Compare commits
71 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 61be1c662a | |||
| 84e8d70da4 | |||
| 8976f4cf3b | |||
| 07730dd24c | |||
| 4eff4d2370 | |||
| 1d6da18b18 | |||
| c342ff3737 | |||
| 8fe26417cf | |||
| 990200230b | |||
| 4eaefd9974 | |||
| 1a685583bd | |||
| 19769efea6 | |||
| 7f64541c5b | |||
| 43a6600378 | |||
| 74e3f5434c | |||
| 220c9c5224 | |||
| cae59b589e | |||
| 703ac9dfcc | |||
| 2df8accf2f | |||
| b5cc0db17e | |||
| 6196e0974a | |||
| 410e9e6d9b | |||
| 84de74721d | |||
| 4403532f35 | |||
| e95e76c145 | |||
| af69e773a0 | |||
| 6488b7bbb4 | |||
| 15d39c96a7 | |||
| 30e4e99908 | |||
| a3c70a5041 | |||
| 12d58a8206 | |||
| c096f4d94e | |||
| 500401d93c | |||
| 43f466eb67 | |||
| fe829d9ae6 | |||
| f80535d742 | |||
| 0eab3b7001 | |||
| 37c5b89c98 | |||
| 0fdf19879a | |||
| f73bf1e313 | |||
| 8c4441bf6b | |||
| 341ff656dc | |||
| 4b44665c7e | |||
| 172e9b34cc | |||
| 96fc3e220a | |||
| 7926751b01 | |||
| 43e1f82303 | |||
| d472de1247 | |||
| 99a137422c | |||
| d351343aa8 | |||
| 2482fb7e62 | |||
| fa9163e462 | |||
| fce2bf7441 | |||
| c9cdfe37db | |||
| 45bb5af99a | |||
| c7b0beb6be | |||
| 79cf97e617 | |||
| 196562c82a | |||
| 267ca73a1b | |||
| aee71fd2e7 | |||
| 8ce1dd3cca | |||
| 4b27943871 | |||
| 8d5b97c67e | |||
| 513c006ce3 | |||
| 2cd2a7d713 | |||
| 94fa964b84 | |||
| 2c642b1a53 | |||
| c15a5554c0 | |||
| e38852a761 | |||
| fd8f1f2491 | |||
| 98b6153070 |
@@ -2,3 +2,4 @@ node_modules/
|
||||
dist/
|
||||
bun.lock
|
||||
*.tgz
|
||||
tsconfig.tsbuildinfo
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
[test]
|
||||
pathIgnorePatterns = ["dist/**"]
|
||||
@@ -0,0 +1,259 @@
|
||||
# @uncaged/workflow — Architecture
|
||||
|
||||
**Last updated:** 2026-05-06 by 小橘 🍊(NEKO Team)
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
A workflow engine that executes single-file ESM bundles. Each workflow is a self-contained `.esm.js` file identified by its XXH64 hash (Crockford Base32). No daemon — processes start on demand and exit when done.
|
||||
|
||||
## Package Structure
|
||||
|
||||
| Package | npm Name | Purpose |
|
||||
|---------|----------|---------|
|
||||
| `workflow` | `@uncaged/workflow` | Core: types, engine, ExtractFn, hash/ULID/registry |
|
||||
| `cli-workflow` | `@uncaged/cli-workflow` | CLI: `uncaged-workflow` command |
|
||||
| `workflow-agent-cursor` | `@uncaged/workflow-agent-cursor` | Cursor CLI agent (extracts workspace from ctx) |
|
||||
| `workflow-agent-hermes` | `@uncaged/workflow-agent-hermes` | Hermes CLI agent |
|
||||
| `workflow-agent-llm` | `@uncaged/workflow-agent-llm` | OpenAI-compatible LLM agent |
|
||||
| `workflow-role-planner` | `@uncaged/workflow-role-planner` | Pure data: phased planning prompt + schema |
|
||||
| `workflow-role-coder` | `@uncaged/workflow-role-coder` | Pure data: coding prompt + schema |
|
||||
| `workflow-role-reviewer` | `@uncaged/workflow-role-reviewer` | Pure data: code review prompt + schema |
|
||||
| `workflow-role-committer` | `@uncaged/workflow-role-committer` | Pure data: git commit prompt + schema |
|
||||
| `workflow-template-solve-issue` | `@uncaged/workflow-template-solve-issue` | Composes roles + moderator into a complete workflow |
|
||||
| `workflow-util-agent` | `@uncaged/workflow-util-agent` | `buildAgentPrompt` + `spawnCli` utilities |
|
||||
|
||||
Monorepo with **bun workspace**, `workspace:*` protocol.
|
||||
|
||||
## Core Types
|
||||
|
||||
```typescript
|
||||
// --- Sentinel values ---
|
||||
const START = "__start__";
|
||||
const END = "__end__";
|
||||
|
||||
// --- RoleMeta: maps role names → their meta types ---
|
||||
type RoleMeta = Record<string, Record<string, unknown>>;
|
||||
|
||||
// --- Role Definition: pure data, no execution logic ---
|
||||
type RoleDefinition<Meta> = {
|
||||
description: string; // human-readable
|
||||
systemPrompt: string; // given to agent
|
||||
extractPrompt: string; // given to extractor
|
||||
schema: z.ZodType<Meta>; // meta shape (Zod v4)
|
||||
};
|
||||
|
||||
// --- Workflow Definition: pure data, no agent binding ---
|
||||
type WorkflowDefinition<M extends RoleMeta> = {
|
||||
description: string;
|
||||
roles: { [K in keyof M & string]: RoleDefinition<M[K]> };
|
||||
moderator: Moderator<M>;
|
||||
};
|
||||
|
||||
// --- Agent: raw string output, reads role info from context ---
|
||||
type AgentFn = (ctx: AgentContext) => Promise<string>;
|
||||
|
||||
// --- Agent Binding: runtime assignment ---
|
||||
type AgentBinding = {
|
||||
agent: AgentFn;
|
||||
overrides?: Partial<Record<string, AgentFn>>;
|
||||
};
|
||||
|
||||
// --- Extract: structured data from context ---
|
||||
type ExtractFn = <T>(schema: z.ZodType<T>, prompt: string, ctx: ExtractContext) => Promise<T>;
|
||||
|
||||
// --- Moderator: pure routing function ---
|
||||
type Moderator<M extends RoleMeta> = (ctx: ModeratorContext<M>) => (keyof M & string) | typeof END;
|
||||
|
||||
// --- Composition ---
|
||||
// createWorkflow(def, binding, extract) => WorkflowFn
|
||||
```
|
||||
|
||||
## Three-Phase Engine Loop
|
||||
|
||||
Each role execution has three distinct phases with progressive context:
|
||||
|
||||
```
|
||||
┌─→ Phase 1: MODERATOR
|
||||
│ Context: ModeratorContext { threadId, start, steps }
|
||||
│ Action: moderator(ctx) → role name | END
|
||||
│
|
||||
│ Phase 2: AGENT
|
||||
│ Context: AgentContext = ModeratorCtx + { currentRole: { name, systemPrompt } }
|
||||
│ Action: agent(ctx) → raw string
|
||||
│
|
||||
│ Phase 3: EXTRACTOR
|
||||
│ Context: ExtractContext = AgentCtx + { agentContent }
|
||||
│ Action: extract(schema, extractPrompt, ctx) → typed meta
|
||||
│
|
||||
│ Merge: RoleStep { role, content, meta, timestamp }
|
||||
│ Append to steps
|
||||
└─────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### Context Types (progressive)
|
||||
|
||||
```typescript
|
||||
// Phase 1: Moderator sees accumulated state only
|
||||
type ModeratorContext<M> = {
|
||||
threadId: string;
|
||||
start: StartStep;
|
||||
steps: RoleStep<M>[];
|
||||
};
|
||||
|
||||
// Phase 2: Agent knows its identity
|
||||
type AgentContext<M> = ModeratorContext<M> & {
|
||||
currentRole: { name: string; systemPrompt: string };
|
||||
};
|
||||
|
||||
// Phase 3: Extractor has agent output
|
||||
type ExtractContext<M> = AgentContext<M> & {
|
||||
agentContent: string;
|
||||
};
|
||||
|
||||
// ThreadContext is an alias for AgentContext (backward compat)
|
||||
type ThreadContext<M> = AgentContext<M>;
|
||||
```
|
||||
|
||||
### Key Properties
|
||||
|
||||
- **Moderator is synchronous and pure** — no I/O, no state mutation
|
||||
- **Agent gets context, not instructions** — reads `ctx.currentRole.systemPrompt`
|
||||
- **Extractor is a general tool** — not limited to post-agent extraction; agents can use it too (e.g. Cursor agent extracts workspace path before execution)
|
||||
- **extractPrompt is a call parameter**, not context state — different callers use different prompts
|
||||
|
||||
## Agent Information Sources
|
||||
|
||||
An agent has exactly three information sources:
|
||||
|
||||
1. **Prior knowledge** — LLM training, agent memory, agent skills
|
||||
2. **Thread context** — `AgentContext` (start, steps, currentRole)
|
||||
3. **Derived information** — from 1 & 2 (e.g. tool calls, shell commands)
|
||||
|
||||
No hidden environment parameters. If an agent needs something (like a workspace path), it extracts it from context using `ExtractFn`.
|
||||
|
||||
## Bundle Contract
|
||||
|
||||
A workflow bundle is a single `.esm.js` file with two named exports:
|
||||
|
||||
```typescript
|
||||
// Named exports (no default export)
|
||||
export const descriptor: WorkflowDescriptor;
|
||||
export const run: WorkflowFn;
|
||||
|
||||
type WorkflowFn = (
|
||||
input: { prompt: string; steps: RoleOutput[] },
|
||||
options: { threadId: string; maxRounds: number },
|
||||
) => AsyncGenerator<RoleOutput, WorkflowResult>;
|
||||
```
|
||||
|
||||
### Constraints
|
||||
|
||||
- Single `.esm.js` file
|
||||
- No dynamic `import()`
|
||||
- All static imports must be Node built-in modules only
|
||||
- XXH64 hash (Crockford Base32) = globally unique version ID
|
||||
|
||||
### Why AsyncGenerator?
|
||||
|
||||
- Each `yield` → engine writes to `.data.jsonl`, checks abort/pause
|
||||
- `return` → engine marks thread complete
|
||||
- Fork = pass historical steps as `input.steps` to a new generator
|
||||
- Zero injection — bundle doesn't import from the engine
|
||||
|
||||
## Storage Layout
|
||||
|
||||
```
|
||||
~/.uncaged/workflow/
|
||||
├── bundles/
|
||||
│ ├── C9NMV6V2TQT81.esm.js # Crockford Base32 of XXH64
|
||||
│ └── C9NMV6V2TQT81.yaml # Role descriptor
|
||||
├── logs/ # One folder per bundle hash
|
||||
│ └── C9NMV6V2TQT81/
|
||||
│ ├── 01KQXKW…YG.data.jsonl # Thread state
|
||||
│ └── 01KQXKW…YG.info.jsonl # Debug log
|
||||
└── workflow.yaml # Registry
|
||||
```
|
||||
|
||||
### ID Encoding: Crockford Base32
|
||||
|
||||
- Case-insensitive, filesystem-safe, no ambiguous chars (0/O, 1/I/L)
|
||||
- Bundle hash: XXH64 → 13-char
|
||||
- Thread ID: ULID → 26-char (10 timestamp + 16 random)
|
||||
|
||||
### Registry (`workflow.yaml`)
|
||||
|
||||
```yaml
|
||||
workflows:
|
||||
solve-issue:
|
||||
hash: "C9NMV6V2TQT81"
|
||||
timestamp: 1714963200000
|
||||
history:
|
||||
- hash: "A7BKR3M1NPQ40"
|
||||
timestamp: 1714876800000
|
||||
```
|
||||
|
||||
### Thread JSONL
|
||||
|
||||
**`.data.jsonl`** — Line 1: start record, Line 2+: role outputs
|
||||
|
||||
```jsonc
|
||||
// Start record
|
||||
{ "name": "solve-issue", "hash": "C9NMV6V2TQT81", "threadId": "01KQXKW…",
|
||||
"parameters": { "prompt": "Fix bug #3", "options": { "maxRounds": 5 } },
|
||||
"timestamp": 1714963200000 }
|
||||
// Role output
|
||||
{ "role": "planner", "content": "...", "meta": { "phases": [...] }, "timestamp": ... }
|
||||
```
|
||||
|
||||
**`.info.jsonl`** — Structured debug log
|
||||
|
||||
```jsonc
|
||||
{ "tag": "4KNMR2PX", "content": "Loading bundle...", "timestamp": ... }
|
||||
```
|
||||
|
||||
Tags are 8-char Crockford Base32 (40-bit random), one per call site. `grep "4KNMR2PX"` → instant code location.
|
||||
|
||||
## Execution Model
|
||||
|
||||
- **No daemon.** `uncaged-workflow run <name>` starts a worker process
|
||||
- Same bundle's threads share one process (memory efficiency)
|
||||
- Process exits when all threads complete
|
||||
- Thread termination via IPC within the process
|
||||
|
||||
## CLI Commands
|
||||
|
||||
| Priority | Command | Description |
|
||||
|----------|---------|-------------|
|
||||
| P1 | `add <name> <file.esm.js>` | Register a bundle |
|
||||
| P1 | `list` | List registered workflows |
|
||||
| P1 | `show <name>` | Show workflow details |
|
||||
| P1 | `remove <name>` | Remove a workflow |
|
||||
| P1 | `run <name> [--prompt] [--max-rounds]` | Start a thread |
|
||||
| P1 | `threads [name]` | List threads |
|
||||
| P1 | `thread <id>` | Show thread state |
|
||||
| P1 | `thread rm <id>` | Delete a thread |
|
||||
| P1 | `ps` | List running threads |
|
||||
| P1 | `kill <thread-id>` | Terminate a running thread |
|
||||
| P2 | `history <name>` | Show version history |
|
||||
| P2 | `rollback <name> [hash]` | Switch to a previous version |
|
||||
| P2 | `pause <thread-id>` | Pause a running thread |
|
||||
| P2 | `resume <thread-id>` | Resume a paused thread |
|
||||
| P3 | `fork <thread-id> [--from-role <role>]` | Fork from historical state |
|
||||
|
||||
All commands implemented and tested. ✅
|
||||
|
||||
## Design Decisions
|
||||
|
||||
| Decision | Rationale |
|
||||
|----------|-----------|
|
||||
| **Role = pure data** | Decouples definition from execution; same role with different agents |
|
||||
| **Agent bound at runtime** | WorkflowDefinition is reusable; agent choice is deployment concern |
|
||||
| **Three-phase context** | Each phase sees only what it needs; clean separation |
|
||||
| **ExtractFn as general tool** | Agents use it for pre-execution extraction; engine uses it for meta |
|
||||
| **Single-file ESM** | Hash = version, no dependency hell, self-contained |
|
||||
| **No daemon** | OS handles process lifecycle; unnecessary complexity |
|
||||
| **Crockford Base32** | Filesystem-safe, readable, compact |
|
||||
| **No concurrency in registry** | Different workflows have different constraints; belongs at workflow/role level |
|
||||
| **No dryRun** | Tests use mock agents + mock fetch; simpler architecture |
|
||||
@@ -0,0 +1,315 @@
|
||||
# Workflow-as-Agent Implementation Plan
|
||||
|
||||
> **For Hermes:** Use subagent-driven-development skill to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Enable workflows to invoke other workflows as agents, backed by global CAS and refs tracking.
|
||||
|
||||
**Architecture:** Migrate CAS from thread-local to global (`~/.uncaged/workflow/cas/`), add `refs` to RoleStep for GC traceability, then build `workflowAsAgent(name)` factory that resolves workflow name → bundle via registry and spawns a child thread.
|
||||
|
||||
**Tech Stack:** TypeScript, Bun, Zod v4, monorepo with `packages/`
|
||||
|
||||
**Issue:** https://git.shazhou.work/uncaged/workflow/issues/25
|
||||
|
||||
---
|
||||
|
||||
## Phase 1: Global CAS Migration
|
||||
|
||||
Move CAS storage from `<threadDir>/<threadId>.cas/` to `~/.uncaged/workflow/cas/` (global, content-addressed, immutable). This is a **breaking change** — thread-local `.cas/` directories are abandoned.
|
||||
|
||||
### Task 1.1: Add `globalCasDir` helper to `storage-root.ts`
|
||||
|
||||
**Objective:** Provide a single function that returns the global CAS directory path.
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/workflow/src/storage-root.ts`
|
||||
- Test: `packages/workflow/__tests__/storage-root.test.ts`
|
||||
|
||||
**Implementation:**
|
||||
|
||||
```typescript
|
||||
// storage-root.ts — add export
|
||||
export function getGlobalCasDir(storageRoot?: string): string {
|
||||
const root = storageRoot ?? getDefaultWorkflowStorageRoot();
|
||||
return join(root, "cas");
|
||||
}
|
||||
```
|
||||
|
||||
Export from `packages/workflow/src/index.ts`.
|
||||
|
||||
### Task 1.2: Update `cmd-cas.ts` to use global CAS
|
||||
|
||||
**Objective:** CLI `cas get/put/list/rm` no longer needs threadId for storage location — CAS is global. But keep threadId in CLI for backward compat of planner/coder prompts (they pass threadId).
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/cli-workflow/src/cmd-cas.ts`
|
||||
|
||||
**Changes:**
|
||||
- `resolveCasDir` → use `getGlobalCasDir(storageRoot)` instead of deriving from thread data path
|
||||
- `cmdCasPut` / `cmdCasGet` / `cmdCasList` / `cmdCasRm`: threadId is still accepted (prompts pass it) but storage goes to global dir
|
||||
- Remove the `resolveThreadDataPath` dependency for CAS operations — thread doesn't need to exist to read CAS
|
||||
|
||||
```typescript
|
||||
import { createThreadCas, getGlobalCasDir } from "@uncaged/workflow";
|
||||
|
||||
export async function cmdCasGet(
|
||||
storageRoot: string,
|
||||
_threadId: string, // kept for CLI compat, not used for path
|
||||
hash: string,
|
||||
): Promise<Result<string, string>> {
|
||||
const cas = createThreadCas(getGlobalCasDir(storageRoot));
|
||||
const content = await cas.get(hash);
|
||||
if (content === null) {
|
||||
return err(`cas entry not found: ${hash}`);
|
||||
}
|
||||
return ok(content);
|
||||
}
|
||||
// ... same pattern for put/list/rm
|
||||
```
|
||||
|
||||
### Task 1.3: Update `cmd-thread.ts` — thread rm no longer deletes `.cas/`
|
||||
|
||||
**Objective:** Since CAS is global, `thread rm` should NOT delete CAS entries. CAS cleanup is GC's job.
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/cli-workflow/src/cmd-thread.ts`
|
||||
- Check: remove any `rmdir` / `unlink` of `<threadId>.cas/` directory
|
||||
|
||||
### Task 1.4: Rename `createThreadCas` → `createCasStore`
|
||||
|
||||
**Objective:** The name `createThreadCas` is misleading now. Rename to `createCasStore`.
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/workflow/src/cas.ts` — rename function
|
||||
- Modify: `packages/workflow/src/index.ts` — update export (keep `createThreadCas` as deprecated alias for one release)
|
||||
- Modify: all consumers (`cmd-cas.ts`)
|
||||
|
||||
### Task 1.5: Update tests
|
||||
|
||||
**Objective:** All CAS-related tests use global dir instead of thread-local.
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/cli-workflow/__tests__/commands.test.ts`
|
||||
- Verify: `bun test` passes
|
||||
|
||||
### Task 1.6: Clean up old thread-local `.cas/` references
|
||||
|
||||
**Objective:** Remove dead code that creates/reads thread-local `.cas/` directories.
|
||||
|
||||
**Files:**
|
||||
- Search all `*.ts` for `.cas` path construction patterns
|
||||
- Remove orphaned helpers
|
||||
|
||||
---
|
||||
|
||||
## Phase 2: RoleStep `refs` Tracking
|
||||
|
||||
Add `refs: string[]` to persisted role steps so GC can trace which CAS entries are alive.
|
||||
|
||||
### Task 2.1: Add `refs` to `RoleOutput` and engine persistence
|
||||
|
||||
**Objective:** Every role step can declare which CAS hashes it produced or consumed.
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/workflow/src/types.ts`
|
||||
- Modify: `packages/workflow/src/engine.ts`
|
||||
|
||||
**Changes to `types.ts`:**
|
||||
|
||||
```typescript
|
||||
export type RoleOutput = {
|
||||
role: string;
|
||||
content: string;
|
||||
meta: Record<string, unknown>;
|
||||
refs: string[]; // CAS hashes produced/consumed by this step
|
||||
};
|
||||
```
|
||||
|
||||
**Changes to `engine.ts`:**
|
||||
- `appendDataLine` for role steps: include `refs` field (default `[]` if not provided)
|
||||
|
||||
### Task 2.2: Auto-populate refs from meta hashes
|
||||
|
||||
**Objective:** The engine should automatically extract CAS hashes from `meta` to populate `refs`, so roles don't need to manually track them.
|
||||
|
||||
**Strategy:** After meta extraction, walk the meta object and collect any string that looks like a CAS hash (Crockford Base32, 13 chars). This is a heuristic but works because CAS hashes are distinctive.
|
||||
|
||||
Alternative (simpler): Let each `RoleDefinition` optionally declare a `extractRefs(meta: M) => string[]` function. For planner, this returns `meta.phases.map(p => p.hash)`. For coder, `[meta.completedPhase]`.
|
||||
|
||||
**Recommended:** The explicit `extractRefs` approach — no magic, no false positives.
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/workflow/src/types.ts` — add optional `extractRefs` to `RoleDefinition`
|
||||
- Modify: `packages/workflow/src/create-workflow.ts` — call `extractRefs` after meta extraction, set on `RoleOutput.refs`
|
||||
- Modify: `packages/workflow-role-planner/src/planner.ts` — implement `extractRefs`
|
||||
- Modify: `packages/workflow-role-coder/src/coder.ts` — implement `extractRefs`
|
||||
|
||||
```typescript
|
||||
// types.ts — RoleDefinition addition
|
||||
export type RoleDefinition<Meta extends Record<string, unknown>> = {
|
||||
description: string;
|
||||
systemPrompt: string;
|
||||
extractPrompt: string;
|
||||
schema: z.ZodType<Meta>;
|
||||
extractRefs?: (meta: Meta) => string[]; // CAS hashes to track
|
||||
};
|
||||
|
||||
// planner.ts
|
||||
extractRefs: (meta) => meta.phases.map(p => p.hash),
|
||||
|
||||
// coder.ts
|
||||
extractRefs: (meta) => [meta.completedPhase],
|
||||
```
|
||||
|
||||
### Task 2.3: Update fork logic to preserve refs
|
||||
|
||||
**Objective:** When forking a thread, `refs` from historical steps must be carried over.
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/workflow/src/fork-thread.ts`
|
||||
- Verify: `ForkHistoricalStep` / `PrefilledDiskStep` include `refs`
|
||||
|
||||
### Task 2.4: Tests for refs tracking
|
||||
|
||||
**Files:**
|
||||
- Add: `packages/workflow/__tests__/refs-tracking.test.ts`
|
||||
- Verify: refs appear in `.data.jsonl` output
|
||||
|
||||
---
|
||||
|
||||
## Phase 3: CAS Garbage Collection
|
||||
|
||||
### Task 3.1: Implement `gc.ts` in `@uncaged/workflow`
|
||||
|
||||
**Objective:** Mark-and-sweep GC — scan all thread `.data.jsonl` files, collect `refs`, delete orphaned CAS entries.
|
||||
|
||||
**Files:**
|
||||
- Create: `packages/workflow/src/gc.ts`
|
||||
- Export from: `packages/workflow/src/index.ts`
|
||||
|
||||
```typescript
|
||||
export type GcResult = {
|
||||
scannedThreads: number;
|
||||
activeRefs: number;
|
||||
deletedEntries: number;
|
||||
deletedHashes: string[];
|
||||
};
|
||||
|
||||
export async function garbageCollectCas(storageRoot: string): Promise<GcResult> {
|
||||
// 1. Find all .data.jsonl files under storageRoot
|
||||
// 2. Parse each, flatMap step.refs → Set<string>
|
||||
// 3. List all CAS entries via createCasStore(globalCasDir).list()
|
||||
// 4. Delete entries not in active set
|
||||
// 5. Return stats
|
||||
}
|
||||
```
|
||||
|
||||
### Task 3.2: Add `uncaged-workflow gc` CLI command
|
||||
|
||||
**Files:**
|
||||
- Create: `packages/cli-workflow/src/cmd-gc.ts`
|
||||
- Modify: `packages/cli-workflow/src/cli-dispatch.ts` — add `gc` subcommand
|
||||
|
||||
### Task 3.3: Run GC on `thread rm`
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/cli-workflow/src/cmd-thread.ts` — after deleting thread data, optionally run GC
|
||||
|
||||
### Task 3.4: Tests for GC
|
||||
|
||||
**Files:**
|
||||
- Create: `packages/cli-workflow/__tests__/gc-cli.test.ts`
|
||||
|
||||
---
|
||||
|
||||
## Phase 4: `workflowAsAgent` Factory
|
||||
|
||||
### Task 4.1: Create `workflowAsAgent` in `@uncaged/workflow`
|
||||
|
||||
**Objective:** Factory function that takes a workflow name, resolves to bundle, returns an `AgentFn`.
|
||||
|
||||
**Files:**
|
||||
- Create: `packages/workflow/src/workflow-as-agent.ts`
|
||||
- Export from: `packages/workflow/src/index.ts`
|
||||
|
||||
```typescript
|
||||
import type { AgentFn } from "./types.js";
|
||||
|
||||
export type WorkflowAsAgentOptions = {
|
||||
storageRoot?: string;
|
||||
};
|
||||
|
||||
export function workflowAsAgent(
|
||||
workflowName: string,
|
||||
options?: WorkflowAsAgentOptions,
|
||||
): AgentFn {
|
||||
return async (ctx) => {
|
||||
const storageRoot = options?.storageRoot ?? getDefaultWorkflowStorageRoot();
|
||||
|
||||
// 1. Read registry → resolve name to bundle hash + path
|
||||
const registry = await readWorkflowRegistry(storageRoot);
|
||||
const entry = getRegisteredWorkflow(registry, workflowName);
|
||||
if (entry === null) {
|
||||
return `ERROR: workflow "${workflowName}" not found in registry`;
|
||||
}
|
||||
|
||||
// 2. Load bundle
|
||||
const bundlePath = join(storageRoot, "bundles", `${entry.hash}.esm.js`);
|
||||
const bundleExports = await extractBundleExports(bundlePath);
|
||||
|
||||
// 3. Create child thread input from ctx.start.content (parent prompt)
|
||||
const input: ThreadInput = {
|
||||
prompt: ctx.start.content,
|
||||
steps: [],
|
||||
};
|
||||
|
||||
// 4. Generate child threadId
|
||||
const childThreadId = generateUlid();
|
||||
|
||||
// 5. Execute — collect all yields, return final content
|
||||
const io: ExecuteThreadIo = { ... };
|
||||
const result = await executeThread(bundleExports.run, workflowName, input, ...);
|
||||
|
||||
// 6. Return summary as agent content
|
||||
return result.summary;
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
### Task 4.2: System-level depth limit
|
||||
|
||||
**Objective:** Prevent infinite recursion. Track depth via thread metadata, enforce a global max (default 3, configurable in `workflow.yaml`).
|
||||
|
||||
**Files:**
|
||||
- Modify: `packages/workflow/src/types.ts` — add `depth` to `WorkflowFnOptions`
|
||||
- Modify: `packages/workflow/src/workflow-as-agent.ts` — increment depth, check limit
|
||||
- Modify: registry or config types for `maxDepth` setting
|
||||
|
||||
### Task 4.3: Tests for workflowAsAgent
|
||||
|
||||
**Files:**
|
||||
- Create: `packages/workflow/__tests__/workflow-as-agent.test.ts`
|
||||
- Test: name resolution, depth limit, child thread execution
|
||||
|
||||
### Task 4.4: Integration test — nested workflow
|
||||
|
||||
**Objective:** Create a minimal test workflow that calls another workflow via `workflowAsAgent`.
|
||||
|
||||
**Files:**
|
||||
- Create: `packages/workflow/__tests__/workflow-as-agent-integration.test.ts`
|
||||
|
||||
---
|
||||
|
||||
## Execution Order
|
||||
|
||||
```
|
||||
Phase 1 (Global CAS) → Phase 2 (refs) → Phase 3 (GC) → Phase 4 (workflowAsAgent)
|
||||
```
|
||||
|
||||
Each phase is independently mergeable. Phase 3 depends on Phase 2 (needs refs to know what's alive). Phase 4 depends on Phase 1 (global CAS for cross-thread sharing).
|
||||
|
||||
## Breaking Changes
|
||||
|
||||
- CAS storage location moves from `<thread>.cas/` to `~/.uncaged/workflow/cas/`
|
||||
- `RoleOutput` gains required `refs: string[]` field
|
||||
- Existing threads with thread-local CAS will lose access to old CAS data (acceptable — those are short-lived workflow artifacts)
|
||||
- `createThreadCas` renamed to `createCasStore` (alias kept temporarily)
|
||||
@@ -1,438 +0,0 @@
|
||||
# RFC-001: Workflow Engine Design
|
||||
|
||||
**Author:** 小橘 🍊(NEKO Team)
|
||||
**Date:** 2026-05-06
|
||||
**Status:** Draft
|
||||
|
||||
---
|
||||
|
||||
## 1. Package Structure
|
||||
|
||||
| Package | npm Name | Binary |
|
||||
|---------|----------|--------|
|
||||
| Core lib | `@uncaged/workflow` | — |
|
||||
| CLI | `@uncaged/cli-workflow` | `uncaged-workflow` |
|
||||
|
||||
Future: `@uncaged/cli` umbrella, invoke via `uncaged workflow <subcommand>`.
|
||||
|
||||
Monorepo uses **bun workspace**.
|
||||
|
||||
## 2. Workflow Physical Implementation
|
||||
|
||||
A **Workflow** is a single-file ESM module that **named-exports** an **AsyncGenerator** function as `run` and workflow metadata as `descriptor`:
|
||||
|
||||
```typescript
|
||||
/** What each yield produces — one role's output. */
|
||||
type RoleOutput = {
|
||||
role: string;
|
||||
content: string;
|
||||
meta: Record<string, unknown>;
|
||||
};
|
||||
|
||||
/** What the generator returns when done. */
|
||||
type WorkflowResult = {
|
||||
returnCode: number;
|
||||
summary: string;
|
||||
};
|
||||
|
||||
/** Input to a workflow — prompt + optional historical steps for fork/resume. */
|
||||
type ThreadInput = {
|
||||
prompt: string;
|
||||
steps: RoleOutput[]; // [] for new thread, pre-filled for fork/resume
|
||||
};
|
||||
|
||||
/** The bundle contract — an AsyncGenerator, not a Promise. */
|
||||
type WorkflowFn = (
|
||||
input: ThreadInput,
|
||||
options: { isDryRun: boolean; maxRounds: number }
|
||||
) => AsyncGenerator<RoleOutput, WorkflowResult>;
|
||||
```
|
||||
|
||||
### Why AsyncGenerator?
|
||||
|
||||
The workflow **yields** each role output instead of writing to an injected writer or
|
||||
exporting a framework-specific shape:
|
||||
|
||||
```typescript
|
||||
// Example bundle — zero framework dependency (named exports only)
|
||||
export const descriptor = {
|
||||
description: "Fix auth bug",
|
||||
roles: {
|
||||
planner: {
|
||||
description: "Plans the fix",
|
||||
schema: { type: "object", properties: { files: { type: "array", items: { type: "string" } } } },
|
||||
},
|
||||
coder: {
|
||||
description: "Implements the plan",
|
||||
schema: { type: "object", properties: { diff: { type: "string" } } },
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
export const run = async function* (input, options) {
|
||||
const plan = await callLLM("plan: " + input.prompt);
|
||||
yield { role: "planner", content: plan, meta: { files: ["src/auth.ts"] } };
|
||||
|
||||
const code = await callLLM("implement: " + plan);
|
||||
yield { role: "coder", content: code, meta: { diff: "..." } };
|
||||
|
||||
return { returnCode: 0, summary: "Fixed auth bug" };
|
||||
};
|
||||
```
|
||||
|
||||
**Engine controls the loop**, not the bundle:
|
||||
- Each `yield` → engine writes to `.data.jsonl`, checks `AbortSignal`, handles pause/resume
|
||||
- `return` → engine writes the final result, marks thread complete
|
||||
- **Fork** = read historical steps from `.data.jsonl`, pass as `input.steps` to a new generator
|
||||
- **Zero injection** — the bundle doesn't import or receive anything from the engine
|
||||
|
||||
### Fork/Resume via ThreadInput
|
||||
|
||||
When using the `createRoleModerator` helper, fork is **naturally handled**:
|
||||
|
||||
```typescript
|
||||
// The moderator receives ThreadContext with historical steps
|
||||
// It sees planner already ran → routes to coder automatically
|
||||
const gen = workflow(
|
||||
{ prompt: "fix bug #3", steps: [{ role: "planner", content: "...", meta: {} }] },
|
||||
{ isDryRun: false, maxRounds: 10 }
|
||||
);
|
||||
// First yield will be coder's output, not planner's
|
||||
```
|
||||
|
||||
No special replay logic needed — the moderator/role pattern inherently supports
|
||||
resuming from any snapshot, because moderator routing is a pure function of the
|
||||
accumulated steps.
|
||||
|
||||
This follows the **Dependency Inversion Principle**: the engine depends on the
|
||||
generator protocol (a language primitive), not on a framework-specific `WorkflowDefinition`.
|
||||
Bundles remain pure functions with no coupling to `@uncaged/workflow`.
|
||||
|
||||
### Relationship to Role/Moderator Pattern
|
||||
|
||||
The Role + Moderator pattern from Section 8 is one **implementation strategy** inside a
|
||||
bundle, not the bundle contract itself. A helper like `createRoleModerator(roles, moderator)`
|
||||
can produce the AsyncGenerator internally, but simple workflows can yield directly without
|
||||
any framework types.
|
||||
|
||||
### Constraints
|
||||
|
||||
- Single `.esm.js` file
|
||||
- Named exports `run` (callable AsyncGenerator workflow) and `descriptor` (metadata object)
|
||||
- No default export
|
||||
- No dynamic `import()`
|
||||
- All static imports must be Node built-in modules only
|
||||
|
||||
This guarantees the file is self-contained, and its **XXH64 hash** (encoded as Crockford Base32) serves as a globally unique version identifier.
|
||||
|
||||
### Role Descriptor (`export const descriptor`)
|
||||
|
||||
The bundle **must** export a `descriptor` object describing roles for tooling/agent consumption.
