||||
run: AgentRunFn;
|
||||
continue: AgentContinueFn;
|
||||
};
|
||||
|
||||
type AgentRunFn = (ctx: AgentContext) => Promise<AgentRunResult>;
|
||||
type AgentContinueFn = (
|
||||
sessionId: string,
|
||||
message: string,
|
||||
store: AgentContext["store"],
|
||||
) => Promise<AgentRunResult>;
|
||||
|
||||
type AgentRunResult = {
|
||||
output: string;
|
||||
detailHash: string;
|
||||
sessionId: string;
|
||||
};
|
||||
```
|
||||
|
||||
Agent CLIs call `createAgent(...)` and invoke the returned function as `main()`.
|
||||
|
||||
### Context
|
||||
|
||||
```typescript
|
||||
function buildContext(threadId: ThreadId, role: string): Promise<AgentContext>
|
||||
function buildContextWithMeta(
|
||||
threadId: ThreadId,
|
||||
role: string,
|
||||
): Promise<AgentContext & { meta: BuildContextMeta }>
|
||||
|
||||
type AgentContext = ModeratorContext & {
|
||||
threadId: ThreadId;
|
||||
role: string;
|
||||
store: Store;
|
||||
workflow: WorkflowPayload;
|
||||
outputFormatInstruction: string;
|
||||
edgePrompt: string;
|
||||
isFirstVisit: boolean;
|
||||
};
|
||||
|
||||
type BuildContextMeta = {
|
||||
storageRoot: string;
|
||||
store: Store;
|
||||
schemas: AgentStore["schemas"];
|
||||
headHash: CasRef;
|
||||
chain: ChainState;
|
||||
};
|
||||
```
|
||||
|
||||
Requires `UWF_EDGE_PROMPT` in the environment (set by `uwf thread step`).
|
||||
|
||||
### Prompt builders
|
||||
|
||||
```typescript
|
||||
function buildRolePrompt(role: RoleDefinition): string
|
||||
function buildOutputFormatInstruction(schema: JSONSchema): string
|
||||
function buildContinuationPrompt(
|
||||
steps: StepContext[],
|
||||
role: string,
|
||||
edgePrompt: string,
|
||||
options?: { includeContent?: boolean; quota?: number },
|
||||
): string
|
||||
```
|
||||
|
||||
### Extract pipeline
|
||||
|
||||
```typescript
|
||||
function resolveExtractModelAlias(config: WorkflowConfig): ModelAlias
|
||||
function resolveModel(config: WorkflowConfig, alias: ModelAlias): ResolvedLlmProvider
|
||||
function extract(
|
||||
rawOutput: string,
|
||||
outputSchema: CasRef,
|
||||
config: WorkflowConfig,
|
||||
): Promise<ExtractResult>
|
||||
|
||||
type ResolvedLlmProvider = { baseUrl: string; apiKey: string; model: string };
|
||||
type ExtractResult = { value: unknown; hash: CasRef };
|
||||
```
|
||||
|
||||
### Frontmatter fast-path
|
||||
|
||||
```typescript
|
||||
function tryFrontmatterFastPath(
|
||||
rawOutput: string,
|
||||
outputSchema: CasRef,
|
||||
store: Store,
|
||||
): Promise<FrontmatterFastPathResult | null>
|
||||
|
||||
type FrontmatterFastPathResult = { body: string; outputHash: CasRef };
|
||||
```
|
||||
|
||||
### Session cache
|
||||
|
||||
```typescript
|
||||
function getCachedSessionId(threadId: ThreadId, role: string): Promise<string | null>
|
||||
function setCachedSessionId(
|
||||
threadId: ThreadId,
|
||||
role: string,
|
||||
sessionId: string,
|
||||
): Promise<void>
|
||||
```
|
||||
|
||||
### Config and storage
|
||||
|
||||
```typescript
|
||||
function getConfigPath(storageRoot: string): string
|
||||
function getEnvPath(storageRoot: string): string
|
||||
function resolveStorageRoot(): string
|
||||
function loadWorkflowConfig(storageRoot: string): Promise<WorkflowConfig>
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
```typescript
|
||||
import { createAgent, buildRolePrompt } from "@uncaged/workflow-agent-kit";
|
||||
import type { AgentContext, AgentRunResult } from "@uncaged/workflow-agent-kit";
|
||||
|
||||
async function run(ctx: AgentContext): Promise<AgentRunResult> {
|
||||
const prompt = buildRolePrompt(ctx.workflow.roles[ctx.role]!);
|
||||
// ... spawn external process, capture output ...
|
||||
return { output: markdown, detailHash: "...", sessionId: "..." };
|
||||
}
|
||||
|
||||
async function continueSession(
|
||||
sessionId: string,
|
||||
message: string,
|
||||
): Promise<AgentRunResult> {
|
||||
// ... continue multi-turn session ...
|
||||
return { output: markdown, detailHash: "...", sessionId };
|
||||
}
|
||||
|
||||
export const main = createAgent({ name: "my-agent", run, continue: continueSession });
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts
|
||||
├── run.ts createAgent entrypoint
|
||||
├── context.ts Thread chain walk, AgentContext builder
|
||||
├── extract.ts LLM structured extract fallback
|
||||
├── frontmatter.ts Frontmatter fast-path validation
|
||||
├── build-role-prompt.ts Role definition → prompt text
|
||||
├── build-output-format-instruction.ts
|
||||
├── build-continuation-prompt.ts
|
||||
├── session-cache.ts Per-thread/session ID persistence
|
||||
├── storage.ts CAS store, config, threads index
|
||||
├── schemas.ts Agent CAS schema registration
|
||||
└── types.ts AgentContext, AgentOptions, etc.
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Reads `config.yaml` and `.env` from the workflow storage root (`~/.uncaged/workflow` by default). See `@uncaged/workflow-protocol` for `WorkflowConfig` shape. Set via `uwf setup`.
|
||||
@@ -8,7 +8,6 @@ const reviewerStep: StepContext = {
|
||||
detail: "2MXBG6PN4A8JR",
|
||||
agent: "uwf-hermes",
|
||||
edgePrompt: "Review the developer's work.",
|
||||
content: null,
|
||||
};
|
||||
|
||||
const developerStep: StepContext = {
|
||||
@@ -17,7 +16,6 @@ const developerStep: StepContext = {
|
||||
detail: "1VPBG9SM5E7WK",
|
||||
agent: "uwf-hermes",
|
||||
edgePrompt: "Implement the fix.",
|
||||
content: null,
|
||||
};
|
||||
|
||||
describe("buildContinuationPrompt", () => {
|
||||
@@ -31,7 +29,6 @@ describe("buildContinuationPrompt", () => {
|
||||
detail: "7BQST3VW9F2MA",
|
||||
agent: "uwf-hermes",
|
||||
edgePrompt: "Revise the plan.",
|
||||
content: null,
|
||||
},
|
||||
];
|
||||
|
||||
@@ -73,162 +70,4 @@ 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");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,14 +0,0 @@
|
||||
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);
|
||||
});
|
||||
});
|
||||
@@ -1,247 +0,0 @@
|
||||
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
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -1,20 +1,11 @@
|
||||
import type { StepContext } from "@uncaged/workflow-protocol";
|
||||
|
||||
function formatStep(step: StepContext, stepNumber: number, includeContent: boolean): string {
|
||||
const lines = [
|
||||
function formatStep(step: StepContext, stepNumber: number): string {
|
||||
return [
|
||||
`### Step ${stepNumber}: ${step.role}`,
|
||||
`Output: ${JSON.stringify(step.output)}`,
|
||||
`Agent: ${step.agent}`,
|
||||
];
|
||||
|
||||
if (includeContent && step.content !== null) {
|
||||
lines.push("");
|
||||
lines.push("#### Step Content");
|
||||
lines.push("");
|
||||
lines.push(step.content);
|
||||
}
|
||||
|
||||
return lines.join("\n");
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
function findLastRoleIndex(steps: StepContext[], role: string): number {
|
||||
@@ -27,45 +18,6 @@ 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.
|
||||
*
|
||||
@@ -76,11 +28,7 @@ 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;
|
||||
|
||||
@@ -89,25 +37,13 @@ export function buildContinuationPrompt(
|
||||
if (sinceSteps.length > 0) {
|
||||
parts.push("## What Happened Since Your Last Turn");
|
||||
const baseStepNumber = lastIndex >= 0 ? lastIndex + 2 : 1;
|
||||
|
||||
// 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];
|
||||
for (let i = 0; i < sinceSteps.length; i++) {
|
||||
const step = sinceSteps[i];
|
||||
if (step === undefined) {
|
||||
continue;
|
||||
}
|
||||
parts.push("");
|
||||
parts.push(formatStep(step, baseStepNumber + i, includeContent));
|
||||
parts.push(formatStep(step, baseStepNumber + i));
|
||||
}
|
||||
parts.push("");
|
||||
}
|
||||
|
||||
@@ -21,6 +21,14 @@ function fail(message: string): never {
|
||||
throw new Error(message);
|
||||
}
|
||||
|
||||
function readEdgePrompt(): string {
|
||||
const value = process.env.UWF_EDGE_PROMPT;
|
||||
if (value === undefined || value === "") {
|
||||
fail("UWF_EDGE_PROMPT environment variable is required");
|
||||
}
|
||||
return value;
|
||||
}
|
||||
|
||||
function walkChain(store: Store, schemas: AgentStore["schemas"], headHash: CasRef): ChainState {
|
||||
const headNode = store.get(headHash);
|
||||
if (headNode === null) {
|
||||
@@ -82,38 +90,6 @@ 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[],
|
||||
@@ -121,14 +97,12 @@ 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;
|
||||
@@ -149,11 +123,7 @@ async function loadWorkflow(store: Store, schemas: AgentStore["schemas"], workfl
|
||||
* Build agent execution context from thread head in threads.yaml.
|
||||
* Walks the CAS chain from head to StartNode and expands step outputs.