|
||||
|
||||
Shape: `{ description: string, roles: Record<string, { description: string, schema: JSONSchema }> }`
|
||||
|
||||
When you register a bundle via `uncaged-workflow add`, the engine imports the module, validates `descriptor`, and writes `{hash}.yaml` next to `{hash}.esm.js` under `bundles/` (same serialized shape as below):
|
||||
|
||||
```yaml
|
||||
description: "Workflow brief introduction"
|
||||
roles:
|
||||
planner:
|
||||
description: "Analyzes the issue and creates a plan"
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
plan:
|
||||
type: string
|
||||
files:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
coder:
|
||||
description: "Implements the plan"
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
diff:
|
||||
type: string
|
||||
```
|
||||
|
||||
Execution uses `run` only; YAML is for tooling and introspection.
|
||||
|
||||
## 3. Storage Layout
|
||||
|
||||
All data lives under `~/.uncaged/workflow/`:
|
||||
|
||||
```
|
||||
~/.uncaged/workflow/
|
||||
├── bundles/ # ESM bundles
|
||||
│ ├── C9NMV6V2TQT81.esm.js # Crockford Base32 of XXH64 hash
|
||||
│ └── C9NMV6V2TQT81.yaml # Role descriptor (from bundle export, at register time)
|
||||
├── logs/ # Thread data, one folder per bundle hash
|
||||
│ └── C9NMV6V2TQT81/
|
||||
│ ├── 01KQXKW18CT8G75T53R8F4G7YG.data.jsonl
|
||||
│ └── 01KQXKW18CT8G75T53R8F4G7YG.info.jsonl
|
||||
└── workflow.yaml # Registry
|
||||
```
|
||||
|
||||
**Not** a git repo. **Not** an npm package. Bundles are self-contained single files.
|
||||
|
||||
### ID Encoding
|
||||
|
||||
All IDs use **Crockford Base32**:
|
||||
- Better readability than Base64
|
||||
- Higher density than hex (shorter filenames)
|
||||
- ULID: 10 chars timestamp (high 2 bits zero-padded for future use) + 16 chars random
|
||||
|
||||
## 4. Registry (`workflow.yaml`)
|
||||
|
||||
```yaml
|
||||
workflows:
|
||||
solve-issue:
|
||||
hash: "C9NMV6V2TQT81"
|
||||
timestamp: 1714963200000
|
||||
history:
|
||||
- hash: "A7BKR3M1NPQ40"
|
||||
timestamp: 1714876800000
|
||||
- hash: "X2FGH8J4KLM56"
|
||||
timestamp: 1714790400000
|
||||
```
|
||||
|
||||
Type:
|
||||
|
||||
```typescript
|
||||
{
|
||||
workflows: Record<string, {
|
||||
hash: string; // Crockford Base32 of current XXH64
|
||||
timestamp: number;
|
||||
history: { hash: string; timestamp: number }[];
|
||||
}>
|
||||
}
|
||||
```
|
||||
|
||||
No concurrency control or timeout settings in the registry — those belong to each workflow/role/adapter.
|
||||
|
||||
## 5. Thread JSONL Format
|
||||
|
||||
### `.data.jsonl` — Thread State
|
||||
|
||||
**Line 1: Start record**
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"name": "solve-issue",
|
||||
"hash": "C9NMV6V2TQT81",
|
||||
"threadId": "01KQXKW18CT8G75T53R8F4G7YG",
|
||||
"parameters": {
|
||||
"prompt": "Fix the login redirect bug in #3",
|
||||
"options": {
|
||||
"isDryRun": false,
|
||||
"maxRounds": 5
|
||||
}
|
||||
},
|
||||
"timestamp": 1714963200000
|
||||
}
|
||||
```
|
||||
|
||||
**Line 2+: Role outputs**
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"role": "planner",
|
||||
"content": "Plan: modify auth middleware...",
|
||||
"meta": { "plan": "...", "files": ["src/auth.ts"] },
|
||||
"timestamp": 1714963201000
|
||||
}
|
||||
```
|
||||
|
||||
### `.info.jsonl` — Debug Log
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"tag": "4KNMR2PX", // 40-bit random, Crockford Base32 (8 chars)
|
||||
"content": "Loading workflow bundle...",
|
||||
"timestamp": 1714963200500
|
||||
}
|
||||
```
|
||||
|
||||
## 6. Execution Model
|
||||
|
||||
- **No daemon.** `uncaged-workflow run <name>` starts a worker process.
|
||||
- Same bundle's threads share one process (memory efficiency).
|
||||
- Process exits automatically when all threads complete.
|
||||
- Thread termination requires **IPC** within the process (not just kill PID).
|
||||
|
||||
## 7. CLI Requirements
|
||||
|
||||
### P1 (Must Have)
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uncaged-workflow add <name> <file.esm.js> [--types <path>]` | Register a compiled `.esm.js` bundle (descriptor extracted from `export const descriptor`) |
|
||||
| `uncaged-workflow list` | List registered workflows |
|
||||
| `uncaged-workflow show <name>` | Show workflow details |
|
||||
| `uncaged-workflow remove <name>` | Remove a workflow |
|
||||
| `uncaged-workflow run <name> [--prompt] [--dry-run] [--max-rounds]` | Start a thread |
|
||||
| `uncaged-workflow threads [name]` | List threads (optionally filter by workflow) |
|
||||
| `uncaged-workflow thread <id>` | Show thread state |
|
||||
| `uncaged-workflow thread rm <id>` | Delete a thread |
|
||||
| `uncaged-workflow ps` | List running threads |
|
||||
| `uncaged-workflow kill <thread-id>` | Terminate a running thread (via IPC) |
|
||||
|
||||
### P2 (Should Have)
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uncaged-workflow history <name>` | Show version history |
|
||||
| `uncaged-workflow rollback <name> [hash]` | Switch to a previous version |
|
||||
| `uncaged-workflow pause <thread-id>` | Pause a running thread |
|
||||
| `uncaged-workflow resume <thread-id>` | Resume a paused thread |
|
||||
|
||||
### P3 (Nice to Have)
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uncaged-workflow fork <thread-id> [--from-role <role>]` | Fork from a historical thread state |
|
||||
|
||||
## 8. Role/Moderator Pattern (Helper, Not Contract)
|
||||
|
||||
The bundle contract is the AsyncGenerator from Section 2. The Role + Moderator pattern
|
||||
below is a **convenience helper** for the common case of multi-role workflows with a
|
||||
routing function. It lives in `@uncaged/workflow` as an optional utility.
|
||||
|
||||
### Helper Function
|
||||
|
||||
```typescript
|
||||
function createRoleModerator<M extends RoleMeta>(
|
||||
def: { roles: { [K in keyof M & string]: Role<M[K]> }; moderator: Moderator<M> }
|
||||
): WorkflowFn; // returns (input: ThreadInput, options) => AsyncGenerator
|
||||
```
|
||||
|
||||
Usage in a bundle:
|
||||
|
||||
```typescript
|
||||
import { createRoleModerator, END } from "@uncaged/workflow";
|
||||
|
||||
export const descriptor = {
|
||||
description: "Example multi-role workflow",
|
||||
roles: {
|
||||
planner: { description: "Plans work", schema: {} },
|
||||
coder: { description: "Writes code", schema: {} },
|
||||
},
|
||||
};
|
||||
|
||||
export const run = createRoleModerator({
|
||||
roles: { planner, coder },
|
||||
moderator(ctx) { return ctx.steps.length === 0 ? "planner" : END; },
|
||||
});
|
||||
// Accepts ThreadInput — fork with pre-filled steps works automatically
|
||||
```
|
||||
|
||||
### Supporting Types
|
||||
|
||||
```typescript
|
||||
/** Sentinel values for automaton control flow. */
|
||||
const START = "__start__" as const;
|
||||
const END = "__end__" as const;
|
||||
|
||||
/** Maps role names → their meta types. Single generic drives all inference. */
|
||||
type RoleMeta = Record<string, Record<string, unknown>>;
|
||||
|
||||
/** Typed output of a Role execution. */
|
||||
type RoleResult<Meta> = { content: string; meta: Meta };
|
||||
|
||||
/** Engine start frame: initial prompt + thread identity. */
|
||||
type StartStep = {
|
||||
role: START;
|
||||
content: string; // the user prompt
|
||||
meta: { maxRounds: number; threadId: string };
|
||||
timestamp: number;
|
||||
};
|
||||
|
||||
/** A completed role step in the thread. */
|
||||
type RoleStep<M extends RoleMeta> = {
|
||||
[K in keyof M & string]: { role: K; meta: M[K]; content: string; timestamp: number };
|
||||
}[keyof M & string];
|
||||
|
||||
/** Thread-scoped context passed to roles and moderator. */
|
||||
type ThreadContext<M extends RoleMeta = RoleMeta> = {
|
||||
threadId: string;
|
||||
start: StartStep;
|
||||
steps: RoleStep<M>[];
|
||||
};
|
||||
|
||||
/**
|
||||
* A Role — receives full thread context, returns typed content + meta.
|
||||
* Implementation can be an agent, LLM call, script, HTTP request, etc.
|
||||
*/
|
||||
type Role<Meta> = (ctx: ThreadContext) => Promise<RoleResult<Meta>>;
|
||||
|
||||
/**
|
||||
* An Agent — raw string output interface for LLM/CLI adapters.
|
||||
* Structured meta is extracted by the role's extract layer.
|
||||
*/
|
||||
type AgentFn = (ctx: ThreadContext, systemPrompt: string) => Promise<string>;
|
||||
|
||||
/**
|
||||
* The Moderator — a pure routing function.
|
||||
* Receives the full thread context (start + all prior steps).
|
||||
* On initial call, `steps` is empty.
|
||||
* Returns the next role name or END to terminate.
|
||||
*/
|
||||
type Moderator<M extends RoleMeta> = (ctx: ThreadContext<M>) => (keyof M & string) | END;
|
||||
|
||||
/** Complete workflow definition as authored by users. */
|
||||
type WorkflowDefinition<M extends RoleMeta> = {
|
||||
name: string;
|
||||
roles: { [K in keyof M & string]: Role<M[K]> };
|
||||
moderator: Moderator<M>;
|
||||
};
|
||||
```
|
||||
|
||||
### Execution Flow (when using createRoleModerator)
|
||||
|
||||
```
|
||||
START (prompt) → Moderator → Role A → Moderator → Role B → ... → Moderator → END
|
||||
```
|
||||
|
||||
1. Engine creates a `StartStep` with the user prompt and maxRounds
|
||||
2. Moderator is called with `steps = []`, returns the first role name
|
||||
3. Role executes, appends a `RoleStep` to the thread
|
||||
4. Moderator is called again with updated steps, returns next role or END
|
||||
5. Repeat until END or maxRounds reached
|
||||
|
||||
### Responsibilities
|
||||
|
||||
| Component | Responsibility | Purity |
|
||||
|-----------|---------------|--------|
|
||||
| **Moderator** | Route to next role based on thread state | Pure function, no side effects |
|
||||
| **Role** | Execute a step (call LLM, run script, etc.) | Async, may have side effects |
|
||||
| **AgentFn** | Low-level LLM/CLI invocation adapter | Async, side effects |
|
||||
|
||||
### Key Constraints
|
||||
|
||||
- Moderator is **synchronous and pure** — no I/O, no state mutation
|
||||
- Roles receive the **full thread context** (not just the last message)
|
||||
- Round count = `steps.length`; max rounds in `start.meta.maxRounds`
|
||||
- The `meta` field on each step is **typed per role** via the `RoleMeta` generic
|
||||
|
||||
## 9. Design Decisions & Rationale
|
||||
|
||||
### Why single-file ESM?
|
||||
- Hash = version. No ambiguity.
|
||||
- No dependency hell. Self-contained.
|
||||
- Simple to distribute, store, and verify.
|
||||
|
||||
### Why no daemon?
|
||||
- Unnecessary complexity for process-per-bundle model.
|
||||
- OS process management (systemd, etc.) handles restarts.
|
||||
- IPC within process handles thread lifecycle.
|
||||
|
||||
### Why Crockford Base32?
|
||||
- Case-insensitive, filesystem-safe.
|
||||
- No ambiguous characters (0/O, 1/I/L).
|
||||
- More compact than hex (13 chars for 64-bit vs 16).
|
||||
|
||||
### Why not control concurrency in registry?
|
||||
- Different workflows have different constraints.
|
||||
- Same workflow may allow cross-project concurrency but not intra-project.
|
||||
- Concurrency belongs at workflow/role/adapter level.
|
||||
+31
-9
@@ -1,9 +1,14 @@
|
||||
import { createRoleModerator, END, type Role } from "@uncaged/workflow";
|
||||
import { createExtract, createWorkflow, END, type RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
type Roles = {
|
||||
greeter: { greeting: string };
|
||||
};
|
||||
|
||||
const greeterMetaSchema = z.object({
|
||||
greeting: z.string(),
|
||||
});
|
||||
|
||||
export const descriptor = {
|
||||
description: "A simple hello world workflow",
|
||||
roles: {
|
||||
@@ -18,14 +23,31 @@ export const descriptor = {
|
||||
},
|
||||
};
|
||||
|
||||
const greeter: Role<Roles["greeter"]> = async (ctx) => ({
|
||||
content: `Hello, ${ctx.start.content}`,
|
||||
meta: { greeting: "Hello!" },
|
||||
const greeter: RoleDefinition<Roles["greeter"]> = {
|
||||
description: "Generates a greeting",
|
||||
systemPrompt: "You greet the user briefly.",
|
||||
extractPrompt: "Extract the greeting string produced for the user.",
|
||||
schema: greeterMetaSchema,
|
||||
extractRefs: null,
|
||||
extractMode: "single",
|
||||
};
|
||||
|
||||
const extract = createExtract({
|
||||
baseUrl: "http://127.0.0.1:9",
|
||||
apiKey: "",
|
||||
model: "",
|
||||
});
|
||||
|
||||
export const run = createRoleModerator<Roles>({
|
||||
roles: { greeter },
|
||||
moderator(ctx) {
|
||||
return ctx.steps.length === 0 ? "greeter" : END;
|
||||
export const run = createWorkflow<Roles>(
|
||||
{
|
||||
roles: { greeter },
|
||||
moderator(ctx) {
|
||||
return ctx.steps.length === 0 ? "greeter" : END;
|
||||
},
|
||||
},
|
||||
});
|
||||
{
|
||||
agent: async (ctx) => `Hello, ${ctx.start.content}`,
|
||||
},
|
||||
extract,
|
||||
null,
|
||||
);
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*"
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
+5
-2
@@ -7,11 +7,14 @@
|
||||
],
|
||||
"scripts": {
|
||||
"build": "bun run --filter '*' build",
|
||||
"check": "biome check .",
|
||||
"check": "bunx tsc --build && biome check .",
|
||||
"typecheck": "bunx tsc --build",
|
||||
"format": "biome format --write .",
|
||||
"test": "bun run --filter '*' test"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@biomejs/biome": "^2.4.14"
|
||||
"@biomejs/biome": "^2.4.14",
|
||||
"@types/xxhashjs": "^0.2.4",
|
||||
"bun-types": "^1.3.13"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -3,8 +3,9 @@ import { mkdir, mkdtemp, readFile, rm, unlink, writeFile } from "node:fs/promise
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { getRegisteredWorkflow, readWorkflowRegistry } from "@uncaged/workflow";
|
||||
import { getGlobalCasDir, getRegisteredWorkflow, readWorkflowRegistry } from "@uncaged/workflow";
|
||||
import { cmdAdd } from "../src/cmd-add.js";
|
||||
import { cmdCasGet, cmdCasList, cmdCasPut, cmdCasRm } from "../src/cmd-cas.js";
|
||||
import { cmdHistory } from "../src/cmd-history.js";
|
||||
import { cmdList, formatListLines } from "../src/cmd-list.js";
|
||||
import { cmdRemove } from "../src/cmd-remove.js";
|
||||
@@ -15,6 +16,9 @@ import { addCliArgs } from "./bundle-fixture.js";
|
||||
const fixtureDescriptor = `export const descriptor = { description: "fixture", roles: {} };
|
||||
`;
|
||||
|
||||
const wfPutImport = `import { putContentMerkleNode } from "@uncaged/workflow";
|
||||
`;
|
||||
|
||||
describe("cli workflow commands", () => {
|
||||
let prevEnv: string | undefined;
|
||||
let storageRoot: string;
|
||||
@@ -40,11 +44,13 @@ describe("cli workflow commands", () => {
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}import fs from "node:fs";
|
||||
`${fixtureDescriptor}${wfPutImport}import fs from "node:fs";
|
||||
|
||||
export const run = async function* (input) {
|
||||
export const run = async function* (input, options) {
|
||||
fs.existsSync(".");
|
||||
yield { role: "noop", content: input.prompt, meta: { done: true } };
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, input.prompt);
|
||||
yield { role: "noop", contentHash: h, meta: { done: true }, refs: [h] };
|
||||
return { returnCode: 0, summary: "done" };
|
||||
}
|
||||
`,
|
||||
@@ -111,8 +117,8 @@ export const run = async function* (input) { return { returnCode: 0, summary: in
|
||||
const bundlePath = join(storageRoot, "solo.esm.js");
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`export const run = async function* (input) {
|
||||
yield { role: "x", content: input.prompt, meta: {} };
|
||||
`export const run = async function* () {
|
||||
yield { role: "x", contentHash: "STUBHASH00000000000000001", meta: {}, refs: [] };
|
||||
return { returnCode: 0, summary: "ok" };
|
||||
}
|
||||
`,
|
||||
@@ -140,8 +146,11 @@ export const run = async function* (input) { return { returnCode: 0, summary: in
|
||||
},
|
||||
},
|
||||
};
|
||||
export const run = async function* (input) {
|
||||
yield { role: "greeter", content: input.prompt, meta: { greeting: "hi" } };
|
||||
${wfPutImport}
|
||||
export const run = async function* (input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, input.prompt);
|
||||
yield { role: "greeter", contentHash: h, meta: { greeting: "hi" }, refs: [h] };
|
||||
return { returnCode: 0, summary: "ok" };
|
||||
};
|
||||
`,
|
||||
@@ -179,8 +188,10 @@ export const run = async function* (input) {
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "x", meta: {} };
|
||||
`${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "x");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "x" };
|
||||
}
|
||||
`,
|
||||
@@ -208,8 +219,10 @@ export const run = async function* (input) {
|
||||
const dtsPath = join(bundleDir, "types.d.ts");
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "x", meta: {} };
|
||||
`${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "x");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "x" };
|
||||
}
|
||||
`,
|
||||
@@ -239,8 +252,10 @@ export const run = async function* (input) {
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "x", meta: {} };
|
||||
`${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "x");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "x" };
|
||||
}
|
||||
`,
|
||||
@@ -260,13 +275,17 @@ export const run = async function* (input) {
|
||||
const bundleDir = join(storageRoot, "src");
|
||||
await mkdir(bundleDir, { recursive: true });
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
const v1 = `${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "v1", meta: {} };
|
||||
const v1 = `${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "v1");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "v1" };
|
||||
}
|
||||
`;
|
||||
const v2 = `${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "v2", meta: {} };
|
||||
const v2 = `${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "v2");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "v2" };
|
||||
}
|
||||
`;
|
||||
@@ -298,13 +317,17 @@ export const run = async function* (input) {
|
||||
const bundleDir = join(storageRoot, "src");
|
||||
await mkdir(bundleDir, { recursive: true });
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
const v1 = `${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "v1", meta: {} };
|
||||
const v1 = `${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "v1");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "v1" };
|
||||
}
|
||||
`;
|
||||
const v2 = `${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "v2", meta: {} };
|
||||
const v2 = `${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "v2");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "v2" };
|
||||
}
|
||||
`;
|
||||
@@ -346,8 +369,10 @@ export const run = async function* (input) {
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "x", meta: {} };
|
||||
`${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "x");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "x" };
|
||||
}
|
||||
`,
|
||||
@@ -357,8 +382,10 @@ export const run = async function* (input) {
|
||||
expect(add1.ok).toBe(true);
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "y", meta: {} };
|
||||
`${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "y");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "y" };
|
||||
}
|
||||
`,
|
||||
@@ -371,14 +398,47 @@ export const run = async function* (input) {
|
||||
expect(bad.ok).toBe(false);
|
||||
});
|
||||
|
||||
test("cas put/get/list/rm use global cas dir (thread id not required for storage)", async () => {
|
||||
const put = await cmdCasPut(storageRoot, "nonexistent-thread-id", "phase doc");
|
||||
expect(put.ok).toBe(true);
|
||||
if (!put.ok) {
|
||||
return;
|
||||
}
|
||||
const hash = put.value;
|
||||
const blobPath = join(getGlobalCasDir(storageRoot), `${hash}.txt`);
|
||||
expect(await readFile(blobPath, "utf8")).toBe("phase doc");
|
||||
|
||||
const got = await cmdCasGet(storageRoot, "other-thread", hash);
|
||||
expect(got.ok).toBe(true);
|
||||
if (!got.ok) {
|
||||
return;
|
||||
}
|
||||
expect(got.value).toBe("phase doc");
|
||||
|
||||
const listed = await cmdCasList(storageRoot, "another-thread");
|
||||
expect(listed.ok).toBe(true);
|
||||
if (!listed.ok) {
|
||||
return;
|
||||
}
|
||||
expect(listed.value).toContain(hash);
|
||||
|
||||
const removed = await cmdCasRm(storageRoot, "rm-thread", hash);
|
||||
expect(removed.ok).toBe(true);
|
||||
|
||||
const missing = await cmdCasGet(storageRoot, "after-rm", hash);
|
||||
expect(missing.ok).toBe(false);
|
||||
});
|
||||
|
||||
test("rollback rejects missing bundle file for target hash", async () => {
|
||||
const bundleDir = join(storageRoot, "src");
|
||||
await mkdir(bundleDir, { recursive: true });
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "x", meta: {} };
|
||||
`${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "x");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "x" };
|
||||
}
|
||||
`,
|
||||
@@ -392,8 +452,10 @@ export const run = async function* (input) {
|
||||
const hash1 = add1.value.hash;
|
||||
await writeFile(
|
||||
bundlePath,
|
||||
`${fixtureDescriptor}export const run = async function* (input) {
|
||||
yield { role: "a", content: "y", meta: {} };
|
||||
`${fixtureDescriptor}${wfPutImport}export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "y");
|
||||
yield { role: "a", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "y" };
|
||||
}
|
||||
`,
|
||||
|
||||
+4
@@ -0,0 +1,4 @@
|
||||
{"name":"demo-live","hash":"C9NMV6V2TQT81","threadId":"01LIVECMPLT01DDDDDDDDDDDDG","parameters":{"prompt":"hello","options":{"maxRounds":5,"depth":0}},"timestamp":1714963400000}
|
||||
{"role":"planner","contentHash":"FF7YQ5W3S2EV6","meta":{"phase":"plan","flags":[1,2]},"refs":[],"timestamp":1714963201000}
|
||||
{"role":"coder","contentHash":"EN34XX1W4WAFJ","meta":{},"refs":[],"timestamp":1714963202000}
|
||||
{"returnCode":0,"summary":"fixture completed"}
|
||||
+2
@@ -0,0 +1,2 @@
|
||||
{"tag":"DEBUGTAG1","content":"bundle loaded","timestamp":1714963400050}
|
||||
{"tag":"DEBUGTAG2","content":"multi\nline","timestamp":1714963400500}
|
||||
+2
@@ -0,0 +1,2 @@
|
||||
{"name":"demo-live","hash":"C9NMV6V2TQT81","threadId":"01LIVEINFLY01DDDDDDDDDDDDG","parameters":{"prompt":"hello","options":{"maxRounds":5,"depth":0}},"timestamp":1714963200000}
|
||||
{"role":"planner","contentHash":"P6M9FHE1GSBN0","meta":{"x":1},"refs":[],"timestamp":1714963201000}
|
||||
+2
@@ -0,0 +1,2 @@
|
||||
{"name":"demo-live-old","hash":"C9NMV6V2TQT81","threadId":"01LIVEOLDER01DDDDDDDDDDDDG","parameters":{"prompt":"old","options":{"maxRounds":5,"depth":0}},"timestamp":1714963000000}
|
||||
{"returnCode":0,"summary":"older thread"}
|
||||
@@ -2,6 +2,7 @@ import { afterEach, beforeEach, describe, expect, test } from "bun:test";
|
||||
import { mkdir, mkdtemp, readFile, rm, writeFile } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { createCasStore, getContentMerklePayload, getGlobalCasDir } from "@uncaged/workflow";
|
||||
import { cmdAdd } from "../src/cmd-add.js";
|
||||
import { cmdFork } from "../src/cmd-fork.js";
|
||||
import { cmdRun } from "../src/cmd-run.js";
|
||||
@@ -9,7 +10,9 @@ import { pathExists } from "../src/fs-utils.js";
|
||||
import { addCliArgs } from "./bundle-fixture.js";
|
||||
|
||||
/** Three-role workflow that respects `input.steps` for fork/resume. */
|
||||
const threeRoleBundleSource = `export const descriptor = {
|
||||
const threeRoleBundleSource = `import { putContentMerkleNode } from "@uncaged/workflow";
|
||||
|
||||
export const descriptor = {
|
||||
description: "fork-cli",
|
||||
roles: {
|
||||
planner: { description: "planner", schema: {} },
|
||||
@@ -17,20 +20,21 @@ const threeRoleBundleSource = `export const descriptor = {
|
||||
reviewer: { description: "reviewer", schema: {} },
|
||||
},
|
||||
};
|
||||
export const run = async function* (input) {
|
||||
export const run = async function* (input, options) {
|
||||
const cas = options.cas;
|
||||
const has = (r) => input.steps.some((s) => s.role === r);
|
||||
if (!has("planner")) {
|
||||
yield { role: "planner", content: "p1", meta: { k: "planner" } };
|
||||
const h = await putContentMerkleNode(cas, "p1");
|
||||
yield { role: "planner", contentHash: h, meta: { k: "planner" }, refs: [h] };
|
||||
}
|
||||
if (!has("coder")) {
|
||||
yield { role: "coder", content: "c1", meta: { k: "coder" } };
|
||||
const h = await putContentMerkleNode(cas, "c1");
|
||||
yield { role: "coder", contentHash: h, meta: { k: "coder" }, refs: [h] };
|
||||
}
|
||||
if (!has("reviewer")) {
|
||||
yield {
|
||||
role: "reviewer",
|
||||
content: "rev-" + String(input.steps.length),
|
||||
meta: { k: "reviewer" },
|
||||
};
|
||||
const body = "rev-" + String(input.steps.length);
|
||||
const h = await putContentMerkleNode(cas, body);
|
||||
yield { role: "reviewer", contentHash: h, meta: { k: "reviewer" }, refs: [h] };
|
||||
}
|
||||
return { returnCode: 0, summary: "done" };
|
||||
};
|
||||
@@ -98,7 +102,7 @@ describe("cli fork", () => {
|
||||
}
|
||||
const hash = added.value.hash;
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -107,7 +111,7 @@ describe("cli fork", () => {
|
||||
const sourceData = join(storageRoot, "logs", hash, `${sourceId}.data.jsonl`);
|
||||
const sourceRunning = join(storageRoot, "logs", hash, `${sourceId}.running`);
|
||||
await waitUntilRunningAbsent(sourceRunning);
|
||||
await waitUntilMinDataLines(sourceData, 4);
|
||||
await waitUntilMinDataLines(sourceData, 5);
|
||||
|
||||
const forked = await cmdFork(storageRoot, sourceId, "planner");
|
||||
expect(forked.ok).toBe(true);
|
||||
@@ -118,21 +122,22 @@ describe("cli fork", () => {
|
||||
const newData = join(storageRoot, "logs", hash, `${newId}.data.jsonl`);
|
||||
const newRunning = join(storageRoot, "logs", hash, `${newId}.running`);
|
||||
await waitUntilRunningAbsent(newRunning);
|
||||
await waitUntilMinDataLines(newData, 4);
|
||||
await waitUntilMinDataLines(newData, 5);
|
||||
|
||||
const text = await readFile(newData, "utf8");
|
||||
const lines = text
|
||||
.trim()
|
||||
.split("\n")
|
||||
.filter((l) => l !== "");
|
||||
expect(lines.length).toBe(4);
|
||||
expect(lines.length).toBe(5);
|
||||
const start = JSON.parse(lines[0] ?? "{}") as Record<string, unknown>;
|
||||
expect(start.threadId).toBe(newId);
|
||||
expect(start.forkFrom).toEqual({ threadId: sourceId });
|
||||
|
||||
const last = JSON.parse(lines[lines.length - 1] ?? "{}") as Record<string, unknown>;
|
||||
expect(last.role).toBe("reviewer");
|
||||
expect(last.content).toBe("rev-1");
|
||||
const lastRoleLine = JSON.parse(lines[lines.length - 2] ?? "{}") as Record<string, unknown>;
|
||||
expect(lastRoleLine.role).toBe("reviewer");
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
expect(await getContentMerklePayload(cas, String(lastRoleLine.contentHash))).toBe("rev-1");
|
||||
});
|
||||
|
||||
test("fork without --from-role retries last role", async () => {
|
||||
@@ -148,7 +153,7 @@ describe("cli fork", () => {
|
||||
}
|
||||
const hash = added.value.hash;
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -157,7 +162,7 @@ describe("cli fork", () => {
|
||||
const sourceData = join(storageRoot, "logs", hash, `${sourceId}.data.jsonl`);
|
||||
const sourceRunning = join(storageRoot, "logs", hash, `${sourceId}.running`);
|
||||
await waitUntilRunningAbsent(sourceRunning);
|
||||
await waitUntilMinDataLines(sourceData, 4);
|
||||
await waitUntilMinDataLines(sourceData, 5);
|
||||
|
||||
const forked = await cmdFork(storageRoot, sourceId, null);
|
||||
expect(forked.ok).toBe(true);
|
||||
@@ -168,22 +173,23 @@ describe("cli fork", () => {
|
||||
const newData = join(storageRoot, "logs", hash, `${newId}.data.jsonl`);
|
||||
const newRunning = join(storageRoot, "logs", hash, `${newId}.running`);
|
||||
await waitUntilRunningAbsent(newRunning);
|
||||
await waitUntilMinDataLines(newData, 4);
|
||||
await waitUntilMinDataLines(newData, 5);
|
||||
|
||||
const text = await readFile(newData, "utf8");
|
||||
const lines = text
|
||||
.trim()
|
||||
.split("\n")
|
||||
.filter((l) => l !== "");
|
||||
expect(lines.length).toBe(4);
|
||||
expect(lines.length).toBe(5);
|
||||
|
||||
const replayCoder = JSON.parse(lines[2] ?? "{}") as Record<string, unknown>;
|
||||
expect(replayCoder.role).toBe("coder");
|
||||
expect(replayCoder.content).toBe("c1");
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
expect(await getContentMerklePayload(cas, String(replayCoder.contentHash))).toBe("c1");
|
||||
|
||||
const last = JSON.parse(lines[lines.length - 1] ?? "{}") as Record<string, unknown>;
|
||||
expect(last.role).toBe("reviewer");
|
||||
expect(last.content).toBe("rev-2");
|
||||
const lastRoleLine = JSON.parse(lines[lines.length - 2] ?? "{}") as Record<string, unknown>;
|
||||
expect(lastRoleLine.role).toBe("reviewer");
|
||||
expect(await getContentMerklePayload(cas, String(lastRoleLine.contentHash))).toBe("rev-2");
|
||||
});
|
||||
|
||||
test("fork rejects unknown role with available names", async () => {
|
||||
@@ -198,7 +204,7 @@ describe("cli fork", () => {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -207,7 +213,7 @@ describe("cli fork", () => {
|
||||
const sourceData = join(storageRoot, "logs", added.value.hash, `${sourceId}.data.jsonl`);
|
||||
const sourceRunning = join(storageRoot, "logs", added.value.hash, `${sourceId}.running`);
|
||||
await waitUntilRunningAbsent(sourceRunning);
|
||||
await waitUntilMinDataLines(sourceData, 4);
|
||||
await waitUntilMinDataLines(sourceData, 5);
|
||||
|
||||
const bad = await cmdFork(storageRoot, sourceId, "ghost-role");
|
||||
expect(bad.ok).toBe(false);
|
||||
|
||||
@@ -0,0 +1,165 @@
|
||||
import { afterEach, beforeEach, describe, expect, test } from "bun:test";
|
||||
import { spawnSync } from "node:child_process";
|
||||
import { mkdir, mkdtemp, rm, writeFile } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
import {
|
||||
createCasStore,
|
||||
garbageCollectCas,
|
||||
getGlobalCasDir,
|
||||
putContentMerkleNode,
|
||||
} from "@uncaged/workflow";
|
||||
import { cmdThreadRemove } from "../src/cmd-thread.js";
|
||||
import { pathExists } from "../src/fs-utils.js";
|
||||
|
||||
const cliEntryPath = fileURLToPath(new URL("../src/cli.ts", import.meta.url));
|
||||
|
||||
async function writeDemoDataJsonl(params: {
|
||||
path: string;
|
||||
threadId: string;
|
||||
bundleHash: string;
|
||||
cas: ReturnType<typeof createCasStore>;
|
||||
activeHash: string;
|
||||
}): Promise<void> {
|
||||
const bodyHash = await putContentMerkleNode(params.cas, "p");
|
||||
const text = [
|
||||
JSON.stringify({
|
||||
name: "demo",
|
||||
hash: params.bundleHash,
|
||||
threadId: params.threadId,
|
||||
parameters: { prompt: "hi", options: { maxRounds: 5 } },
|
||||
timestamp: 100,
|
||||
}),
|
||||
JSON.stringify({
|
||||
role: "planner",
|
||||
contentHash: bodyHash,
|
||||
meta: {},
|
||||
refs: [params.activeHash, bodyHash],
|
||||
timestamp: 101,
|
||||
}),
|
||||
"",
|
||||
].join("\n");
|
||||
await writeFile(params.path, text, "utf8");
|
||||
}
|
||||
|
||||
describe("gc cli and garbageCollectCas", () => {
|
||||
let prevEnv: string | undefined;
|
||||
let storageRoot: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
prevEnv = process.env.UNCAGED_WORKFLOW_STORAGE_ROOT;
|
||||
storageRoot = await mkdtemp(join(tmpdir(), "uncaged-wf-gc-"));
|
||||
process.env.UNCAGED_WORKFLOW_STORAGE_ROOT = storageRoot;
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
if (prevEnv === undefined) {
|
||||
delete process.env.UNCAGED_WORKFLOW_STORAGE_ROOT;
|
||||
} else {
|
||||
process.env.UNCAGED_WORKFLOW_STORAGE_ROOT = prevEnv;
|
||||
}
|
||||
await rm(storageRoot, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("garbageCollectCas keeps CAS entries referenced by thread refs", async () => {
|
||||
const bundleHash = "C9NMV6V2TQT81";
|
||||
const threadId = "01AAA1111111111111111111";
|
||||
const logsDir = join(storageRoot, "logs", bundleHash);
|
||||
await mkdir(logsDir, { recursive: true });
|
||||
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
const activeHash = await cas.put("active-blob");
|
||||
const orphanHash = await cas.put("orphan-blob");
|
||||
|
||||
await writeDemoDataJsonl({
|
||||
path: join(logsDir, `${threadId}.data.jsonl`),
|
||||
threadId,
|
||||
bundleHash,
|
||||
cas,
|
||||
activeHash,
|
||||
});
|
||||
|
||||
const gc = await garbageCollectCas(storageRoot);
|
||||
expect(gc.ok).toBe(true);
|
||||
if (!gc.ok) {
|
||||
return;
|
||||
}
|
||||
expect(gc.value.scannedThreads).toBe(1);
|
||||
expect(gc.value.activeRefs).toBe(2);
|
||||
expect(gc.value.deletedEntries).toBe(1);
|
||||
expect(gc.value.deletedHashes).toEqual([orphanHash]);
|
||||
|
||||
expect(await pathExists(join(getGlobalCasDir(storageRoot), `${activeHash}.txt`))).toBe(true);
|
||||
expect(await pathExists(join(getGlobalCasDir(storageRoot), `${orphanHash}.txt`))).toBe(false);
|
||||
});
|
||||
|
||||
test("garbageCollectCas deletes orphaned CAS when no threads reference them", async () => {
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
const orphanHash = await cas.put("lonely");
|
||||
|
||||
const gc = await garbageCollectCas(storageRoot);
|
||||
expect(gc.ok).toBe(true);
|
||||
if (!gc.ok) {
|
||||
return;
|
||||
}
|
||||
expect(gc.value.scannedThreads).toBe(0);
|
||||
expect(gc.value.activeRefs).toBe(0);
|
||||
expect(gc.value.deletedEntries).toBe(1);
|
||||
expect(gc.value.deletedHashes).toEqual([orphanHash]);
|
||||
expect(await pathExists(join(getGlobalCasDir(storageRoot), `${orphanHash}.txt`))).toBe(false);
|
||||
});
|
||||
|
||||
test("cli gc prints stats", async () => {
|
||||
const bundleHash = "C9NMV6V2TQT81";
|
||||
const threadId = "01BBB2222222222222222222";
|
||||
const logsDir = join(storageRoot, "logs", bundleHash);
|
||||
await mkdir(logsDir, { recursive: true });
|
||||
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
const activeHash = await cas.put("keep-me");
|
||||
await cas.put("drop-me");
|
||||
|
||||
await writeDemoDataJsonl({
|
||||
path: join(logsDir, `${threadId}.data.jsonl`),
|
||||
threadId,
|
||||
bundleHash,
|
||||
cas,
|
||||
activeHash,
|
||||
});
|
||||
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const proc = spawnSync(process.execPath, [cliEntryPath, "cas", "gc"], {
|
||||
env,
|
||||
encoding: "utf8",
|
||||
});
|
||||
expect(proc.status).toBe(0);
|
||||
expect(String(proc.stdout).trim()).toBe("scanned 1 threads, 2 active refs, deleted 1 entries");
|
||||
});
|
||||
|
||||
test("thread rm triggers gc so unreferenced CAS is removed", async () => {
|
||||
const bundleHash = "C9NMV6V2TQT81";
|
||||
const threadId = "01CCC3333333333333333333";
|
||||
const logsDir = join(storageRoot, "logs", bundleHash);
|
||||
await mkdir(logsDir, { recursive: true });
|
||||
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
const activeHash = await cas.put("pinned-by-ref");
|
||||
await writeDemoDataJsonl({
|
||||
path: join(logsDir, `${threadId}.data.jsonl`),
|
||||
threadId,
|
||||
bundleHash,
|
||||
cas,
|
||||
activeHash,
|
||||
});
|
||||
|
||||
const orphanHash = await cas.put("orphan-after-rm");
|
||||
const orphanPath = join(getGlobalCasDir(storageRoot), `${orphanHash}.txt`);
|
||||
|
||||
const removed = await cmdThreadRemove(storageRoot, threadId);
|
||||
expect(removed.ok).toBe(true);
|
||||
|
||||
expect(await pathExists(orphanPath)).toBe(false);
|
||||
expect(await pathExists(join(getGlobalCasDir(storageRoot), `${activeHash}.txt`))).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,84 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { runCli } from "../src/cli-dispatch.js";
|
||||
import { formatSkillDoc } from "../src/cmd-help.js";
|
||||
|
||||
const STORAGE_ROOT = "/tmp/help-test-storage";
|
||||
|
||||
describe("help command", () => {
|
||||
test("help returns 0", async () => {
|
||||
const code = await runCli(STORAGE_ROOT, ["help"]);
|
||||
expect(code).toBe(0);
|
||||
});
|
||||
|
||||
test("help --skill returns 0", async () => {
|
||||
const code = await runCli(STORAGE_ROOT, ["help", "--skill"]);
|
||||
expect(code).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe("formatSkillDoc", () => {
|
||||
const doc = formatSkillDoc();
|
||||
|
||||
test("contains title", () => {
|
||||
expect(doc).toContain("# uncaged-workflow CLI Reference");
|
||||
});
|
||||
|
||||
test("contains all command group headers", () => {
|
||||
expect(doc).toContain("### workflow");
|
||||
expect(doc).toContain("### thread");
|
||||
expect(doc).toContain("### cas");
|
||||
expect(doc).toContain("### init");
|
||||
expect(doc).toContain("### Top-level shortcuts");
|
||||
});
|
||||
|
||||
test("contains core concepts", () => {
|
||||
expect(doc).toContain("## Core Concepts");
|
||||
expect(doc).toContain("Workflow");
|
||||
expect(doc).toContain("Bundle");
|
||||
expect(doc).toContain("Thread");
|
||||
expect(doc).toContain("CAS");
|
||||
expect(doc).toContain("Registry");
|
||||
});
|
||||
|
||||
test("mentions all workflow subcommands", () => {
|
||||
for (const sub of ["add", "list", "show", "rm", "history", "rollback"]) {
|
||||
expect(doc).toContain(`workflow ${sub}`);
|
||||
}
|
||||
});
|
||||
|
||||
test("mentions all thread subcommands", () => {
|
||||
for (const sub of [
|
||||
"run",
|
||||
"list",
|
||||
"show",
|
||||
"rm",
|
||||
"fork",
|
||||
"ps",
|
||||
"kill",
|
||||
"live",
|
||||
"pause",
|
||||
"resume",
|
||||
]) {
|
||||
expect(doc).toContain(`thread ${sub}`);
|
||||
}
|
||||
});
|
||||
|
||||
test("mentions all cas subcommands", () => {
|
||||
for (const sub of ["get", "put", "list", "rm", "gc"]) {
|
||||
expect(doc).toContain(`cas ${sub}`);
|
||||
}
|
||||
});
|
||||
|
||||
test("contains exit codes section", () => {
|
||||
expect(doc).toContain("## Exit Codes");
|
||||
});
|
||||
|
||||
test("contains environment variables section", () => {
|
||||
expect(doc).toContain("## Environment Variables");
|
||||
expect(doc).toContain("UNCAGED_WORKFLOW_STORAGE_ROOT");
|
||||
});
|
||||
|
||||
test("contains typical workflow section", () => {
|
||||
expect(doc).toContain("## Typical Workflow");
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,142 @@
|
||||
import { afterEach, beforeEach, describe, expect, test } from "bun:test";
|
||||
import { mkdir, readFile, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { runCli } from "../src/cli-dispatch.js";
|
||||
import { cmdInitTemplate, cmdInitWorkspace } from "../src/cmd-init.js";
|
||||
import { pathExists } from "../src/fs-utils.js";
|
||||
|
||||
describe("init template", () => {
|
||||
let parent: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
parent = join(
|
||||
tmpdir(),
|
||||
`wf-init-template-${Date.now()}-${Math.random().toString(36).slice(2)}`,
|
||||
);
|
||||
await mkdir(parent, { recursive: true });
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(parent, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("creates templates/<name> with expected files", async () => {
|
||||
const ws = await cmdInitWorkspace(parent, "my-workflows");
|
||||
expect(ws.ok).toBe(true);
|
||||
if (!ws.ok) {
|
||||
return;
|
||||
}
|
||||
const root = ws.value.rootPath;
|
||||
|
||||
const created = await cmdInitTemplate(root, "review-pr");
|
||||
expect(created.ok).toBe(true);
|
||||
if (!created.ok) {
|
||||
return;
|
||||
}
|
||||
|
||||
const tdir = join(root, "templates", "review-pr");
|
||||
expect(created.value.templatePath).toBe(tdir);
|
||||
expect(await pathExists(join(tdir, "package.json"))).toBe(true);
|
||||
expect(await pathExists(join(tdir, "tsconfig.json"))).toBe(true);
|
||||
expect(await pathExists(join(tdir, "src", "roles.ts"))).toBe(true);
|
||||
expect(await pathExists(join(tdir, "src", "moderator.ts"))).toBe(true);
|
||||
expect(await pathExists(join(tdir, "src", "index.ts"))).toBe(true);
|
||||
|
||||
const pkg = JSON.parse(await readFile(join(tdir, "package.json"), "utf8")) as {
|
||||
name: string;
|
||||
type: string;
|
||||
dependencies: Record<string, string>;
|
||||
};
|
||||
expect(pkg.type).toBe("module");
|
||||
expect(pkg.dependencies["@uncaged/workflow"]).toBeDefined();
|
||||
expect(pkg.dependencies.zod).toBeDefined();
|
||||
expect(pkg.name).toContain("review-pr");
|
||||
|
||||
const idx = await readFile(join(tdir, "src", "index.ts"), "utf8");
|
||||
expect(idx).toContain("WorkflowDefinition");
|
||||
|
||||
const roles = await readFile(join(tdir, "src", "roles.ts"), "utf8");
|
||||
expect(roles).not.toContain("interface ");
|
||||
expect(roles).not.toContain("?:");
|
||||
expect(roles).not.toContain("export default");
|
||||
|
||||
const moder = await readFile(join(tdir, "src", "moderator.ts"), "utf8");
|
||||
expect(moder).not.toContain("export default");
|
||||
});
|
||||
|
||||
test("finds workspace walking up from nested cwd", async () => {
|
||||
const ws = await cmdInitWorkspace(parent, "ws");
|
||||
expect(ws.ok).toBe(true);
|
||||
if (!ws.ok) {
|
||||
return;
|
||||
}
|
||||
const root = ws.value.rootPath;
|
||||
const nested = join(root, "a", "b");
|
||||
await mkdir(nested, { recursive: true });
|
||||
|
||||
const created = await cmdInitTemplate(nested, "nested-tpl");
|
||||
expect(created.ok).toBe(true);
|
||||
if (!created.ok) {
|
||||
return;
|
||||
}
|
||||
expect(await pathExists(join(root, "templates", "nested-tpl", "src", "index.ts"))).toBe(true);
|
||||
});
|
||||
|
||||
test("errors when not inside a workflow workspace", async () => {
|
||||
const orphan = join(parent, "nowhere");
|
||||
await mkdir(orphan, { recursive: true });
|
||||
const r = await cmdInitTemplate(orphan, "x");
|
||||
expect(r.ok).toBe(false);
|
||||
if (!r.ok) {
|
||||
expect(r.error).toContain("templates/*");
|
||||
}
|
||||
});
|
||||
|
||||
test("errors when template directory already exists", async () => {
|
||||
const ws = await cmdInitWorkspace(parent, "ws");
|
||||
expect(ws.ok).toBe(true);
|
||||
if (!ws.ok) {
|
||||
return;
|
||||
}
|
||||
const root = ws.value.rootPath;
|
||||
|
||||
const first = await cmdInitTemplate(root, "dup");
|
||||
expect(first.ok).toBe(true);
|
||||
|
||||
const second = await cmdInitTemplate(root, "dup");
|
||||
expect(second.ok).toBe(false);
|
||||
if (!second.ok) {
|
||||
expect(second.error).toContain("already exists");
|
||||
}
|
||||
});
|
||||
|
||||
test("errors on invalid template name", async () => {
|
||||
const ws = await cmdInitWorkspace(parent, "ws");
|
||||
expect(ws.ok).toBe(true);
|
||||
if (!ws.ok) {
|
||||
return;
|
||||
}
|
||||
const bad = await cmdInitTemplate(ws.value.rootPath, "a/b");
|
||||
expect(bad.ok).toBe(false);
|
||||
});
|
||||
|
||||
test.serial("runCli init template uses cwd and succeeds in workspace", async () => {
|
||||
const ws = await cmdInitWorkspace(parent, "cli-ws");
|
||||
expect(ws.ok).toBe(true);
|
||||
if (!ws.ok) {
|
||||
return;
|
||||
}
|
||||
const root = ws.value.rootPath;
|
||||
const prev = process.cwd();
|
||||
try {
|
||||
process.chdir(root);
|
||||
const code = await runCli(join(parent, "_storage"), ["init", "template", "from-cli"]);
|
||||
expect(code).toBe(0);
|
||||
expect(await pathExists(join(root, "templates", "from-cli", "package.json"))).toBe(true);
|
||||
} finally {
|
||||
process.chdir(prev);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,152 @@
|
||||
import { afterEach, beforeEach, describe, expect, test } from "bun:test";
|
||||
import { mkdir, readFile, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { formatCliUsage, runCli } from "../src/cli-dispatch.js";
|
||||
import { cmdInitWorkspace } from "../src/cmd-init.js";
|
||||
import { pathExists } from "../src/fs-utils.js";
|
||||
|
||||
describe("init workspace", () => {
|
||||
let parent: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
parent = join(tmpdir(), `wf-init-${Date.now()}-${Math.random().toString(36).slice(2)}`);
|
||||
await mkdir(parent, { recursive: true });
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(parent, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("creates expected files and directories", async () => {
|
||||
const created = await cmdInitWorkspace(parent, "my-workflows");
|
||||
expect(created.ok).toBe(true);
|
||||
if (!created.ok) {
|
||||
return;
|
||||
}
|
||||
|
||||
const root = created.value.rootPath;
|
||||
expect(await pathExists(join(root, "package.json"))).toBe(true);
|
||||
expect(await pathExists(join(root, "biome.json"))).toBe(true);
|
||||
expect(await pathExists(join(root, "tsconfig.json"))).toBe(true);
|
||||
expect(await pathExists(join(root, "AGENTS.md"))).toBe(true);
|
||||
expect(await pathExists(join(root, "README.md"))).toBe(true);
|
||||
expect(await pathExists(join(root, "templates"))).toBe(true);
|
||||
expect(await pathExists(join(root, "templates", ".gitkeep"))).toBe(true);
|
||||
expect(await pathExists(join(root, "workflows", "package.json"))).toBe(true);
|
||||
|
||||
const rootPkg = JSON.parse(await readFile(join(root, "package.json"), "utf8")) as {
|
||||
workspaces: string[];
|
||||
};
|
||||
expect(rootPkg.workspaces).toEqual(["templates/*", "workflows"]);
|
||||
|
||||
const wfPkg = JSON.parse(await readFile(join(root, "workflows", "package.json"), "utf8")) as {
|
||||
type: string;
|
||||
dependencies: Record<string, string>;
|
||||
};
|
||||
expect(wfPkg.type).toBe("module");
|
||||
expect(wfPkg.dependencies["@uncaged/workflow"]).toBeDefined();
|
||||
expect(wfPkg.dependencies.zod).toBeDefined();
|
||||
|
||||
const tsconfig = JSON.parse(await readFile(join(root, "tsconfig.json"), "utf8")) as {
|
||||
compilerOptions: { strict: boolean; module: string; target: string };
|
||||
};
|
||||
expect(tsconfig.compilerOptions.strict).toBe(true);
|
||||
expect(tsconfig.compilerOptions.module).toBe("ESNext");
|
||||
expect(tsconfig.compilerOptions.target).toBe("ESNext");
|
||||
});
|
||||
|
||||
test("AGENTS.md contains coding agent guide sections and terms", async () => {
|
||||
const created = await cmdInitWorkspace(parent, "my-workflows");
|
||||
expect(created.ok).toBe(true);
|
||||
if (!created.ok) {
|
||||
return;
|
||||
}
|
||||
|
||||
const agentsPath = join(created.value.rootPath, "AGENTS.md");
|
||||
const body = await readFile(agentsPath, "utf8");
|
||||
|
||||
for (const section of [
|
||||
"项目结构",
|
||||
"核心概念",
|
||||
"开发流程",
|
||||
"编码规范",
|
||||
"Template",
|
||||
"Build",
|
||||
"常见陷阱",
|
||||
]) {
|
||||
expect(body).toContain(section);
|
||||
}
|
||||
|
||||
for (const term of [
|
||||
"RoleDefinition",
|
||||
"WorkflowDefinition",
|
||||
"Moderator",
|
||||
"AgentFn",
|
||||
"ExtractFn",
|
||||
"RoleMeta",
|
||||
]) {
|
||||
expect(body).toContain(term);
|
||||
}
|
||||
|
||||
expect(body).toMatch(/type[\s\S]*interface/i);
|
||||
expect(body).toMatch(/function[\s\S]*class/i);
|
||||
expect(body).toContain("Crockford Base32");
|
||||
expect(body).toMatch(/no[\s\S]*default export/i);
|
||||
expect(body).toMatch(/no[\s\S]*console/i);
|
||||
expect(body).toMatch(/no[\s\S]*dynamic import/i);
|
||||
|
||||
expect(body).toContain("bun run check");
|
||||
expect(body).toContain("bun test");
|
||||
expect(body).toContain("uncaged-workflow");
|
||||
expect(body).toContain("bun build");
|
||||
expect(body).toContain("CLAUDE.md");
|
||||
expect(body).toContain("docs/architecture.md");
|
||||
});
|
||||
|
||||
test("errors when directory already exists", async () => {
|
||||
const first = await cmdInitWorkspace(parent, "dup");
|
||||
expect(first.ok).toBe(true);
|
||||
|
||||
const second = await cmdInitWorkspace(parent, "dup");
|
||||
expect(second.ok).toBe(false);
|
||||
if (!second.ok) {
|
||||
expect(second.error).toContain("already exists");
|
||||
}
|
||||
});
|
||||
|
||||
test("errors on invalid workspace name", async () => {
|
||||
const slash = await cmdInitWorkspace(parent, "a/b");
|
||||
expect(slash.ok).toBe(false);
|
||||
|
||||
const dots = await cmdInitWorkspace(parent, "..");
|
||||
expect(dots.ok).toBe(false);
|
||||
|
||||
const empty = await cmdInitWorkspace(parent, "");
|
||||
expect(empty.ok).toBe(false);
|
||||
});
|
||||
|
||||
test("usage lists init subcommands", () => {
|
||||
const u = formatCliUsage();
|
||||
expect(u).toContain("uncaged-workflow init workspace <name>");
|
||||
expect(u).toContain("uncaged-workflow init template <name>");
|
||||
});
|
||||
|
||||
test("runCli rejects unknown init subcommand", async () => {
|
||||
const code = await runCli(join(parent, "_storage"), ["init", "bogus", "name"]);
|
||||
expect(code).toBe(1);
|
||||
});
|
||||
|
||||
test.serial("runCli init workspace uses cwd", async () => {
|
||||
const prev = process.cwd();
|
||||
try {
|
||||
process.chdir(parent);
|
||||
const code = await runCli(join(parent, "_storage"), ["init", "workspace", "from-cli"]);
|
||||
expect(code).toBe(0);
|
||||
expect(await pathExists(join(parent, "from-cli", "workflows", "package.json"))).toBe(true);
|
||||
} finally {
|
||||
process.chdir(prev);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,369 @@
|
||||
import { afterEach, beforeEach, describe, expect, test } from "bun:test";
|
||||
import { spawn, spawnSync } from "node:child_process";
|
||||
import { cp, mkdir, mkdtemp, readFile, rm, writeFile } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
|
||||
import { createCasStore, getGlobalCasDir, putContentMerkleNode } from "@uncaged/workflow";
|
||||
|
||||
import {
|
||||
formatLiveDebugLine,
|
||||
formatLiveTimeLabel,
|
||||
LIVE_CONTENT_MAX_LINES,
|
||||
type LiveRoleRow,
|
||||
renderLiveRoleStepLines,
|
||||
} from "../src/cmd-live.js";
|
||||
import { parseLiveArgv } from "../src/live-argv.js";
|
||||
|
||||
const cliEntryPath = fileURLToPath(new URL("../src/cli.ts", import.meta.url));
|
||||
const fixtureRoot = fileURLToPath(new URL("./fixtures/live", import.meta.url));
|
||||
|
||||
/** Bodies for Merkle content nodes; hashes must match `.data.jsonl` fixtures. */
|
||||
const LIVE_FIXTURE_PLANNER_BODY =
|
||||
"alpha\nbeta\ngamma\nLINE4\nLINE5\nLINE6\nLINE7\nLINE8\nLINE9\nLINE10\nLINE11";
|
||||
|
||||
describe("live helpers", () => {
|
||||
test("formatLiveTimeLabel pads HH:MM:SS", () => {
|
||||
const label = formatLiveTimeLabel(new Date("2024-06-01T09:08:07.000Z").getTime());
|
||||
expect(label).toMatch(/^\d{2}:\d{2}:\d{2}$/);
|
||||
});
|
||||
|
||||
test("formatLiveDebugLine flattens newlines in message", () => {
|
||||
const line = formatLiveDebugLine(0, "TAG1", "a\nb");
|
||||
expect(line).toContain("[TAG1]");
|
||||
expect(line).toContain("a b");
|
||||
expect(line).not.toContain("\n");
|
||||
});
|
||||
|
||||
test("renderLiveRoleStepLines truncates content to LIVE_CONTENT_MAX_LINES", () => {
|
||||
const lines = Array.from({ length: LIVE_CONTENT_MAX_LINES + 3 }, (_, i) => `L${i + 1}`);
|
||||
const row: LiveRoleRow = {
|
||||
role: "r",
|
||||
content: lines.join("\n"),
|
||||
meta: { k: "v" },
|
||||
timestamp: 0,
|
||||
};
|
||||
const out = renderLiveRoleStepLines(row, "r");
|
||||
const body = out.filter((l) => l.startsWith(" L"));
|
||||
expect(body.length).toBe(LIVE_CONTENT_MAX_LINES);
|
||||
expect(out.some((l) => l.includes("more line"))).toBe(true);
|
||||
expect(out.some((l) => l.startsWith(" meta: "))).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe("parseLiveArgv", () => {
|
||||
test("parses thread id and flags in any order", () => {
|
||||
const a = parseLiveArgv(["01ABC", "--debug", "--role", "planner"]);
|
||||
expect(a.ok).toBe(true);
|
||||
if (a.ok) {
|
||||
expect(a.value.threadId).toBe("01ABC");
|
||||
expect(a.value.latest).toBe(false);
|
||||
expect(a.value.debug).toBe(true);
|
||||
expect(a.value.role).toBe("planner");
|
||||
}
|
||||
const b = parseLiveArgv(["--latest", "--role", "x"]);
|
||||
expect(b.ok).toBe(true);
|
||||
if (b.ok) {
|
||||
expect(b.value.latest).toBe(true);
|
||||
expect(b.value.threadId).toBe(null);
|
||||
expect(b.value.role).toBe("x");
|
||||
}
|
||||
});
|
||||
|
||||
test("rejects --latest with thread id", () => {
|
||||
const r = parseLiveArgv(["--latest", "01ABC"]);
|
||||
expect(r.ok).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("live CLI", () => {
|
||||
let prevEnv: string | undefined;
|
||||
let storageRoot: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
prevEnv = process.env.UNCAGED_WORKFLOW_STORAGE_ROOT;
|
||||
storageRoot = await mkdtemp(join(tmpdir(), "uncaged-wf-live-"));
|
||||
process.env.UNCAGED_WORKFLOW_STORAGE_ROOT = storageRoot;
|
||||
await mkdir(join(storageRoot, "logs", "C9NMV6V2TQT81"), { recursive: true });
|
||||
await cp(
|
||||
join(fixtureRoot, "logs", "C9NMV6V2TQT81", "01LIVECMPLT01DDDDDDDDDDDDG.data.jsonl"),
|
||||
join(storageRoot, "logs", "C9NMV6V2TQT81", "01LIVECMPLT01DDDDDDDDDDDDG.data.jsonl"),
|
||||
);
|
||||
await cp(
|
||||
join(fixtureRoot, "logs", "C9NMV6V2TQT81", "01LIVECMPLT01DDDDDDDDDDDDG.info.jsonl"),
|
||||
join(storageRoot, "logs", "C9NMV6V2TQT81", "01LIVECMPLT01DDDDDDDDDDDDG.info.jsonl"),
|
||||
);
|
||||
await cp(
|
||||
join(fixtureRoot, "logs", "C9NMV6V2TQT81", "01LIVEINFLY01DDDDDDDDDDDDG.data.jsonl"),
|
||||
join(storageRoot, "logs", "C9NMV6V2TQT81", "01LIVEINFLY01DDDDDDDDDDDDG.data.jsonl"),
|
||||
);
|
||||
await cp(
|
||||
join(fixtureRoot, "logs", "C9NMV6V2TQT81", "01LIVEOLDER01DDDDDDDDDDDDG.data.jsonl"),
|
||||
join(storageRoot, "logs", "C9NMV6V2TQT81", "01LIVEOLDER01DDDDDDDDDDDDG.data.jsonl"),
|
||||
);
|
||||
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
await putContentMerkleNode(cas, LIVE_FIXTURE_PLANNER_BODY);
|
||||
await putContentMerkleNode(cas, "patch");
|
||||
await putContentMerkleNode(cas, "still running");
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
if (prevEnv === undefined) {
|
||||
delete process.env.UNCAGED_WORKFLOW_STORAGE_ROOT;
|
||||
} else {
|
||||
process.env.UNCAGED_WORKFLOW_STORAGE_ROOT = prevEnv;
|
||||
}
|
||||
await rm(storageRoot, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("prints role steps and summary for a completed thread", async () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const proc = spawn(process.execPath, [cliEntryPath, "live", "01LIVECMPLT01DDDDDDDDDDDDG"], {
|
||||
env,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
});
|
||||
const stdout = await new Promise<string>((resolve, reject) => {
|
||||
let buf = "";
|
||||
proc.stdout?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.stderr?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.on("error", reject);
|
||||
proc.on("exit", (code: number | null) => {
|
||||
if (code === 0) {
|
||||
resolve(buf);
|
||||
} else {
|
||||
reject(new Error(`exit ${code}: ${buf}`));
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
expect(stdout).toContain("planner");
|
||||
expect(stdout).toContain("coder");
|
||||
expect(stdout).toContain("meta:");
|
||||
expect(stdout).toContain('"phase":"plan"');
|
||||
expect(stdout).toContain("LINE10");
|
||||
expect(stdout).not.toContain("LINE11");
|
||||
expect(stdout).toContain("more line");
|
||||
expect(stdout).toContain("completed: returnCode=0");
|
||||
expect(stdout).toContain("fixture completed");
|
||||
});
|
||||
|
||||
test("--latest tails the newest thread by start timestamp", async () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const proc = spawn(process.execPath, [cliEntryPath, "live", "--latest"], {
|
||||
env,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
});
|
||||
const stdout = await new Promise<string>((resolve, reject) => {
|
||||
let buf = "";
|
||||
proc.stdout?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.stderr?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.on("error", reject);
|
||||
proc.on("exit", (code: number | null) => {
|
||||
if (code === 0) {
|
||||
resolve(buf);
|
||||
} else {
|
||||
reject(new Error(`exit ${code}: ${buf}`));
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
expect(stdout).toContain("fixture completed");
|
||||
expect(stdout).not.toContain("older thread");
|
||||
});
|
||||
|
||||
test("--debug prints .info.jsonl records after data output", async () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
[cliEntryPath, "live", "01LIVECMPLT01DDDDDDDDDDDDG", "--debug"],
|
||||
{
|
||||
env,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
},
|
||||
);
|
||||
const stdout = await new Promise<string>((resolve, reject) => {
|
||||
let buf = "";
|
||||
proc.stdout?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.stderr?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.on("error", reject);
|
||||
proc.on("exit", (code: number | null) => {
|
||||
if (code === 0) {
|
||||
resolve(buf);
|
||||
} else {
|
||||
reject(new Error(`exit ${code}: ${buf}`));
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
expect(stdout).toContain("[DEBUGTAG1]");
|
||||
expect(stdout).toContain("bundle loaded");
|
||||
expect(stdout).toContain("[DEBUGTAG2]");
|
||||
expect(stdout).toContain("multi line");
|
||||
});
|
||||
|
||||
test("--role filters out non-matching roles", async () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
[cliEntryPath, "live", "01LIVECMPLT01DDDDDDDDDDDDG", "--role", "planner"],
|
||||
{
|
||||
env,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
},
|
||||
);
|
||||
const stdout = await new Promise<string>((resolve, reject) => {
|
||||
let buf = "";
|
||||
proc.stdout?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.stderr?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.on("error", reject);
|
||||
proc.on("exit", (code: number | null) => {
|
||||
if (code === 0) {
|
||||
resolve(buf);
|
||||
} else {
|
||||
reject(new Error(`exit ${code}: ${buf}`));
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
expect(stdout).toContain("planner");
|
||||
expect(stdout).not.toContain("patch");
|
||||
expect(stdout).toContain("completed: returnCode=0");
|
||||
});
|
||||
|
||||
test("--latest --debug --role combine", async () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
[cliEntryPath, "live", "--latest", "--debug", "--role", "planner"],
|
||||
{
|
||||
env,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
},
|
||||
);
|
||||
const stdout = await new Promise<string>((resolve, reject) => {
|
||||
let buf = "";
|
||||
proc.stdout?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.stderr?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.on("error", reject);
|
||||
proc.on("exit", (code: number | null) => {
|
||||
if (code === 0) {
|
||||
resolve(buf);
|
||||
} else {
|
||||
reject(new Error(`exit ${code}: ${buf}`));
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
expect(stdout).toContain("[DEBUGTAG1]");
|
||||
expect(stdout).toContain("planner");
|
||||
expect(stdout).not.toContain("patch");
|
||||
expect(stdout).toContain("fixture completed");
|
||||
});
|
||||
|
||||
test("unknown thread id exits 1", () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const r = spawnSync(process.execPath, [cliEntryPath, "live", "01UNKNOWNXXXXXXXXXXXXXXXXX"], {
|
||||
env,
|
||||
encoding: "utf8",
|
||||
});
|
||||
expect(r.status).toBe(1);
|
||||
expect(String(r.stderr ?? "")).toContain("thread not found");
|
||||
});
|
||||
|
||||
test("follows file until WorkflowResult is appended", async () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const dataPath = join(
|
||||
storageRoot,
|
||||
"logs",
|
||||
"C9NMV6V2TQT81",
|
||||
"01LIVEINFLY01DDDDDDDDDDDDG.data.jsonl",
|
||||
);
|
||||
|
||||
const proc = spawn(process.execPath, [cliEntryPath, "live", "01LIVEINFLY01DDDDDDDDDDDDG"], {
|
||||
env,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
});
|
||||
|
||||
await new Promise((r) => setTimeout(r, 120));
|
||||
const prior = await readFile(dataPath, "utf8");
|
||||
await writeFile(
|
||||
dataPath,
|
||||
`${prior.replace(/\s*$/, "")}\n${JSON.stringify({ returnCode: 0, summary: "caught up" })}\n`,
|
||||
"utf8",
|
||||
);
|
||||
|
||||
const stdout = await new Promise<string>((resolve, reject) => {
|
||||
let buf = "";
|
||||
proc.stdout?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.stderr?.on("data", (c: Buffer) => {
|
||||
buf += c.toString("utf8");
|
||||
});
|
||||
proc.on("error", reject);
|
||||
proc.on("exit", (code: number | null) => {
|
||||
if (code === 0) {
|
||||
resolve(buf);
|
||||
} else {
|
||||
reject(new Error(`exit ${code}: ${buf}`));
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
expect(stdout).toContain("planner");
|
||||
expect(stdout).toContain("completed: returnCode=0");
|
||||
expect(stdout).toContain("caught up");
|
||||
});
|
||||
});
|
||||
|
||||
describe("live --latest with empty storage", () => {
|
||||
let prevEnv: string | undefined;
|
||||
let emptyRoot: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
prevEnv = process.env.UNCAGED_WORKFLOW_STORAGE_ROOT;
|
||||
emptyRoot = await mkdtemp(join(tmpdir(), "uncaged-wf-live-empty-"));
|
||||
process.env.UNCAGED_WORKFLOW_STORAGE_ROOT = emptyRoot;
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
if (prevEnv === undefined) {
|
||||
delete process.env.UNCAGED_WORKFLOW_STORAGE_ROOT;
|
||||
} else {
|
||||
process.env.UNCAGED_WORKFLOW_STORAGE_ROOT = prevEnv;
|
||||
}
|
||||
await rm(emptyRoot, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("exits 1 when no threads exist", () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: emptyRoot };
|
||||
const r = spawnSync(process.execPath, [cliEntryPath, "live", "--latest"], {
|
||||
env,
|
||||
encoding: "utf8",
|
||||
});
|
||||
expect(r.status).toBe(1);
|
||||
expect(String(r.stderr ?? "")).toContain("no threads");
|
||||
});
|
||||
});
|
||||
@@ -4,7 +4,9 @@ import { mkdir, mkdtemp, readFile, rm, writeFile } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { dirname, join } from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
import { getGlobalCasDir } from "@uncaged/workflow";
|
||||
import { cmdAdd } from "../src/cmd-add.js";
|
||||
import { cmdCasPut } from "../src/cmd-cas.js";
|
||||
import { cmdKill } from "../src/cmd-kill.js";
|
||||
import { cmdPause } from "../src/cmd-pause.js";
|
||||
import { cmdPs } from "../src/cmd-ps.js";
|
||||
@@ -12,9 +14,12 @@ import { cmdResume } from "../src/cmd-resume.js";
|
||||
import { cmdRun } from "../src/cmd-run.js";
|
||||
import { cmdThreadRemove, cmdThreadShow } from "../src/cmd-thread.js";
|
||||
import { cmdThreads } from "../src/cmd-threads.js";
|
||||
import { pathExists } from "../src/fs-utils.js";
|
||||
import { pathExists, readTextFileIfExists } from "../src/fs-utils.js";
|
||||
import { addCliArgs } from "./bundle-fixture.js";
|
||||
|
||||
const wfPutImport = `import { putContentMerkleNode } from "@uncaged/workflow";
|
||||
`;
|
||||
|
||||
const threadFixtureDescriptor = `export const descriptor = {
|
||||
description: "thread-cli",
|
||||
roles: {
|
||||
@@ -29,18 +34,26 @@ const threadFixtureDescriptor = `export const descriptor = {
|
||||
`;
|
||||
|
||||
const fastBundleSource = `${threadFixtureDescriptor}
|
||||
export const run = async function* (input) {
|
||||
yield { role: "planner", content: "plan", meta: { plan: input.prompt } };
|
||||
yield { role: "coder", content: "code", meta: { diff: "y" } };
|
||||
${wfPutImport}
|
||||
export const run = async function* (input, options) {
|
||||
const cas = options.cas;
|
||||
let h = await putContentMerkleNode(cas, "plan");
|
||||
yield { role: "planner", contentHash: h, meta: { plan: input.prompt }, refs: [h] };
|
||||
h = await putContentMerkleNode(cas, "code");
|
||||
yield { role: "coder", contentHash: h, meta: { diff: "y" }, refs: [h] };
|
||||
return { returnCode: 0, summary: "done" };
|
||||
};
|
||||
`;
|
||||
|
||||
const slowPlannerBundleSource = `${threadFixtureDescriptor}
|
||||
export const run = async function* (input) {
|
||||
${wfPutImport}
|
||||
export const run = async function* (input, options) {
|
||||
await new Promise((r) => setTimeout(r, 400));
|
||||
yield { role: "planner", content: "plan", meta: { plan: input.prompt } };
|
||||
yield { role: "coder", content: "code", meta: { diff: "y" } };
|
||||
const cas = options.cas;
|
||||
let h = await putContentMerkleNode(cas, "plan");
|
||||
yield { role: "planner", contentHash: h, meta: { plan: input.prompt }, refs: [h] };
|
||||
h = await putContentMerkleNode(cas, "code");
|
||||
yield { role: "coder", contentHash: h, meta: { diff: "y" }, refs: [h] };
|
||||
return { returnCode: 0, summary: "done" };
|
||||
};
|
||||
`;
|
||||
@@ -48,27 +61,38 @@ export const run = async function* (input) {
|
||||
const cliEntryPath = fileURLToPath(new URL("../src/cli.ts", import.meta.url));
|
||||
|
||||
const abortablePlannerBundleSource = `${threadFixtureDescriptor}
|
||||
export const run = async function* (input) {
|
||||
${wfPutImport}
|
||||
export const run = async function* (input, options) {
|
||||
await new Promise((r) => setTimeout(r, 600));
|
||||
yield { role: "planner", content: "plan", meta: { plan: input.prompt } };
|
||||
yield { role: "coder", content: "code", meta: { diff: "y" } };
|
||||
const cas = options.cas;
|
||||
let h = await putContentMerkleNode(cas, "plan");
|
||||
yield { role: "planner", contentHash: h, meta: { plan: input.prompt }, refs: [h] };
|
||||
h = await putContentMerkleNode(cas, "code");
|
||||
yield { role: "coder", contentHash: h, meta: { diff: "y" }, refs: [h] };
|
||||
return { returnCode: 0, summary: "done" };
|
||||
};
|
||||
`;
|
||||
|
||||
const pauseResumeBundleSource = `${threadFixtureDescriptor}
|
||||
export const run = async function* (input) {
|
||||
yield { role: "first", content: "f", meta: {} };
|
||||
${wfPutImport}
|
||||
export const run = async function* (_input, options) {
|
||||
const cas = options.cas;
|
||||
let h = await putContentMerkleNode(cas, "f");
|
||||
yield { role: "first", contentHash: h, meta: {}, refs: [h] };
|
||||
await new Promise((r) => setTimeout(r, 1500));
|
||||
yield { role: "second", content: "s", meta: {} };
|
||||
h = await putContentMerkleNode(cas, "s");
|
||||
yield { role: "second", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "done" };
|
||||
};
|
||||
`;
|
||||
|
||||
const delayedFirstYieldBundleSource = `${threadFixtureDescriptor}
|
||||
export const run = async function* (input) {
|
||||
${wfPutImport}
|
||||
export const run = async function* (_input, options) {
|
||||
await new Promise((r) => setTimeout(r, 900));
|
||||
yield { role: "only", content: "x", meta: {} };
|
||||
const cas = options.cas;
|
||||
const h = await putContentMerkleNode(cas, "x");
|
||||
yield { role: "only", contentHash: h, meta: {}, refs: [h] };
|
||||
return { returnCode: 0, summary: "done" };
|
||||
};
|
||||
`;
|
||||
@@ -138,7 +162,7 @@ describe("cli thread commands", () => {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -175,15 +199,67 @@ describe("cli thread commands", () => {
|
||||
expect(await pathExists(dataPath)).toBe(false);
|
||||
});
|
||||
|
||||
test("thread rm runs GC and removes CAS blobs not referenced by any remaining thread", async () => {
|
||||
const bundleDir = join(storageRoot, "src");
|
||||
await mkdir(bundleDir, { recursive: true });
|
||||
const bundlePath = join(bundleDir, "demo.esm.js");
|
||||
await writeFile(bundlePath, fastBundleSource, "utf8");