|
||||
*/
|
||||
export async function buildContext(
|
||||
threadId: ThreadId,
|
||||
role: string,
|
||||
edgePrompt: string,
|
||||
): Promise<AgentContext> {
|
||||
export async function buildContext(threadId: ThreadId, role: string): Promise<AgentContext> {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
const agentStore = await createAgentStore(storageRoot);
|
||||
const { store, schemas } = agentStore;
|
||||
@@ -172,6 +142,7 @@ export async function buildContext(
|
||||
}
|
||||
|
||||
const steps = await buildHistory(store, chain.stepsNewestFirst);
|
||||
const edgePrompt = readEdgePrompt();
|
||||
const isFirstVisit = !steps.some((s) => s.role === role);
|
||||
|
||||
return {
|
||||
@@ -201,7 +172,6 @@ export type BuildContextMeta = {
|
||||
export async function buildContextWithMeta(
|
||||
threadId: ThreadId,
|
||||
role: string,
|
||||
edgePrompt: string,
|
||||
): Promise<AgentContext & { meta: BuildContextMeta }> {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
const agentStore = await createAgentStore(storageRoot);
|
||||
@@ -221,6 +191,7 @@ export async function buildContextWithMeta(
|
||||
}
|
||||
|
||||
const steps = await buildHistory(store, chain.stepsNewestFirst);
|
||||
const edgePrompt = readEdgePrompt();
|
||||
const isFirstVisit = !steps.some((s) => s.role === role);
|
||||
|
||||
return {
|
||||
|
||||
@@ -12,7 +12,7 @@ export {
|
||||
export type { FrontmatterFastPathResult } from "./frontmatter.js";
|
||||
export { tryFrontmatterFastPath } from "./frontmatter.js";
|
||||
export { createAgent } from "./run.js";
|
||||
export { getCachedSessionId, getCachePath, setCachedSessionId } from "./session-cache.js";
|
||||
export { getCachedSessionId, setCachedSessionId } from "./session-cache.js";
|
||||
export { getConfigPath, getEnvPath, loadWorkflowConfig, resolveStorageRoot } from "./storage.js";
|
||||
export type {
|
||||
AgentContext,
|
||||
|
||||
@@ -22,24 +22,16 @@ function agentLabel(name: string): string {
|
||||
return `uwf-${name}`;
|
||||
}
|
||||
|
||||
const USAGE = "usage: <agent-cli> --thread <id> --role <role> --prompt <text>";
|
||||
|
||||
function getNamedArg(argv: string[], name: string): string {
|
||||
const idx = argv.indexOf(name);
|
||||
if (idx === -1 || idx + 1 >= argv.length) {
|
||||
return "";
|
||||
function parseArgv(argv: string[]): { threadId: ThreadId; role: string } {
|
||||
const threadId = argv[2];
|
||||
const role = argv[3];
|
||||
if (threadId === undefined || threadId === "") {
|
||||
fail("usage: <agent-cli> <thread-id> <role>");
|
||||
}
|
||||
return argv[idx + 1];
|
||||
}
|
||||
|
||||
function parseArgv(argv: string[]): { threadId: ThreadId; role: string; prompt: string } {
|
||||
const threadId = getNamedArg(argv, "--thread");
|
||||
const role = getNamedArg(argv, "--role");
|
||||
const prompt = getNamedArg(argv, "--prompt");
|
||||
if (threadId === "") fail(USAGE);
|
||||
if (role === "") fail(USAGE);
|
||||
if (prompt === "") fail(USAGE);
|
||||
return { threadId: threadId as ThreadId, role, prompt };
|
||||
if (role === undefined || role === "") {
|
||||
fail("usage: <agent-cli> <thread-id> <role>");
|
||||
}
|
||||
return { threadId: threadId as ThreadId, role };
|
||||
}
|
||||
|
||||
function runWithMessage<T>(label: string, fn: () => Promise<T>): Promise<T> {
|
||||
@@ -111,11 +103,11 @@ async function persistStep(options: {
|
||||
|
||||
export function createAgent(options: AgentOptions): () => Promise<void> {
|
||||
return async function main(): Promise<void> {
|
||||
const { threadId, role, prompt } = parseArgv(process.argv);
|
||||
const { threadId, role } = parseArgv(process.argv);
|
||||
const storageRoot = resolveStorageRoot();
|
||||
loadDotenv({ path: getEnvPath(storageRoot) });
|
||||
|
||||
const ctx = await runWithMessage("context", () => buildContextWithMeta(threadId, role, prompt));
|
||||
const ctx = await runWithMessage("context", () => buildContextWithMeta(threadId, role));
|
||||
|
||||
const roleDef = ctx.workflow.roles[role];
|
||||
if (roleDef === undefined) {
|
||||
|
||||
@@ -8,8 +8,8 @@ import { resolveStorageRoot } from "./storage.js";
|
||||
|
||||
type SessionCache = Record<string, string>;
|
||||
|
||||
export function getCachePath(agentName: string): string {
|
||||
return join(resolveStorageRoot(), "cache", `${agentName}-sessions.json`);
|
||||
function getCachePath(): string {
|
||||
return join(resolveStorageRoot(), "cache", "agent-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(agentName: string): Promise<SessionCache> {
|
||||
const path = getCachePath(agentName);
|
||||
async function readCache(): Promise<SessionCache> {
|
||||
const path = getCachePath();
|
||||
try {
|
||||
const text = await readFile(path, "utf8");
|
||||
const raw = JSON.parse(text) as unknown;
|
||||
@@ -40,45 +40,36 @@ async function readCache(agentName: string): Promise<SessionCache> {
|
||||
if (err.code === "ENOENT") {
|
||||
return {};
|
||||
}
|
||||
// Treat JSON parse errors as empty cache
|
||||
if (err.name === "SyntaxError") {
|
||||
return {};
|
||||
}
|
||||
throw e;
|
||||
}
|
||||
}
|
||||
|
||||
async function writeCache(agentName: string, cache: SessionCache): Promise<void> {
|
||||
const path = getCachePath(agentName);
|
||||
async function writeCache(cache: SessionCache): Promise<void> {
|
||||
const path = getCachePath();
|
||||
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, `.${agentName}-sessions.${randomBytes(4).toString("hex")}.tmp`);
|
||||
const tmpPath = join(dir, `.agent-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(
|
||||
agentName: string,
|
||||
threadId: ThreadId,
|
||||
role: string,
|
||||
): Promise<string | null> {
|
||||
const cache = await readCache(agentName);
|
||||
export async function getCachedSessionId(threadId: ThreadId, role: string): Promise<string | null> {
|
||||
const cache = await readCache();
|
||||
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(agentName);
|
||||
const cache = await readCache();
|
||||
cache[cacheKey(threadId, role)] = sessionId;
|
||||
await writeCache(agentName, cache);
|
||||
await writeCache(cache);
|
||||
}
|
||||
|
||||
@@ -13,7 +13,7 @@ export type AgentContext = ModeratorContext & {
|
||||
*/
|
||||
outputFormatInstruction: string;
|
||||
/**
|
||||
* Edge prompt from the graph transition that led to this role (--prompt CLI arg).
|
||||
* Edge prompt from the graph transition that led to this role (UWF_EDGE_PROMPT).
|
||||
* Always the real moderator instruction for this step.
|
||||
*/
|
||||
edgePrompt: string;
|
||||
|
||||
@@ -1,84 +0,0 @@
|
||||
# @uncaged/workflow-dashboard
|
||||
|
||||
Web graph editor for visualizing and editing workflow YAML definitions.
|
||||
|
||||
## Overview
|
||||
|
||||
A private alpha web app (not part of the runtime engine stack). Provides a React + `@xyflow/react` canvas for editing workflow roles, conditions, and graph transitions. Uses `@uncaged/workflow-protocol` types for validation and YAML round-tripping.
|
||||
|
||||
Planned integration: local `uwf connect` over WebSocket to sync YAML between CLI and the browser editor. The REST API and Elysia backend are currently stubs for development.
|
||||
|
||||
**Dependencies:** `@uncaged/workflow-protocol`, `@xyflow/react`, React 19, react-router v7, Vite 8, Tailwind CSS v4, Elysia
|
||||
|
||||
## Installation
|
||||
|
||||
Monorepo-only ( `"private": true` ). Not published to npm.
|
||||
|
||||
```bash
|
||||
cd packages/workflow-dashboard
|
||||
bun install --no-cache
|
||||
```
|
||||
|
||||
## CLI Usage
|
||||
|
||||
Start the Vite dev server (port 3000):
|
||||
|
||||
```bash
|
||||
cd packages/workflow-dashboard
|
||||
bun run dev
|
||||
```
|
||||
|
||||
Build for production:
|
||||
|
||||
```bash
|
||||
bun run build
|
||||
```
|
||||
|
||||
Open `http://localhost:3000` in a browser.
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
workflow-dashboard/
|
||||
├── server.ts Vite dev server entry (port 3000)
|
||||
├── vite.config.ts Vite + React + Tailwind + Elysia plugin
|
||||
├── vite-dev.ts Custom Vite plugin
|
||||
├── index.html
|
||||
├── components.json shadcn configuration
|
||||
├── server/
|
||||
│ ├── api.ts Elysia REST API (health + workflow CRUD stub)
|
||||
│ └── workflow.ts Workflow file read/write + format conversion
|
||||
└── src/
|
||||
├── main.tsx React DOM entry
|
||||
├── app.tsx Root layout
|
||||
├── router.tsx Hash-mode routes
|
||||
├── index.css
|
||||
├── lib/utils.ts Tailwind cn() helper
|
||||
├── components/ui/ shadcn components (button, card, dialog, input, …)
|
||||
├── pages/
|
||||
│ ├── home.tsx Workflow list
|
||||
│ ├── detail.tsx Workflow detail view
|
||||
│ └── editor.tsx Full editor page
|
||||
└── editor/ Core graph editor
|
||||
├── flow.tsx FlowEditor component
|
||||
├── context.tsx State (useSyncExternalStore + Immer)
|
||||
├── injection.ts DI container
|
||||
├── type.ts Internal editor types
|
||||
├── model/ Node/edge state model
|
||||
├── nodes/ Start, role, end node components
|
||||
├── edges/ Conditional edge rendering
|
||||
├── panel/ Toolbar, add/edit panels
|
||||
├── trans/ YAML ↔ graph conversion (trans-in, trans-out, validate)
|
||||
├── layout/ Auto-layout
|
||||
└── utils/ Event helpers, click-outside hook
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
| Setting | Default | Notes |
|
||||
|---------|---------|-------|
|
||||
| Dev server port | `3000` | Set in `server.ts` |
|
||||
| Workflow storage (dev) | `tmp/workflow/` | YAML files during development |
|
||||
| Path alias | `@/` → `src/` | Configured in `vite.config.ts` |
|
||||
|
||||
No library API — this package is an application, not importable as a module.