|
||||
|
||||
const added = await cmdAdd(storageRoot, addCliArgs("solve-issue", bundlePath));
|
||||
expect(added.ok).toBe(true);
|
||||
if (!added.ok) {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
}
|
||||
|
||||
const threadId = ran.value.threadId;
|
||||
|
||||
let threads = await cmdThreads(storageRoot, []);
|
||||
for (
|
||||
let attempt = 0;
|
||||
attempt < 50 && threads.ok && !threads.value.some((l) => l.includes(threadId));
|
||||
attempt++
|
||||
) {
|
||||
await new Promise((r) => setTimeout(r, 20));
|
||||
threads = await cmdThreads(storageRoot, []);
|
||||
}
|
||||
|
||||
const dataPath = join(storageRoot, "logs", added.value.hash, `${threadId}.data.jsonl`);
|
||||
const runningPath = join(dirname(dataPath), `${threadId}.running`);
|
||||
await waitUntilRunningFileAbsent(runningPath, 120);
|
||||
|
||||
const put = await cmdCasPut(storageRoot, threadId, "keep-after-thread-rm");
|
||||
expect(put.ok).toBe(true);
|
||||
if (!put.ok) {
|
||||
return;
|
||||
}
|
||||
const hash = put.value;
|
||||
const casBlob = join(getGlobalCasDir(storageRoot), `${hash}.txt`);
|
||||
|
||||
const removed = await cmdThreadRemove(storageRoot, threadId);
|
||||
expect(removed.ok).toBe(true);
|
||||
|
||||
const stillThere = await readTextFileIfExists(casBlob);
|
||||
expect(stillThere).toBeNull();
|
||||
});
|
||||
|
||||
test("cli entrypoint dispatches threads / ps (spawn)", () => {
|
||||
const env = { ...process.env, UNCAGED_WORKFLOW_STORAGE_ROOT: storageRoot };
|
||||
const threads = spawnSync(process.execPath, [cliEntryPath, "threads"], {
|
||||
const threads = spawnSync(process.execPath, [cliEntryPath, "thread", "list"], {
|
||||
env,
|
||||
encoding: "utf8",
|
||||
});
|
||||
expect(threads.status).toBe(0);
|
||||
|
||||
const ps = spawnSync(process.execPath, [cliEntryPath, "ps"], { env, encoding: "utf8" });
|
||||
const ps = spawnSync(process.execPath, [cliEntryPath, "thread", "ps"], {
|
||||
env,
|
||||
encoding: "utf8",
|
||||
});
|
||||
expect(ps.status).toBe(0);
|
||||
});
|
||||
|
||||
@@ -199,7 +275,7 @@ describe("cli thread commands", () => {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -229,7 +305,7 @@ describe("cli thread commands", () => {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -250,7 +326,7 @@ describe("cli thread commands", () => {
|
||||
.trim()
|
||||
.split("\n")
|
||||
.filter((l) => l !== "");
|
||||
expect(lines.length).toBe(2);
|
||||
expect(lines.length).toBe(3);
|
||||
|
||||
const runningPath = join(dirname(dataPath), `${threadId}.running`);
|
||||
expect(await pathExists(runningPath)).toBe(false);
|
||||
@@ -268,7 +344,7 @@ describe("cli thread commands", () => {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -289,8 +365,8 @@ describe("cli thread commands", () => {
|
||||
const resumed = await cmdResume(storageRoot, threadId);
|
||||
expect(resumed.ok).toBe(true);
|
||||
|
||||
await waitUntilMinDataLines(dataPath, 3, 120);
|
||||
expect(await countDataJsonlLines(dataPath)).toBe(3);
|
||||
await waitUntilMinDataLines(dataPath, 4, 120);
|
||||
expect(await countDataJsonlLines(dataPath)).toBe(4);
|
||||
|
||||
const runningPath = join(dirname(dataPath), `${threadId}.running`);
|
||||
await waitUntilRunningFileAbsent(runningPath, 100);
|
||||
@@ -309,7 +385,7 @@ describe("cli thread commands", () => {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
@@ -338,7 +414,7 @@ describe("cli thread commands", () => {
|
||||
return;
|
||||
}
|
||||
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", false, 5);
|
||||
const ran = await cmdRun(storageRoot, "solve-issue", "hello", 5);
|
||||
expect(ran.ok).toBe(true);
|
||||
if (!ran.ok) {
|
||||
return;
|
||||
|
||||
@@ -1,9 +1,14 @@
|
||||
import { printCliError, printCliLine, printCliWarn } from "./cli-output.js";
|
||||
import { cmdAdd, formatAddSuccess, parseAddArgv } from "./cmd-add.js";
|
||||
import { cmdCasGet, cmdCasList, cmdCasPut, cmdCasRm } from "./cmd-cas.js";
|
||||
import { cmdFork, parseForkArgv } from "./cmd-fork.js";
|
||||
import { cmdGc } from "./cmd-gc.js";
|
||||
import { formatSkillDoc } from "./cmd-help.js";
|
||||
import { cmdHistory } from "./cmd-history.js";
|
||||
import { cmdInitTemplate, cmdInitWorkspace } from "./cmd-init.js";
|
||||
import { cmdKill } from "./cmd-kill.js";
|
||||
import { cmdList, formatListLines } from "./cmd-list.js";
|
||||
import { cmdLive } from "./cmd-live.js";
|
||||
import { cmdPause } from "./cmd-pause.js";
|
||||
import { cmdPs } from "./cmd-ps.js";
|
||||
import { cmdRemove } from "./cmd-remove.js";
|
||||
@@ -13,33 +18,89 @@ import { cmdRun } from "./cmd-run.js";
|
||||
import { cmdShow, formatShowYaml } from "./cmd-show.js";
|
||||
import { cmdThreadRemove, cmdThreadShow } from "./cmd-thread.js";
|
||||
import { cmdThreads } from "./cmd-threads.js";
|
||||
import { parseLiveArgv } from "./live-argv.js";
|
||||
import { parseRunArgv } from "./run-argv.js";
|
||||
|
||||
function usage(): string {
|
||||
export function formatCliUsage(): string {
|
||||
return [
|
||||
"Usage:",
|
||||
" uncaged-workflow add <name> <file.esm.js> [--types <path>]",
|
||||
" uncaged-workflow list",
|
||||
" uncaged-workflow show <name>",
|
||||
" uncaged-workflow remove <name>",
|
||||
" uncaged-workflow run <name> [--prompt <text>] [--dry-run] [--max-rounds N]",
|
||||
" uncaged-workflow ps",
|
||||
" uncaged-workflow kill <thread-id>",
|
||||
" uncaged-workflow history <name>",
|
||||
" uncaged-workflow rollback <name> [hash]",
|
||||
" uncaged-workflow pause <thread-id>",
|
||||
" uncaged-workflow resume <thread-id>",
|
||||
" uncaged-workflow threads [name]",
|
||||
" uncaged-workflow thread <id>",
|
||||
" uncaged-workflow workflow add <name> <file.esm.js> [--types <path>]",
|
||||
" uncaged-workflow workflow list",
|
||||
" uncaged-workflow workflow show <name>",
|
||||
" uncaged-workflow workflow rm <name>",
|
||||
" uncaged-workflow workflow history <name>",
|
||||
" uncaged-workflow workflow rollback <name> [hash]",
|
||||
"",
|
||||
" uncaged-workflow thread run <name> [--prompt <text>] [--max-rounds N]",
|
||||
" uncaged-workflow thread list [name]",
|
||||
" uncaged-workflow thread show <id>",
|
||||
" uncaged-workflow thread rm <id>",
|
||||
" uncaged-workflow fork <thread-id> [--from-role <role>]",
|
||||
" uncaged-workflow thread ps",
|
||||
" uncaged-workflow thread kill <thread-id>",
|
||||
" uncaged-workflow thread live <thread-id> [--debug] [--role <name>]",
|
||||
" uncaged-workflow thread live --latest [--debug] [--role <name>]",
|
||||
" uncaged-workflow thread pause <thread-id>",
|
||||
" uncaged-workflow thread resume <thread-id>",
|
||||
" uncaged-workflow thread fork <thread-id> [--from-role <role>]",
|
||||
"",
|
||||
" uncaged-workflow cas get <thread-id> <hash>",
|
||||
" uncaged-workflow cas put <thread-id> <content>",
|
||||
" uncaged-workflow cas list <thread-id>",
|
||||
" uncaged-workflow cas rm <thread-id> <hash>",
|
||||
" uncaged-workflow cas gc",
|
||||
"",
|
||||
" uncaged-workflow init workspace <name>",
|
||||
" uncaged-workflow init template <name>",
|
||||
"",
|
||||
" uncaged-workflow run <name> [...] (shortcut for thread run)",
|
||||
" uncaged-workflow live <thread-id> [...] (shortcut for thread live)",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
function printDeprecation(oldCmd: string, newCmd: string): void {
|
||||
printCliWarn(`⚠ "${oldCmd}" is deprecated, use "${newCmd}" instead`);
|
||||
}
|
||||
|
||||
type DispatchFn = (storageRoot: string, argv: string[]) => Promise<number>;
|
||||
|
||||
// ── Individual dispatch functions ──────────────────────────────────────
|
||||
|
||||
async function dispatchInit(_storageRoot: string, argv: string[]): Promise<number> {
|
||||
const sub = argv[0];
|
||||
const name = argv[1];
|
||||
if (sub === undefined || name === undefined || argv.length > 2) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: init requires workspace|template <name>`);
|
||||
return 1;
|
||||
}
|
||||
|
||||
if (sub === "workspace") {
|
||||
const result = await cmdInitWorkspace(process.cwd(), name);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
return 1;
|
||||
}
|
||||
printCliLine(`initialized workflow workspace at ${result.value.rootPath}`);
|
||||
return 0;
|
||||
}
|
||||
|
||||
if (sub === "template") {
|
||||
const result = await cmdInitTemplate(process.cwd(), name);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
return 1;
|
||||
}
|
||||
printCliLine(`initialized template at ${result.value.templatePath}`);
|
||||
return 0;
|
||||
}
|
||||
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown init subcommand: ${sub}`);
|
||||
return 1;
|
||||
}
|
||||
|
||||
async function dispatchAdd(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const parsed = parseAddArgv(argv);
|
||||
if (!parsed.ok) {
|
||||
printCliError(`${usage()}\n\nerror: ${parsed.error}`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: ${parsed.error}`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdAdd(storageRoot, parsed.value);
|
||||
@@ -56,7 +117,7 @@ async function dispatchAdd(storageRoot: string, argv: string[]): Promise<number>
|
||||
|
||||
async function dispatchList(storageRoot: string, argv: string[]): Promise<number> {
|
||||
if (argv.length > 0) {
|
||||
printCliError(`${usage()}\n\nerror: list takes no arguments`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: list takes no arguments`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdList(storageRoot);
|
||||
@@ -73,7 +134,7 @@ async function dispatchList(storageRoot: string, argv: string[]): Promise<number
|
||||
async function dispatchShow(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const name = argv[0];
|
||||
if (name === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: show requires <name>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: show requires <name>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdShow(storageRoot, name);
|
||||
@@ -88,7 +149,7 @@ async function dispatchShow(storageRoot: string, argv: string[]): Promise<number
|
||||
async function dispatchRemove(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const name = argv[0];
|
||||
if (name === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: remove requires <name>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: remove requires <name>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdRemove(storageRoot, name);
|
||||
@@ -103,7 +164,7 @@ async function dispatchRemove(storageRoot: string, argv: string[]): Promise<numb
|
||||
async function dispatchRun(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const parsed = parseRunArgv(argv);
|
||||
if (!parsed.ok) {
|
||||
printCliError(`${usage()}\n\nerror: ${parsed.error}`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: ${parsed.error}`);
|
||||
return 1;
|
||||
}
|
||||
|
||||
@@ -111,7 +172,6 @@ async function dispatchRun(storageRoot: string, argv: string[]): Promise<number>
|
||||
storageRoot,
|
||||
parsed.value.name,
|
||||
parsed.value.prompt,
|
||||
parsed.value.dryRun,
|
||||
parsed.value.maxRounds,
|
||||
);
|
||||
if (!result.ok) {
|
||||
@@ -125,7 +185,7 @@ async function dispatchRun(storageRoot: string, argv: string[]): Promise<number>
|
||||
|
||||
async function dispatchPs(storageRoot: string, argv: string[]): Promise<number> {
|
||||
if (argv.length > 0) {
|
||||
printCliError(`${usage()}\n\nerror: ps takes no arguments`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: ps takes no arguments`);
|
||||
return 1;
|
||||
}
|
||||
for (const line of await cmdPs(storageRoot)) {
|
||||
@@ -137,7 +197,7 @@ async function dispatchPs(storageRoot: string, argv: string[]): Promise<number>
|
||||
async function dispatchKill(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const threadId = argv[0];
|
||||
if (threadId === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: kill requires <thread-id>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: kill requires <thread-id>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdKill(storageRoot, threadId);
|
||||
@@ -149,10 +209,19 @@ async function dispatchKill(storageRoot: string, argv: string[]): Promise<number
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchLive(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const parsed = parseLiveArgv(argv);
|
||||
if (!parsed.ok) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: ${parsed.error}`);
|
||||
return 1;
|
||||
}
|
||||
return cmdLive(storageRoot, parsed.value);
|
||||
}
|
||||
|
||||
async function dispatchHistory(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const name = argv[0];
|
||||
if (name === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: history requires <name>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: history requires <name>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdHistory(storageRoot, name);
|
||||
@@ -169,7 +238,7 @@ async function dispatchHistory(storageRoot: string, argv: string[]): Promise<num
|
||||
async function dispatchRollback(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const name = argv[0];
|
||||
if (name === undefined || argv.length > 2) {
|
||||
printCliError(`${usage()}\n\nerror: rollback requires <name> [hash]`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: rollback requires <name> [hash]`);
|
||||
return 1;
|
||||
}
|
||||
const hashArg = argv[1];
|
||||
@@ -185,7 +254,7 @@ async function dispatchRollback(storageRoot: string, argv: string[]): Promise<nu
|
||||
async function dispatchPause(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const threadId = argv[0];
|
||||
if (threadId === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: pause requires <thread-id>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: pause requires <thread-id>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdPause(storageRoot, threadId);
|
||||
@@ -200,7 +269,7 @@ async function dispatchPause(storageRoot: string, argv: string[]): Promise<numbe
|
||||
async function dispatchResume(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const threadId = argv[0];
|
||||
if (threadId === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: resume requires <thread-id>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: resume requires <thread-id>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdResume(storageRoot, threadId);
|
||||
@@ -212,7 +281,7 @@ async function dispatchResume(storageRoot: string, argv: string[]): Promise<numb
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchThreads(storageRoot: string, argv: string[]): Promise<number> {
|
||||
async function dispatchThreadList(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const result = await cmdThreads(storageRoot, argv);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
@@ -224,10 +293,10 @@ async function dispatchThreads(storageRoot: string, argv: string[]): Promise<num
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchThread(storageRoot: string, argv: string[]): Promise<number> {
|
||||
async function dispatchThreadShow(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const id = argv[0];
|
||||
if (id === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: thread requires <id>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: thread show requires <id>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdThreadShow(storageRoot, id);
|
||||
@@ -242,7 +311,7 @@ async function dispatchThread(storageRoot: string, argv: string[]): Promise<numb
|
||||
async function dispatchThreadRm(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const id = argv[0];
|
||||
if (id === undefined || argv.length > 1) {
|
||||
printCliError(`${usage()}\n\nerror: thread rm requires <id>`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: thread rm requires <id>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdThreadRemove(storageRoot, id);
|
||||
@@ -254,18 +323,27 @@ async function dispatchThreadRm(storageRoot: string, argv: string[]): Promise<nu
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchThreadBranch(storageRoot: string, rest: string[]): Promise<number> {
|
||||
const sub = rest[0];
|
||||
if (sub === "rm") {
|
||||
return dispatchThreadRm(storageRoot, rest.slice(1));
|
||||
async function dispatchGc(storageRoot: string, argv: string[]): Promise<number> {
|
||||
if (argv.length > 0) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: gc takes no arguments`);
|
||||
return 1;
|
||||
}
|
||||
return dispatchThread(storageRoot, rest);
|
||||
const result = await cmdGc(storageRoot);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
return 1;
|
||||
}
|
||||
const stats = result.value;
|
||||
printCliLine(
|
||||
`scanned ${stats.scannedThreads} threads, ${stats.activeRefs} active refs, deleted ${stats.deletedEntries} entries`,
|
||||
);
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchFork(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const parsed = parseForkArgv(argv);
|
||||
if (!parsed.ok) {
|
||||
printCliError(`${usage()}\n\nerror: ${parsed.error}`);
|
||||
printCliError(`${formatCliUsage()}\n\nerror: ${parsed.error}`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdFork(storageRoot, parsed.value.threadId, parsed.value.fromRole);
|
||||
@@ -277,40 +355,219 @@ async function dispatchFork(storageRoot: string, argv: string[]): Promise<number
|
||||
return 0;
|
||||
}
|
||||
|
||||
type DispatchFn = (storageRoot: string, argv: string[]) => Promise<number>;
|
||||
// ── CAS subcommand table ───────────────────────────────────────────────
|
||||
|
||||
const COMMAND_TABLE: Record<string, DispatchFn> = {
|
||||
async function dispatchCasGet(storageRoot: string, rest: string[]): Promise<number> {
|
||||
const threadId = rest[0];
|
||||
const hash = rest[1];
|
||||
if (threadId === undefined || hash === undefined || rest.length > 2) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: cas get requires <thread-id> <hash>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdCasGet(storageRoot, threadId, hash);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
return 1;
|
||||
}
|
||||
printCliLine(result.value);
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchCasPut(storageRoot: string, rest: string[]): Promise<number> {
|
||||
const threadId = rest[0];
|
||||
const content = rest[1];
|
||||
if (threadId === undefined || content === undefined || rest.length > 2) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: cas put requires <thread-id> <content>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdCasPut(storageRoot, threadId, content);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
return 1;
|
||||
}
|
||||
printCliLine(result.value);
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchCasList(storageRoot: string, rest: string[]): Promise<number> {
|
||||
const threadId = rest[0];
|
||||
if (threadId === undefined || rest.length > 1) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: cas list requires <thread-id>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdCasList(storageRoot, threadId);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
return 1;
|
||||
}
|
||||
for (const hash of result.value) {
|
||||
printCliLine(hash);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
async function dispatchCasRm(storageRoot: string, rest: string[]): Promise<number> {
|
||||
const threadId = rest[0];
|
||||
const hash = rest[1];
|
||||
if (threadId === undefined || hash === undefined || rest.length > 2) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: cas rm requires <thread-id> <hash>`);
|
||||
return 1;
|
||||
}
|
||||
const result = await cmdCasRm(storageRoot, threadId, hash);
|
||||
if (!result.ok) {
|
||||
printCliError(result.error);
|
||||
return 1;
|
||||
}
|
||||
printCliLine(`removed cas entry ${hash}`);
|
||||
return 0;
|
||||
}
|
||||
|
||||
const CAS_SUBCOMMAND_TABLE: Record<string, DispatchFn> = {
|
||||
get: dispatchCasGet,
|
||||
put: dispatchCasPut,
|
||||
list: dispatchCasList,
|
||||
rm: dispatchCasRm,
|
||||
gc: dispatchGc,
|
||||
};
|
||||
|
||||
async function dispatchCas(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const sub = argv[0];
|
||||
if (sub === undefined) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown cas subcommand: (none)`);
|
||||
return 1;
|
||||
}
|
||||
const handler = CAS_SUBCOMMAND_TABLE[sub];
|
||||
if (handler === undefined) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown cas subcommand: ${sub}`);
|
||||
return 1;
|
||||
}
|
||||
return handler(storageRoot, argv.slice(1));
|
||||
}
|
||||
|
||||
// ── Workflow subcommand table (Phase 1) ────────────────────────────────
|
||||
|
||||
const WORKFLOW_SUBCOMMAND_TABLE: Record<string, DispatchFn> = {
|
||||
add: dispatchAdd,
|
||||
list: dispatchList,
|
||||
show: dispatchShow,
|
||||
remove: dispatchRemove,
|
||||
run: dispatchRun,
|
||||
ps: dispatchPs,
|
||||
kill: dispatchKill,
|
||||
rm: dispatchRemove,
|
||||
history: dispatchHistory,
|
||||
rollback: dispatchRollback,
|
||||
};
|
||||
|
||||
async function dispatchWorkflow(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const sub = argv[0];
|
||||
if (sub === undefined) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown workflow subcommand: (none)`);
|
||||
return 1;
|
||||
}
|
||||
const handler = WORKFLOW_SUBCOMMAND_TABLE[sub];
|
||||
if (handler !== undefined) {
|
||||
return handler(storageRoot, argv.slice(1));
|
||||
}
|
||||
if (sub === "remove") {
|
||||
printDeprecation("workflow remove", "workflow rm");
|
||||
return dispatchRemove(storageRoot, argv.slice(1));
|
||||
}
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown workflow subcommand: ${sub}`);
|
||||
return 1;
|
||||
}
|
||||
|
||||
// ── Thread subcommand table (Phase 2) ──────────────────────────────────
|
||||
|
||||
const THREAD_SUBCOMMAND_TABLE: Record<string, DispatchFn> = {
|
||||
run: dispatchRun,
|
||||
list: dispatchThreadList,
|
||||
show: dispatchThreadShow,
|
||||
rm: dispatchThreadRm,
|
||||
fork: dispatchFork,
|
||||
ps: dispatchPs,
|
||||
kill: dispatchKill,
|
||||
live: dispatchLive,
|
||||
pause: dispatchPause,
|
||||
resume: dispatchResume,
|
||||
threads: dispatchThreads,
|
||||
thread: dispatchThreadBranch,
|
||||
fork: dispatchFork,
|
||||
};
|
||||
|
||||
async function dispatchThread(storageRoot: string, argv: string[]): Promise<number> {
|
||||
const sub = argv[0];
|
||||
if (sub === undefined) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown thread subcommand: (none)`);
|
||||
return 1;
|
||||
}
|
||||
const handler = THREAD_SUBCOMMAND_TABLE[sub];
|
||||
if (handler === undefined) {
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown thread subcommand: ${sub}`);
|
||||
return 1;
|
||||
}
|
||||
return handler(storageRoot, argv.slice(1));
|
||||
}
|
||||
|
||||
// ── Help ────────────────────────────────────────────────────────────────
|
||||
|
||||
async function dispatchHelp(_storageRoot: string, argv: string[]): Promise<number> {
|
||||
if (argv.includes("--skill")) {
|
||||
printCliLine(formatSkillDoc());
|
||||
} else {
|
||||
printCliLine(formatCliUsage());
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
// ── Top-level command table (Phase 3) ──────────────────────────────────
|
||||
|
||||
const COMMAND_TABLE: Record<string, DispatchFn> = {
|
||||
// Grouped commands (primary)
|
||||
workflow: dispatchWorkflow,
|
||||
thread: dispatchThread,
|
||||
cas: dispatchCas,
|
||||
init: dispatchInit,
|
||||
help: dispatchHelp,
|
||||
|
||||
// Top-level shortcuts (no deprecation)
|
||||
run: dispatchRun,
|
||||
live: dispatchLive,
|
||||
};
|
||||
|
||||
// Deprecated flat commands that delegate to grouped commands
|
||||
const DEPRECATED_ALIASES: Record<string, { newCmd: string; handler: DispatchFn }> = {
|
||||
add: { newCmd: "workflow add", handler: dispatchAdd },
|
||||
list: { newCmd: "workflow list", handler: dispatchList },
|
||||
show: { newCmd: "workflow show", handler: dispatchShow },
|
||||
remove: { newCmd: "workflow rm", handler: dispatchRemove },
|
||||
ps: { newCmd: "thread ps", handler: dispatchPs },
|
||||
kill: { newCmd: "thread kill", handler: dispatchKill },
|
||||
pause: { newCmd: "thread pause", handler: dispatchPause },
|
||||
resume: { newCmd: "thread resume", handler: dispatchResume },
|
||||
threads: { newCmd: "thread list", handler: dispatchThreadList },
|
||||
fork: { newCmd: "thread fork", handler: dispatchFork },
|
||||
gc: { newCmd: "cas gc", handler: dispatchGc },
|
||||
history: { newCmd: "workflow history", handler: dispatchHistory },
|
||||
rollback: { newCmd: "workflow rollback", handler: dispatchRollback },
|
||||
};
|
||||
|
||||
export async function runCli(storageRoot: string, argv: string[]): Promise<number> {
|
||||
if (argv.length === 0) {
|
||||
printCliError(usage());
|
||||
printCliError(formatCliUsage());
|
||||
return 1;
|
||||
}
|
||||
const command = argv[0];
|
||||
if (command === undefined) {
|
||||
printCliError(usage());
|
||||
printCliError(formatCliUsage());
|
||||
return 1;
|
||||
}
|
||||
const rest = argv.slice(1);
|
||||
|
||||
const dispatch = COMMAND_TABLE[command];
|
||||
if (dispatch === undefined) {
|
||||
printCliError(`${usage()}\n\nerror: unknown command ${command}`);
|
||||
return 1;
|
||||
if (dispatch !== undefined) {
|
||||
return dispatch(storageRoot, rest);
|
||||
}
|
||||
return dispatch(storageRoot, rest);
|
||||
|
||||
const deprecated = DEPRECATED_ALIASES[command];
|
||||
if (deprecated !== undefined) {
|
||||
printDeprecation(command, deprecated.newCmd);
|
||||
return deprecated.handler(storageRoot, rest);
|
||||
}
|
||||
|
||||
printCliError(`${formatCliUsage()}\n\nerror: unknown command ${command}`);
|
||||
return 1;
|
||||
}
|
||||
|
||||
Regular → Executable
@@ -192,7 +192,7 @@ export async function cmdAdd(
|
||||
return validated;
|
||||
}
|
||||
|
||||
const extracted = await extractBundleExports(resolvedPath);
|
||||
const extracted = await extractBundleExports(resolvedPath, { storageRoot });
|
||||
if (!extracted.ok) {
|
||||
return extracted;
|
||||
}
|
||||
|
||||
@@ -0,0 +1,43 @@
|
||||
import { createCasStore, err, getGlobalCasDir, ok, type Result } from "@uncaged/workflow";
|
||||
|
||||
export async function cmdCasGet(
|
||||
storageRoot: string,
|
||||
_threadId: string,
|
||||
hash: string,
|
||||
): Promise<Result<string, string>> {
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
const content = await cas.get(hash);
|
||||
if (content === null) {
|
||||
return err(`cas entry not found: ${hash}`);
|
||||
}
|
||||
return ok(content);
|
||||
}
|
||||
|
||||
export async function cmdCasPut(
|
||||
storageRoot: string,
|
||||
_threadId: string,
|
||||
content: string,
|
||||
): Promise<Result<string, string>> {
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
const hash = await cas.put(content);
|
||||
return ok(hash);
|
||||
}
|
||||
|
||||
export async function cmdCasList(
|
||||
storageRoot: string,
|
||||
_threadId: string,
|
||||
): Promise<Result<string[], string>> {
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
const hashes = await cas.list();
|
||||
return ok(hashes);
|
||||
}
|
||||
|
||||
export async function cmdCasRm(
|
||||
storageRoot: string,
|
||||
_threadId: string,
|
||||
hash: string,
|
||||
): Promise<Result<void, string>> {
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
await cas.delete(hash);
|
||||
return ok(undefined);
|
||||
}
|
||||
@@ -65,8 +65,9 @@ export async function cmdFork(
|
||||
const newThreadId = generateUlid(Date.now());
|
||||
const stepsOnWire = plan.value.historicalSteps.map((s) => ({
|
||||
role: s.role,
|
||||
content: s.content,
|
||||
contentHash: s.contentHash,
|
||||
meta: s.meta,
|
||||
refs: s.refs,
|
||||
timestamp: s.timestamp,
|
||||
}));
|
||||
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
import { type GcResult, garbageCollectCas, type Result } from "@uncaged/workflow";
|
||||
|
||||
export async function cmdGc(storageRoot: string): Promise<Result<GcResult, string>> {
|
||||
return garbageCollectCas(storageRoot);
|
||||
}
|
||||
@@ -0,0 +1,86 @@
|
||||
export function formatSkillDoc(): string {
|
||||
return `# uncaged-workflow CLI Reference
|
||||
|
||||
## Core Concepts
|
||||
|
||||
| Concept | Description |
|
||||
|---------|-------------|
|
||||
| **Workflow** | A single-file ESM bundle (\`.esm.js\`) that exports \`run\` and \`descriptor\`. Identified by name and XXH64 hash. |
|
||||
| **Bundle** | The physical \`.esm.js\` file stored in the bundles directory. Immutable once written. |
|
||||
| **Thread** | A single execution of a workflow, identified by a ULID. Persists state as JSONL files. |
|
||||
| **CAS** | Content-Addressable Storage. Per-thread key-value store keyed by content hash. |
|
||||
| **Registry** | \`workflow.yaml\` — maps workflow names to their current and historical bundle hashes. |
|
||||
|
||||
## Commands
|
||||
|
||||
### workflow
|
||||
|
||||
| Command | Args | Description |
|
||||
|---------|------|-------------|
|
||||
| \`workflow add\` | \`<name> <file.esm.js> [--types <path>]\` | Register a workflow bundle in the registry |
|
||||
| \`workflow list\` | (none) | List all registered workflows |
|
||||
| \`workflow show\` | \`<name>\` | Show details of a registered workflow |
|
||||
| \`workflow rm\` | \`<name>\` | Remove a workflow from the registry |
|
||||
| \`workflow history\` | \`<name>\` | Show version history of a workflow |
|
||||
| \`workflow rollback\` | \`<name> [hash]\` | Rollback a workflow to a previous version |
|
||||
|
||||
### thread
|
||||
|
||||
| Command | Args | Description |
|
||||
|---------|------|-------------|
|
||||
| \`thread run\` | \`<name> [--prompt <text>] [--max-rounds N]\` | Start a new thread executing a workflow |
|
||||
| \`thread list\` | \`[name]\` | List threads, optionally filtered by workflow name |
|
||||
| \`thread show\` | \`<id>\` | Show thread details and state |
|
||||
| \`thread rm\` | \`<id>\` | Remove a thread |
|
||||
| \`thread fork\` | \`<thread-id> [--from-role <role>]\` | Fork a thread, optionally from a specific role |
|
||||
| \`thread ps\` | (none) | List running threads |
|
||||
| \`thread kill\` | \`<thread-id>\` | Kill a running thread |
|
||||
| \`thread live\` | \`<thread-id> [--debug] [--role <name>]\` or \`--latest [--debug] [--role <name>]\` | Attach to a thread and stream output live |
|
||||
| \`thread pause\` | \`<thread-id>\` | Pause a running thread |
|
||||
| \`thread resume\` | \`<thread-id>\` | Resume a paused thread |
|
||||
|
||||
### cas
|
||||
|
||||
| Command | Args | Description |
|
||||
|---------|------|-------------|
|
||||
| \`cas get\` | \`<thread-id> <hash>\` | Retrieve content by hash from a thread's CAS |
|
||||
| \`cas put\` | \`<thread-id> <content>\` | Store content in a thread's CAS, returns hash |
|
||||
| \`cas list\` | \`<thread-id>\` | List all CAS entries for a thread |
|
||||
| \`cas rm\` | \`<thread-id> <hash>\` | Remove a CAS entry |
|
||||
| \`cas gc\` | (none) | Garbage-collect unreferenced CAS entries |
|
||||
|
||||
### init
|
||||
|
||||
| Command | Args | Description |
|
||||
|---------|------|-------------|
|
||||
| \`init workspace\` | \`<name>\` | Initialize a new workflow workspace |
|
||||
| \`init template\` | \`<name>\` | Initialize a new workflow template |
|
||||
|
||||
### Top-level shortcuts
|
||||
|
||||
| Command | Equivalent | Description |
|
||||
|---------|------------|-------------|
|
||||
| \`run\` | \`thread run\` | Shortcut to start a thread |
|
||||
| \`live\` | \`thread live\` | Shortcut to attach to a thread |
|
||||
|
||||
## Typical Workflow
|
||||
|
||||
1. \`uncaged-workflow workflow add my-wf ./my-wf.esm.js\` — register a workflow
|
||||
2. \`uncaged-workflow run my-wf --prompt "do the thing"\` — start a thread
|
||||
3. \`uncaged-workflow live --latest\` — attach and watch output
|
||||
4. \`uncaged-workflow thread show <thread-id>\` — inspect completed thread
|
||||
|
||||
## Exit Codes
|
||||
|
||||
| Code | Meaning |
|
||||
|------|---------|
|
||||
| 0 | Success |
|
||||
| 1 | Error |
|
||||
|
||||
## Environment Variables
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| \`UNCAGED_WORKFLOW_STORAGE_ROOT\` | Override the default storage directory for all workflow data |
|
||||
`;
|
||||
}
|
||||
@@ -0,0 +1,415 @@
|
||||
import { mkdir, readFile, writeFile } from "node:fs/promises";
|
||||
import { dirname, join, resolve } from "node:path";
|
||||
|
||||
import { err, ok, type Result } from "@uncaged/workflow";
|
||||
|
||||
import { pathExists } from "./fs-utils.js";
|
||||
|
||||
export type CmdInitWorkspaceSuccess = {
|
||||
rootPath: string;
|
||||
};
|
||||
|
||||
export type CmdInitTemplateSuccess = {
|
||||
templatePath: string;
|
||||
};
|
||||
|
||||
function validateWorkspaceSegment(name: string): Result<void, string> {
|
||||
if (name.length === 0) {
|
||||
return err("workspace name must not be empty");
|
||||
}
|
||||
if (name === "." || name === "..") {
|
||||
return err("invalid workspace name");
|
||||
}
|
||||
if (name.includes("/") || name.includes("\\")) {
|
||||
return err("workspace name must not contain path separators");
|
||||
}
|
||||
return ok(undefined);
|
||||
}
|
||||
|
||||
function rootPackageJson(workspaceName: string): string {
|
||||
return `${JSON.stringify(
|
||||
{
|
||||
name: workspaceName,
|
||||
private: true,
|
||||
type: "module",
|
||||
workspaces: ["templates/*", "workflows"],
|
||||
},
|
||||
null,
|
||||
2,
|
||||
)}\n`;
|
||||
}
|
||||
|
||||
function workflowsPackageJson(): string {
|
||||
return `${JSON.stringify(
|
||||
{
|
||||
name: "workflows",
|
||||
version: "0.0.0",
|
||||
private: true,
|
||||
type: "module",
|
||||
dependencies: {
|
||||
"@uncaged/workflow": "^0.1.0",
|
||||
zod: "^4.0.0",
|
||||
},
|
||||
},
|
||||
null,
|
||||
2,
|
||||
)}\n`;
|
||||
}
|
||||
|
||||
function biomeJson(): string {
|
||||
return `${JSON.stringify(
|
||||
{
|
||||
$schema: "https://biomejs.dev/schemas/2.4.14/schema.json",
|
||||
files: {
|
||||
includes: ["**", "!**/node_modules", "!**/dist"],
|
||||
},
|
||||
formatter: {
|
||||
indentWidth: 2,
|
||||
},
|
||||
linter: {
|
||||
enabled: true,
|
||||
rules: {
|
||||
recommended: true,
|
||||
},
|
||||
},
|
||||
},
|
||||
null,
|
||||
2,
|
||||
)}\n`;
|
||||
}
|
||||
|
||||
function tsconfigJson(): string {
|
||||
return `${JSON.stringify(
|
||||
{
|
||||
compilerOptions: {
|
||||
strict: true,
|
||||
target: "ESNext",
|
||||
module: "ESNext",
|
||||
moduleResolution: "Bundler",
|
||||
skipLibCheck: true,
|
||||
},
|
||||
},
|
||||
null,
|
||||
2,
|
||||
)}\n`;
|
||||
}
|
||||
|
||||
function agentsMd(): string {
|
||||
return `# AGENTS — Workflow 工作区开发指南
|
||||
|
||||
面向在本仓库中编写 workflow 的 coding agent。引擎层术语与架构细节与 **@uncaged/workflow** 上游文档一致,编写时可对照 \`CLAUDE.md\` 与 \`docs/architecture.md\`。
|
||||
|
||||
## 1. 项目结构(workspace / template / workflow instance)
|
||||
|
||||
| 层级 | 目录 / 产物 | 职责 |
|
||||
|------|----------------|------|
|
||||
| **Workspace** | 仓库根(\`package.json\` 含 \`workspaces: ["templates/*", "workflows"]\`) | Bun monorepo:统一管理本地模板包与 workflow 实例 |
|
||||
| **Template** | \`templates/<name>/\`(如 \`src/roles.ts\`、\`src/moderator.ts\`、\`src/index.ts\`) | 纯数据:**WorkflowDefinition**(各 **RoleDefinition** + **Moderator**),**不绑定**具体 Agent |
|
||||
| **Workflow instance** | \`workflows/\`(或单独包) | 把模板与运行时 **AgentFn** / **ExtractFn** 组合,产出可注册的 **单文件 ESM bundle**(\`run\` + \`descriptor\` 命名导出) |
|
||||
|
||||
Init 生成的骨架:\`templates/\` 下放可复用定义,\`workflows/\` 下放绑定与打包入口。
|
||||
|
||||
## 2. 核心概念
|
||||
|
||||
- **RoleMeta**:\`Record<string, Record<string, unknown>>\`,角色名 → 该角色结构化 meta 的形状约定。
|
||||
- **RoleDefinition<Meta>**:纯数据——\`description\`、\`systemPrompt\`、\`extractPrompt\`、\`schema\`(Zod v4)。不含执行逻辑。
|
||||
- **WorkflowDefinition<M extends RoleMeta>**:\`description\` + \`roles\`(各角色定义)+ **Moderator**。
|
||||
- **Moderator**:\`(ctx: ModeratorContext<M>) => (角色名) | END\`。同步、纯函数,只做路由。
|
||||
- **AgentFn**:\`(ctx: AgentContext) => Promise<string>\`,原始文本输出;从上下文读取当前角色的 \`systemPrompt\`。
|
||||
- **ExtractFn**:从上下文与 prompt 解析结构化数据(引擎与 Agent 都可使用)。
|
||||
|
||||
引擎循环简述:**Moderator** → 选角色 → **Agent** 产出文本 → **Extract** 写入 **meta** → 追加 step,重复直至 **END**。详见 \`docs/architecture.md\` 中的三阶段说明。
|
||||
|
||||
## 3. 开发流程
|
||||
|
||||
1. **定义 RoleMeta**:为每个角色约定 meta 的 TypeScript 类型(与 Zod schema 对齐)。
|
||||
2. **编写 RoleDefinition**:为每个角色写 Zod \`schema\`,补齐 \`systemPrompt\` / \`extractPrompt\` / \`description\`。
|
||||
3. **编写 Moderator**:根据 \`ctx.steps\` 与业务状态返回下一个角色名或 \`END\`。
|
||||
4. **组装 WorkflowDefinition**:在模板 \`index\` 中导出 definition(以及必要的角色 / moderator 导出)。
|
||||
5. **实例化**:在 workflow 包中使用 \`createWorkflow(def, binding, extract)\`(或项目约定的封装)绑定 **AgentFn** / **ExtractFn**。
|
||||
6. **构建**:打包为单个 **.esm.js** bundle,使用 **uncaged-workflow add** 注册。
|
||||
|
||||
## 4. 编码规范
|
||||
|
||||
与 **CLAUDE.md** 对齐,摘要如下:
|
||||
|
||||
- **Functional-first**:优先 \`function\` + \`type\`,避免面向对象业务模型。
|
||||
- **type 而非 interface**:类型别名一律用 \`type\`,不要使用 \`interface\`。
|
||||
- **显式可空**:不要用 \`?:\`;可空字段写成 \`T | null\`。
|
||||
- **function 而非 class**:不用 class(第三方库要求或 \`Error\` 子类除外)。
|
||||
- **Crockford Base32**:日志 tag、bundle hash、thread id 等标识约定(引擎侧);工作区内自定义日志若沿用引擎 logger,tag 为 8 字符 Crockford Base32,且每个调用点唯一。
|
||||
- **Named exports only**:不要使用 **default export**;workflow bundle 须 **export const run** 与 **export const descriptor**。
|
||||
- **No console.log**:库代码用结构化 logger;CLI 用户输出可按项目 Biome 规则例外标注。
|
||||
- **No dynamic import**:业务与 bundle 内禁止 \`import()\`;例外仅限「运行时路径由用户提供的 bundle 加载器」(引擎内部)。
|
||||
|
||||
## 5. Template 复用
|
||||
|
||||
- **已发布模板**:可通过 npm 依赖 \`@uncaged/workflow-template-*\` 等包,在 workflow 实例中 import 其 **WorkflowDefinition** 再绑定 Agent。
|
||||
- **本地模板**:放在本仓库 \`templates/<name>/\`,由 workspace 协议引用(如 \`"template-foo": "workspace:*"\` 或相对路径),便于同源修改与版本控制。
|
||||
|
||||
选择模板时保持 **definition 与 agent 绑定分离**:模板只描述「做什么、顺序如何」,实例决定「谁执行、如何抽取 meta」。
|
||||
|
||||
## 6. Build and Test
|
||||
|
||||
日常命令:
|
||||
|
||||
\`\`\`sh
|
||||
bun install
|
||||
bun run check # Biome:lint + format
|
||||
bun test
|
||||
bun build # 若包内配置了 build 脚本则用于产出 dist / bundle
|
||||
uncaged-workflow add <name> <path/to/bundle.esm.js>
|
||||
\`\`\`
|
||||
|
||||
提交前至少运行 **bun run check** 与 **bun test**;registry 与本地运行流参见 README 与 CLI 文档。
|
||||
|
||||
## 7. 常见陷阱
|
||||
|
||||
- **No dynamic import**:bundle 须静态可分析;动态 \`import()\` 会破坏哈希与加载约束。
|
||||
- **No default export**:引擎只接受命名导出 \`run\` / \`descriptor\`。
|
||||
- **No console.log**:避免在可被 Biome \`noConsole\` 规则覆盖的代码路径直接使用 console。
|
||||
- **Single-file ESM bundle**:交付物是单一 \`.esm.js\`;静态 import 仅限 Node 内置(见 architecture 文档中的 Bundle Contract)。
|
||||
|
||||
---
|
||||
|
||||
编写新 workflow 时,先对齐 **RoleMeta → RoleDefinition(Zod)→ Moderator → 绑定 → 单文件 bundle**,再对照本节规范自检。
|
||||
`;
|
||||
}
|
||||
|
||||
function readmeMd(workspaceName: string): string {
|
||||
return `# ${workspaceName}
|
||||
|
||||
Local workflow development workspace (Bun monorepo).
|
||||
|
||||
## Layout
|
||||
|
||||
- \`templates/\` — reusable workflow definition packages (roles + moderator), no agent binding
|
||||
- \`workflows/\` — workflow instances that bind templates to agents and export \`run\` + \`descriptor\`
|
||||
|
||||
## Commands
|
||||
|
||||
\`\`\`sh
|
||||
bun install
|
||||
bun run check # after you add scripts / Biome
|
||||
uncaged-workflow add <name> <bundle.esm.js>
|
||||
uncaged-workflow run <name>
|
||||
\`\`\`
|
||||
|
||||
Create this skeleton with:
|
||||
|
||||
\`\`\`sh
|
||||
uncaged-workflow init workspace ${workspaceName}
|
||||
\`\`\`
|
||||
`;
|
||||
}
|
||||
|
||||
export async function cmdInitWorkspace(
|
||||
parentDir: string,
|
||||
workspaceName: string,
|
||||
): Promise<Result<CmdInitWorkspaceSuccess, string>> {
|
||||
const validated = validateWorkspaceSegment(workspaceName);
|
||||
if (!validated.ok) {
|
||||
return validated;
|
||||
}
|
||||
|
||||
const rootPath = join(parentDir, workspaceName);
|
||||
if (await pathExists(rootPath)) {
|
||||
return err(`directory already exists: ${rootPath}`);
|
||||
}
|
||||
|
||||
await mkdir(rootPath, { recursive: false });
|
||||
await mkdir(join(rootPath, "templates"), { recursive: false });
|
||||
await mkdir(join(rootPath, "workflows"), { recursive: false });
|
||||
|
||||
await Promise.all([
|
||||
writeFile(join(rootPath, "package.json"), rootPackageJson(workspaceName), "utf8"),
|
||||
writeFile(join(rootPath, "biome.json"), biomeJson(), "utf8"),
|
||||
writeFile(join(rootPath, "tsconfig.json"), tsconfigJson(), "utf8"),
|
||||
writeFile(join(rootPath, "AGENTS.md"), agentsMd(), "utf8"),
|
||||
writeFile(join(rootPath, "README.md"), readmeMd(workspaceName), "utf8"),
|
||||
writeFile(join(rootPath, "templates", ".gitkeep"), "", "utf8"),
|
||||
writeFile(join(rootPath, "workflows", "package.json"), workflowsPackageJson(), "utf8"),
|
||||
]);
|
||||
|
||||
return ok({ rootPath });
|
||||
}
|
||||
|
||||
function hasTemplatesWorkspaceGlob(workspaces: unknown): boolean {
|
||||
return Array.isArray(workspaces) && workspaces.includes("templates/*");
|
||||
}
|
||||
|
||||
async function readPackageJsonWorkspaces(dir: string): Promise<unknown | null> {
|
||||
const pkgPath = join(dir, "package.json");
|
||||
if (!(await pathExists(pkgPath))) {
|
||||
return null;
|
||||
}
|
||||
let raw: string;
|
||||
try {
|
||||
raw = await readFile(pkgPath, "utf8");
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
let parsed: unknown;
|
||||
try {
|
||||
parsed = JSON.parse(raw) as unknown;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
if (typeof parsed !== "object" || parsed === null || !("workspaces" in parsed)) {
|
||||
return null;
|
||||
}
|
||||
return (parsed as { workspaces: unknown }).workspaces;
|
||||
}
|
||||
|
||||
/** Resolve uncaged-workflow workspace root (package.json with `templates/*` in `workspaces`). */
|
||||
async function findWorkflowWorkspaceRoot(startDir: string): Promise<Result<string, string>> {
|
||||
let dir = resolve(startDir);
|
||||
for (;;) {
|
||||
const workspaces = await readPackageJsonWorkspaces(dir);
|
||||
if (workspaces !== null && hasTemplatesWorkspaceGlob(workspaces)) {
|
||||
return ok(dir);
|
||||
}
|
||||
const parent = dirname(dir);
|
||||
if (parent === dir) {
|
||||
return err(
|
||||
'not inside a workflow workspace (no package.json with workspaces containing "templates/*")',
|
||||
);
|
||||
}
|
||||
dir = parent;
|
||||
}
|
||||
}
|
||||
|
||||
function templatePackageJson(templateName: string): string {
|
||||
return `${JSON.stringify(
|
||||
{
|
||||
name: `template-${templateName}`,
|
||||
version: "0.0.0",
|
||||
private: true,
|
||||
type: "module",
|
||||
dependencies: {
|
||||
"@uncaged/workflow": "^0.1.0",
|
||||
zod: "^4.0.0",
|
||||
},
|
||||
},
|
||||
null,
|
||||
2,
|
||||
)}\n`;
|
||||
}
|
||||
|
||||
function templateTsconfigJson(): string {
|
||||
return `${JSON.stringify(
|
||||
{
|
||||
extends: "../../tsconfig.json",
|
||||
compilerOptions: {
|
||||
rootDir: "src",
|
||||
outDir: "dist",
|
||||
},
|
||||
include: ["src/**/*.ts"],
|
||||
},
|
||||
null,
|
||||
2,
|
||||
)}\n`;
|
||||
}
|
||||
|
||||
function templateRolesTs(): string {
|
||||
return `import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const HELLO_TEMPLATE_DESCRIPTION =
|
||||
"Minimal starter template: one greeter role, then END.";
|
||||
|
||||
export type HelloTemplateMeta = {
|
||||
greeter: {
|
||||
message: string;
|
||||
};
|
||||
};
|
||||
|
||||
const greeterMetaSchema = z.object({
|
||||
message: z.string(),
|
||||
});
|
||||
|
||||
export const greeterRole: RoleDefinition<HelloTemplateMeta["greeter"]> = {
|
||||
description: "Says hello — replace with your first role.",
|
||||
systemPrompt: "You are a helpful assistant. Reply with one short friendly sentence.",
|
||||
extractPrompt: "Extract the assistant's greeting as message.",
|
||||
schema: greeterMetaSchema,
|
||||
extractRefs: null,
|
||||
};
|
||||
`;
|
||||
}
|
||||
|
||||
function templateModeratorTs(): string {
|
||||
return `import { END, type Moderator, type ModeratorContext } from "@uncaged/workflow";
|
||||
|
||||
import type { HelloTemplateMeta } from "./roles.js";
|
||||
|
||||
export const helloTemplateModerator: Moderator<HelloTemplateMeta> = (
|
||||
ctx: ModeratorContext<HelloTemplateMeta>,
|
||||
) => {
|
||||
if (ctx.steps.length === 0) {
|
||||
return "greeter";
|
||||
}
|
||||
return END;
|
||||
};
|
||||
`;
|
||||
}
|
||||
|
||||
function templateIndexTs(): string {
|
||||
return `import type { WorkflowDefinition } from "@uncaged/workflow";
|
||||
|
||||
import { helloTemplateModerator } from "./moderator.js";
|
||||
import {
|
||||
HELLO_TEMPLATE_DESCRIPTION,
|
||||
type HelloTemplateMeta,
|
||||
greeterRole,
|
||||
} from "./roles.js";
|
||||
|
||||
export {
|
||||
HELLO_TEMPLATE_DESCRIPTION,
|
||||
type HelloTemplateMeta,
|
||||
greeterRole,
|
||||
} from "./roles.js";
|
||||
export { helloTemplateModerator } from "./moderator.js";
|
||||
|
||||
export const helloTemplateWorkflowDefinition: WorkflowDefinition<HelloTemplateMeta> = {
|
||||
description: HELLO_TEMPLATE_DESCRIPTION,
|
||||
roles: {
|
||||
greeter: greeterRole,
|
||||
},
|
||||
moderator: helloTemplateModerator,
|
||||
};
|
||||
`;
|
||||
}
|
||||
|
||||
export async function cmdInitTemplate(
|
||||
startDir: string,
|
||||
templateName: string,
|
||||
): Promise<Result<CmdInitTemplateSuccess, string>> {
|
||||
const validated = validateWorkspaceSegment(templateName);
|
||||
if (!validated.ok) {
|
||||
return validated;
|
||||
}
|
||||
|
||||
const rootResult = await findWorkflowWorkspaceRoot(startDir);
|
||||
if (!rootResult.ok) {
|
||||
return rootResult;
|
||||
}
|
||||
|
||||
const workspaceRoot = rootResult.value;
|
||||
const templateDir = join(workspaceRoot, "templates", templateName);
|
||||
if (await pathExists(templateDir)) {
|
||||
return err(`template already exists: ${templateDir}`);
|
||||
}
|
||||
|
||||
await mkdir(join(templateDir, "src"), { recursive: true });
|
||||
|
||||
await Promise.all([
|
||||
writeFile(join(templateDir, "package.json"), templatePackageJson(templateName), "utf8"),
|
||||
writeFile(join(templateDir, "tsconfig.json"), templateTsconfigJson(), "utf8"),
|
||||
writeFile(join(templateDir, "src", "roles.ts"), templateRolesTs(), "utf8"),
|
||||
writeFile(join(templateDir, "src", "moderator.ts"), templateModeratorTs(), "utf8"),
|
||||
writeFile(join(templateDir, "src", "index.ts"), templateIndexTs(), "utf8"),
|
||||
]);
|
||||
|
||||
return ok({ templatePath: templateDir });
|
||||
}
|
||||
@@ -0,0 +1,463 @@
|
||||
import { watch } from "node:fs";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { dirname, join } from "node:path";
|
||||
|
||||
import {
|
||||
type CasStore,
|
||||
createCasStore,
|
||||
getContentMerklePayload,
|
||||
getGlobalCasDir,
|
||||
tryParseRoleStepRecord,
|
||||
tryParseWorkflowResultRecord,
|
||||
type WorkflowCompletion,
|
||||
} from "@uncaged/workflow";
|
||||
|
||||
import { printCliError, printCliLine } from "./cli-output.js";
|
||||
import { pathExists } from "./fs-utils.js";
|
||||
import type { ParsedLiveArgv } from "./live-argv.js";
|
||||
import { findLatestThreadDataPath, resolveThreadDataPath } from "./thread-scan.js";
|
||||
|
||||
export const LIVE_CONTENT_MAX_LINES = 10;
|
||||
|
||||
export type LiveRoleRow = {
|
||||
role: string;
|
||||
content: string;
|
||||
meta: Record<string, unknown>;
|
||||
timestamp: number;
|
||||
};
|
||||
|
||||
export function formatLiveTimeLabel(timestampMs: number): string {
|
||||
const d = new Date(timestampMs);
|
||||
const hh = String(d.getHours()).padStart(2, "0");
|
||||
const mm = String(d.getMinutes()).padStart(2, "0");
|
||||
const ss = String(d.getSeconds()).padStart(2, "0");
|
||||
return `${hh}:${mm}:${ss}`;
|
||||
}
|
||||
|
||||
function shouldUseColor(): boolean {
|
||||
return process.stdout.isTTY === true && process.env.NO_COLOR === undefined;
|
||||
}
|
||||
|
||||
function highlightLiveRole(name: string): string {
|
||||
if (!shouldUseColor()) {
|
||||
return name;
|
||||
}
|
||||
return `\x1b[1m\x1b[36m${name}\x1b[0m`;
|
||||
}
|
||||
|
||||
function dimGreyLine(line: string): string {
|
||||
if (!shouldUseColor()) {
|
||||
return line;
|
||||
}
|
||||
return `\x1b[2m\x1b[90m${line}\x1b[0m`;
|
||||
}
|
||||
|
||||
export function formatLiveDebugLine(timestampMs: number, tag: string, message: string): string {
|
||||
const label = `[${formatLiveTimeLabel(timestampMs)}] [${tag}] ${message.replace(/\n/g, " ")}`;
|
||||
return dimGreyLine(label);
|
||||
}
|
||||
|
||||
export function renderLiveRoleStepLines(row: LiveRoleRow, roleDisplay: string): string[] {
|
||||
const header = `[${formatLiveTimeLabel(row.timestamp)}] ▶ ${roleDisplay}`;
|
||||
const lines: string[] = [header];
|
||||
const parts = row.content.split("\n");
|
||||
const shown = parts.slice(0, LIVE_CONTENT_MAX_LINES);
|
||||
for (const ln of shown) {
|
||||
lines.push(` ${ln}`);
|
||||
}
|
||||
const omitted = parts.length - shown.length;
|
||||
if (omitted > 0) {
|
||||
lines.push(` … (${omitted} more line${omitted === 1 ? "" : "s"})`);
|
||||
}
|
||||
lines.push(` meta: ${JSON.stringify(row.meta)}`);
|
||||
return lines;
|
||||
}
|
||||
|
||||
function printSummary(result: WorkflowCompletion): void {
|
||||
printCliLine(`completed: returnCode=${result.returnCode} — ${result.summary}`);
|
||||
}
|
||||
|
||||
type LiveSessionState = {
|
||||
sawStart: boolean;
|
||||
completed: boolean;
|
||||
carry: string;
|
||||
contentOffset: number;
|
||||
};
|
||||
|
||||
type InfoLiveState = {
|
||||
carry: string;
|
||||
contentOffset: number;
|
||||
};
|
||||
|
||||
function tryParseInfoRecord(obj: Record<string, unknown>): {
|
||||
tag: string;
|
||||
content: string;
|
||||
timestamp: number;
|
||||
} | null {
|
||||
const tag = obj.tag;
|
||||
const content = obj.content;
|
||||
const timestamp = obj.timestamp;
|
||||
if (
|
||||
typeof tag !== "string" ||
|
||||
typeof content !== "string" ||
|
||||
typeof timestamp !== "number" ||
|
||||
!Number.isFinite(timestamp)
|
||||
) {
|
||||
return null;
|
||||
}
|
||||
return { tag, content, timestamp };
|
||||
}
|
||||
|
||||
async function handleJsonlLine(
|
||||
rawLine: string,
|
||||
state: LiveSessionState,
|
||||
roleFilter: string | null,
|
||||
cas: CasStore,
|
||||
): Promise<{ parseError: string | null; workflowResult: WorkflowCompletion | null }> {
|
||||
const trimmed = rawLine.trim();
|
||||
if (trimmed === "") {
|
||||
return { parseError: null, workflowResult: null };
|
||||
}
|
||||
|
||||
let rec: unknown;
|
||||
try {
|
||||
rec = JSON.parse(trimmed) as unknown;
|
||||
} catch {
|
||||
return { parseError: "invalid JSON in thread data file", workflowResult: null };
|
||||
}
|
||||
if (rec === null || typeof rec !== "object") {
|
||||
return { parseError: "invalid record in thread data file", workflowResult: null };
|
||||
}
|
||||
const obj = rec as Record<string, unknown>;
|
||||
|
||||
if (!state.sawStart) {
|
||||
state.sawStart = true;
|
||||
return { parseError: null, workflowResult: null };
|
||||
}
|
||||
|
||||
const wf = tryParseWorkflowResultRecord(obj);
|
||||
if (wf !== null) {
|
||||
state.completed = true;
|
||||
return { parseError: null, workflowResult: wf };
|
||||
}
|
||||
|
||||
const roleRow = tryParseRoleStepRecord(obj);
|
||||
if (roleRow === null) {
|
||||
return {
|
||||
parseError: "unrecognized record in thread data (expected role step or result)",
|
||||
workflowResult: null,
|
||||
};
|
||||
}
|
||||
|
||||
if (roleFilter !== null && roleRow.role !== roleFilter) {
|
||||
return { parseError: null, workflowResult: null };
|
||||
}
|
||||
|
||||
const payload = await getContentMerklePayload(cas, roleRow.contentHash);
|
||||
const content =
|
||||
payload !== null ? payload : `(content not in CAS; contentHash=${roleRow.contentHash})`;
|
||||
|
||||
const row: LiveRoleRow = {
|
||||
role: roleRow.role,
|
||||
content,
|
||||
meta: roleRow.meta,
|
||||
timestamp: roleRow.timestamp,
|
||||
};
|
||||
for (const outLine of renderLiveRoleStepLines(row, highlightLiveRole(row.role))) {
|
||||
printCliLine(outLine);
|
||||
}
|
||||
return { parseError: null, workflowResult: null };
|
||||
}
|
||||
|
||||
async function pumpNewContent(
|
||||
dataPath: string,
|
||||
state: LiveSessionState,
|
||||
roleFilter: string | null,
|
||||
cas: CasStore,
|
||||
): Promise<number | null> {
|
||||
let text: string;
|
||||
try {
|
||||
text = await readFile(dataPath, "utf8");
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
|
||||
if (text.length < state.contentOffset) {
|
||||
state.contentOffset = 0;
|
||||
state.carry = "";
|
||||
}
|
||||
|
||||
const chunk = text.slice(state.contentOffset);
|
||||
state.contentOffset = text.length;
|
||||
state.carry += chunk;
|
||||
|
||||
const parts = state.carry.split("\n");
|
||||
state.carry = parts.pop() ?? "";
|
||||
|
||||
for (const line of parts) {
|
||||
const { parseError, workflowResult } = await handleJsonlLine(line, state, roleFilter, cas);
|
||||
if (parseError !== null) {
|
||||
printCliError(parseError);
|
||||
return 1;
|
||||
}
|
||||
if (workflowResult !== null) {
|
||||
printSummary(workflowResult);
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
async function pumpNewInfoContent(infoPath: string, state: InfoLiveState): Promise<void> {
|
||||
let text: string;
|
||||
try {
|
||||
text = await readFile(infoPath, "utf8");
|
||||
} catch {
|
||||
return;
|
||||
}
|
||||
|
||||
if (text.length < state.contentOffset) {
|
||||
state.contentOffset = 0;
|
||||
state.carry = "";
|
||||
}
|
||||
|
||||
const chunk = text.slice(state.contentOffset);
|
||||
state.contentOffset = text.length;
|
||||
state.carry += chunk;
|
||||
|
||||
const parts = state.carry.split("\n");
|
||||
state.carry = parts.pop() ?? "";
|
||||
|
||||
for (const line of parts) {
|
||||
const trimmed = line.trim();
|
||||
if (trimmed === "") {
|
||||
continue;
|
||||
}
|
||||
let rec: unknown;
|
||||
try {
|
||||
rec = JSON.parse(trimmed) as unknown;
|
||||
} catch {
|
||||
continue;
|
||||
}
|
||||
if (rec === null || typeof rec !== "object") {
|
||||
continue;
|
||||
}
|
||||
const parsed = tryParseInfoRecord(rec as Record<string, unknown>);
|
||||
if (parsed === null) {
|
||||
continue;
|
||||
}
|
||||
printCliLine(formatLiveDebugLine(parsed.timestamp, parsed.tag, parsed.content));
|
||||
}
|
||||
}
|
||||
|
||||
type WatchPumpTask = {
|
||||
path: string;
|
||||
pump: () => Promise<number | null>;
|
||||
};
|
||||
|
||||
async function runWatchPumpStep(
|
||||
settled: () => boolean,
|
||||
pump: () => Promise<number | null>,
|
||||
closeAll: () => void,
|
||||
finish: (code: number) => void,
|
||||
): Promise<void> {
|
||||
if (settled()) {
|
||||
return;
|
||||
}
|
||||
try {
|
||||
const code = await pump();
|
||||
if (code !== null) {
|
||||
closeAll();
|
||||
finish(code);
|
||||
}
|
||||
} catch (e) {
|
||||
closeAll();
|
||||
throw e instanceof Error ? e : new Error(String(e));
|
||||
}
|
||||
}
|
||||
|
||||
function watchLivePaths(params: { tasks: WatchPumpTask[]; signal: AbortSignal }): Promise<number> {
|
||||
const { tasks, signal } = params;
|
||||
|
||||
return new Promise((resolve, reject) => {
|
||||
let settled = false;
|
||||
const finish = (code: number): void => {
|
||||
if (settled) {
|
||||
return;
|
||||
}
|
||||
settled = true;
|
||||
resolve(code);
|
||||
};
|
||||
|
||||
const pumpChains = new Map<string, Promise<void>>();
|
||||
for (const t of tasks) {
|
||||
pumpChains.set(t.path, Promise.resolve());
|
||||
}
|
||||
|
||||
const watchers: ReturnType<typeof watch>[] = [];
|
||||
|
||||
const closeAll = (): void => {
|
||||
for (const w of watchers) {
|
||||
w.close();
|
||||
}
|
||||
};
|
||||
|
||||
function schedulePump(path: string, pump: () => Promise<number | null>): void {
|
||||
const prev = pumpChains.get(path) ?? Promise.resolve();
|
||||
const next = (async () => {
|
||||
await prev;
|
||||
await runWatchPumpStep(() => settled, pump, closeAll, finish);
|
||||
})();
|
||||
pumpChains.set(path, next);
|
||||
}
|
||||
|
||||
for (const { path, pump } of tasks) {
|
||||
const watcher = watch(path, (eventType) => {
|
||||
if (eventType === "rename") {
|
||||
return;
|
||||
}
|
||||
schedulePump(path, pump);
|
||||
});
|
||||
watchers.push(watcher);
|
||||
watcher.on("error", (err: Error) => {
|
||||
closeAll();
|
||||
reject(err);
|
||||
});
|
||||
}
|
||||
|
||||
const onAbort = (): void => {
|
||||
closeAll();
|
||||
finish(0);
|
||||
};
|
||||
signal.addEventListener("abort", onAbort, { once: true });
|
||||
|
||||
for (const { path, pump } of tasks) {
|
||||
schedulePump(path, pump);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
type LiveThreadTarget = {
|
||||
threadId: string;
|
||||
dataPath: string;
|
||||
};
|
||||
|
||||
async function resolveLiveThreadTarget(
|
||||
storageRoot: string,
|
||||
parsed: ParsedLiveArgv,
|
||||
): Promise<LiveThreadTarget | null> {
|
||||
if (parsed.latest) {
|
||||
const found = await findLatestThreadDataPath(storageRoot);
|
||||
if (found === null) {
|
||||
printCliError("live: no threads found");
|
||||
return null;
|
||||
}
|
||||
return found;
|
||||
}
|
||||
|
||||
const id = parsed.threadId;
|
||||
if (id === null) {
|
||||
printCliError("live: internal error: missing thread id");
|
||||
return null;
|
||||
}
|
||||
const resolved = await resolveThreadDataPath(storageRoot, id);
|
||||
if (resolved === null) {
|
||||
printCliError(`thread not found: ${id}`);
|
||||
return null;
|
||||
}
|
||||
return { threadId: id, dataPath: resolved };
|
||||
}
|
||||
|
||||
async function buildLiveWatchTasks(params: {
|
||||
dataPath: string;
|
||||
infoPath: string;
|
||||
debug: boolean;
|
||||
dataState: LiveSessionState;
|
||||
infoState: InfoLiveState;
|
||||
roleFilter: string | null;
|
||||
cas: CasStore;
|
||||
}): Promise<WatchPumpTask[]> {
|
||||
const { dataPath, infoPath, debug, dataState, infoState, roleFilter, cas } = params;
|
||||
const tasks: WatchPumpTask[] = [
|
||||
{
|
||||
path: dataPath,
|
||||
pump: () => pumpNewContent(dataPath, dataState, roleFilter, cas),
|
||||
},
|
||||
];
|
||||
|
||||
if (debug && (await pathExists(infoPath))) {
|
||||
tasks.push({
|
||||
path: infoPath,
|
||||
pump: async () => {
|
||||
await pumpNewInfoContent(infoPath, infoState);
|
||||
return null;
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
return tasks;
|
||||
}
|
||||
|
||||
export async function cmdLive(storageRoot: string, parsed: ParsedLiveArgv): Promise<number> {
|
||||
const target = await resolveLiveThreadTarget(storageRoot, parsed);
|
||||
if (target === null) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
const { threadId, dataPath } = target;
|
||||
const roleFilter = parsed.role;
|
||||
const infoPath = join(dirname(dataPath), `${threadId}.info.jsonl`);
|
||||
const cas = createCasStore(getGlobalCasDir(storageRoot));
|
||||
|
||||
const dataState: LiveSessionState = {
|
||||
sawStart: false,
|
||||
completed: false,
|
||||
carry: "",
|
||||
contentOffset: 0,
|
||||
};
|
||||
|
||||
const infoState: InfoLiveState = {
|
||||
carry: "",
|
||||
contentOffset: 0,
|
||||
};
|
||||
|
||||
const controller = new AbortController();
|
||||
const onSigInt = (): void => {
|
||||
controller.abort();
|
||||
};
|
||||
process.on("SIGINT", onSigInt);
|
||||
|
||||
try {
|
||||
const firstData = await pumpNewContent(dataPath, dataState, roleFilter, cas);
|
||||
if (firstData === 1) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
if (parsed.debug && (await pathExists(infoPath))) {
|
||||
await pumpNewInfoContent(infoPath, infoState);
|
||||
}
|
||||
|
||||
if (firstData === 0 || dataState.completed) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
const tasks = await buildLiveWatchTasks({
|
||||
dataPath,
|
||||
infoPath,
|
||||
debug: parsed.debug,
|
||||
dataState,
|
||||
infoState,
|
||||
roleFilter,
|
||||
cas,
|
||||
});
|
||||
|
||||
return await watchLivePaths({ tasks, signal: controller.signal });
|
||||
} catch (e) {
|
||||
const message = e instanceof Error ? e.message : String(e);
|
||||
printCliError(`live: ${message}`);
|
||||
return 1;
|
||||
} finally {
|
||||
process.off("SIGINT", onSigInt);
|
||||
}
|
||||
}
|
||||
@@ -44,6 +44,7 @@ export async function cmdRollback(
|
||||
}
|
||||
|
||||
const nextRegistry = {
|
||||
config: reg.value.config,
|
||||
workflows: { ...reg.value.workflows, [name]: rolled.value },
|
||||
};
|
||||
const written = await writeWorkflowRegistry(storageRoot, nextRegistry);
|
||||
|
||||
@@ -15,7 +15,6 @@ export async function cmdRun(
|
||||
storageRoot: string,
|
||||
name: string,
|
||||
prompt: string,
|
||||
isDryRun: boolean,
|
||||
maxRounds: number,
|
||||
): Promise<Result<{ threadId: string }, string>> {
|
||||
const nameOk = validateCliWorkflowName(name);
|
||||
@@ -47,7 +46,7 @@ export async function cmdRun(
|
||||
threadId,
|
||||
workflowName: name,
|
||||
prompt,
|
||||
options: { isDryRun, maxRounds },
|
||||
options: { maxRounds, depth: 0 },
|
||||
},
|
||||
{ awaitResponseLine: false },
|
||||
);
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { unlink } from "node:fs/promises";
|
||||
import { dirname, join } from "node:path";
|
||||
|
||||
import { err, ok, type Result } from "@uncaged/workflow";
|
||||
import { err, garbageCollectCas, ok, type Result } from "@uncaged/workflow";
|
||||
|
||||
import { readTextFileIfExists } from "./fs-utils.js";
|
||||
import { resolveThreadDataPath } from "./thread-scan.js";
|
||||
@@ -38,5 +38,7 @@ export async function cmdThreadRemove(
|
||||
await unlink(infoPath).catch(() => {});
|
||||
await unlink(runningPath).catch(() => {});
|
||||
|
||||
await garbageCollectCas(storageRoot);
|
||||
|
||||
return ok(undefined);
|
||||
}
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
import { err, ok, type Result } from "@uncaged/workflow";
|
||||
|
||||
export type ParsedLiveArgv = {
|
||||
threadId: string | null;
|
||||
latest: boolean;
|
||||
debug: boolean;
|
||||
role: string | null;
|
||||
};
|
||||
|
||||
type LiveArgvScan = {
|
||||
latest: boolean;
|
||||
debug: boolean;
|
||||
role: string | null;
|
||||
threadId: string | null;
|
||||
};
|
||||
|
||||
function applyLiveArgvToken(argv: string[], i: number, s: LiveArgvScan): Result<number, string> {
|
||||
const a = argv[i];
|
||||
if (a === "--latest") {
|
||||
s.latest = true;
|
||||
return ok(i + 1);
|
||||
}
|
||||
if (a === "--debug") {
|
||||
s.debug = true;
|
||||
return ok(i + 1);
|
||||
}
|
||||
if (a === "--role") {
|
||||
const v = argv[i + 1];
|
||||
if (v === undefined || v.startsWith("--")) {
|
||||
return err("missing value for --role");
|
||||
}
|
||||
s.role = v;
|
||||
return ok(i + 2);
|
||||
}
|
||||
if (a.startsWith("--")) {
|
||||
return err(`unknown live flag: ${a}`);
|
||||
}
|
||||
if (s.threadId !== null) {
|
||||
return err("unexpected extra argument");
|
||||
}
|
||||
s.threadId = a;
|
||||
return ok(i + 1);
|
||||
}
|
||||
|
||||
export function parseLiveArgv(argv: string[]): Result<ParsedLiveArgv, string> {
|
||||
const s: LiveArgvScan = {
|
||||
latest: false,
|
||||
debug: false,
|
||||
role: null,
|
||||
threadId: null,
|
||||
};
|
||||
|
||||
let i = 0;
|
||||
while (i < argv.length) {
|
||||
const step = applyLiveArgvToken(argv, i, s);
|
||||
if (!step.ok) {
|
||||
return step;
|
||||
}
|
||||
i = step.value;
|
||||
}
|
||||
|
||||
if (s.latest && s.threadId !== null) {
|
||||
return err("live --latest does not take <thread-id>");
|
||||
}
|
||||
if (!s.latest && s.threadId === null) {
|
||||
return err("live requires <thread-id> or --latest");
|
||||
}
|
||||
|
||||
return ok({
|
||||
threadId: s.threadId,
|
||||
latest: s.latest,
|
||||
debug: s.debug,
|
||||
role: s.role,
|
||||
});
|
||||
}
|
||||
@@ -3,20 +3,13 @@ import { err, ok, type Result } from "@uncaged/workflow";
|
||||
export type ParsedRunArgv = {
|
||||
name: string;
|
||||
prompt: string;
|
||||
dryRun: boolean;
|
||||
maxRounds: number;
|
||||
};
|
||||
|
||||
type FlagOk =
|
||||
| { kind: "dry-run" }
|
||||
| { kind: "prompt"; value: string }
|
||||
| { kind: "max-rounds"; value: number };
|
||||
type FlagOk = { kind: "prompt"; value: string } | { kind: "max-rounds"; value: number };
|
||||
|
||||
function parseFlagAt(argv: string[], index: number): Result<FlagOk, string> | null {
|
||||
const flag = argv[index];
|
||||
if (flag === "--dry-run") {
|
||||
return ok({ kind: "dry-run" });
|
||||
}
|
||||
if (flag === "--prompt") {
|
||||
const value = argv[index + 1];
|
||||
if (value === undefined) {
|
||||
@@ -41,7 +34,6 @@ function parseFlagAt(argv: string[], index: number): Result<FlagOk, string> | nu
|
||||
export function parseRunArgv(argv: string[]): Result<ParsedRunArgv, string> {
|
||||
let name: string | undefined;
|
||||
let prompt = "";
|
||||
let dryRun = false;
|
||||
let maxRounds = 5;
|
||||
|
||||
let i = 0;
|
||||
@@ -62,11 +54,6 @@ export function parseRunArgv(argv: string[]): Result<ParsedRunArgv, string> {
|
||||
}
|
||||
|
||||
const flag = parsed.value;
|
||||
if (flag.kind === "dry-run") {
|
||||
dryRun = true;
|
||||
i += 1;
|
||||
continue;
|
||||
}
|
||||
if (flag.kind === "prompt") {
|
||||
prompt = flag.value;
|
||||
i += 2;
|
||||
@@ -80,5 +67,5 @@ export function parseRunArgv(argv: string[]): Result<ParsedRunArgv, string> {
|
||||
return err("run requires <name>");
|
||||
}
|
||||
|
||||
return ok({ name, prompt, dryRun, maxRounds });
|
||||
return ok({ name, prompt, maxRounds });
|
||||
}
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { readdir } from "node:fs/promises";
|
||||
import { readdir, stat } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { pathExists, readTextFileIfExists } from "./fs-utils.js";
|
||||
@@ -15,6 +15,28 @@ export type HistoricalThreadRow = {
|
||||
workflowName: string | null;
|
||||
};
|
||||
|
||||
async function readThreadStartTimestampMs(dataPath: string): Promise<number | null> {
|
||||
const text = await readTextFileIfExists(dataPath);
|
||||
if (text === null) {
|
||||
return null;
|
||||
}
|
||||
const firstLine = text.split("\n")[0];
|
||||
if (firstLine === undefined || firstLine.trim() === "") {
|
||||
return null;
|
||||
}
|
||||
let parsed: unknown;
|
||||
try {
|
||||
parsed = JSON.parse(firstLine) as unknown;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
if (parsed === null || typeof parsed !== "object") {
|
||||
return null;
|
||||
}
|
||||
const ts = (parsed as Record<string, unknown>).timestamp;
|
||||
return typeof ts === "number" && Number.isFinite(ts) ? ts : null;
|
||||
}
|
||||
|
||||
async function readWorkflowNameFromDataJsonl(dataPath: string): Promise<string | null> {
|
||||
const text = await readTextFileIfExists(dataPath);
|
||||
if (text === null) {
|
||||
@@ -124,6 +146,50 @@ export async function listHistoricalThreads(
|
||||
return out;
|
||||
}
|
||||
|
||||
/**
|
||||
* Picks the thread whose `.data.jsonl` is newest by start-record `timestamp`,
|
||||
* falling back to file `mtime` when the timestamp is missing.