|
||||
@@ -31,10 +31,8 @@
|
||||
"@types/react": "^19.2.14",
|
||||
"@types/react-dom": "^19.2.3",
|
||||
"@vitejs/plugin-react": "^6.0.2",
|
||||
"@vitest/ui": "^4.1.7",
|
||||
"tailwindcss": "^4.2.4",
|
||||
"typescript": "^5.8.3",
|
||||
"vite": "^8.0.13",
|
||||
"vitest": "^4.1.7"
|
||||
"vite": "^8.0.13"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,83 +0,0 @@
|
||||
import type { Edge, Node } from "@xyflow/react";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { LayoutLR } from "../index.js";
|
||||
|
||||
function makeNode(id: string): Node {
|
||||
return { id, type: "role", data: {}, position: { x: 0, y: 0 } } as Node;
|
||||
}
|
||||
|
||||
function makeEdge(source: string, target: string): Edge {
|
||||
return { id: `${source}-${target}`, source, target } as Edge;
|
||||
}
|
||||
|
||||
describe("LayoutLR / assignLayers", () => {
|
||||
it("1.1 Empty graph: start gets layer 0, end gets higher layer", () => {
|
||||
const nodes = [makeNode("start"), makeNode("end")];
|
||||
const result = LayoutLR(nodes, []);
|
||||
const start = result.find((n) => n.id === "start");
|
||||
const end = result.find((n) => n.id === "end");
|
||||
// start has no position change necessarily, but positions should be assigned
|
||||
expect(start).toBeDefined();
|
||||
expect(end).toBeDefined();
|
||||
// end should be to the right of start
|
||||
expect((end?.position.x ?? 0) > (start?.position.x ?? 0)).toBe(true);
|
||||
});
|
||||
|
||||
it("1.2 Linear chain: start → A → B → end — layers assigned in order", () => {
|
||||
const nodes = [makeNode("start"), makeNode("A"), makeNode("B"), makeNode("end")];
|
||||
const edges = [makeEdge("start", "A"), makeEdge("A", "B"), makeEdge("B", "end")];
|
||||
const result = LayoutLR(nodes, edges);
|
||||
const xOf = (id: string) => result.find((n) => n.id === id)?.position.x ?? 0;
|
||||
expect(xOf("start") < xOf("A")).toBe(true);
|
||||
expect(xOf("A") < xOf("B")).toBe(true);
|
||||
expect(xOf("B") < xOf("end")).toBe(true);
|
||||
});
|
||||
|
||||
it("1.3 Diamond: A and B share same layer", () => {
|
||||
const nodes = [makeNode("start"), makeNode("A"), makeNode("B"), makeNode("C"), makeNode("end")];
|
||||
const edges = [
|
||||
makeEdge("start", "A"),
|
||||
makeEdge("start", "B"),
|
||||
makeEdge("A", "C"),
|
||||
makeEdge("B", "C"),
|
||||
makeEdge("C", "end"),
|
||||
];
|
||||
const result = LayoutLR(nodes, edges);
|
||||
const xOf = (id: string) => result.find((n) => n.id === id)?.position.x ?? 0;
|
||||
expect(xOf("A")).toBe(xOf("B")); // same layer
|
||||
expect(xOf("A") < xOf("C")).toBe(true);
|
||||
expect(xOf("C") < xOf("end")).toBe(true);
|
||||
});
|
||||
|
||||
it("1.4 Isolated node placed in middle layer (not layer 0, not end layer)", () => {
|
||||
const nodes = [makeNode("start"), makeNode("A"), makeNode("isolated"), makeNode("end")];
|
||||
const edges = [makeEdge("start", "A"), makeEdge("A", "end")];
|
||||
const result = LayoutLR(nodes, edges);
|
||||
const xOf = (id: string) => result.find((n) => n.id === id)?.position.x ?? 0;
|
||||
const xIsolated = xOf("isolated");
|
||||
expect(xIsolated > xOf("start")).toBe(true);
|
||||
expect(xIsolated < xOf("end")).toBe(true);
|
||||
});
|
||||
|
||||
it("1.5 end node is always last (highest x)", () => {
|
||||
const nodes = [makeNode("start"), makeNode("A"), makeNode("B"), makeNode("end")];
|
||||
const edges = [makeEdge("start", "A"), makeEdge("A", "B"), makeEdge("B", "end")];
|
||||
const result = LayoutLR(nodes, edges);
|
||||
const endX = result.find((n) => n.id === "end")?.position.x ?? 0;
|
||||
for (const node of result) {
|
||||
if (node.id !== "end") {
|
||||
expect(node.position.x < endX).toBe(true);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
it("1.6 start node is always first (x = 0 or smallest x)", () => {
|
||||
const nodes = [makeNode("start"), makeNode("A"), makeNode("end")];
|
||||
const edges = [makeEdge("start", "A"), makeEdge("A", "end")];
|
||||
const result = LayoutLR(nodes, edges);
|
||||
const startX = result.find((n) => n.id === "start")?.position.x ?? 0;
|
||||
for (const node of result) {
|
||||
expect(node.position.x >= startX).toBe(true);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -43,65 +43,6 @@ function buildGraph(nodes: Node[], edges: Edge[]) {
|
||||
return { outgoing, incoming, inDegree };
|
||||
}
|
||||
|
||||
function processTarget(
|
||||
target: string,
|
||||
newLayer: number,
|
||||
layers: Map<string, number>,
|
||||
inDegree: Map<string, number>,
|
||||
queue: string[],
|
||||
): void {
|
||||
const existingLayer = layers.get(target);
|
||||
if (existingLayer === undefined) {
|
||||
layers.set(target, newLayer);
|
||||
inDegree.set(target, (inDegree.get(target) ?? 1) - 1);
|
||||
if (inDegree.get(target) === 0) queue.push(target);
|
||||
} else {
|
||||
layers.set(target, Math.max(existingLayer, newLayer));
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* BFS 分层（排除 end 节点，稍后单独处理）
|
||||
*/
|
||||
function bfsLayers(
|
||||
outgoing: Map<string, string[]>,
|
||||
inDegree: Map<string, number>,
|
||||
layers: Map<string, number>,
|
||||
): void {
|
||||
const queue: string[] = ["start"];
|
||||
while (queue.length > 0) {
|
||||
const current = queue.shift() ?? "";
|
||||
const currentLayer = layers.get(current) ?? 0;
|
||||
for (const target of outgoing.get(current) ?? []) {
|
||||
if (target === "end") continue;
|
||||
processTarget(target, currentLayer + 1, layers, inDegree, queue);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 处理孤立节点（没有被分配层级的非 start/end 节点），放在中间层
|
||||
*/
|
||||
function placeIsolatedNodes(nodes: Node[], layers: Map<string, number>, maxLayer: number): void {
|
||||
const middleLayer = Math.max(1, Math.floor((maxLayer + 1) / 2));
|
||||
for (const node of nodes) {
|
||||
if (node.id !== "start" && node.id !== "end" && !layers.has(node.id)) {
|
||||
layers.set(node.id, middleLayer);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 计算最大层级（排除 end 节点）
|
||||
*/
|
||||
function maxLayerExcludingEnd(layers: Map<string, number>): number {
|
||||
let max = 0;
|
||||
for (const [id, layer] of layers) {
|
||||
if (id !== "end") max = Math.max(max, layer);
|
||||
}
|
||||
return max;
|
||||
}
|
||||
|
||||
/**
|
||||
* 使用拓扑排序将节点分层
|
||||
* - 'start' 节点固定在第 0 层
|
||||
@@ -111,15 +52,62 @@ function maxLayerExcludingEnd(layers: Map<string, number>): number {
|
||||
function assignLayers(nodes: Node[], edges: Edge[]): Map<string, number> {
|
||||
const { outgoing, inDegree } = buildGraph(nodes, edges);
|
||||
const layers = new Map<string, number>();
|
||||
const queue: string[] = [];
|
||||
|
||||
// 1. start 节点固定在第 0 层
|
||||
layers.set("start", 0);
|
||||
bfsLayers(outgoing, inDegree, layers);
|
||||
queue.push("start");
|
||||
|
||||
const afterBfsMax = maxLayerExcludingEnd(layers);
|
||||
placeIsolatedNodes(nodes, layers, afterBfsMax);
|
||||
// 2. BFS 分层（排除 end 节点，稍后单独处理）
|
||||
while (queue.length > 0) {
|
||||
const current = queue.shift() ?? "";
|
||||
const currentLayer = layers.get(current) ?? 0;
|
||||
|
||||
const finalMax = maxLayerExcludingEnd(layers);
|
||||
layers.set("end", finalMax + 1);
|
||||
for (const target of outgoing.get(current) ?? []) {
|
||||
// 跳过 end 节点，稍后处理
|
||||
if (target === "end") continue;
|
||||
|
||||
const newLayer = currentLayer + 1;
|
||||
const existingLayer = layers.get(target);
|
||||
|
||||
if (existingLayer === undefined) {
|
||||
layers.set(target, newLayer);
|
||||
inDegree.set(target, (inDegree.get(target) ?? 1) - 1);
|
||||
if (inDegree.get(target) === 0) {
|
||||
queue.push(target);
|
||||
}
|
||||
} else {
|
||||
// 如果已有层级，取更大的值（确保所有前驱都在前面）
|
||||
layers.set(target, Math.max(existingLayer, newLayer));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 找到当前最大层级
|
||||
let maxLayer = 0;
|
||||
for (const layer of layers.values()) {
|
||||
maxLayer = Math.max(maxLayer, layer);
|
||||
}
|
||||
|
||||
// 4. 处理孤立节点（没有被分配层级的非 start/end 节点）
|
||||
// 把它们放在中间层
|
||||
const middleLayer = Math.max(1, Math.floor((maxLayer + 1) / 2));
|
||||
for (const node of nodes) {
|
||||
if (node.id !== "start" && node.id !== "end" && !layers.has(node.id)) {
|
||||
layers.set(node.id, middleLayer);
|
||||
}
|
||||
}
|
||||
|
||||
// 5. 重新计算最大层级（可能因为孤立节点而变化）
|
||||
maxLayer = 0;
|
||||
for (const [id, layer] of layers) {
|
||||
if (id !== "end") {
|
||||
maxLayer = Math.max(maxLayer, layer);
|
||||
}
|
||||
}
|
||||
|
||||
// 6. end 节点固定在最后一层
|
||||
layers.set("end", maxLayer + 1);
|
||||
|
||||
return layers;
|
||||
}
|
||||
|
||||
@@ -30,24 +30,23 @@ export const handlers = define.memoize((use, model) => {
|
||||
});
|
||||
};
|
||||
|
||||
function isProtectedNode(node: AnyWorkNode): boolean {
|
||||
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 }) => {
|
||||
if (nodes.some(isProtectedNode)) return false;
|
||||
for (const node of nodes) {
|
||||
if (node.type === "start" || node.type === "end") {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
if (edges.length > 0) {
|
||||
const allEdges = use(edgesModel)[0];
|
||||
if (edges.some((e) => isFirstConditionalSibling(e, allEdges))) return false;
|
||||
for (const edge of edges) {
|
||||
if (edge.type !== "conditional") continue;
|
||||
const siblings = allEdges.filter(
|
||||
(e) => e.source === edge.source && e.type === "conditional",
|
||||
);
|
||||
if (siblings.length >= 2 && siblings[0].id === edge.id) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
model.startTransaction();
|
||||
return true;
|
||||
@@ -97,28 +96,25 @@ export const handlers = define.memoize((use, model) => {
|
||||
use(editNodeViewModel)[1].cancel();
|
||||
}
|
||||
|
||||
function handleEscape() {
|
||||
const [addView, addViewActions] = use(addNodeViewModel);
|
||||
const [editView, editViewActions] = use(editNodeViewModel);
|
||||
if (addView) addViewActions.cancel();
|
||||
if (editView) editViewActions.cancel();
|
||||
}
|
||||
|
||||
function handleUndoRedo(event: React.KeyboardEvent<HTMLDivElement>) {
|
||||
if (event.code === "KeyZ" && (event.ctrlKey || event.metaKey)) {
|
||||
if (event.shiftKey) model.redo();
|
||||
else model.undo();
|
||||
} else if (event.code === "KeyY" && (event.ctrlKey || event.metaKey)) {
|
||||
model.redo();
|
||||
}
|
||||
}
|
||||
|
||||
function handleKeyDown(event: React.KeyboardEvent<HTMLDivElement>) {
|
||||
if (event.code === "Escape") {
|
||||
handleEscape();
|
||||
const [addView, addViewActions] = use(addNodeViewModel);
|
||||
const [editView, editViewActions] = use(editNodeViewModel);
|
||||
if (addView) addViewActions.cancel();
|
||||
if (editView) editViewActions.cancel();
|
||||
return;
|
||||
}
|
||||
handleUndoRedo(event);
|
||||
|
||||
if (event.code === "KeyZ") {
|
||||
if (event.ctrlKey || event.metaKey) {
|
||||
if (event.shiftKey) model.redo();
|
||||
else model.undo();
|
||||
}
|
||||
} else if (event.code === "KeyY") {
|
||||
if (event.ctrlKey || event.metaKey) {
|
||||
model.redo();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function loadSteps(steps: WorkFlowSteps) {
|
||||
|
||||
@@ -10,15 +10,16 @@ import {
|
||||
import { Input } from "../../components/ui/input.tsx";
|
||||
import { Label } from "../../components/ui/label.tsx";
|
||||
import { Textarea } from "../../components/ui/textarea.tsx";
|
||||
import { addNodeViewModel } from "../model/index.ts";
|
||||
import { type AddNodeState, addNodeViewModel } from "../model/index.ts";
|
||||
import type { RoleNodeData } from "../type.ts";
|
||||
|
||||
type FormProps = {
|
||||
state: AddNodeState;
|
||||
onSubmit: (params: { data: RoleNodeData }) => void;
|
||||
onCancel: () => void;
|
||||
};
|
||||
|
||||
function Form({ onSubmit, onCancel }: FormProps): ReactNode {
|
||||
function Form({ state, onSubmit, onCancel }: FormProps): ReactNode {
|
||||
const [name, setName] = useState("新角色");
|
||||
const [description, setDescription] = useState("");
|
||||
const [identity, setIdentity] = useState("");
|
||||
@@ -136,7 +137,7 @@ export function AddNodeDialog(): ReactNode {
|
||||
}}
|
||||
>
|
||||
<DialogContent showCloseButton={false} className="sm:max-w-md">
|
||||
{state && <Form onSubmit={commit} onCancel={cancel} />}
|
||||
{state && <Form state={state} onSubmit={commit} onCancel={cancel} />}
|
||||
</DialogContent>
|
||||
</Dialog>
|
||||
);
|
||||
|
||||
@@ -1,109 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { transIn } from "../trans-in.js";
|
||||
import type { WorkFlowStep } from "../type.js";
|
||||
|
||||
function makeStep(name: string, transitions: WorkFlowStep["transitions"]): WorkFlowStep {
|
||||
return {
|
||||
role: {
|
||||
name,
|
||||
description: "",
|
||||
identity: "",
|
||||
prepare: "",
|
||||
execute: "",
|
||||
report: "",
|
||||
},
|
||||
transitions,
|
||||
};
|
||||
}
|
||||
|
||||
describe("transIn", () => {
|
||||
it("4.1 Empty steps → start + end nodes, no edges", () => {
|
||||
const { nodes, edges } = transIn([]);
|
||||
expect(nodes).toHaveLength(2);
|
||||
expect(nodes.find((n) => n.id === "start")).toBeDefined();
|
||||
expect(nodes.find((n) => n.id === "end")).toBeDefined();
|
||||
expect(edges).toHaveLength(0);
|
||||
});
|
||||
|
||||
it("4.2 Single step with no END transition → start→role edge exists", () => {
|
||||
const steps = [makeStep("A", [])];
|
||||
const { nodes, edges } = transIn(steps);
|
||||
expect(nodes).toHaveLength(3); // start, end, role-A
|
||||
const startEdge = edges.find((e) => e.source === "start");
|
||||
expect(startEdge).toBeDefined();
|
||||
const roleNode = nodes.find((n) => n.type === "role");
|
||||
expect(startEdge?.target).toBe(roleNode?.id);
|
||||
});
|
||||
|
||||
it("4.3 Single step with END transition → edge to end node exists", () => {
|
||||
const steps = [makeStep("A", [{ condition: null, target: "END" }])];
|
||||
const { edges } = transIn(steps);
|
||||
const endEdge = edges.find((e) => e.target === "end");
|
||||
expect(endEdge).toBeDefined();
|
||||
});
|
||||
|
||||
it("4.4 Two steps with default transitions chain", () => {
|
||||
const steps = [
|
||||
makeStep("A", [{ condition: null, target: "B" }]),
|
||||
makeStep("B", [{ condition: null, target: "END" }]),
|
||||
];
|
||||
const { edges } = transIn(steps);
|
||||
// Should have start→A, A→B, B→end
|
||||
expect(edges.find((e) => e.source === "start")).toBeDefined();
|
||||
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);
|
||||
});
|
||||
|
||||
it("4.5 Step with multiple transitions → conditional edges", () => {
|
||||
const steps = [
|
||||
makeStep("A", [
|
||||
{ condition: null, target: "B" },
|
||||
{ condition: "x>0", 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);
|
||||
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(elseEdge).toBeDefined();
|
||||
// if-branch has condition
|
||||
const ifEdge = outEdges.find(
|
||||
(e) => (e as { data?: { condition?: string } }).data?.condition === "x>0",
|
||||
);
|
||||
expect(ifEdge).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" }]),
|
||||
];
|
||||
const { edges } = transIn(steps);
|
||||
// start→A and start→B; end has 2 incoming edges
|
||||
const incomingToEnd = edges.filter((e) => e.target === "end");
|
||||
expect(incomingToEnd[0].targetHandle).toBe("input");
|
||||
});
|
||||
|
||||
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" }]),
|
||||
];
|
||||
const { edges } = transIn(steps);
|
||||
const aId = edges.find((e) => e.source === "start")?.target;
|
||||
// B→A edge target should be same node as start→A edge target
|
||||
const bToAEdge = edges.find(
|
||||
(e) => e.source !== "start" && e.target === aId && e.target !== "end",
|
||||
);
|
||||
expect(bToAEdge).toBeDefined();
|
||||
});
|
||||
});
|
||||
@@ -1,137 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { AnyWorkEdge, AnyWorkNode } from "../../type.js";
|
||||
import { validate } from "../validate.js";
|
||||
|
||||
function roleNode(id: string): AnyWorkNode {
|
||||
return {
|
||||
id,
|
||||
type: "role",
|
||||
data: { name: id, description: "", identity: "", prepare: "", execute: "", report: "" },
|
||||
position: { x: 0, y: 0 },
|
||||
} as AnyWorkNode;
|
||||
}
|
||||
|
||||
function startNode(): AnyWorkNode {
|
||||
return {
|
||||
id: "start",
|
||||
type: "start",
|
||||
data: { label: "Start" },
|
||||
position: { x: 0, y: 0 },
|
||||
} as AnyWorkNode;
|
||||
}
|
||||
|
||||
function endNode(): AnyWorkNode {
|
||||
return {
|
||||
id: "end",
|
||||
type: "end",
|
||||
data: { label: "End" },
|
||||
position: { x: 0, y: 0 },
|
||||
} as AnyWorkNode;
|
||||
}
|
||||
|
||||
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 {
|
||||
return {
|
||||
id: `${source}-${target}-cond`,
|
||||
source,
|
||||
target,
|
||||
type: "conditional" as const,
|
||||
data: { condition },
|
||||
animated: true,
|
||||
} as AnyWorkEdge;
|
||||
}
|
||||
|
||||
// Helper: build a minimal valid graph with 2 role nodes for validateRoleNodes tests
|
||||
function baseNodes(...roles: AnyWorkNode[]): AnyWorkNode[] {
|
||||
return [startNode(), ...roles, endNode()];
|
||||
}
|
||||
|
||||
describe("validateRoleNodes (via validate)", () => {
|
||||
it("5.1 Role node with no incoming edge → error about missing input", () => {
|
||||
const n1 = roleNode("n1");
|
||||
const n2 = roleNode("n2");
|
||||
const nodes = baseNodes(n1, n2);
|
||||
// n1 has no incoming, n2 has incoming+outgoing
|
||||
const edges = [defaultEdge("start", "n2"), defaultEdge("n1", "end"), defaultEdge("n2", "end")];
|
||||
const result = validate(nodes, edges);
|
||||
const nodeErrors = result.errors.filter((e) => e.nodeId === "n1");
|
||||
expect(nodeErrors.some((e) => e.message.includes("缺少输入连接"))).toBe(true);
|
||||
});
|
||||
|
||||
it("5.2 Role node with no outgoing edge → error about missing output", () => {
|
||||
const n1 = roleNode("n1");
|
||||
const n2 = roleNode("n2");
|
||||
const nodes = baseNodes(n1, n2);
|
||||
const edges = [
|
||||
defaultEdge("start", "n1"),
|
||||
defaultEdge("start", "n2"),
|
||||
defaultEdge("n2", "end"),
|
||||
// n1 has no outgoing
|
||||
];
|
||||
const result = validate(nodes, edges);
|
||||
const nodeErrors = result.errors.filter((e) => e.nodeId === "n1");
|
||||
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", () => {
|
||||
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
|
||||
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);
|
||||
});
|
||||
|
||||
it("5.4 Mix of conditional and non-conditional 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"),
|
||||
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);
|
||||
});
|
||||
|
||||
it("5.5 Valid role node (1 in, 1 out default) → no errors for that node", () => {
|
||||
const n1 = roleNode("n1");
|
||||
const n2 = roleNode("n2");
|
||||
const nodes = baseNodes(n1, n2);
|
||||
const edges = [defaultEdge("start", "n1"), defaultEdge("n1", "n2"), defaultEdge("n2", "end")];
|
||||
const result = validate(nodes, edges);
|
||||
const roleErrors = result.errors.filter((e) => e.nodeId === "n1" || e.nodeId === "n2");
|
||||
expect(roleErrors).toHaveLength(0);
|
||||
});
|
||||
|
||||
it("5.6 Valid role node (1 in, 2 conditional out with conditions) → 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
|
||||
defaultEdge("n2", "end"),
|
||||
defaultEdge("n3", "end"),
|
||||
];
|
||||
const result = validate(nodes, edges);
|
||||
const n1Errors = result.errors.filter((e) => e.nodeId === "n1");
|
||||
expect(n1Errors).toHaveLength(0);
|
||||
});
|
||||
});
|
||||
@@ -28,109 +28,6 @@ function assignHandles(
|
||||
}
|
||||
}
|
||||
|
||||
function buildNodeMap(
|
||||
steps: WorkFlowStep[],
|
||||
nodes: AnyWorkNode[],
|
||||
): { nameToId: Map<string, string>; idToOrder: Map<string, number> } {
|
||||
const nameToId = new Map<string, string>();
|
||||
const idToOrder = new Map<string, number>();
|
||||
nameToId.set("END", "end");
|
||||
idToOrder.set("start", -1);
|
||||
idToOrder.set("end", steps.length);
|
||||