|
||||
* Tie-breaker: larger `mtime` wins when start timestamps are equal.
|
||||
*/
|
||||
export async function findLatestThreadDataPath(
|
||||
storageRoot: string,
|
||||
): Promise<{ threadId: string; dataPath: string } | null> {
|
||||
const threads = await listHistoricalThreads(storageRoot, null);
|
||||
if (threads.length === 0) {
|
||||
return null;
|
||||
}
|
||||
|
||||
let best: {
|
||||
threadId: string;
|
||||
dataPath: string;
|
||||
primary: number;
|
||||
secondary: number;
|
||||
} | null = null;
|
||||
|
||||
for (const t of threads) {
|
||||
const dataPath = join(storageRoot, "logs", t.hash, `${t.threadId}.data.jsonl`);
|
||||
let mtimeMs = 0;
|
||||
try {
|
||||
const st = await stat(dataPath);
|
||||
mtimeMs = st.mtimeMs;
|
||||
} catch {
|
||||
continue;
|
||||
}
|
||||
const startTs = await readThreadStartTimestampMs(dataPath);
|
||||
const primary = startTs !== null ? startTs : mtimeMs;
|
||||
const secondary = mtimeMs;
|
||||
if (
|
||||
best === null ||
|
||||
primary > best.primary ||
|
||||
(primary === best.primary && secondary > best.secondary)
|
||||
) {
|
||||
best = { threadId: t.threadId, dataPath, primary, secondary };
|
||||
}
|
||||
}
|
||||
|
||||
return best === null ? null : { threadId: best.threadId, dataPath: best.dataPath };
|
||||
}
|
||||
|
||||
export async function resolveThreadDataPath(
|
||||
storageRoot: string,
|
||||
threadId: string,
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { type ChildProcessWithoutNullStreams, spawn } from "node:child_process";
|
||||
import { type ChildProcess, spawn } from "node:child_process";
|
||||
import { mkdir, readdir, unlink, writeFile } from "node:fs/promises";
|
||||
import { createConnection } from "node:net";
|
||||
import { join } from "node:path";
|
||||
@@ -23,7 +23,7 @@ function isProcessAlive(pid: number): boolean {
|
||||
|
||||
async function waitForReadyLine(
|
||||
childStdout: NodeJS.ReadableStream,
|
||||
child: ChildProcessWithoutNullStreams,
|
||||
child: ChildProcess,
|
||||
): Promise<Result<number, string>> {
|
||||
return await new Promise((resolve) => {
|
||||
let buf = "";
|
||||
|
||||
@@ -14,7 +14,8 @@
|
||||
"sourceMap": true,
|
||||
"composite": true,
|
||||
"outDir": "dist",
|
||||
"rootDir": "src"
|
||||
"rootDir": "src",
|
||||
"types": ["bun-types"]
|
||||
},
|
||||
"references": [{ "path": "../workflow" }],
|
||||
"include": ["src/**/*.ts"]
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -1,33 +1,41 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import type { ExtractContext, ExtractFn } from "@uncaged/workflow";
|
||||
import type * as z from "zod/v4";
|
||||
import { createCursorAgent, validateCursorAgentConfig } from "../src/index.js";
|
||||
|
||||
const testExtract: ExtractFn = async <T extends Record<string, unknown>>(
|
||||
_schema: z.ZodType<T>,
|
||||
_prompt: string,
|
||||
_ctx: ExtractContext,
|
||||
): Promise<T> => ({ workspace: "/tmp" }) as unknown as T;
|
||||
|
||||
describe("validateCursorAgentConfig", () => {
|
||||
test("accepts valid config", () => {
|
||||
const r = validateCursorAgentConfig({
|
||||
workdir: "/tmp",
|
||||
model: null,
|
||||
timeout: null,
|
||||
timeout: 0,
|
||||
extract: testExtract,
|
||||
});
|
||||
expect(r.ok).toBe(true);
|
||||
});
|
||||
|
||||
test("rejects empty workdir", () => {
|
||||
test("rejects non-function extract", () => {
|
||||
const r = validateCursorAgentConfig({
|
||||
workdir: " ",
|
||||
model: null,
|
||||
timeout: null,
|
||||
timeout: 0,
|
||||
extract: null as unknown as ExtractFn,
|
||||
});
|
||||
expect(r.ok).toBe(false);
|
||||
if (!r.ok) {
|
||||
expect(r.error).toContain("workdir");
|
||||
expect(r.error).toContain("extract");
|
||||
}
|
||||
});
|
||||
|
||||
test("rejects negative timeout", () => {
|
||||
const r = validateCursorAgentConfig({
|
||||
workdir: "/tmp",
|
||||
model: null,
|
||||
timeout: -1,
|
||||
extract: testExtract,
|
||||
});
|
||||
expect(r.ok).toBe(false);
|
||||
});
|
||||
@@ -36,9 +44,9 @@ describe("validateCursorAgentConfig", () => {
|
||||
describe("createCursorAgent", () => {
|
||||
test("returns an AgentFn", () => {
|
||||
const agent = createCursorAgent({
|
||||
workdir: "/tmp",
|
||||
model: null,
|
||||
timeout: null,
|
||||
timeout: 0,
|
||||
extract: testExtract,
|
||||
});
|
||||
expect(typeof agent).toBe("function");
|
||||
});
|
||||
@@ -46,9 +54,9 @@ describe("createCursorAgent", () => {
|
||||
test("throws on invalid config at construction", () => {
|
||||
expect(() =>
|
||||
createCursorAgent({
|
||||
workdir: "",
|
||||
model: null,
|
||||
timeout: null,
|
||||
timeout: -1,
|
||||
extract: testExtract,
|
||||
}),
|
||||
).toThrow();
|
||||
});
|
||||
|
||||
@@ -10,6 +10,7 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"@uncaged/workflow-util-agent": "workspace:*"
|
||||
"@uncaged/workflow-util-agent": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
import type { AgentFn } from "@uncaged/workflow";
|
||||
import type { AgentFn, ExtractContext } from "@uncaged/workflow";
|
||||
import { buildAgentPrompt, type SpawnCliError, spawnCli } from "@uncaged/workflow-util-agent";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
import type { CursorAgentConfig } from "./types.js";
|
||||
import { validateCursorAgentConfig } from "./validate-config.js";
|
||||
@@ -8,6 +9,12 @@ export { buildAgentPrompt } from "@uncaged/workflow-util-agent";
|
||||
export type { CursorAgentConfig } from "./types.js";
|
||||
export { validateCursorAgentConfig } from "./validate-config.js";
|
||||
|
||||
const cursorWorkspaceSchema = z.object({
|
||||
workspace: z
|
||||
.string()
|
||||
.describe("Absolute path to the project/repository directory the agent should work in"),
|
||||
});
|
||||
|
||||
function throwCursorSpawnError(error: SpawnCliError): never {
|
||||
if (error.kind === "non_zero_exit") {
|
||||
throw new Error(
|
||||
@@ -27,7 +34,7 @@ function resolveCursorModel(model: string | null): string {
|
||||
return model === null ? "auto" : model;
|
||||
}
|
||||
|
||||
/** Runs `cursor-agent` in {@link CursorAgentConfig.workdir} with a prompt built from context + system prompt. */
|
||||
/** Runs `cursor-agent` with workspace from {@link CursorAgentConfig.extract} and prompt from context. */
|
||||
export function createCursorAgent(config: CursorAgentConfig): AgentFn {
|
||||
const validated = validateCursorAgentConfig(config);
|
||||
if (!validated.ok) {
|
||||
@@ -35,22 +42,33 @@ export function createCursorAgent(config: CursorAgentConfig): AgentFn {
|
||||
}
|
||||
|
||||
const modelFlag = resolveCursorModel(config.model);
|
||||
const timeoutMs = config.timeout;
|
||||
const timeoutMs = config.timeout > 0 ? config.timeout : null;
|
||||
|
||||
return async (ctx, systemPrompt) => {
|
||||
const fullPrompt = buildAgentPrompt(systemPrompt, ctx);
|
||||
return async (ctx) => {
|
||||
const extractCtx: ExtractContext = {
|
||||
...ctx,
|
||||
agentContent: "",
|
||||
};
|
||||
const { workspace } = await config.extract(
|
||||
cursorWorkspaceSchema,
|
||||
"From the thread context, determine the absolute filesystem path where the project/repository is located.",
|
||||
extractCtx,
|
||||
);
|
||||
const fullPrompt = await buildAgentPrompt(ctx);
|
||||
const args = [
|
||||
"-p",
|
||||
fullPrompt,
|
||||
"--model",
|
||||
modelFlag,
|
||||
"--workspace",
|
||||
workspace,
|
||||
"--output-format",
|
||||
"text",
|
||||
"--trust",
|
||||
"--force",
|
||||
];
|
||||
const run = await spawnCli("cursor-agent", args, {
|
||||
cwd: config.workdir,
|
||||
cwd: workspace,
|
||||
timeoutMs,
|
||||
});
|
||||
if (!run.ok) {
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
import type { ExtractFn } from "@uncaged/workflow";
|
||||
|
||||
export type CursorAgentConfig = {
|
||||
workdir: string;
|
||||
model: string | null;
|
||||
timeout: number | null;
|
||||
timeout: number;
|
||||
extract: ExtractFn;
|
||||
};
|
||||
|
||||
@@ -3,11 +3,11 @@ import { err, ok, type Result } from "@uncaged/workflow";
|
||||
import type { CursorAgentConfig } from "./types.js";
|
||||
|
||||
export function validateCursorAgentConfig(config: CursorAgentConfig): Result<void, string> {
|
||||
if (config.workdir.trim() === "") {
|
||||
return err("workdir must be a non-empty string");
|
||||
if (typeof config.extract !== "function") {
|
||||
return err("extract must be a function");
|
||||
}
|
||||
if (config.timeout !== null && config.timeout < 0) {
|
||||
return err("timeout must be null or a non-negative number (milliseconds)");
|
||||
if (config.timeout < 0) {
|
||||
return err("timeout must be a non-negative number (milliseconds); use 0 for no limit");
|
||||
}
|
||||
return ok(undefined);
|
||||
}
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -34,8 +34,8 @@ export function createHermesAgent(config: HermesAgentConfig): AgentFn {
|
||||
|
||||
const timeoutMs = config.timeout;
|
||||
|
||||
return async (ctx, systemPrompt) => {
|
||||
const fullPrompt = buildAgentPrompt(systemPrompt, ctx);
|
||||
return async (ctx) => {
|
||||
const fullPrompt = await buildAgentPrompt(ctx);
|
||||
const args = [
|
||||
"chat",
|
||||
"-q",
|
||||
|
||||
File diff suppressed because one or more lines are too long
+19
-9
@@ -1,8 +1,14 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { START, type ThreadContext } from "@uncaged/workflow";
|
||||
import { mkdtempSync } from "node:fs";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { createCasStore, START, type ThreadContext } from "@uncaged/workflow";
|
||||
|
||||
import { createLlmAdapter } from "../src/create-llm-adapter.js";
|
||||
|
||||
const casDir = mkdtempSync(join(tmpdir(), "wf-llm-adapter-cas-"));
|
||||
const testCas = createCasStore(casDir);
|
||||
|
||||
function makeCtx(userContent: string): ThreadContext {
|
||||
return {
|
||||
start: {
|
||||
@@ -11,7 +17,11 @@ function makeCtx(userContent: string): ThreadContext {
|
||||
meta: { maxRounds: 10 },
|
||||
timestamp: 1,
|
||||
},
|
||||
depth: 0,
|
||||
steps: [],
|
||||
threadId: "01TEST000000000000000000TR",
|
||||
currentRole: { name: "planner", systemPrompt: "system instructions" },
|
||||
cas: testCas,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -19,17 +29,17 @@ describe("createLlmAdapter", () => {
|
||||
const originalFetch = globalThis.fetch;
|
||||
|
||||
test("posts system + user (start.content) and returns assistant text", async () => {
|
||||
globalThis.fetch = () =>
|
||||
globalThis.fetch = (() =>
|
||||
Promise.resolve(
|
||||
new Response(JSON.stringify({ choices: [{ message: { content: "model reply" } }] }), {
|
||||
status: 200,
|
||||
headers: { "Content-Type": "application/json" },
|
||||
}),
|
||||
);
|
||||
)) as unknown as typeof fetch;
|
||||
|
||||
const provider = { baseUrl: "https://api.example/v1", apiKey: "k", model: "m" };
|
||||
const adapter = createLlmAdapter(provider);
|
||||
const out = await adapter(makeCtx("trigger text"), "system instructions");
|
||||
const out = await adapter(makeCtx("trigger text"));
|
||||
|
||||
globalThis.fetch = originalFetch;
|
||||
|
||||
@@ -37,28 +47,28 @@ describe("createLlmAdapter", () => {
|
||||
});
|
||||
|
||||
test("throws on non-ok fetch response", async () => {
|
||||
globalThis.fetch = () =>
|
||||
globalThis.fetch = (() =>
|
||||
Promise.resolve(
|
||||
new Response("Internal Server Error", {
|
||||
status: 500,
|
||||
headers: { "Content-Type": "text/plain" },
|
||||
}),
|
||||
);
|
||||
)) as unknown as typeof fetch;
|
||||
|
||||
const provider = { baseUrl: "https://api.example/v1", apiKey: "k", model: "m" };
|
||||
const adapter = createLlmAdapter(provider);
|
||||
|
||||
await expect(adapter(makeCtx("hi"), "sys")).rejects.toThrow("llm:");
|
||||
await expect(adapter(makeCtx("hi"))).rejects.toThrow("llm:");
|
||||
globalThis.fetch = originalFetch;
|
||||
});
|
||||
|
||||
test("throws on fetch network failure", async () => {
|
||||
globalThis.fetch = () => Promise.reject(new Error("ECONNREFUSED"));
|
||||
globalThis.fetch = (() => Promise.reject(new Error("ECONNREFUSED"))) as unknown as typeof fetch;
|
||||
|
||||
const provider = { baseUrl: "https://api.example/v1", apiKey: "k", model: "m" };
|
||||
const adapter = createLlmAdapter(provider);
|
||||
|
||||
await expect(adapter(makeCtx("hi"), "sys")).rejects.toThrow();
|
||||
await expect(adapter(makeCtx("hi"))).rejects.toThrow();
|
||||
globalThis.fetch = originalFetch;
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-agent-llm",
|
||||
"version": "0.1.0",
|
||||
"type": "module",
|
||||
"main": "src/index.ts",
|
||||
"types": "src/index.ts",
|
||||
"scripts": {
|
||||
"build": "echo 'TODO'",
|
||||
"test": "bun test"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*"
|
||||
}
|
||||
}
|
||||
+13
-5
@@ -1,6 +1,14 @@
|
||||
import { type AgentFn, err, ok, type Result, type ThreadContext } from "@uncaged/workflow";
|
||||
import {
|
||||
type AgentContext,
|
||||
type AgentFn,
|
||||
err,
|
||||
type LlmProvider,
|
||||
ok,
|
||||
type Result,
|
||||
} from "@uncaged/workflow";
|
||||
|
||||
import type { LlmMessage, LlmProvider } from "@uncaged/workflow-util-role";
|
||||
/** OpenAI chat completion message shape (passed to `/chat/completions`). */
|
||||
export type LlmMessage = { role: "system" | "user" | "assistant"; content: string };
|
||||
|
||||
export type LlmChatError =
|
||||
| { kind: "http_error"; status: number; body: string }
|
||||
@@ -89,13 +97,13 @@ export async function chatCompletionText(options: {
|
||||
return parseAssistantText(res.value);
|
||||
}
|
||||
|
||||
/** Single-turn chat adapter: system comes from `createRole` prompt; user is the thread start frame. */
|
||||
/** Single-turn chat adapter: system prompt comes from {@link AgentContext.currentRole}. */
|
||||
export function createLlmAdapter(provider: LlmProvider): AgentFn {
|
||||
return async (ctx: ThreadContext, systemPrompt: string) => {
|
||||
return async (ctx: AgentContext) => {
|
||||
const result = await chatCompletionText({
|
||||
provider,
|
||||
messages: [
|
||||
{ role: "system", content: systemPrompt },
|
||||
{ role: "system", content: ctx.currentRole.systemPrompt },
|
||||
{ role: "user", content: ctx.start.content },
|
||||
],
|
||||
});
|
||||
@@ -0,0 +1,6 @@
|
||||
export {
|
||||
chatCompletionText,
|
||||
createLlmAdapter,
|
||||
type LlmChatError,
|
||||
type LlmMessage,
|
||||
} from "./create-llm-adapter.js";
|
||||
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-role-coder",
|
||||
"version": "0.1.0",
|
||||
"type": "module",
|
||||
"main": "src/index.ts",
|
||||
"types": "src/index.ts",
|
||||
"scripts": {
|
||||
"build": "echo 'TODO'",
|
||||
"test": "echo no tests"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const coderMetaSchema = z.object({
|
||||
completedPhase: z.string(),
|
||||
filesChanged: z.array(z.string()),
|
||||
summary: z.string(),
|
||||
});
|
||||
|
||||
export type CoderMeta = z.infer<typeof coderMetaSchema>;
|
||||
|
||||
const CODER_SYSTEM = `You are a **coder**. Read the thread for the plan and work on the NEXT incomplete phase only.
|
||||
|
||||
## Finding the current thread ID
|
||||
|
||||
The thread ID is a 26-character Crockford Base32 string (e.g. \`06F03H5V6JTMDST6P3TVH42RWM\`). It appears in the first message of this conversation. If you are unsure, run:
|
||||
|
||||
uncaged-workflow threads
|
||||
|
||||
and use the ID of the active thread.
|
||||
|
||||
## Reading phase details
|
||||
|
||||
Each planner phase is identified by a content-hash and a title. To read a phase's full details (name, description, acceptance criteria), run:
|
||||
|
||||
uncaged-workflow cas get <THREAD_ID> <HASH>
|
||||
|
||||
Replace \`<THREAD_ID>\` with the actual thread ID and \`<HASH>\` with the phase hash from the plan.
|
||||
|
||||
## Completing a phase
|
||||
|
||||
Report which phase you completed using the phase **hash** (not the title). If you legitimately finish every remaining phase in this single turn, set completedPhase to the **last** phase hash in the plan (the workflow treats that as full completion). List the files you changed and summarize what you did.`;
|
||||
|
||||
export const coderRole: RoleDefinition<CoderMeta> = {
|
||||
description:
|
||||
"Implements the next incomplete planner phase and reports structured completion metadata.",
|
||||
systemPrompt: CODER_SYSTEM,
|
||||
extractPrompt:
|
||||
"Extract completedPhase: the planner phase hash finished this round (exact hash string from the plan). If multiple phases were finished in one round, use the last finished phase hash. Extract filesChanged and a summary of the work.",
|
||||
schema: coderMetaSchema,
|
||||
extractRefs: (meta) => [meta.completedPhase],
|
||||
extractMode: "single",
|
||||
};
|
||||
@@ -0,0 +1 @@
|
||||
export { type CoderMeta, coderMetaSchema, coderRole } from "./coder.js";
|
||||
+1
-1
@@ -6,5 +6,5 @@
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [{ "path": "../workflow" }, { "path": "../workflow-util-role" }]
|
||||
"references": [{ "path": "../workflow" }]
|
||||
}
|
||||
@@ -1,110 +1,19 @@
|
||||
import { describe, expect, spyOn, test } from "bun:test";
|
||||
import { execFile } from "node:child_process";
|
||||
import { appendFile, mkdir, mkdtemp, writeFile } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { promisify } from "node:util";
|
||||
import { describe, expect, test } from "bun:test";
|
||||
|
||||
import type { AgentFn, ThreadContext } from "@uncaged/workflow";
|
||||
import { START } from "@uncaged/workflow";
|
||||
import * as utilRole from "@uncaged/workflow-util-role";
|
||||
import { committerMetaSchema, committerRole } from "../src/committer.js";
|
||||
|
||||
import { createCommitterRole } from "../src/committer.js";
|
||||
import { gitExec } from "../src/git-exec.js";
|
||||
|
||||
const execFileAsync = promisify(execFile);
|
||||
|
||||
async function git(repo: string, args: string[]): Promise<void> {
|
||||
await gitExec(repo, args);
|
||||
}
|
||||
|
||||
async function setupRepoWithRemote(): Promise<{ repo: string }> {
|
||||
const base = await mkdtemp(join(tmpdir(), "wf-committer-"));
|
||||
const bare = join(base, "origin.git");
|
||||
const repo = join(base, "work");
|
||||
await mkdir(repo, { recursive: true });
|
||||
await mkdir(bare, { recursive: true });
|
||||
await execFileAsync("git", ["init"], { cwd: repo, encoding: "utf8" });
|
||||
await git(repo, ["config", "user.email", "t@t"]);
|
||||
await git(repo, ["config", "user.name", "t"]);
|
||||
await writeFile(join(repo, "README.md"), "# hi\n", "utf8");
|
||||
await git(repo, ["add", "README.md"]);
|
||||
await git(repo, ["commit", "-m", "init"]);
|
||||
await execFileAsync("git", ["init", "--bare"], { cwd: bare, encoding: "utf8" });
|
||||
await git(repo, ["remote", "add", "origin", bare]);
|
||||
await git(repo, ["push", "-u", "origin", "HEAD"]);
|
||||
return { repo };
|
||||
}
|
||||
|
||||
function makeCtx(): ThreadContext {
|
||||
return {
|
||||
start: {
|
||||
role: START,
|
||||
content: "do thing",
|
||||
meta: { maxRounds: 10 },
|
||||
timestamp: Date.now(),
|
||||
},
|
||||
steps: [],
|
||||
};
|
||||
}
|
||||
|
||||
const provider = { baseUrl: "https://example.com/v1", apiKey: "k", model: "m" };
|
||||
|
||||
describe("createCommitterRole", () => {
|
||||
test("returns committed false when working tree clean", async () => {
|
||||
const { repo } = await setupRepoWithRemote();
|
||||
const agent: AgentFn = async () => {
|
||||
throw new Error("agent should not run");
|
||||
};
|
||||
const role = createCommitterRole(
|
||||
agent,
|
||||
{ provider, dryRun: null, dryRunMeta: { branch: "dry-run", message: "chore: dry run" } },
|
||||
{ cwd: repo, remote: "origin", threadId: null },
|
||||
);
|
||||
const out = await role(makeCtx());
|
||||
expect(out.meta.committed).toBe(false);
|
||||
describe("committerRole", () => {
|
||||
test("committed sample validates against schema", () => {
|
||||
const parsed = committerMetaSchema.safeParse({
|
||||
status: "committed" as const,
|
||||
branch: "feat/example",
|
||||
commitSha: "abc1234",
|
||||
});
|
||||
expect(parsed.success).toBe(true);
|
||||
});
|
||||
|
||||
test("dry-run skips pipeline", async () => {
|
||||
const agent: AgentFn = async () => {
|
||||
throw new Error("agent should not run");
|
||||
};
|
||||
const role = createCommitterRole(agent, {
|
||||
provider,
|
||||
dryRun: true,
|
||||
dryRunMeta: { branch: "dry-run", message: "chore: dry run" },
|
||||
});
|
||||
const out = await role(makeCtx());
|
||||
expect(out.content).toBe("[dry-run] committer skipped");
|
||||
expect(out.meta).toEqual({ committed: true });
|
||||
});
|
||||
|
||||
test("commits and pushes when changes exist", async () => {
|
||||
const { repo } = await setupRepoWithRemote();
|
||||
await appendFile(join(repo, "README.md"), "\nmore\n", "utf8");
|
||||
|
||||
const spy = spyOn(utilRole, "extractMetaOrThrow").mockResolvedValue({
|
||||
branch: "feat/test-commit",
|
||||
message: "feat: add more",
|
||||
});
|
||||
|
||||
const agent: AgentFn = async () => "plan text";
|
||||
const role = createCommitterRole(
|
||||
agent,
|
||||
{ provider, dryRun: null, dryRunMeta: { branch: "dry-run", message: "chore: dry run" } },
|
||||
{ cwd: repo, remote: "origin", threadId: null },
|
||||
);
|
||||
|
||||
const out = await role(makeCtx());
|
||||
expect(out.meta.committed).toBe(true);
|
||||
expect(spy).toHaveBeenCalled();
|
||||
|
||||
const branches = await gitExec(repo, ["branch", "--list", "feat/test-commit"]);
|
||||
expect(branches).toContain("feat/test-commit");
|
||||
|
||||
const remoteRefs = await gitExec(repo, ["ls-remote", "--heads", "origin", "feat/test-commit"]);
|
||||
expect(remoteRefs.trim().length).toBeGreaterThan(0);
|
||||
|
||||
spy.mockRestore();
|
||||
test("exposes generic committer system prompt", () => {
|
||||
expect(committerRole.systemPrompt).toContain("git committer");
|
||||
expect(committerRole.systemPrompt).not.toContain("project is at");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -10,7 +10,6 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"@uncaged/workflow-util-role": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,153 +1,36 @@
|
||||
import type { AgentFn, Role, RoleResult, ThreadContext } from "@uncaged/workflow";
|
||||
import {
|
||||
decorateRole,
|
||||
extractMetaOrThrow,
|
||||
type LlmProvider,
|
||||
onFail,
|
||||
withDryRun,
|
||||
} from "@uncaged/workflow-util-role";
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
import { gitExec } from "./git-exec.js";
|
||||
export const committerMetaSchema = z.discriminatedUnion("status", [
|
||||
z.object({
|
||||
status: z.literal("committed"),
|
||||
branch: z.string(),
|
||||
commitSha: z.string(),
|
||||
}),
|
||||
z.object({
|
||||
status: z.literal("recoverable"),
|
||||
error: z.string(),
|
||||
logRef: z.string().nullable(),
|
||||
}),
|
||||
z.object({
|
||||
status: z.literal("unrecoverable"),
|
||||
error: z.string(),
|
||||
logRef: z.string().nullable(),
|
||||
}),
|
||||
]);
|
||||
|
||||
export const committerMetaSchema = z.object({
|
||||
committed: z
|
||||
.boolean()
|
||||
.describe("true if branch created, changes committed, and pushed successfully"),
|
||||
});
|
||||
export type CommitterMeta = z.infer<typeof committerMetaSchema>;
|
||||
|
||||
const committerPlanSchema = z.object({
|
||||
branch: z.string().describe("Feature branch name, e.g. feat/slug or fix/slug"),
|
||||
message: z.string().describe("Single-line conventional commit subject"),
|
||||
});
|
||||
const COMMITTER_SYSTEM = `You are the git committer. Create a branch and commit the changes.