for (let si = 0; si < steps.length; si++) {
|
||||
const step = steps[si];
|
||||
const nodeId = `n${uuid()}`;
|
||||
nameToId.set(step.role.name, nodeId);
|
||||
idToOrder.set(nodeId, si);
|
||||
nodes.push({ id: nodeId, type: "role", data: { ...step.role }, position: { x: 0, y: 0 } });
|
||||
}
|
||||
return { nameToId, idToOrder };
|
||||
}
|
||||
|
||||
function sortTransitions(step: WorkFlowStep): WorkFlowStep["transitions"] {
|
||||
if (step.transitions.length <= 1) return step.transitions;
|
||||
return [...step.transitions].sort((a, b) => {
|
||||
if (a.condition === null && b.condition !== null) return -1;
|
||||
if (a.condition !== null && b.condition === null) return 1;
|
||||
return 0;
|
||||
});
|
||||
}
|
||||
|
||||
function buildStepEdges(
|
||||
sourceId: string,
|
||||
step: WorkFlowStep,
|
||||
nameToId: Map<string, string>,
|
||||
): { elseEdges: AnyWorkEdge[]; ifEdges: AnyWorkEdge[] } {
|
||||
const hasMultiple = step.transitions.length > 1;
|
||||
const sorted = sortTransitions(step);
|
||||
const elseEdges: AnyWorkEdge[] = [];
|
||||
const ifEdges: AnyWorkEdge[] = [];
|
||||
|
||||
for (let i = 0; i < sorted.length; i++) {
|
||||
const t = sorted[i];
|
||||
const targetId = nameToId.get(t.target);
|
||||
if (!targetId) continue;
|
||||
const edgeId = `e-${sourceId}-${targetId}-${i}`;
|
||||
if (hasMultiple || t.condition !== null) {
|
||||
const edge: ConditionalEdge = {
|
||||
id: edgeId,
|
||||
source: sourceId,
|
||||
target: targetId,
|
||||
sourceHandle: "output",
|
||||
targetHandle: "input",
|
||||
type: "conditional",
|
||||
data: { condition: t.condition ?? "" },
|
||||
animated: true,
|
||||
};
|
||||
if (hasMultiple && i === 0) elseEdges.push(edge);
|
||||
else ifEdges.push(edge);
|
||||
} else {
|
||||
elseEdges.push({
|
||||
id: edgeId,
|
||||
source: sourceId,
|
||||
target: targetId,
|
||||
sourceHandle: "output",
|
||||
targetHandle: "input",
|
||||
animated: true,
|
||||
});
|
||||
}
|
||||
}
|
||||
return { elseEdges, ifEdges };
|
||||
}
|
||||
|
||||
function pushStepEdges(
|
||||
edges: AnyWorkEdge[],
|
||||
elseEdges: AnyWorkEdge[],
|
||||
ifEdges: 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(
|
||||
(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] });
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function assignTargetHandles(edges: AnyWorkEdge[], idToOrder: Map<string, number>): void {
|
||||
const incomingByTarget = new Map<string, number[]>();
|
||||
for (let i = 0; i < edges.length; i++) {
|
||||
const target = edges[i].target;
|
||||
if (!incomingByTarget.has(target)) incomingByTarget.set(target, []);
|
||||
incomingByTarget.get(target)?.push(i);
|
||||
}
|
||||
for (const indices of incomingByTarget.values()) {
|
||||
indices.sort(
|
||||
(a, b) => (idToOrder.get(edges[a].source) ?? 0) - (idToOrder.get(edges[b].source) ?? 0),
|
||||
);
|
||||
assignHandles(indices, edges, IN_HANDLES, "targetHandle");
|
||||
}
|
||||
}
|
||||
|
||||
export function transIn(steps: WorkFlowStep[]): Result {
|
||||
const startNode: AnyWorkNode = {
|
||||
id: "start",
|
||||
@@ -145,12 +42,30 @@ export function transIn(steps: WorkFlowStep[]): Result {
|
||||
position: { x: 250, y: 0 },
|
||||
};
|
||||
|
||||
if (steps.length === 0) return { nodes: [startNode, endNode], edges: [] };
|
||||
if (steps.length === 0) {
|
||||
return { nodes: [startNode, endNode], edges: [] };
|
||||
}
|
||||
|
||||
const nodes: AnyWorkNode[] = [startNode, endNode];
|
||||
const edges: AnyWorkEdge[] = [];
|
||||
const nameToId = new Map<string, string>();
|
||||
const idToOrder = new Map<string, number>();
|
||||
nameToId.set("END", "end");
|
||||
idToOrder.set("start", -1);
|
||||
idToOrder.set("end", steps.length);
|
||||
|
||||
const { nameToId, idToOrder } = buildNodeMap(steps, nodes);
|
||||
for (let si = 0; si < steps.length; si++) {
|
||||
const step = steps[si];
|
||||
const nodeId = `n${uuid()}`;
|
||||
nameToId.set(step.role.name, nodeId);
|
||||
idToOrder.set(nodeId, si);
|
||||
nodes.push({
|
||||
id: nodeId,
|
||||
type: "role",
|
||||
data: { ...step.role },
|
||||
position: { x: 0, y: 0 },
|
||||
});
|
||||
}
|
||||
|
||||
const firstStepId = nameToId.get(steps[0].role.name) ?? "";
|
||||
edges.push({
|
||||
@@ -164,11 +79,88 @@ export function transIn(steps: WorkFlowStep[]): Result {
|
||||
|
||||
for (const step of steps) {
|
||||
const sourceId = nameToId.get(step.role.name) ?? "";
|
||||
const { elseEdges, ifEdges } = buildStepEdges(sourceId, step, nameToId);
|
||||
pushStepEdges(edges, elseEdges, ifEdges, idToOrder);
|
||||
const _sourceOrder = idToOrder.get(sourceId) ?? 0;
|
||||
const hasMultipleTransitions = step.transitions.length > 1;
|
||||
|
||||
const sorted = hasMultipleTransitions
|
||||
? [...step.transitions].sort((a, b) => {
|
||||
if (a.condition === null && b.condition !== null) return -1;
|
||||
if (a.condition !== null && b.condition === null) return 1;
|
||||
return 0;
|
||||
})
|
||||
: step.transitions;
|
||||
|
||||
const elseEdges: AnyWorkEdge[] = [];
|
||||
const ifEdges: AnyWorkEdge[] = [];
|
||||
|
||||
for (let i = 0; i < sorted.length; i++) {
|
||||
const t = sorted[i];
|
||||
const targetId = nameToId.get(t.target);
|
||||
if (!targetId) continue;
|
||||
|
||||
const edgeId = `e-${sourceId}-${targetId}-${i}`;
|
||||
|
||||
if (hasMultipleTransitions || t.condition !== null) {
|
||||
const edge: ConditionalEdge = {
|
||||
id: edgeId,
|
||||
source: sourceId,
|
||||
target: targetId,
|
||||
sourceHandle: "output",
|
||||
targetHandle: "input",
|
||||
type: "conditional",
|
||||
data: { condition: t.condition ?? "" },
|
||||
animated: true,
|
||||
};
|
||||
if (hasMultipleTransitions && i === 0) {
|
||||
elseEdges.push(edge);
|
||||
} else {
|
||||
ifEdges.push(edge);
|
||||
}
|
||||
} else {
|
||||
elseEdges.push({
|
||||
id: edgeId,
|
||||
source: sourceId,
|
||||
target: targetId,
|
||||
sourceHandle: "output",
|
||||
targetHandle: "input",
|
||||
animated: true,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// out: else → output (right); if → sort by target order desc (rightmost first), then top/bottom
|
||||
for (const e of elseEdges) {
|
||||
edges.push({ ...e, sourceHandle: "output" });
|
||||
}
|
||||
if (ifEdges.length > 0) {
|
||||
const sortedIf = [...ifEdges].sort((a, b) => {
|
||||
const oa = idToOrder.get(a.target) ?? 0;
|
||||
const ob = idToOrder.get(b.target) ?? 0;
|
||||
return ob - oa;
|
||||
});
|
||||
const ifHandles = ["output-top", "output-bottom"] as const;
|
||||
for (let i = 0; i < sortedIf.length; i++) {
|
||||
edges.push({ ...sortedIf[i], sourceHandle: ifHandles[i % ifHandles.length] });
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
assignTargetHandles(edges, idToOrder);
|
||||
// in: group by target, sort by source order asc (leftmost first), assign input > input-top > input-bottom
|
||||
const incomingByTarget = new Map<string, number[]>();
|
||||
for (let i = 0; i < edges.length; i++) {
|
||||
const target = edges[i].target;
|
||||
if (!incomingByTarget.has(target)) incomingByTarget.set(target, []);
|
||||
incomingByTarget.get(target)?.push(i);
|
||||
}
|
||||
|
||||
for (const indices of incomingByTarget.values()) {
|
||||
indices.sort((a, b) => {
|
||||
const oa = idToOrder.get(edges[a].source) ?? 0;
|
||||
const ob = idToOrder.get(edges[b].source) ?? 0;
|
||||
return oa - ob;
|
||||
});
|
||||
assignHandles(indices, edges, IN_HANDLES, "targetHandle");
|
||||
}
|
||||
|
||||
return { nodes, edges };
|
||||
}
|
||||
|
||||
@@ -91,36 +91,6 @@ function validateEndNode(
|
||||
}
|
||||
}
|
||||
|
||||
function hasEmptyConditionOnIfEdge(conditionalEdges: AnyWorkEdge[]): boolean {
|
||||
return conditionalEdges.slice(1).some((edge) => {
|
||||
const cond = (edge as ConditionalEdge).data?.condition?.trim();
|
||||
return !cond;
|
||||
});
|
||||
}
|
||||
|
||||
function validateRoleNodeEdges(
|
||||
node: AnyWorkNode,
|
||||
outEdges: AnyWorkEdge[],
|
||||
inEdges: AnyWorkEdge[],
|
||||
errors: ValidationError[],
|
||||
): void {
|
||||
if (inEdges.length === 0) {
|
||||
errors.push({ nodeId: node.id, message: "角色节点缺少输入连接" });
|
||||
}
|
||||
if (outEdges.length === 0) {
|
||||
errors.push({ nodeId: node.id, message: "角色节点缺少输出连接" });
|
||||
return;
|
||||
}
|
||||
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" });
|
||||
}
|
||||
}
|
||||
|
||||
function validateRoleNodes(
|
||||
roleNodes: AnyWorkNode[],
|
||||
outgoing: Map<string, AnyWorkEdge[]>,
|
||||
@@ -128,7 +98,31 @@ function validateRoleNodes(
|
||||
errors: ValidationError[],
|
||||
): void {
|
||||
for (const node of roleNodes) {
|
||||
validateRoleNodeEdges(node, outgoing.get(node.id) ?? [], incoming.get(node.id) ?? [], errors);
|
||||
const inEdges = incoming.get(node.id) ?? [];
|
||||
const outEdges = outgoing.get(node.id) ?? [];
|
||||
|
||||
if (inEdges.length === 0) {
|
||||
errors.push({ nodeId: node.id, message: "角色节点缺少输入连接" });
|
||||
}
|
||||
if (outEdges.length === 0) {
|
||||
errors.push({ nodeId: node.id, message: "角色节点缺少输出连接" });
|
||||
}
|
||||
|
||||
if (outEdges.length > 1) {
|
||||
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 {
|
||||
const ifEdges = conditionalEdges.slice(1);
|
||||
for (const edge of ifEdges) {
|
||||
const condEdge = edge as ConditionalEdge;
|
||||
if (!condEdge.data?.condition?.trim()) {
|
||||
errors.push({ nodeId: node.id, message: "条件边的条件表达式不能为空" });
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,14 +0,0 @@
|
||||
import path from "node:path";
|
||||
import { defineConfig } from "vitest/config";
|
||||
|
||||
export default defineConfig({
|
||||
test: {
|
||||
environment: "node",
|
||||
include: ["src/**/__tests__/**/*.test.ts"],
|
||||
},
|
||||
resolve: {
|
||||
alias: {
|
||||
"@": path.resolve(import.meta.dirname, "./src"),
|
||||
},
|
||||
},
|
||||
});
|
||||
@@ -1,60 +0,0 @@
|
||||
# @uncaged/workflow-moderator
|
||||
|
||||
JSONata-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`).
|
||||
|
||||
**Dependencies:** `@uncaged/workflow-protocol`, `jsonata`
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
bun add @uncaged/workflow-moderator
|
||||
```
|
||||
|
||||
## API
|
||||
|
||||
### Functions
|
||||
|
||||
```typescript
|
||||
function evaluate(
|
||||
workflow: WorkflowPayload,
|
||||
context: ModeratorContext,
|
||||
): Promise<Result<EvaluateResult, Error>>
|
||||
```
|
||||
|
||||
Returns `{ ok: true, value: { role, prompt } }` where `role` is the next role name or `"$END"`, and `prompt` is the edge instruction for the agent.
|
||||
|
||||
### Types
|
||||
|
||||
```typescript
|
||||
type EvaluateResult = {
|
||||
role: string;
|
||||
prompt: string;
|
||||
};
|
||||
```
|
||||
|
||||
The `Result<T, E>` type is local to this package (`{ ok: true; value: T } | { ok: false; error: E }`), not re-exported from `index.ts`.
|
||||
|
||||
## Usage
|
||||
|
||||
```typescript
|
||||
import { evaluate } from "@uncaged/workflow-moderator";
|
||||
import type { ModeratorContext, WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
|
||||
const result = await evaluate(workflow, context);
|
||||
if (result.ok && result.value.role !== "$END") {
|
||||
console.log(`Next role: ${result.value.role}, prompt: ${result.value.prompt}`);
|
||||
}
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts Public exports
|
||||
├── evaluate.ts Graph walk + JSONata condition evaluation
|
||||
└── types.ts EvaluateResult, Result
|
||||
```
|
||||
@@ -1,95 +1,312 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import type { Target, WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
import type { ModeratorContext, WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
|
||||
import { evaluate } from "../src/evaluate.js";
|
||||
|
||||
const solveIssueGraph: WorkflowPayload["graph"] = {
|
||||
$START: {
|
||||
_: { role: "planner", prompt: "Start planning from the issue in the task." },
|
||||
const solveIssueWorkflow: WorkflowPayload = {
|
||||
name: "solve-issue",
|
||||
description: "End-to-end issue resolution",
|
||||
roles: {
|
||||
planner: {
|
||||
description: "Creates implementation plan",
|
||||
goal: "You are a planning agent.",
|
||||
capabilities: ["planning"],
|
||||
procedure: "Create a step-by-step plan.",
|
||||
output: "Output the plan and steps.",
|
||||
frontmatter: "5GWKR8TN1V3JA",
|
||||
},
|
||||
developer: {
|
||||
description: "Implements code changes",
|
||||
goal: "You are a developer agent.",
|
||||
capabilities: ["coding"],
|
||||
procedure: "Implement the plan.",
|
||||
output: "List files changed and summary.",
|
||||
frontmatter: "8CNWT4KR6D1HV",
|
||||
},
|
||||
reviewer: {
|
||||
description: "Reviews code changes",
|
||||
goal: "You are a code reviewer.",
|
||||
capabilities: ["code-review"],
|
||||
procedure: "Review the implementation.",
|
||||
output: "Approve or reject with comments.",
|
||||
frontmatter: "1VPBG9SM5E7WK",
|
||||
},
|
||||
},
|
||||
planner: {
|
||||
_: { role: "developer", prompt: "Implement the plan: {{plan}}" },
|
||||
conditions: {
|
||||
needsClarification: {
|
||||
description: "Planner requests clarification from user",
|
||||
expression: "$exists($last('planner').needsClarification)",
|
||||
},
|
||||
rejected: {
|
||||
description: "Reviewer rejected the implementation",
|
||||
expression: "$last('reviewer').approved = false",
|
||||
},
|
||||
},
|
||||
developer: {
|
||||
_: { role: "reviewer", prompt: "Review the changes: {{summary}}" },
|
||||
},
|
||||
reviewer: {
|
||||
approved: { role: "$END", prompt: "Done." },
|
||||
rejected: { role: "developer", prompt: "Fix: {{comments}}" },
|
||||
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: "$END", condition: null, prompt: "Review passed; end workflow." },
|
||||
],
|
||||
},
|
||||
};
|
||||
|
||||
function makeContext(steps: ModeratorContext["steps"]): ModeratorContext {
|
||||
return {
|
||||
start: {
|
||||
workflow: "4KNM2PXR3B1QW",
|
||||
prompt: "Fix the login bug",
|
||||
},
|
||||
steps,
|
||||
};
|
||||
}
|
||||
|
||||
describe("evaluate", () => {
|
||||
test("$START → first role (unit status _)", () => {
|
||||
const result = evaluate(solveIssueGraph, "$START", { status: "_" });
|
||||
test("$START → first role (fallback)", async () => {
|
||||
const result = await evaluate(solveIssueWorkflow, makeContext([]));
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: { role: "planner", prompt: "Start planning from the issue in the task." },
|
||||
});
|
||||
});
|
||||
|
||||
test("status-based routing (reviewer rejected → developer)", () => {
|
||||
const result = evaluate(solveIssueGraph, "reviewer", {
|
||||
status: "rejected",
|
||||
comments: "missing tests",
|
||||
});
|
||||
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);
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: { role: "developer", prompt: "Fix: missing tests" },
|
||||
value: { role: "developer", prompt: "Reviewer rejected; return to developer." },
|
||||
});
|
||||
});
|
||||
|
||||
test("status-based routing (reviewer approved → $END)", () => {
|
||||
const result = evaluate(solveIssueGraph, "reviewer", { status: "approved" });
|
||||
test("fallback when condition does not match → $END", async () => {
|
||||
const context = makeContext([
|
||||
{
|
||||
role: "reviewer",
|
||||
output: { approved: true },
|
||||
detail: "2MXBG6PN4A8JR",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
]);
|
||||
const result = await evaluate(solveIssueWorkflow, context);
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: { role: "$END", prompt: "Done." },
|
||||
value: { role: "$END", prompt: "Review passed; end workflow." },
|
||||
});
|
||||
});
|
||||
|
||||
test("missing role in graph → error", () => {
|
||||
const result = evaluate(solveIssueGraph, "unknown-role", { status: "_" });
|
||||
test("missing role in graph → error", async () => {
|
||||
const context = makeContext([
|
||||
{
|
||||
role: "unknown-role",
|
||||
output: {},
|
||||
detail: "2MXBG6PN4A8JR",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
]);
|
||||
const result = await evaluate(solveIssueWorkflow, context);
|
||||
expect(result.ok).toBe(false);
|
||||
if (!result.ok) {
|
||||
expect(result.error.message).toBe('no transitions defined for role "unknown-role"');
|
||||
}
|
||||
});
|
||||
|
||||
test("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",
|
||||
});
|
||||
test("output expansion in context works with JSONata", async () => {
|
||||
const context = makeContext([
|
||||
{
|
||||
role: "planner",
|
||||
output: { needsClarification: true },
|
||||
detail: "7BQST3VW9F2MA",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
]);
|
||||
const result = await evaluate(solveIssueWorkflow, context);
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: { role: "developer", prompt: "Implement the plan: Add auth middleware" },
|
||||
value: { role: "developer", prompt: "Clarification is needed; hand off to developer." },
|
||||
});
|
||||
});
|
||||
|
||||
test("mustache template with nested object paths", () => {
|
||||
const graph: Record<string, Record<string, Target>> = {
|
||||
reviewer: {
|
||||
_: {
|
||||
role: "developer",
|
||||
prompt: "Address: {{review.comments}}",
|
||||
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 result = evaluate(graph, "reviewer", {
|
||||
status: "_",
|
||||
review: { comments: "refactor the handler" },
|
||||
});
|
||||
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);
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: { role: "developer", prompt: "Address: refactor the handler" },
|
||||
value: { role: "$END", prompt: "Development failed; end." },
|
||||
});
|
||||
});
|
||||
|
||||
test("$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.",
|
||||
},
|
||||
],
|
||||
},
|
||||
};
|
||||
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);
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: { role: "$END", prompt: "First plan was ready; end." },
|
||||
});
|
||||
});
|
||||
|
||||
test("$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 → $exists returns false → fallback to developer
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
value: { role: "developer", prompt: "No reviewer yet; implement." },
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -19,10 +19,9 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow-protocol": "workspace:^",
|
||||
"mustache": "^4.2.0"
|
||||
"jsonata": "^1.8.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/mustache": "^4.2.6",
|
||||
"typescript": "^5.8.3"
|
||||
},
|
||||
"publishConfig": {
|
||||
|
||||
@@ -1,39 +1,65 @@
|
||||
import type { Target } from "@uncaged/workflow-protocol";
|
||||
import mustache from "mustache";
|
||||
import type { ModeratorContext, WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
import jsonata from "jsonata";
|
||||
|
||||
import type { EvaluateResult, Result } from "./types.js";
|
||||
|
||||
const START_ROLE = "$START";
|
||||
const UNIT_STATUS = "_";
|
||||
|
||||
type LastOutput = Record<string, unknown> & { status: string };
|
||||
|
||||
export function evaluate(
|
||||
graph: Record<string, Record<string, Target>>,
|
||||
lastRole: string,
|
||||
lastOutput: LastOutput,
|
||||
): Result<EvaluateResult, Error> {
|
||||
const status = lastRole === START_ROLE ? UNIT_STATUS : lastOutput.status;
|
||||
|
||||
const roleTargets = graph[lastRole];
|
||||
if (roleTargets === undefined) {
|
||||
return {
|
||||
ok: false,
|
||||
error: new Error(`no transitions defined for role "${lastRole}"`),
|
||||
};
|
||||
function isTruthy(value: unknown): boolean {
|
||||
if (value === null || value === undefined) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const target = roleTargets[status];
|
||||
if (target === undefined) {
|
||||
return {
|
||||
ok: false,
|
||||
error: new Error(`no transition for role "${lastRole}" with status "${status}"`),
|
||||
};
|
||||
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;
|
||||
}
|
||||
|
||||
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;
|
||||
}
|
||||
|
||||
async function evaluateJsonata(
|
||||
expression: string,
|
||||
context: ModeratorContext,
|
||||
): Promise<Result<unknown, Error>> {
|
||||
try {
|
||||
const prompt = mustache.render(target.prompt, lastOutput);
|
||||
return { ok: true, value: { role: target.role, prompt } };
|
||||
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 };
|
||||
} catch (error) {
|
||||
return {
|
||||
ok: false,
|
||||
@@ -41,3 +67,51 @@ export function evaluate(
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
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}"`),
|
||||
};
|
||||
}
|
||||
|
||||
@@ -1,193 +0,0 @@
|
||||
# @uncaged/workflow-protocol
|
||||
|
||||
Shared TypeScript types and JSON Schema constants for the workflow engine.
|
||||
|
||||
## Overview
|
||||
|
||||
This is the contract layer (Layer 0). It defines `WorkflowPayload`, thread node payloads, moderator context, CLI output shapes, and configuration types used across every other package. It has no runtime logic beyond exporting schema objects from `@uncaged/json-cas`.
|
||||
|
||||
**Dependencies:** `@uncaged/json-cas`, `@uncaged/json-cas-fs`
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
bun add @uncaged/workflow-protocol
|
||||
```
|
||||
|
||||
## API
|
||||
|
||||
All exports come from `src/index.ts`.