|
||||
Report the branch name and commit SHA. On failure, classify as recoverable or unrecoverable.
|
||||
Do not attempt to fix failures yourself.`;
|
||||
|
||||
export type CommitterPlanMeta = z.infer<typeof committerPlanSchema>;
|
||||
|
||||
export type CommitterGitConfig = {
|
||||
cwd: string;
|
||||
remote: string;
|
||||
/** When non-null, prompts mention `uncaged-workflow thread <id>` for extra context. */
|
||||
threadId: string | null;
|
||||
export const committerRole: RoleDefinition<CommitterMeta> = {
|
||||
description: "Creates a branch and commits changes.",
|
||||
systemPrompt: COMMITTER_SYSTEM,
|
||||
extractPrompt:
|
||||
"Extract the commit result: committed (with branch and SHA), recoverable failure, or unrecoverable failure. Include error details and log references if applicable.",
|
||||
schema: committerMetaSchema,
|
||||
extractRefs: null,
|
||||
extractMode: "single",
|
||||
};
|
||||
|
||||
export const DEFAULT_COMMITTER_GIT_CONFIG: CommitterGitConfig = {
|
||||
cwd: ".",
|
||||
remote: "origin",
|
||||
threadId: null,
|
||||
};
|
||||
|
||||
function resolveExtractDryRun(extractDryRun: boolean | null): boolean {
|
||||
return extractDryRun === true;
|
||||
}
|
||||
|
||||
function summarizeThreadContext(ctx: ThreadContext): string {
|
||||
const lines: string[] = [`Initial prompt:\n${ctx.start.content}`];
|
||||
for (const step of ctx.steps) {
|
||||
const snippet = step.content.length > 800 ? `${step.content.slice(0, 800)}…` : step.content;
|
||||
lines.push(`\n### ${step.role}\n${snippet}`);
|
||||
}
|
||||
return lines.join("\n");
|
||||
}
|
||||
|
||||
function sanitizeBranch(branch: string): string {
|
||||
const t = branch.trim();
|
||||
if (
|
||||
t === "" ||
|
||||
t.includes("..") ||
|
||||
t.includes(" ") ||
|
||||
t.startsWith("-") ||
|
||||
t.includes("\n") ||
|
||||
t.includes("\t")
|
||||
) {
|
||||
throw new Error(`invalid branch name: ${branch}`);
|
||||
}
|
||||
return t;
|
||||
}
|
||||
|
||||
function sanitizeCommitMessage(message: string): string {
|
||||
const line = message.trim().split(/\r?\n/)[0] ?? "";
|
||||
if (line === "") {
|
||||
throw new Error("commit message is empty");
|
||||
}
|
||||
return line;
|
||||
}
|
||||
|
||||
function committerPlanPrompt(ctx: ThreadContext, gitConfig: CommitterGitConfig): string {
|
||||
const threadLine =
|
||||
gitConfig.threadId !== null
|
||||
? `Optional CLI context: run \`uncaged-workflow thread ${gitConfig.threadId}\` if available.\n`
|
||||
: "";
|
||||
|
||||
return `You plan a git branch and a single-line conventional commit message for the following workflow thread.
|
||||
|
||||
${threadLine}
|
||||
## Thread context
|
||||
|
||||
${summarizeThreadContext(ctx)}
|
||||
|
||||
## Your task
|
||||
|
||||
Infer a good branch name (\`feat/<slug>\` or \`fix/<slug>\`) and a conventional commit **subject** (one line, no body).
|
||||
|
||||
Reply with enough detail that a maintainer understands the change; structured extraction will read \`branch\` and \`message\` from your answer.`;
|
||||
}
|
||||
|
||||
async function runCommitterPipeline(
|
||||
ctx: ThreadContext,
|
||||
agent: AgentFn,
|
||||
extract: { provider: LlmProvider; dryRun: boolean | null; dryRunMeta: CommitterPlanMeta },
|
||||
gitConfig: CommitterGitConfig,
|
||||
): Promise<RoleResult<CommitterMeta>> {
|
||||
const cwd = gitConfig.cwd;
|
||||
const porcelain = await gitExec(cwd, ["status", "--porcelain"]);
|
||||
if (porcelain.trim() === "") {
|
||||
return {
|
||||
content: "Working tree clean; nothing to commit.",
|
||||
meta: { committed: false },
|
||||
};
|
||||
}
|
||||
|
||||
const prompt = committerPlanPrompt(ctx, gitConfig);
|
||||
const raw = await agent(ctx, prompt);
|
||||
const plan = await extractMetaOrThrow("committer-plan", raw, committerPlanSchema, {
|
||||
provider: extract.provider,
|
||||
dryRun: resolveExtractDryRun(extract.dryRun),
|
||||
dryRunMeta: extract.dryRunMeta,
|
||||
});
|
||||
|
||||
const branch = sanitizeBranch(plan.branch);
|
||||
const message = sanitizeCommitMessage(plan.message);
|
||||
|
||||
await gitExec(cwd, ["checkout", "-b", branch]);
|
||||
await gitExec(cwd, ["add", "-A"]);
|
||||
await gitExec(cwd, ["commit", "-m", message]);
|
||||
await gitExec(cwd, ["push", "-u", gitConfig.remote, branch]);
|
||||
|
||||
return {
|
||||
content: raw,
|
||||
meta: { committed: true },
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Git committer role: LLM proposes branch + message; this package runs git via `child_process`.
|
||||
* Decorators match nerve semantics: dry-run skips work with `committed: true`; failures yield `committed: false`.
|
||||
*/
|
||||
export function createCommitterRole(
|
||||
adapter: AgentFn,
|
||||
extract: { provider: LlmProvider; dryRun: boolean | null; dryRunMeta: CommitterPlanMeta },
|
||||
gitConfig: CommitterGitConfig = DEFAULT_COMMITTER_GIT_CONFIG,
|
||||
): Role<CommitterMeta> {
|
||||
const inner: Role<CommitterMeta> = async (ctx) =>
|
||||
runCommitterPipeline(ctx, adapter, extract, gitConfig);
|
||||
|
||||
return decorateRole(inner, [
|
||||
withDryRun<CommitterMeta>({
|
||||
label: "committer",
|
||||
meta: { committed: true },
|
||||
dryRun: resolveExtractDryRun(extract.dryRun),
|
||||
}),
|
||||
onFail<CommitterMeta>({ label: "committer", meta: { committed: false } }),
|
||||
]);
|
||||
}
|
||||
|
||||
@@ -1,26 +0,0 @@
|
||||
import { execFile } from "node:child_process";
|
||||
import { promisify } from "node:util";
|
||||
|
||||
const execFileAsync = promisify(execFile);
|
||||
|
||||
/** Runs `git` with args in `cwd`; throws if git exits non-zero. */
|
||||
export async function gitExec(cwd: string, args: readonly string[]): Promise<string> {
|
||||
try {
|
||||
const r = await execFileAsync("git", [...args], {
|
||||
cwd,
|
||||
encoding: "utf8",
|
||||
maxBuffer: 10 * 1024 * 1024,
|
||||
});
|
||||
return r.stdout;
|
||||
} catch (e) {
|
||||
const stderr =
|
||||
typeof e === "object" &&
|
||||
e !== null &&
|
||||
"stderr" in e &&
|
||||
typeof (e as { stderr: unknown }).stderr === "string"
|
||||
? (e as { stderr: string }).stderr
|
||||
: "";
|
||||
const msg = e instanceof Error ? e.message : String(e);
|
||||
throw new Error(`git ${args.join(" ")} failed: ${msg}${stderr ? ` (${stderr.trim()})` : ""}`);
|
||||
}
|
||||
}
|
||||
@@ -1,9 +1 @@
|
||||
export {
|
||||
type CommitterGitConfig,
|
||||
type CommitterMeta,
|
||||
type CommitterPlanMeta,
|
||||
committerMetaSchema,
|
||||
createCommitterRole,
|
||||
DEFAULT_COMMITTER_GIT_CONFIG,
|
||||
} from "./committer.js";
|
||||
export { gitExec } from "./git-exec.js";
|
||||
export { type CommitterMeta, committerMetaSchema, committerRole } from "./committer.js";
|
||||
|
||||
@@ -6,5 +6,5 @@
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [{ "path": "../workflow" }, { "path": "../workflow-util-role" }]
|
||||
"references": [{ "path": "../workflow" }]
|
||||
}
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -1,156 +0,0 @@
|
||||
import { afterEach, describe, expect, mock, spyOn, test } from "bun:test";
|
||||
import type { AgentFn, ThreadContext } from "@uncaged/workflow";
|
||||
import { START } from "@uncaged/workflow";
|
||||
import * as extractMetaModule from "@uncaged/workflow-util-role";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
import { createRole } from "../src/create-role.js";
|
||||
|
||||
const provider = {
|
||||
baseUrl: "https://example.com/v1",
|
||||
apiKey: "k",
|
||||
model: "m",
|
||||
};
|
||||
|
||||
function toolCallResponse(argsJson: string): Response {
|
||||
return new Response(
|
||||
JSON.stringify({
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
tool_calls: [
|
||||
{
|
||||
function: {
|
||||
name: "extract",
|
||||
arguments: argsJson,
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
],
|
||||
}),
|
||||
{ status: 200, headers: { "Content-Type": "application/json" } },
|
||||
);
|
||||
}
|
||||
|
||||
function makeCtx(): ThreadContext {
|
||||
return {
|
||||
start: {
|
||||
role: START,
|
||||
content: "",
|
||||
meta: { maxRounds: 10 },
|
||||
timestamp: Date.now(),
|
||||
},
|
||||
steps: [],
|
||||
};
|
||||
}
|
||||
|
||||
describe("createRole", () => {
|
||||
const originalFetch = globalThis.fetch;
|
||||
|
||||
afterEach(() => {
|
||||
globalThis.fetch = originalFetch;
|
||||
mock.restore();
|
||||
});
|
||||
|
||||
test("runs AgentFn then structured extract", async () => {
|
||||
globalThis.fetch = () => Promise.resolve(toolCallResponse(JSON.stringify({ n: 3 })));
|
||||
|
||||
const schema = z.object({ n: z.number() });
|
||||
const agent: AgentFn = async (_ctx, prompt) => prompt;
|
||||
const role = createRole({
|
||||
name: "test",
|
||||
schema,
|
||||
systemPrompt: "hello",
|
||||
agent,
|
||||
extract: { provider, dryRun: null, dryRunMeta: { n: 0 } },
|
||||
});
|
||||
|
||||
const out = await role(makeCtx());
|
||||
expect(out.content).toBe("hello");
|
||||
expect(out.meta).toEqual({ n: 3 });
|
||||
});
|
||||
|
||||
test("passes ThreadContext to AgentFn", async () => {
|
||||
globalThis.fetch = () => Promise.resolve(toolCallResponse(JSON.stringify({ n: 0 })));
|
||||
|
||||
const seen: ThreadContext[] = [];
|
||||
const agent: AgentFn = async (ctx, _prompt) => {
|
||||
seen.push(ctx);
|
||||
return "x";
|
||||
};
|
||||
const role = createRole({
|
||||
name: "test",
|
||||
schema: z.object({ n: z.number() }),
|
||||
systemPrompt: "p",
|
||||
agent,
|
||||
extract: { provider, dryRun: null, dryRunMeta: { n: 0 } },
|
||||
});
|
||||
await role(makeCtx());
|
||||
|
||||
expect(seen).toHaveLength(1);
|
||||
expect(seen[0].steps).toEqual([]);
|
||||
});
|
||||
|
||||
test("resolves dynamic systemPrompt functions before AgentFn", async () => {
|
||||
globalThis.fetch = () => Promise.resolve(toolCallResponse(JSON.stringify({ n: 99 })));
|
||||
|
||||
const schema = z.object({ n: z.number() });
|
||||
const agent: AgentFn = async (_ctx, prompt) => prompt;
|
||||
const role = createRole({
|
||||
name: "test",
|
||||
schema,
|
||||
systemPrompt: async (ctx) => `rounds=${ctx.steps.length}`,
|
||||
agent,
|
||||
extract: { provider, dryRun: null, dryRunMeta: { n: 0 } },
|
||||
});
|
||||
|
||||
const ctx = makeCtx();
|
||||
const out = await role(ctx);
|
||||
expect(out.content).toBe("rounds=0");
|
||||
expect(out.meta).toEqual({ n: 99 });
|
||||
});
|
||||
|
||||
test("extract dryRun null runs live extract path", async () => {
|
||||
const spy = spyOn(extractMetaModule, "extractMetaOrThrow").mockResolvedValue({ n: 0 });
|
||||
|
||||
const agent: AgentFn = async () => "raw";
|
||||
const role = createRole({
|
||||
name: "r1",
|
||||
schema: z.object({ n: z.number() }),
|
||||
systemPrompt: "p",
|
||||
agent,
|
||||
extract: { provider, dryRun: null, dryRunMeta: { n: 0 } },
|
||||
});
|
||||
await role(makeCtx());
|
||||
|
||||
expect(spy).toHaveBeenCalledWith(
|
||||
"r1",
|
||||
"raw",
|
||||
expect.anything(),
|
||||
expect.objectContaining({ provider, dryRun: false, dryRunMeta: { n: 0 } }),
|
||||
);
|
||||
});
|
||||
|
||||
test("extract.dryRun true uses structured extract dry-run", async () => {
|
||||
const spy = spyOn(extractMetaModule, "extractMetaOrThrow").mockResolvedValue({ n: 0 });
|
||||
|
||||
const agent: AgentFn = async () => "raw";
|
||||
const role = createRole({
|
||||
name: "r2",
|
||||
schema: z.object({ n: z.number() }),
|
||||
systemPrompt: "p",
|
||||
agent,
|
||||
extract: { provider, dryRun: true, dryRunMeta: { n: 0 } },
|
||||
});
|
||||
await role(makeCtx());
|
||||
|
||||
expect(spy).toHaveBeenCalledWith(
|
||||
"r2",
|
||||
"raw",
|
||||
expect.anything(),
|
||||
expect.objectContaining({ dryRun: true, dryRunMeta: { n: 0 } }),
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -1,35 +0,0 @@
|
||||
import type { AgentFn, Role, ThreadContext } from "@uncaged/workflow";
|
||||
import { extractMetaOrThrow, type LlmProvider } from "@uncaged/workflow-util-role";
|
||||
import type * as z from "zod/v4";
|
||||
|
||||
export type CreateRoleArgs<M extends Record<string, unknown>> = {
|
||||
name: string;
|
||||
schema: z.ZodType<M>;
|
||||
systemPrompt: string | ((ctx: ThreadContext) => Promise<string>);
|
||||
agent: AgentFn;
|
||||
extract: {
|
||||
provider: LlmProvider;
|
||||
/** When `true`, structured extract returns `dryRunMeta`. When `null`, live API extract. */
|
||||
dryRun: boolean | null;
|
||||
dryRunMeta: M;
|
||||
};
|
||||
};
|
||||
|
||||
function resolveExtractDryRun(extractDryRun: boolean | null): boolean {
|
||||
return extractDryRun === true;
|
||||
}
|
||||
|
||||
/** Builds a {@link Role} from an {@link AgentFn}, system prompt, Zod meta schema, and extract wiring. */
|
||||
export function createRole<M extends Record<string, unknown>>(args: CreateRoleArgs<M>): Role<M> {
|
||||
return async (ctx: ThreadContext) => {
|
||||
const promptText =
|
||||
typeof args.systemPrompt === "string" ? args.systemPrompt : await args.systemPrompt(ctx);
|
||||
const raw = await args.agent(ctx, promptText);
|
||||
const meta = await extractMetaOrThrow(args.name, raw, args.schema, {
|
||||
provider: args.extract.provider,
|
||||
dryRun: resolveExtractDryRun(args.extract.dryRun),
|
||||
dryRunMeta: args.extract.dryRunMeta,
|
||||
});
|
||||
return { content: raw, meta };
|
||||
};
|
||||
}
|
||||
@@ -1,21 +0,0 @@
|
||||
export {
|
||||
buildDescriptorFromRoles,
|
||||
decorateRole,
|
||||
extractMetaOrThrow,
|
||||
type LlmError,
|
||||
type LlmExtractArgs,
|
||||
type LlmMessage,
|
||||
type LlmProvider,
|
||||
llmErrorToCause,
|
||||
llmExtract,
|
||||
llmExtractWithRetry,
|
||||
type MetaExtractConfig,
|
||||
type OnFailOptions,
|
||||
onFail,
|
||||
type RoleDecorator,
|
||||
type RoleDescriptorInput,
|
||||
type WithDryRunOptions,
|
||||
withDryRun,
|
||||
} from "@uncaged/workflow-util-role";
|
||||
export { chatCompletionText, createLlmAdapter, type LlmChatError } from "./create-llm-adapter.js";
|
||||
export { type CreateRoleArgs, createRole } from "./create-role.js";
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-role-planner",
|
||||
"version": "0.1.0",
|
||||
"type": "module",
|
||||
"main": "src/index.ts",
|
||||
"types": "src/index.ts",
|
||||
"scripts": {
|
||||
"build": "echo 'TODO'",
|
||||
"test": "echo no tests"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
export {
|
||||
type PlannerMeta,
|
||||
phaseSchema,
|
||||
plannerMetaSchema,
|
||||
plannerRole,
|
||||
} from "./planner.js";
|
||||
@@ -0,0 +1,54 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const phaseSchema = z.object({
|
||||
hash: z.string(),
|
||||
title: z.string(),
|
||||
});
|
||||
|
||||
export const plannerMetaSchema = z.object({
|
||||
phases: z.array(phaseSchema),
|
||||
});
|
||||
|
||||
export type PlannerMeta = z.infer<typeof plannerMetaSchema>;
|
||||
|
||||
const PLANNER_SYSTEM = `You are a **planner** for a software task. Break the work into **sequential phases** the coder will execute one at a time.
|
||||
|
||||
## Finding the current thread ID
|
||||
|
||||
The thread ID is a 26-character Crockford Base32 string (e.g. \`06F03H5V6JTMDST6P3TVH42RWM\`). It appears in the first message of this conversation. If you are unsure, run:
|
||||
|
||||
uncaged-workflow threads
|
||||
|
||||
and use the ID of the active thread.
|
||||
|
||||
## Storing phase details — MANDATORY
|
||||
|
||||
For each phase you MUST store its full detail text in CAS using this exact CLI command:
|
||||
|
||||
uncaged-workflow cas put <THREAD_ID> '# <name>
|
||||
|
||||
Description: <description>
|
||||
|
||||
Acceptance: <acceptance>'
|
||||
|
||||
Replace \`<THREAD_ID>\` with the actual thread ID you found above. The command prints a content-hash to stdout — use that hash as the phase identifier.
|
||||
|
||||
**Do NOT store phase details in any other way** (no temp files, no invented paths). The CLI command is the only supported storage mechanism.
|
||||
|
||||
## Output format
|
||||
|
||||
After storing all phases via the CLI, output compact JSON only:
|
||||
{ "phases": [{ "hash": "<hash-from-cas-put>", "title": "<one-line-summary>" }] }
|
||||
|
||||
Order phases so earlier steps unblock later ones. Cover root cause, edge cases, and verification across the phases.`;
|
||||
|
||||
export const plannerRole: RoleDefinition<PlannerMeta> = {
|
||||
description: "Breaks the task into sequential phases for the coder.",
|
||||
systemPrompt: PLANNER_SYSTEM,
|
||||
extractPrompt:
|
||||
"Extract the implementation phases from the agent's output. Each phase has a hash (the CAS content-hash returned by the cas put command) and a title (one-line summary).",
|
||||
schema: plannerMetaSchema,
|
||||
extractRefs: (meta) => meta.phases.map((p) => p.hash),
|
||||
extractMode: "single",
|
||||
};
|
||||
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [{ "path": "../workflow" }]
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-role-preparer",
|
||||
"version": "0.1.0",
|
||||
"type": "module",
|
||||
"main": "src/index.ts",
|
||||
"types": "src/index.ts",
|
||||
"scripts": {
|
||||
"build": "echo 'TODO'",
|
||||
"test": "echo no tests"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,5 @@
|
||||
export {
|
||||
type PreparerMeta,
|
||||
preparerMetaSchema,
|
||||
preparerRole,
|
||||
} from "./preparer.js";
|
||||
@@ -0,0 +1,52 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
const toolchainSchema = z.object({
|
||||
packageManager: z.union([z.string(), z.null()]),
|
||||
testCommand: z.union([z.string(), z.null()]),
|
||||
lintCommand: z.union([z.string(), z.null()]),
|
||||
buildCommand: z.union([z.string(), z.null()]),
|
||||
});
|
||||
|
||||
export const preparerMetaSchema = z.object({
|
||||
repoPath: z.string(),
|
||||
defaultBranch: z.string(),
|
||||
conventions: z.union([z.string(), z.null()]),
|
||||
toolchain: toolchainSchema,
|
||||
});
|
||||
|
||||
export type PreparerMeta = z.infer<typeof preparerMetaSchema>;
|
||||
|
||||
const PREPARER_SYSTEM = `You are a **preparer** for a software task. Your job is to locate (or clone) the target repository locally, ensure it is up to date, and gather project context before work begins.
|
||||
|
||||
## Responsibilities
|
||||
|
||||
1. Parse the issue/task prompt to identify the target repository (URL, org/repo, or name).
|
||||
2. Search for an existing local clone in these locations (in order):
|
||||
- ~/Code/<repo-name>/
|
||||
- ~/repos/<repo-name>/
|
||||
- ~/Code/<org>/<repo-name>/
|
||||
- ~/repos/<org>/<repo-name>/
|
||||
3. If not found locally, \`git clone\` it into ~/repos/<repo-name>/.
|
||||
4. \`git checkout main && git pull\` (or the default branch) to ensure latest.
|
||||
5. Read project conventions: \`CLAUDE.md\`, \`CONTRIBUTING.md\`, \`.cursor/rules/*.mdc\`, \`CONVENTIONS.md\`.
|
||||
6. Detect toolchain: package manager, test runner, linter, build system.
|
||||
|
||||
## Output
|
||||
|
||||
Report your findings as structured data:
|
||||
- **repoPath**: absolute path to the local repo
|
||||
- **defaultBranch**: the default branch name (e.g. "main")
|
||||
- **conventions**: a summary of project conventions found, or null if none
|
||||
- **toolchain**: detected commands for packageManager, testCommand, lintCommand, buildCommand (null if not detected)`;
|
||||
|
||||
export const preparerRole: RoleDefinition<PreparerMeta> = {
|
||||
description:
|
||||
"Locates or clones the target repository, ensures it is up to date, and gathers project context (conventions, toolchain).",
|
||||
systemPrompt: PREPARER_SYSTEM,
|
||||
extractPrompt:
|
||||
"Extract repoPath (absolute path), defaultBranch, conventions (summary string or null), and toolchain (packageManager, testCommand, lintCommand, buildCommand — each string or null).",
|
||||
schema: preparerMetaSchema,
|
||||
extractRefs: null,
|
||||
extractMode: "single",
|
||||
};
|
||||
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist"
|
||||
},
|
||||
"include": ["src"]
|
||||
}
|
||||
@@ -1,92 +1,15 @@
|
||||
import { afterEach, describe, expect, mock, test } from "bun:test";
|
||||
import { describe, expect, test } from "bun:test";
|
||||
|
||||
import type { AgentFn, ThreadContext } from "@uncaged/workflow";
|
||||
import { START } from "@uncaged/workflow";
|
||||
import { reviewerMetaSchema, reviewerRole } from "../src/reviewer.js";
|
||||
|
||||
import { createReviewerRole, DEFAULT_REVIEWER_CONFIG } from "../src/reviewer.js";
|
||||
|
||||
function toolCallResponse(argsJson: string): Response {
|
||||
return new Response(
|
||||
JSON.stringify({
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
tool_calls: [
|
||||
{
|
||||
function: {
|
||||
name: "extract",
|
||||
arguments: argsJson,
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
],
|
||||
}),
|
||||
{ status: 200, headers: { "Content-Type": "application/json" } },
|
||||
);
|
||||
}
|
||||
|
||||
function makeCtx(): ThreadContext {
|
||||
return {
|
||||
start: {
|
||||
role: START,
|
||||
content: "task",
|
||||
meta: { maxRounds: 10 },
|
||||
timestamp: Date.now(),
|
||||
},
|
||||
steps: [],
|
||||
};
|
||||
}
|
||||
|
||||
const provider = { baseUrl: "https://example.com/v1", apiKey: "k", model: "m" };
|
||||
|
||||
describe("createReviewerRole", () => {
|
||||
const originalFetch = globalThis.fetch;
|
||||
|
||||
afterEach(() => {
|
||||
globalThis.fetch = originalFetch;
|
||||
mock.restore();
|
||||
describe("reviewerRole", () => {
|
||||
test("approved sample validates against schema", () => {
|
||||
const parsed = reviewerMetaSchema.safeParse({ status: "approved" as const });
|
||||
expect(parsed.success).toBe(true);
|
||||
});
|
||||
|
||||
test("runs reviewer extract", async () => {
|
||||
globalThis.fetch = () => Promise.resolve(toolCallResponse(JSON.stringify({ approved: true })));
|
||||
|
||||
const agent: AgentFn = async (_ctx, prompt) => {
|
||||
expect(prompt).toContain("git diff");
|
||||
expect(prompt).toContain(DEFAULT_REVIEWER_CONFIG.cwd);
|
||||
return "review done";
|
||||
};
|
||||
|
||||
const role = createReviewerRole(agent, {
|
||||
provider,
|
||||
dryRun: null,
|
||||
dryRunMeta: { approved: true },
|
||||
});
|
||||
const out = await role(makeCtx());
|
||||
expect(out.meta).toEqual({ approved: true });
|
||||
});
|
||||
|
||||
test("includes uncaged-workflow thread hint when threadId set", async () => {
|
||||
globalThis.fetch = () => Promise.resolve(toolCallResponse(JSON.stringify({ approved: false })));
|
||||
|
||||
let seen = "";
|
||||
const agent: AgentFn = async (_ctx, prompt) => {
|
||||
seen = prompt;
|
||||
return "x";
|
||||
};
|
||||
|
||||
const role = createReviewerRole(
|
||||
agent,
|
||||
{ provider, dryRun: null, dryRunMeta: { approved: false } },
|
||||
{
|
||||
cwd: "/proj",
|
||||
conventionsPath: null,
|
||||
extraChecks: [],
|
||||
threadId: "01ABCDEF234567890ABCDEFGH",
|
||||
},
|
||||
);
|
||||
await role(makeCtx());
|
||||
expect(seen).toContain("uncaged-workflow thread 01ABCDEF234567890ABCDEFGH");
|
||||
test("system prompt is generic (no cwd)", () => {
|
||||
expect(reviewerRole.systemPrompt).toContain("code reviewer");
|
||||
expect(reviewerRole.systemPrompt).not.toContain("project is at");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -10,8 +10,6 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"@uncaged/workflow-role-llm": "workspace:*",
|
||||
"@uncaged/workflow-util-role": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,7 +1 @@
|
||||
export {
|
||||
createReviewerRole,
|
||||
DEFAULT_REVIEWER_CONFIG,
|
||||
type ReviewerConfig,
|
||||
type ReviewerMeta,
|
||||
reviewerMetaSchema,
|
||||
} from "./reviewer.js";
|
||||
export { type ReviewerMeta, reviewerMetaSchema, reviewerRole } from "./reviewer.js";
|
||||
|
||||
@@ -1,108 +1,26 @@
|
||||
import type { AgentFn, Role, ThreadContext } from "@uncaged/workflow";
|
||||
import { createRole } from "@uncaged/workflow-role-llm";
|
||||
import type { LlmProvider } from "@uncaged/workflow-util-role";
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const reviewerMetaSchema = z.object({
|
||||
approved: z.boolean().describe("true if the diff is clean and ready to merge"),
|
||||
});
|
||||
export const reviewerMetaSchema = z.discriminatedUnion("status", [
|
||||
z.object({
|
||||
status: z.literal("approved"),
|
||||
}),
|
||||
z.object({
|
||||
status: z.literal("rejected"),
|
||||
issues: z.array(z.string()).describe("blocking issues that must be fixed"),
|
||||
}),
|
||||
]);
|
||||
export type ReviewerMeta = z.infer<typeof reviewerMetaSchema>;
|
||||
|
||||
export type ReviewerConfig = {
|
||||
cwd: string;
|
||||
conventionsPath: string | null;
|
||||
extraChecks: ReadonlyArray<string>;
|
||||
/** When non-null, prompts reference `uncaged-workflow thread <id>`. */
|
||||
threadId: string | null;
|
||||
const REVIEWER_SYSTEM = `You are a code reviewer. Review the current git diff. Give a clear approve or reject verdict.
|
||||
Only reject for blocking issues. End with your verdict.`;
|
||||
|
||||
export const reviewerRole: RoleDefinition<ReviewerMeta> = {
|
||||
description: "Runs git diff checks and sets approved when the change is ready.",
|
||||
systemPrompt: REVIEWER_SYSTEM,
|
||||
extractPrompt:
|
||||
"Extract the review verdict: approved or rejected. If rejected, list the blocking issues.",
|
||||
schema: reviewerMetaSchema,
|
||||
extractRefs: null,
|
||||
extractMode: "single",
|
||||
};
|
||||
|
||||
export const DEFAULT_REVIEWER_CONFIG: ReviewerConfig = {
|
||||
cwd: ".",
|
||||
conventionsPath: "CONVENTIONS.md",
|
||||
extraChecks: [],
|
||||
threadId: null,
|
||||
};
|
||||
|
||||
function summarizeThreadContext(ctx: ThreadContext): string {
|
||||
const lines: string[] = [`Initial prompt:\n${ctx.start.content}`];
|
||||
for (const step of ctx.steps) {
|
||||
const snippet = step.content.length > 600 ? `${step.content.slice(0, 600)}…` : step.content;
|
||||
lines.push(`\n### ${step.role}\n${snippet}`);
|
||||
}
|
||||
return lines.join("\n");
|
||||
}
|
||||
|
||||
function reviewerPrompt(config: ReviewerConfig, ctx: ThreadContext): string {
|
||||
const { cwd, conventionsPath, extraChecks, threadId } = config;
|
||||
|
||||
const conventionsBlock =
|
||||
conventionsPath !== null ? `Read project conventions: \`cat ${cwd}/${conventionsPath}\`\n` : "";
|
||||
|
||||
const threadBlock =
|
||||
threadId !== null
|
||||
? `Read the workflow thread for context: \`uncaged-workflow thread ${threadId}\`\n`
|
||||
: `## Thread context (no thread id)\n\n${summarizeThreadContext(ctx)}\n`;
|
||||
|
||||
const extraBlock =
|
||||
extraChecks.length > 0
|
||||
? `\n### Project-specific checks\n${extraChecks.map((c) => `- ${c}`).join("\n")}\n`
|
||||
: "";
|
||||
|
||||
return `You are a **code reviewer**. You run after the coder and before the tester.
|
||||
|
||||
**IMPORTANT: The project is at \`${cwd}\`. Always \`cd ${cwd}\` first.**
|
||||
|
||||
${threadBlock}
|
||||
${conventionsBlock}
|
||||
## Your job — static analysis of the git diff
|
||||
|
||||
Run these commands and analyze the output:
|
||||
|
||||
1. **\`cd ${cwd} && git diff --stat\`** — see what files changed
|
||||
2. **\`cd ${cwd} && git diff\`** — read the actual diff
|
||||
3. **\`cd ${cwd} && git status --short\`** — check for untracked files
|
||||
|
||||
## Checklist
|
||||
|
||||
### Reject (approved: false) — tell coder exactly what to fix
|
||||
- **Garbage files**: build artifacts, lockfiles, IDE config that should not be committed
|
||||
- **Secrets/credentials**: API keys, tokens, passwords hardcoded in the diff
|
||||
- **Unrelated changes**: files modified outside the scope of the task
|
||||
${
|
||||
conventionsPath !== null
|
||||
? `- **Convention violations**: patterns that contradict ${conventionsPath}\n`
|
||||
: ""
|
||||
}${extraBlock}
|
||||
### Approve (approved: true) — no comment needed
|
||||
- Diff is clean, focused, follows project standards
|
||||
|
||||
End with:
|
||||
\`\`\`json
|
||||
{ "approved": true }
|
||||
\`\`\`
|
||||
or
|
||||
\`\`\`json
|
||||
{ "approved": false }
|
||||
\`\`\``;
|
||||
}
|
||||
|
||||
/**
|
||||
* Code review role: agent inspects git diffs; structured extract yields `approved`.