|
||||
|
||||
### JSON Schema constants
|
||||
|
||||
```typescript
|
||||
START_NODE_SCHEMA: JSONSchema
|
||||
STEP_NODE_SCHEMA: JSONSchema
|
||||
WORKFLOW_SCHEMA: JSONSchema
|
||||
```
|
||||
|
||||
### Core identifiers
|
||||
|
||||
```typescript
|
||||
type CasRef = string // XXH64 hash, 13-char Crockford Base32
|
||||
type ThreadId = string // ULID, 26-char Crockford Base32
|
||||
type WorkflowName = string
|
||||
type RoleName = string
|
||||
```
|
||||
|
||||
### Workflow definition
|
||||
|
||||
```typescript
|
||||
type RoleDefinition = {
|
||||
description: string;
|
||||
goal: string;
|
||||
capabilities: string[];
|
||||
procedure: string;
|
||||
output: string;
|
||||
frontmatter: CasRef;
|
||||
};
|
||||
|
||||
type Transition = {
|
||||
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[]>;
|
||||
};
|
||||
```
|
||||
|
||||
### Thread nodes
|
||||
|
||||
```typescript
|
||||
type StepRecord = {
|
||||
role: string;
|
||||
output: CasRef;
|
||||
detail: CasRef;
|
||||
agent: string;
|
||||
edgePrompt: string;
|
||||
};
|
||||
|
||||
type StartNodePayload = {
|
||||
workflow: CasRef;
|
||||
prompt: string;
|
||||
};
|
||||
|
||||
type StepNodePayload = StepRecord & {
|
||||
start: CasRef;
|
||||
prev: CasRef | null;
|
||||
};
|
||||
```
|
||||
|
||||
### Moderator context
|
||||
|
||||
```typescript
|
||||
type StepContext = Omit<StepRecord, "output"> & { output: unknown; content: string | null };
|
||||
|
||||
type ModeratorContext = {
|
||||
start: StartNodePayload;
|
||||
steps: StepContext[];
|
||||
};
|
||||
```
|
||||
|
||||
### Configuration
|
||||
|
||||
```typescript
|
||||
type ProviderAlias = string;
|
||||
type ModelAlias = string;
|
||||
type AgentAlias = string;
|
||||
|
||||
type ProviderConfig = { baseUrl: string; apiKeyEnv: string };
|
||||
type ModelConfig = {
|
||||
provider: ProviderAlias;
|
||||
name: string;
|
||||
};
|
||||
|
||||
type AgentConfig = {
|
||||
command: string;
|
||||
args: string[];
|
||||
};
|
||||
|
||||
type WorkflowConfig = {
|
||||
providers: Record<ProviderAlias, ProviderConfig>;
|
||||
models: Record<ModelAlias, ModelConfig>;
|
||||
agents: Record<AgentAlias, AgentConfig>;
|
||||
defaultAgent: AgentAlias;
|
||||
agentOverrides: Record<WorkflowName, Record<RoleName, AgentAlias>> | null;
|
||||
defaultModel: ModelAlias;
|
||||
modelOverrides: Record<Scenario, ModelAlias> | null;
|
||||
};
|
||||
```
|
||||
|
||||
### CLI output types
|
||||
|
||||
```typescript
|
||||
type StartOutput = { workflow: CasRef; thread: ThreadId };
|
||||
|
||||
type StepOutput = {
|
||||
workflow: CasRef;
|
||||
thread: ThreadId;
|
||||
head: CasRef;
|
||||
done: boolean;
|
||||
};
|
||||
|
||||
type StepEntry = {
|
||||
hash: CasRef;
|
||||
role: string;
|
||||
output: unknown;
|
||||
detail: CasRef;
|
||||
agent: string;
|
||||
timestamp: number;
|
||||
};
|
||||
|
||||
type StartEntry = {
|
||||
hash: CasRef;
|
||||
workflow: CasRef;
|
||||
prompt: string;
|
||||
timestamp: number;
|
||||
};
|
||||
|
||||
type ThreadStepsOutput = {
|
||||
thread: ThreadId;
|
||||
workflow: CasRef;
|
||||
steps: [StartEntry, ...StepEntry[]];
|
||||
};
|
||||
|
||||
type ThreadForkOutput = {
|
||||
thread: ThreadId;
|
||||
forkedFrom: { step: CasRef };
|
||||
};
|
||||
|
||||
type ThreadListItem = {
|
||||
thread: ThreadId;
|
||||
workflow: CasRef;
|
||||
head: CasRef;
|
||||
};
|
||||
|
||||
type ThreadsIndex = Record<ThreadId, CasRef>;
|
||||
|
||||
type Scenario = string;
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts Public re-exports
|
||||
├── types.ts All type definitions
|
||||
└── schemas.ts START_NODE_SCHEMA, STEP_NODE_SCHEMA, WORKFLOW_SCHEMA
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
This package defines `WorkflowConfig` types only. Runtime config loading lives in `@uncaged/workflow-agent-kit` (`loadWorkflowConfig`).
|
||||
@@ -7,6 +7,7 @@ export type {
|
||||
AgentAlias,
|
||||
AgentConfig,
|
||||
CasRef,
|
||||
ConditionDefinition,
|
||||
ModelAlias,
|
||||
ModelConfig,
|
||||
ModeratorContext,
|
||||
@@ -14,8 +15,6 @@ export type {
|
||||
ProviderConfig,
|
||||
RoleDefinition,
|
||||
RoleName,
|
||||
RunningThreadItem,
|
||||
RunningThreadsOutput,
|
||||
Scenario,
|
||||
StartEntry,
|
||||
StartNodePayload,
|
||||
@@ -25,12 +24,12 @@ export type {
|
||||
StepNodePayload,
|
||||
StepOutput,
|
||||
StepRecord,
|
||||
Target,
|
||||
ThreadForkOutput,
|
||||
ThreadId,
|
||||
ThreadListItem,
|
||||
ThreadStepsOutput,
|
||||
ThreadsIndex,
|
||||
Transition,
|
||||
WorkflowConfig,
|
||||
WorkflowName,
|
||||
WorkflowPayload,
|
||||
|
||||
@@ -14,11 +14,22 @@ const ROLE_DEFINITION: JSONSchema = {
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
const TARGET: JSONSchema = {
|
||||
const CONDITION_DEFINITION: JSONSchema = {
|
||||
type: "object",
|
||||
required: ["role", "prompt"],
|
||||
required: ["description", "expression"],
|
||||
properties: {
|
||||
description: { type: "string" },
|
||||
expression: { type: "string" },
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
const TRANSITION: JSONSchema = {
|
||||
type: "object",
|
||||
required: ["role", "condition", "prompt"],
|
||||
properties: {
|
||||
role: { type: "string" },
|
||||
condition: { anyOf: [{ type: "string" }, { type: "null" }] },
|
||||
prompt: { type: "string" },
|
||||
},
|
||||
additionalProperties: false,
|
||||
@@ -27,7 +38,7 @@ const TARGET: JSONSchema = {
|
||||
export const WORKFLOW_SCHEMA: JSONSchema = {
|
||||
title: "Workflow",
|
||||
type: "object",
|
||||
required: ["name", "description", "roles", "graph"],
|
||||
required: ["name", "description", "roles", "conditions", "graph"],
|
||||
properties: {
|
||||
name: { type: "string" },
|
||||
description: { type: "string" },
|
||||
@@ -35,11 +46,15 @@ export const WORKFLOW_SCHEMA: JSONSchema = {
|
||||
type: "object",
|
||||
additionalProperties: ROLE_DEFINITION,
|
||||
},
|
||||
conditions: {
|
||||
type: "object",
|
||||
additionalProperties: CONDITION_DEFINITION,
|
||||
},
|
||||
graph: {
|
||||
type: "object",
|
||||
additionalProperties: {
|
||||
type: "object",
|
||||
additionalProperties: TARGET,
|
||||
type: "array",
|
||||
items: TRANSITION,
|
||||
},
|
||||
},
|
||||
},
|
||||
|
||||
@@ -27,16 +27,23 @@ export type RoleDefinition = {
|
||||
frontmatter: CasRef;
|
||||
};
|
||||
|
||||
export type Target = {
|
||||
export type Transition = {
|
||||
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>;
|
||||
graph: Record<string, Record<string, Target>>;
|
||||
conditions: Record<string, ConditionDefinition>;
|
||||
graph: Record<string, Transition[]>;
|
||||
};
|
||||
|
||||
// ── 4.3 Thread 节点 ─────────────────────────────────────────────────
|
||||
@@ -56,7 +63,6 @@ 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 = {
|
||||
@@ -78,7 +84,6 @@ export type StepOutput = {
|
||||
thread: ThreadId;
|
||||
head: CasRef;
|
||||
done: boolean;
|
||||
background: boolean | null;
|
||||
};
|
||||
|
||||
/** uwf thread steps — single step entry */
|
||||
@@ -121,19 +126,6 @@ export type ThreadListItem = {
|
||||
head: CasRef;
|
||||
};
|
||||
|
||||
/** uwf thread running — single running thread entry */
|
||||
export type RunningThreadItem = {
|
||||
thread: ThreadId;
|
||||
workflow: CasRef;
|
||||
pid: number;
|
||||
startedAt: number;
|
||||
};
|
||||
|
||||
/** uwf thread running output */
|
||||
export type RunningThreadsOutput = {
|
||||
threads: RunningThreadItem[];
|
||||
};
|
||||
|
||||
// ── 4.6 配置 ────────────────────────────────────────────────────────
|
||||
|
||||
/** Alias types for config references */
|
||||
|
||||
@@ -1,64 +0,0 @@
|
||||
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>");
|
||||
}
|
||||
@@ -1,146 +1,32 @@
|
||||
# @uncaged/workflow-util
|
||||
|
||||
Shared utilities: encoding, IDs, logging, frontmatter parsing, storage paths, and CLI reference generation.
|
||||
Shared utilities: encoding, IDs, logging, storage paths, and ref-field normalization.
|
||||
|
||||
## Overview
|
||||
## What This Package Does
|
||||
|
||||
Layer 1 shared infrastructure used across CLI, agent-kit, and agent packages. Provides Crockford Base32 encoding, ULID generation, structured logging with fixed 8-char tags, frontmatter markdown parsing/validation, process-level debug logging, and helpers for the default workflow data directory.
|
||||
It provides filesystem-safe Base32 and ULID generation, the structured logger used across packages, helpers for the default workflow data directory and global CAS path, and utilities to merge/normalize `refs` on steps. It re-exports `ok`/`err` from protocol for convenience.
|
||||
|
||||
**Dependencies:** none (standalone)
|
||||
## Key Exports
|
||||
|
||||
## Installation
|
||||
From `src/index.ts`:
|
||||
|
||||
```bash
|
||||
bun add @uncaged/workflow-util
|
||||
```
|
||||
- **Base32:** `CROCKFORD_BASE32_ALPHABET`, `decodeCrockfordBase32Bits`, `decodeCrockfordToUint64`, `encodeCrockfordBase32Bits`, `encodeUint64AsCrockford`
|
||||
- **Logger:** `createLogger`
|
||||
- **Refs:** `mergeRefsWithContentHash`, `normalizeRefsField`
|
||||
- **Result:** `ok`, `err` (from `@uncaged/workflow-protocol`)
|
||||
- **Paths:** `getDefaultWorkflowStorageRoot`, `getGlobalCasDir`
|
||||
- **ULID:** `generateUlid`
|
||||
- **Types:** `CreateLoggerOptions`, `LogFn`, `LoggerSink`, `Result`
|
||||
|
||||
## API
|
||||
## Dependencies
|
||||
|
||||
All exports come from `src/index.ts`.
|
||||
|
||||
### Encoding and IDs
|
||||
|
||||
```typescript
|
||||
function encodeUint64AsCrockford(value: bigint): string
|
||||
function generateUlid(nowMs: number): string
|
||||
function extractUlidTimestamp(ulid: string): number | null
|
||||
```
|
||||
|
||||
### Logging
|
||||
|
||||
```typescript
|
||||
function createLogger(options?: { sink: { kind: "stderr" } }): LogFn
|
||||
|
||||
type LogFn = (tag: string, message: string) => void
|
||||
// CreateLoggerOptions and LoggerSink are internal types
|
||||
```
|
||||
|
||||
### Process logger
|
||||
|
||||
```typescript
|
||||
function createProcessLogger(options: CreateProcessLoggerOptions): ProcessLogger
|
||||
|
||||
type ProcessLogger = {
|
||||
pid: string;
|
||||
log: ProcessLogFn;
|
||||
};
|
||||
|
||||
type ProcessLoggerContext = {
|
||||
thread: string | null;
|
||||
workflow: string | null;
|
||||
};
|
||||
|
||||
type CreateProcessLoggerOptions = {
|
||||
storageRoot: string | null;
|
||||
context: ProcessLoggerContext;
|
||||
};
|
||||
|
||||
type ProcessLogFn = (
|
||||
tag: string,
|
||||
msg: string,
|
||||
context: Record<string, string> | null,
|
||||
) => void;
|
||||
```
|
||||
|
||||
### Frontmatter markdown
|
||||
|
||||
```typescript
|
||||
function parseFrontmatterMarkdown(raw: string): ParsedFrontmatterMarkdown
|
||||
function validateFrontmatter(
|
||||
parsed: ParsedFrontmatterMarkdown,
|
||||
schema: Record<string, unknown>,
|
||||
): FrontmatterValidationError[]
|
||||
|
||||
type ParsedFrontmatterMarkdown = {
|
||||
frontmatter: Record<string, unknown>;
|
||||
body: string;
|
||||
};
|
||||
|
||||
type AgentFrontmatter = { /* standard agent frontmatter fields */ };
|
||||
type FrontmatterScope = string;
|
||||
type FrontmatterStatus = string;
|
||||
type FrontmatterValidationError = { path: string; message: string };
|
||||
```
|
||||
|
||||
### Result helpers
|
||||
|
||||
```typescript
|
||||
function ok<T>(value: T): Result<T, never>
|
||||
function err<E>(error: E): Result<never, E>
|
||||
|
||||
type Result<T, E> = { ok: true; value: T } | { ok: false; error: E }
|
||||
```
|
||||
|
||||
### Storage paths
|
||||
|
||||
```typescript
|
||||
function getDefaultWorkflowStorageRoot(): string
|
||||
function getGlobalCasDir(storageRoot: string | undefined): string
|
||||
```
|
||||
|
||||
### Refs and misc
|
||||
|
||||
```typescript
|
||||
function normalizeRefsField(value: unknown): string[]
|
||||
function generateCliReference(): string
|
||||
function env(name: string, fallback: string): string
|
||||
```
|
||||
- **Workspace:** `@uncaged/workflow-protocol` — `Result` and shared types used by helpers
|
||||
|
||||
## Usage
|
||||
|
||||
```typescript
|
||||
import {
|
||||
createLogger,
|
||||
generateUlid,
|
||||
getDefaultWorkflowStorageRoot,
|
||||
parseFrontmatterMarkdown,
|
||||
} from "@uncaged/workflow-util";
|
||||
import { createLogger, getDefaultWorkflowStorageRoot, generateUlid } from "@uncaged/workflow-util";
|
||||
|
||||
const log = createLogger();
|
||||
log("4KNMR2PX", "Loading workflow...");
|
||||
|
||||
const root = getDefaultWorkflowStorageRoot();
|
||||
const threadId = generateUlid(Date.now());
|
||||
log("4KNMR2PX", "example");
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts
|
||||
├── base32.ts Crockford Base32 encode/decode
|
||||
├── ulid.ts ULID generation
|
||||
├── logger.ts Structured logger
|
||||
├── process-logger/ Process-level debug log files
|
||||
├── frontmatter-markdown/ Parse and validate agent frontmatter
|
||||
├── refs-field.ts Normalize refs arrays on CAS nodes
|
||||
├── result.ts ok / err helpers
|
||||
├── storage-root.ts Default ~/.uncaged/workflow paths
|
||||
├── env.ts Environment variable helper
|
||||
├── cli-reference.ts Markdown CLI reference generator
|
||||
└── types.ts LogFn, Result, logger options
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
`getDefaultWorkflowStorageRoot()` resolves to `~/.uncaged/workflow` unless overridden by environment (see `storage-root.ts`).
|
||||
|
||||
@@ -1,55 +0,0 @@
|
||||
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);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -15,7 +15,7 @@ uwf setup --provider <name> --base-url <url> \\
|
||||
## Workflow Commands
|
||||
|
||||
\`\`\`
|
||||
uwf workflow add <file> # register a workflow from YAML file
|
||||
uwf workflow put <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
|
||||
\`\`\`
|
||||
@@ -24,27 +24,20 @@ uwf workflow list # list all registered workflows
|
||||
|
||||
\`\`\`
|
||||
uwf thread start <workflow> -p <prompt> # create a thread (no execution)
|
||||
uwf thread exec <thread-id> # execute one moderator→agent→extract cycle
|
||||
uwf thread step <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 threads
|
||||
[--status <status>] # filter: idle, running, or completed
|
||||
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 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 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
|
||||
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
|
||||
\`\`\`
|
||||
|
||||
## CAS Commands
|
||||
@@ -85,9 +78,10 @@ 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 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.
|
||||
- **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.
|
||||
`;
|
||||
}
|
||||
|
||||
@@ -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 { extractUlidTimestamp, generateUlid } from "./ulid.js";
|
||||
export { generateUlid } from "./ulid.js";
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { decodeCrockfordBase32Bits, encodeCrockfordBase32Bits } from "./base32.js";
|
||||
import { encodeCrockfordBase32Bits } from "./base32.js";
|
||||
|
||||
const ULID_TIME_BITS = 48;
|
||||
const ULID_RANDOM_BITS = 80;
|
||||
@@ -26,19 +26,3 @@ 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);
|
||||
}
|
||||
|
||||
@@ -1,89 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# batch-solve.sh — solve multiple Gitea issues via solve-issue workflow
|
||||
#
|
||||
# Usage:
|
||||
# ./scripts/batch-solve.sh [--agent CMD] [--repo OWNER/REPO] [--count N] ISSUE_NUM...
|
||||
#
|
||||
# Examples:
|
||||
# ./scripts/batch-solve.sh 448 449
|
||||
# ./scripts/batch-solve.sh --agent "bun run $(pwd)/packages/workflow-agent-claude-code/src/cli.ts" 448 449
|
||||
# ./scripts/batch-solve.sh --repo uncaged/workflow --count 15 448 449
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
AGENT=""
|
||||
REPO="uncaged/workflow"
|
||||
COUNT=10
|
||||
ISSUES=()
|
||||
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--agent) AGENT="$2"; shift 2 ;;
|
||||
--repo) REPO="$2"; shift 2 ;;
|
||||
--count) COUNT="$2"; shift 2 ;;
|
||||
*) ISSUES+=("$1"); shift ;;
|
||||
esac
|
||||
done
|
||||
|
||||
if [[ ${#ISSUES[@]} -eq 0 ]]; then
|
||||
echo "Usage: $0 [--agent CMD] [--repo OWNER/REPO] [--count N] ISSUE_NUM..." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
AGENT_FLAG=""
|
||||
if [[ -n "$AGENT" ]]; then
|
||||
AGENT_FLAG="--agent $AGENT"
|
||||
fi
|
||||
|
||||
TOTAL=${#ISSUES[@]}
|
||||
PASSED=0
|
||||
FAILED=0
|
||||
RESULTS=()
|
||||
|
||||
echo "━━━ Batch solve: ${TOTAL} issues ━━━"
|
||||
echo ""
|
||||
|
||||
for i in "${!ISSUES[@]}"; do
|
||||
ISSUE="${ISSUES[$i]}"
|
||||
NUM=$((i + 1))
|
||||
echo "┌─── [$NUM/$TOTAL] Issue #${ISSUE} ───"
|
||||
|
||||
# Read issue title
|
||||
TITLE=$(tea issues "$ISSUE" -r "$REPO" 2>/dev/null | head -1 | sed 's/^# #[0-9]* //' | sed 's/ (.*//' || echo "unknown")
|
||||
echo "│ Title: $TITLE"
|
||||
|
||||
# Start thread
|
||||
PROMPT="Fix issue #${ISSUE} in ${REPO}. Read the issue first with 'tea issues ${ISSUE} -r ${REPO}' for full spec."
|
||||
THREAD_JSON=$(uwf thread start solve-issue -p "$PROMPT" 2>&1)
|
||||
THREAD_ID=$(echo "$THREAD_JSON" | python3 -c "import json,sys; print(json.load(sys.stdin)['thread'])")
|
||||
echo "│ Thread: $THREAD_ID"
|
||||
|
||||
# Run steps
|
||||
echo "│ Running (max $COUNT steps)..."
|
||||
# shellcheck disable=SC2086
|
||||
if STEP_OUTPUT=$(uwf thread step "$THREAD_ID" $AGENT_FLAG -c "$COUNT" 2>&1); then
|
||||
# Check if done
|
||||
LAST_DONE=$(echo "$STEP_OUTPUT" | python3 -c "import json,sys; lines=sys.stdin.read().strip(); data=json.loads(lines); print(data[-1].get('done', False))")
|
||||
if [[ "$LAST_DONE" == "True" ]]; then
|
||||
echo "│ ✅ Done!"
|
||||
PASSED=$((PASSED + 1))
|
||||
RESULTS+=("✅ #${ISSUE} — ${TITLE}")
|
||||
else
|
||||
echo "│ ⚠️ Ran out of steps (not done)"
|
||||
FAILED=$((FAILED + 1))
|
||||
RESULTS+=("⚠️ #${ISSUE} — ${TITLE} (incomplete)")
|
||||
fi
|
||||
else
|
||||
echo "│ ❌ Failed"
|
||||
FAILED=$((FAILED + 1))
|
||||
RESULTS+=("❌ #${ISSUE} — ${TITLE} (error)")
|
||||
fi
|
||||
|
||||
echo "└───"
|
||||
echo ""
|
||||
done
|
||||
|
||||
echo "━━━ Results: ${PASSED}/${TOTAL} passed, ${FAILED} failed ━━━"
|
||||
for R in "${RESULTS[@]}"; do
|
||||
echo " $R"
|
||||
done
|
||||
Reference in New Issue
Block a user