|
||||
*/
|
||||
export function createReviewerRole(
|
||||
adapter: AgentFn,
|
||||
extract: { provider: LlmProvider; dryRun: boolean | null; dryRunMeta: ReviewerMeta },
|
||||
config: ReviewerConfig = DEFAULT_REVIEWER_CONFIG,
|
||||
): Role<ReviewerMeta> {
|
||||
return createRole({
|
||||
name: "reviewer",
|
||||
schema: reviewerMetaSchema,
|
||||
systemPrompt: async (ctx) => reviewerPrompt(config, ctx),
|
||||
agent: adapter,
|
||||
extract: {
|
||||
provider: extract.provider,
|
||||
dryRun: extract.dryRun,
|
||||
dryRunMeta: extract.dryRunMeta,
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
@@ -6,9 +6,5 @@
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [
|
||||
{ "path": "../workflow" },
|
||||
{ "path": "../workflow-role-llm" },
|
||||
{ "path": "../workflow-util-role" }
|
||||
]
|
||||
"references": [{ "path": "../workflow" }]
|
||||
}
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,39 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
|
||||
import { submitterMetaSchema, submitterRole } from "../src/submitter.js";
|
||||
|
||||
describe("submitterRole", () => {
|
||||
test("submitted sample validates against schema", () => {
|
||||
const parsed = submitterMetaSchema.safeParse({
|
||||
status: "submitted" as const,
|
||||
prUrl: "https://github.com/example/repo/pull/42",
|
||||
});
|
||||
expect(parsed.success).toBe(true);
|
||||
});
|
||||
|
||||
test("failed sample validates against schema", () => {
|
||||
const parsed = submitterMetaSchema.safeParse({
|
||||
status: "failed" as const,
|
||||
error: "gh not authenticated",
|
||||
});
|
||||
expect(parsed.success).toBe(true);
|
||||
});
|
||||
|
||||
test("rejects unknown status discriminant", () => {
|
||||
const parsed = submitterMetaSchema.safeParse({
|
||||
status: "queued",
|
||||
prUrl: "https://example.com",
|
||||
});
|
||||
expect(parsed.success).toBe(false);
|
||||
});
|
||||
|
||||
test("exposes submitter system prompt", () => {
|
||||
expect(submitterRole.systemPrompt).toContain("submitter");
|
||||
expect(submitterRole.systemPrompt).toContain("pull request");
|
||||
});
|
||||
|
||||
test("uses single extract mode without refs", () => {
|
||||
expect(submitterRole.extractMode).toBe("single");
|
||||
expect(submitterRole.extractRefs).toBeNull();
|
||||
});
|
||||
});
|
||||
+1
-4
@@ -1,12 +1,9 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-util-role",
|
||||
"name": "@uncaged/workflow-role-submitter",
|
||||
"version": "0.1.0",
|
||||
"type": "module",
|
||||
"main": "src/index.ts",
|
||||
"types": "src/index.ts",
|
||||
"exports": {
|
||||
".": "./src/index.ts"
|
||||
},
|
||||
"scripts": {
|
||||
"build": "echo 'TODO'",
|
||||
"test": "bun test"
|
||||
@@ -0,0 +1 @@
|
||||
export { type SubmitterMeta, submitterMetaSchema, submitterRole } from "./submitter.js";
|
||||
@@ -0,0 +1,44 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const submitterMetaSchema = z.discriminatedUnion("status", [
|
||||
z.object({
|
||||
status: z.literal("submitted"),
|
||||
prUrl: z.string(),
|
||||
}),
|
||||
z.object({
|
||||
status: z.literal("failed"),
|
||||
error: z.string(),
|
||||
}),
|
||||
]);
|
||||
|
||||
export type SubmitterMeta = z.infer<typeof submitterMetaSchema>;
|
||||
|
||||
const SUBMITTER_SYSTEM = `You are the **submitter**. Your job is to push the work branch to the remote and open a pull request.
|
||||
|
||||
## Inputs
|
||||
|
||||
Read the thread for context:
|
||||
- The **preparer**'s output gives you the absolute repo path and the default branch (and remote URL by inspecting the repo).
|
||||
- The **developer**'s output gives you the branch name that was committed and a list of files changed plus a summary of the work.
|
||||
|
||||
## Procedure
|
||||
|
||||
1. \`cd\` into the repo path from the preparer's output.
|
||||
2. Push the developer's branch to the remote: \`git push -u origin <branch>\`.
|
||||
3. Open a pull request (e.g. via \`gh pr create\`) targeting the default branch. The PR title should be short and describe the change. The PR description should summarize what changed (drawing from the developer's summary and filesChanged) and reference the original issue/task if applicable.
|
||||
4. Report the resulting PR URL.
|
||||
|
||||
On any failure (push rejected, gh not authenticated, PR creation failed, etc.), report status="failed" with a short error message. Do not retry — surface the error so the moderator can decide.`;
|
||||
|
||||
const SUBMITTER_EXTRACT_PROMPT =
|
||||
"Extract the submission result. status='submitted' with prUrl on success, or status='failed' with a short error message on failure.";
|
||||
|
||||
export const submitterRole: RoleDefinition<SubmitterMeta> = {
|
||||
description: "Pushes the developer's branch to the remote and opens a pull request.",
|
||||
systemPrompt: SUBMITTER_SYSTEM,
|
||||
extractPrompt: SUBMITTER_EXTRACT_PROMPT,
|
||||
schema: submitterMetaSchema,
|
||||
extractRefs: null,
|
||||
extractMode: "single",
|
||||
};
|
||||
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [{ "path": "../workflow" }]
|
||||
}
|
||||
+1
-5
@@ -1,19 +1,15 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-role-llm",
|
||||
"name": "@uncaged/workflow-role-tester",
|
||||
"version": "0.1.0",
|
||||
"type": "module",
|
||||
"main": "src/index.ts",
|
||||
"types": "src/index.ts",
|
||||
"exports": {
|
||||
".": "./src/index.ts"
|
||||
},
|
||||
"scripts": {
|
||||
"build": "echo 'TODO'",
|
||||
"test": "bun test"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"@uncaged/workflow-util-role": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
export { type TesterMeta, testerMetaSchema, testerRole } from "./tester.js";
|
||||
@@ -0,0 +1,27 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const testerMetaSchema = z.discriminatedUnion("status", [
|
||||
z.object({
|
||||
status: z.literal("passed"),
|
||||
details: z.string(),
|
||||
}),
|
||||
z.object({
|
||||
status: z.literal("failed"),
|
||||
details: z.string(),
|
||||
}),
|
||||
]);
|
||||
|
||||
export type TesterMeta = z.infer<typeof testerMetaSchema>;
|
||||
|
||||
const TESTER_SYSTEM = `You are a tester. Run the project's test suite, build, and lint commands. Check what commands are available from the preparer's output in the thread. Report pass/fail with details of what failed.`;
|
||||
|
||||
export const testerRole: RoleDefinition<TesterMeta> = {
|
||||
description: "Runs test, build, and lint commands and reports pass or fail with details.",
|
||||
systemPrompt: TESTER_SYSTEM,
|
||||
extractPrompt:
|
||||
"Extract the verification result: passed with summary details, or failed with details of what broke.",
|
||||
schema: testerMetaSchema,
|
||||
extractRefs: null,
|
||||
extractMode: "single",
|
||||
};
|
||||
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [{ "path": "../workflow" }]
|
||||
}
|
||||
@@ -0,0 +1,260 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import {
|
||||
END,
|
||||
type ModeratorContext,
|
||||
type RoleStep,
|
||||
START,
|
||||
validateWorkflowDescriptor,
|
||||
} from "@uncaged/workflow";
|
||||
|
||||
import type { CommitterMeta } from "@uncaged/workflow-role-committer";
|
||||
import type { PlannerMeta } from "@uncaged/workflow-role-planner";
|
||||
|
||||
import { buildDevelopDescriptor } from "../src/descriptor.js";
|
||||
import { developModerator } from "../src/index.js";
|
||||
import type { DevelopMeta } from "../src/roles.js";
|
||||
|
||||
const DEFAULT_PHASES: PlannerMeta["phases"] = [
|
||||
{
|
||||
hash: "4KNMR2PX",
|
||||
title: "Do the work",
|
||||
},
|
||||
];
|
||||
|
||||
function makeStart(maxRounds: number): ModeratorContext<DevelopMeta>["start"] {
|
||||
return {
|
||||
role: START,
|
||||
content: "Implement the feature",
|
||||
meta: { maxRounds },
|
||||
timestamp: 0,
|
||||
};
|
||||
}
|
||||
|
||||
function makeCtx(
|
||||
maxRounds: number,
|
||||
steps: ModeratorContext<DevelopMeta>["steps"],
|
||||
): ModeratorContext<DevelopMeta> {
|
||||
return {
|
||||
threadId: "01TEST000000000000000000TR",
|
||||
depth: 0,
|
||||
start: makeStart(maxRounds),
|
||||
steps,
|
||||
};
|
||||
}
|
||||
|
||||
function plannerStep(phases: PlannerMeta["phases"] = DEFAULT_PHASES): RoleStep<DevelopMeta> {
|
||||
return {
|
||||
role: "planner",
|
||||
contentHash: "STUBHASHPLANNER001",
|
||||
meta: { phases },
|
||||
refs: phases.map((p) => p.hash),
|
||||
timestamp: 1,
|
||||
};
|
||||
}
|
||||
|
||||
function coderStep(completedPhase = "4KNMR2PX"): RoleStep<DevelopMeta> {
|
||||
return {
|
||||
role: "coder",
|
||||
contentHash: "STUBHASHCODER00001",
|
||||
meta: { completedPhase, filesChanged: ["a.ts"], summary: "implemented" },
|
||||
refs: [completedPhase],
|
||||
timestamp: 2,
|
||||
};
|
||||
}
|
||||
|
||||
function reviewerStep(approved: boolean): RoleStep<DevelopMeta> {
|
||||
return {
|
||||
role: "reviewer",
|
||||
contentHash: "STUBHASHREVIEWER01",
|
||||
meta: approved
|
||||
? { status: "approved" as const }
|
||||
: { status: "rejected" as const, issues: ["needs fix"] },
|
||||
refs: [],
|
||||
timestamp: 3,
|
||||
};
|
||||
}
|
||||
|
||||
function testerStep(passed: boolean): RoleStep<DevelopMeta> {
|
||||
return {
|
||||
role: "tester",
|
||||
contentHash: "STUBHASHTESTER01",
|
||||
meta: passed
|
||||
? { status: "passed" as const, details: "all checks passed" }
|
||||
: { status: "failed" as const, details: "lint failed" },
|
||||
refs: [],
|
||||
timestamp: 4,
|
||||
};
|
||||
}
|
||||
|
||||
function committerStep(meta: CommitterMeta): RoleStep<DevelopMeta> {
|
||||
return {
|
||||
role: "committer",
|
||||
contentHash: "STUBHASHCOMMITTER1",
|
||||
meta,
|
||||
refs: [],
|
||||
timestamp: 5,
|
||||
};
|
||||
}
|
||||
|
||||
describe("developModerator", () => {
|
||||
test("routes initial → planner → coder → reviewer → tester → committer → END", () => {
|
||||
expect(developModerator(makeCtx(20, []))).toBe("planner");
|
||||
expect(developModerator(makeCtx(20, [plannerStep()]))).toBe("coder");
|
||||
expect(developModerator(makeCtx(20, [plannerStep(), coderStep()]))).toBe("reviewer");
|
||||
expect(developModerator(makeCtx(20, [plannerStep(), coderStep(), reviewerStep(true)]))).toBe(
|
||||
"tester",
|
||||
);
|
||||
expect(
|
||||
developModerator(
|
||||
makeCtx(20, [plannerStep(), coderStep(), reviewerStep(true), testerStep(true)]),
|
||||
),
|
||||
).toBe("committer");
|
||||
expect(
|
||||
developModerator(
|
||||
makeCtx(20, [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(true),
|
||||
testerStep(true),
|
||||
committerStep({ status: "committed", branch: "feat/x", commitSha: "abc1234" }),
|
||||
]),
|
||||
),
|
||||
).toBe(END);
|
||||
});
|
||||
|
||||
test("reviewer rejects → coder retry when budget allows", () => {
|
||||
const steps: ModeratorContext<DevelopMeta>["steps"] = [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(false),
|
||||
];
|
||||
expect(developModerator(makeCtx(20, steps))).toBe("coder");
|
||||
});
|
||||
|
||||
test("reviewer rejects → END when max rounds exhausted", () => {
|
||||
const steps: ModeratorContext<DevelopMeta>["steps"] = [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(false),
|
||||
];
|
||||
expect(developModerator(makeCtx(4, steps))).toBe(END);
|
||||
});
|
||||
|
||||
test("tester failed → coder retry when budget allows", () => {
|
||||
const steps: ModeratorContext<DevelopMeta>["steps"] = [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(true),
|
||||
testerStep(false),
|
||||
];
|
||||
expect(developModerator(makeCtx(20, steps))).toBe("coder");
|
||||
});
|
||||
|
||||
test("tester failed → END when max rounds exhausted", () => {
|
||||
const steps: ModeratorContext<DevelopMeta>["steps"] = [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(true),
|
||||
testerStep(false),
|
||||
];
|
||||
expect(developModerator(makeCtx(5, steps))).toBe(END);
|
||||
});
|
||||
|
||||
test("multiple planner phases → coder until all complete, then reviewer", () => {
|
||||
const phases: PlannerMeta["phases"] = [
|
||||
{ hash: "AA000001", title: "first phase" },
|
||||
{ hash: "AA000002", title: "second phase" },
|
||||
];
|
||||
expect(developModerator(makeCtx(20, [plannerStep(phases)]))).toBe("coder");
|
||||
expect(developModerator(makeCtx(20, [plannerStep(phases), coderStep("AA000001")]))).toBe(
|
||||
"coder",
|
||||
);
|
||||
expect(
|
||||
developModerator(
|
||||
makeCtx(20, [plannerStep(phases), coderStep("AA000001"), coderStep("AA000002")]),
|
||||
),
|
||||
).toBe("reviewer");
|
||||
});
|
||||
|
||||
test("one-shot coder reports only last phase hash → reviewer (moderator treats as all phases done)", () => {
|
||||
const phases: PlannerMeta["phases"] = [
|
||||
{ hash: "BB000001", title: "setup branch" },
|
||||
{ hash: "BB000002", title: "write tests" },
|
||||
{ hash: "BB000003", title: "verify" },
|
||||
{ hash: "BB000004", title: "polish" },
|
||||
];
|
||||
expect(developModerator(makeCtx(20, [plannerStep(phases), coderStep("BB000004")]))).toBe(
|
||||
"reviewer",
|
||||
);
|
||||
});
|
||||
|
||||
test("unrecognised completedPhase hash → coder retry when budget allows", () => {
|
||||
const phases: PlannerMeta["phases"] = [
|
||||
{ hash: "CC000001", title: "first phase" },
|
||||
{ hash: "CC000002", title: "second phase" },
|
||||
];
|
||||
expect(developModerator(makeCtx(20, [plannerStep(phases), coderStep("all-done")]))).toBe(
|
||||
"coder",
|
||||
);
|
||||
});
|
||||
|
||||
test("incomplete phases → END when max rounds exhausted", () => {
|
||||
const phases: PlannerMeta["phases"] = [
|
||||
{ hash: "DD000001", title: "first phase" },
|
||||
{ hash: "DD000002", title: "second phase" },
|
||||
];
|
||||
const steps: ModeratorContext<DevelopMeta>["steps"] = [
|
||||
plannerStep(phases),
|
||||
coderStep("DD000001"),
|
||||
];
|
||||
expect(developModerator(makeCtx(3, steps))).toBe(END);
|
||||
});
|
||||
|
||||
test("committer → END for any committer meta status", () => {
|
||||
const committed = committerStep({ status: "committed", branch: "f", commitSha: "x" });
|
||||
const recoverable = committerStep({
|
||||
status: "recoverable",
|
||||
error: "merge conflict",
|
||||
logRef: null,
|
||||
});
|
||||
const unrecoverable = committerStep({
|
||||
status: "unrecoverable",
|
||||
error: "repo missing",
|
||||
logRef: "log1",
|
||||
});
|
||||
const base: ModeratorContext<DevelopMeta>["steps"] = [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(true),
|
||||
testerStep(true),
|
||||
];
|
||||
expect(developModerator(makeCtx(20, [...base, committed]))).toBe(END);
|
||||
expect(developModerator(makeCtx(20, [...base, recoverable]))).toBe(END);
|
||||
expect(developModerator(makeCtx(20, [...base, unrecoverable]))).toBe(END);
|
||||
});
|
||||
});
|
||||
|
||||
describe("buildDevelopDescriptor", () => {
|
||||
test("lists all roles with schemas that validate", () => {
|
||||
const descriptor = buildDevelopDescriptor();
|
||||
const validated = validateWorkflowDescriptor(descriptor);
|
||||
expect(validated.ok).toBe(true);
|
||||
if (!validated.ok) {
|
||||
throw new Error(validated.error);
|
||||
}
|
||||
expect(Object.keys(validated.value.roles).sort()).toEqual([
|
||||
"coder",
|
||||
"committer",
|
||||
"planner",
|
||||
"reviewer",
|
||||
"tester",
|
||||
]);
|
||||
for (const key of ["planner", "coder", "reviewer", "tester", "committer"] as const) {
|
||||
const role = validated.value.roles[key];
|
||||
expect(role).toBeDefined();
|
||||
expect(typeof role.schema).toBe("object");
|
||||
expect(role.schema).not.toBeNull();
|
||||
expect(Array.isArray(role.schema)).toBe(false);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-template-develop",
|
||||
"version": "0.1.0",
|
||||
"type": "module",
|
||||
"main": "src/index.ts",
|
||||
"types": "src/index.ts",
|
||||
"scripts": {
|
||||
"build": "echo 'TODO'",
|
||||
"test": "bun test"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"@uncaged/workflow-role-coder": "workspace:*",
|
||||
"@uncaged/workflow-role-committer": "workspace:*",
|
||||
"@uncaged/workflow-role-planner": "workspace:*",
|
||||
"@uncaged/workflow-role-reviewer": "workspace:*",
|
||||
"@uncaged/workflow-role-tester": "workspace:*"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
import { buildDescriptor } from "@uncaged/workflow";
|
||||
|
||||
import { developModerator } from "./moderator.js";
|
||||
import { DEVELOP_WORKFLOW_DESCRIPTION, developRoles } from "./roles.js";
|
||||
|
||||
export function buildDevelopDescriptor() {
|
||||
return buildDescriptor({
|
||||
description: DEVELOP_WORKFLOW_DESCRIPTION,
|
||||
roles: developRoles,
|
||||
moderator: developModerator,
|
||||
});
|
||||
}
|
||||
@@ -0,0 +1,60 @@
|
||||
import {
|
||||
type AgentBinding,
|
||||
createWorkflow,
|
||||
type ExtractFn,
|
||||
type LlmProvider,
|
||||
type WorkflowDefinition,
|
||||
type WorkflowFn,
|
||||
} from "@uncaged/workflow";
|
||||
|
||||
import { developModerator } from "./moderator.js";
|
||||
import { DEVELOP_WORKFLOW_DESCRIPTION, type DevelopMeta, developRoles } from "./roles.js";
|
||||
|
||||
export {
|
||||
type CoderMeta,
|
||||
coderMetaSchema,
|
||||
coderRole,
|
||||
} from "@uncaged/workflow-role-coder";
|
||||
export {
|
||||
type CommitterMeta,
|
||||
committerMetaSchema,
|
||||
committerRole,
|
||||
} from "@uncaged/workflow-role-committer";
|
||||
export {
|
||||
type PlannerMeta,
|
||||
phaseSchema,
|
||||
plannerMetaSchema,
|
||||
plannerRole,
|
||||
} from "@uncaged/workflow-role-planner";
|
||||
export {
|
||||
type ReviewerMeta,
|
||||
reviewerMetaSchema,
|
||||
reviewerRole,
|
||||
} from "@uncaged/workflow-role-reviewer";
|
||||
export {
|
||||
type TesterMeta,
|
||||
testerMetaSchema,
|
||||
testerRole,
|
||||
} from "@uncaged/workflow-role-tester";
|
||||
export { buildDevelopDescriptor } from "./descriptor.js";
|
||||
export { developModerator } from "./moderator.js";
|
||||
export {
|
||||
DEVELOP_WORKFLOW_DESCRIPTION,
|
||||
type DevelopMeta,
|
||||
type DevelopRoles,
|
||||
developRoles,
|
||||
} from "./roles.js";
|
||||
|
||||
export const developWorkflowDefinition: WorkflowDefinition<DevelopMeta> = {
|
||||
description: DEVELOP_WORKFLOW_DESCRIPTION,
|
||||
roles: developRoles,
|
||||
moderator: developModerator,
|
||||
};
|
||||
|
||||
export function createDevelopRun(
|
||||
binding: AgentBinding,
|
||||
extract: ExtractFn,
|
||||
llmProvider: LlmProvider | null,
|
||||
): WorkflowFn {
|
||||
return createWorkflow(developWorkflowDefinition, binding, extract, llmProvider);
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
import type { Moderator, ModeratorContext } from "@uncaged/workflow";
|
||||
import { END } from "@uncaged/workflow";
|
||||
|
||||
import type { DevelopMeta } from "./roles.js";
|
||||
|
||||
function coderFinishedAllPlannedPhases(
|
||||
phases: ReadonlyArray<{ hash: string }>,
|
||||
coderCompletedPhases: ReadonlyArray<string>,
|
||||
): boolean {
|
||||
if (phases.length === 0) {
|
||||
return true;
|
||||
}
|
||||
const plannedHashes = new Set(phases.map((p) => p.hash));
|
||||
const lastHash = phases[phases.length - 1].hash;
|
||||
const explicit = new Set(coderCompletedPhases.filter((h) => plannedHashes.has(h)));
|
||||
if (phases.every((p) => explicit.has(p.hash))) {
|
||||
return true;
|
||||
}
|
||||
if (coderCompletedPhases.some((h) => h === lastHash)) {
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
function nextAfterCoder(
|
||||
ctx: ModeratorContext<DevelopMeta>,
|
||||
maxRounds: number,
|
||||
): (keyof DevelopMeta & string) | typeof END {
|
||||
const plannerStep = ctx.steps.find((s) => s.role === "planner");
|
||||
if (plannerStep === undefined) {
|
||||
return "reviewer";
|
||||
}
|
||||
const phases = plannerStep.meta.phases;
|
||||
const coderCompletedPhases = ctx.steps
|
||||
.filter((s) => s.role === "coder")
|
||||
.map((s) => s.meta.completedPhase);
|
||||
const allDone = coderFinishedAllPlannedPhases(phases, coderCompletedPhases);
|
||||
if (allDone) {
|
||||
return "reviewer";
|
||||
}
|
||||
if (ctx.steps.length < maxRounds - 1) {
|
||||
return "coder";
|
||||
}
|
||||
return END;
|
||||
}
|
||||
|
||||
export const developModerator: Moderator<DevelopMeta> = (ctx) => {
|
||||
const maxRounds = ctx.start.meta.maxRounds;
|
||||
|
||||
if (ctx.steps.length === 0) {
|
||||
return "planner";
|
||||
}
|
||||
|
||||
const last = ctx.steps[ctx.steps.length - 1];
|
||||
|
||||
if (last.role === "planner") {
|
||||
return "coder";
|
||||
}
|
||||
|
||||
if (last.role === "coder") {
|
||||
return nextAfterCoder(ctx, maxRounds);
|
||||
}
|
||||
|
||||
if (last.role === "reviewer") {
|
||||
if (last.meta.status === "approved") {
|
||||
return "tester";
|
||||
}
|
||||
if (ctx.steps.length < maxRounds - 1) {
|
||||
return "coder";
|
||||
}
|
||||
return END;
|
||||
}
|
||||
|
||||
if (last.role === "tester") {
|
||||
if (last.meta.status === "passed") {
|
||||
return "committer";
|
||||
}
|
||||
if (ctx.steps.length < maxRounds - 1) {
|
||||
return "coder";
|
||||
}
|
||||
return END;
|
||||
}
|
||||
|
||||
if (last.role === "committer") {
|
||||
return END;
|
||||
}
|
||||
|
||||
return END;
|
||||
};
|
||||
@@ -0,0 +1,29 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import { type CoderMeta, coderRole } from "@uncaged/workflow-role-coder";
|
||||
import { type CommitterMeta, committerRole } from "@uncaged/workflow-role-committer";
|
||||
import { type PlannerMeta, plannerRole } from "@uncaged/workflow-role-planner";
|
||||
import { type ReviewerMeta, reviewerRole } from "@uncaged/workflow-role-reviewer";
|
||||
import { type TesterMeta, testerRole } from "@uncaged/workflow-role-tester";
|
||||
|
||||
export const DEVELOP_WORKFLOW_DESCRIPTION =
|
||||
"Plan phases, implement incrementally, review, verify with tests/build/lint, and commit (planner → coder [repeat per phase] → reviewer → tester → committer).";
|
||||
|
||||
export type DevelopMeta = {
|
||||
planner: PlannerMeta;
|
||||
coder: CoderMeta;
|
||||
reviewer: ReviewerMeta;
|
||||
tester: TesterMeta;
|
||||
committer: CommitterMeta;
|
||||
};
|
||||
|
||||
export type DevelopRoles = {
|
||||
[K in keyof DevelopMeta]: RoleDefinition<DevelopMeta[K]>;
|
||||
};
|
||||
|
||||
export const developRoles: DevelopRoles = {
|
||||
planner: plannerRole,
|
||||
coder: coderRole,
|
||||
reviewer: reviewerRole,
|
||||
tester: testerRole,
|
||||
committer: committerRole,
|
||||
};
|
||||
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [
|
||||
{ "path": "../workflow" },
|
||||
{ "path": "../workflow-role-coder" },
|
||||
{ "path": "../workflow-role-committer" },
|
||||
{ "path": "../workflow-role-planner" },
|
||||
{ "path": "../workflow-role-reviewer" },
|
||||
{ "path": "../workflow-role-tester" }
|
||||
]
|
||||
}
|
||||
@@ -1,17 +1,104 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { afterEach, describe, expect, test } from "bun:test";
|
||||
import { mkdtemp, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import {
|
||||
createCasStore,
|
||||
createExtract,
|
||||
END,
|
||||
type ModeratorContext,
|
||||
type RoleStep,
|
||||
START,
|
||||
type ThreadContext,
|
||||
validateWorkflowDescriptor,
|
||||
} from "@uncaged/workflow";
|
||||
|
||||
import { buildSolveIssueDescriptor } from "../src/descriptor.js";
|
||||
import { solveIssueModerator } from "../src/moderator.js";
|
||||
import { createSolveIssueRoles, type SolveIssueMeta } from "../src/roles.js";
|
||||
import type { PreparerMeta } from "@uncaged/workflow-role-preparer";
|
||||
import type { SubmitterMeta } from "@uncaged/workflow-role-submitter";
|
||||
|
||||
function makeStart(maxRounds: number): ThreadContext<SolveIssueMeta>["start"] {
|
||||
import { buildSolveIssueDescriptor } from "../src/descriptor.js";
|
||||
import type { DeveloperMeta } from "../src/developer.js";
|
||||
import { createSolveIssueRun, solveIssueModerator } from "../src/index.js";
|
||||
import type { SolveIssueMeta } from "../src/roles.js";
|
||||
|
||||
function jsonResponse(payload: Record<string, unknown>): Response {
|
||||
return new Response(JSON.stringify(payload), {
|
||||
status: 200,
|
||||
headers: { "Content-Type": "application/json" },
|
||||
});
|
||||
}
|
||||
|
||||
function readToolListFromBody(init: RequestInit | undefined): readonly Record<string, unknown>[] {
|
||||
if (init === undefined || init.body === undefined || init.body === null) {
|
||||
return [];
|
||||
}
|
||||
const body = JSON.parse(String(init.body)) as Record<string, unknown>;
|
||||
const tools = body.tools;
|
||||
if (!Array.isArray(tools)) {
|
||||
return [];
|
||||
}
|
||||
return tools.filter((t): t is Record<string, unknown> => t !== null && typeof t === "object");
|
||||
}
|
||||
|
||||
function singleToolName(tools: readonly Record<string, unknown>[]): string {
|
||||
if (tools.length === 0) {
|
||||
return "extract";
|
||||
}
|
||||
const fn = tools[0].function as Record<string, unknown> | undefined;
|
||||
return typeof fn?.name === "string" ? fn.name : "extract";
|
||||
}
|
||||
|
||||
function buildSingleModeResponse(args: Record<string, unknown>, toolName: string): Response {
|
||||
return jsonResponse({
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
tool_calls: [
|
||||
{
|
||||
type: "function",
|
||||
function: { name: toolName, arguments: JSON.stringify(args) },
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
],
|
||||
});
|
||||
}
|
||||
|
||||
function buildReactModeResponse(args: Record<string, unknown>): Response {
|
||||
// reactExtract accepts a plain-JSON assistant message and validates it
|
||||
// directly against the schema, so we skip the cas_get / extract tool dance.
|
||||
return jsonResponse({
|
||||
choices: [{ message: { content: JSON.stringify(args) } }],
|
||||
});
|
||||
}
|
||||
|
||||
function installMockChatCompletions(sequence: ReadonlyArray<Record<string, unknown>>): () => void {
|
||||
const origFetch = globalThis.fetch;
|
||||
let i = 0;
|
||||
const mockFetch = async (
|
||||
_input: Parameters<typeof fetch>[0],
|
||||
init?: RequestInit,
|
||||
): Promise<Response> => {
|
||||
const args = sequence[i] ?? sequence[sequence.length - 1];
|
||||
if (args === undefined) {
|
||||
throw new Error("installMockChatCompletions: empty sequence");
|
||||
}
|
||||
i += 1;
|
||||
const tools = readToolListFromBody(init);
|
||||
if (tools.length > 1) {
|
||||
return buildReactModeResponse(args);
|
||||
}
|
||||
return buildSingleModeResponse(args, singleToolName(tools));
|
||||
};
|
||||
globalThis.fetch = Object.assign(mockFetch, {
|
||||
preconnect: origFetch.preconnect.bind(origFetch),
|
||||
}) as typeof fetch;
|
||||
return () => {
|
||||
globalThis.fetch = origFetch;
|
||||
};
|
||||
}
|
||||
|
||||
function makeStart(maxRounds: number): ModeratorContext<SolveIssueMeta>["start"] {
|
||||
return {
|
||||
role: START,
|
||||
content: "Fix the flaky login test",
|
||||
@@ -22,107 +109,286 @@ function makeStart(maxRounds: number): ThreadContext<SolveIssueMeta>["start"] {
|
||||
|
||||
function makeCtx(
|
||||
maxRounds: number,
|
||||
steps: ThreadContext<SolveIssueMeta>["steps"],
|
||||
): ThreadContext<SolveIssueMeta> {
|
||||
steps: ModeratorContext<SolveIssueMeta>["steps"],
|
||||
): ModeratorContext<SolveIssueMeta> {
|
||||
return {
|
||||
threadId: "01TEST000000000000000000TR",
|
||||
depth: 0,
|
||||
start: makeStart(maxRounds),
|
||||
steps,
|
||||
};
|
||||
}
|
||||
|
||||
function plannerStep(): RoleStep<SolveIssueMeta> {
|
||||
function preparerStep(): RoleStep<SolveIssueMeta> {
|
||||
return {
|
||||
role: "planner",
|
||||
content: "plan",
|
||||
meta: { plan: "do work", files: ["a.ts"], approach: "minimal fix" },
|
||||
role: "preparer",
|
||||
contentHash: "STUBHASHPREPARER01",
|
||||
meta: {
|
||||
repoPath: "/home/user/repos/test",
|
||||
defaultBranch: "main",
|
||||
conventions: null,
|
||||
toolchain: {
|
||||
packageManager: "bun",
|
||||
testCommand: "bun test",
|
||||
lintCommand: null,
|
||||
buildCommand: "bun run build",
|
||||
},
|
||||
},
|
||||
refs: [],
|
||||
timestamp: 0,
|
||||
};
|
||||
}
|
||||
|
||||
function developerStep(): RoleStep<SolveIssueMeta> {
|
||||
return {
|
||||
role: "developer",
|
||||
contentHash: "STUBHASHDEVELOPER1",
|
||||
meta: {
|
||||
branch: "feat/issue-1",
|
||||
commitSha: "abc1234",
|
||||
filesChanged: ["src/login.ts"],
|
||||
summary: "Fixed flaky login test by stabilising async setup.",
|
||||
},
|
||||
refs: [],
|
||||
timestamp: 1,
|
||||
};
|
||||
}
|
||||
|
||||
function coderStep(): RoleStep<SolveIssueMeta> {
|
||||
function submitterStep(meta: SubmitterMeta): RoleStep<SolveIssueMeta> {
|
||||
return {
|
||||
role: "coder",
|
||||
content: "code",
|
||||
meta: { filesChanged: ["a.ts"], summary: "fixed" },
|
||||
role: "submitter",
|
||||
contentHash: "STUBHASHSUBMITTER1",
|
||||
meta,
|
||||
refs: [],
|
||||
timestamp: 2,
|
||||
};
|
||||
}
|
||||
|
||||
function reviewerStep(approved: boolean): RoleStep<SolveIssueMeta> {
|
||||
return {
|
||||
role: "reviewer",
|
||||
content: "rev",
|
||||
meta: { approved },
|
||||
timestamp: 3,
|
||||
};
|
||||
}
|
||||
const stubExtract = createExtract({
|
||||
baseUrl: "http://127.0.0.1:9",
|
||||
apiKey: "",
|
||||
model: "test",
|
||||
});
|
||||
|
||||
function committerStep(): RoleStep<SolveIssueMeta> {
|
||||
return {
|
||||
role: "committer",
|
||||
content: "commit",
|
||||
meta: { committed: true },
|
||||
timestamp: 4,
|
||||
};
|
||||
}
|
||||
const stubLlmProvider = {
|
||||
baseUrl: "http://127.0.0.1:9",
|
||||
apiKey: "",
|
||||
model: "test",
|
||||
};
|
||||
|
||||
describe("solveIssueModerator", () => {
|
||||
test("routes planner → coder → reviewer → committer → END", () => {
|
||||
expect(solveIssueModerator(makeCtx(20, []))).toBe("planner");
|
||||
expect(solveIssueModerator(makeCtx(20, [plannerStep()]))).toBe("coder");
|
||||
expect(solveIssueModerator(makeCtx(20, [plannerStep(), coderStep()]))).toBe("reviewer");
|
||||
expect(solveIssueModerator(makeCtx(20, [plannerStep(), coderStep(), reviewerStep(true)]))).toBe(
|
||||
"committer",
|
||||
);
|
||||
test("routes initial → preparer → developer → submitter → END", () => {
|
||||
expect(solveIssueModerator(makeCtx(20, []))).toBe("preparer");
|
||||
expect(solveIssueModerator(makeCtx(20, [preparerStep()]))).toBe("developer");
|
||||
expect(solveIssueModerator(makeCtx(20, [preparerStep(), developerStep()]))).toBe("submitter");
|
||||
expect(
|
||||
solveIssueModerator(
|
||||
makeCtx(20, [plannerStep(), coderStep(), reviewerStep(true), committerStep()]),
|
||||
makeCtx(20, [
|
||||
preparerStep(),
|
||||
developerStep(),
|
||||
submitterStep({
|
||||
status: "submitted",
|
||||
prUrl: "https://github.com/example/repo/pull/1",
|
||||
}),
|
||||
]),
|
||||
),
|
||||
).toBe(END);
|
||||
});
|
||||
|
||||
test("reviewer rejects → coder retry when budget allows", () => {
|
||||
const steps: ThreadContext<SolveIssueMeta>["steps"] = [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(false),
|
||||
];
|
||||
expect(solveIssueModerator(makeCtx(20, steps))).toBe("coder");
|
||||
test("submitter failed → END", () => {
|
||||
expect(
|
||||
solveIssueModerator(
|
||||
makeCtx(20, [
|
||||
preparerStep(),
|
||||
developerStep(),
|
||||
submitterStep({ status: "failed", error: "gh not authenticated" }),
|
||||
]),
|
||||
),
|
||||
).toBe(END);
|
||||
});
|
||||
|
||||
test("reviewer rejects → END when max rounds exhausted", () => {
|
||||
const steps: ThreadContext<SolveIssueMeta>["steps"] = [
|
||||
plannerStep(),
|
||||
coderStep(),
|
||||
reviewerStep(false),
|
||||
];
|
||||
expect(solveIssueModerator(makeCtx(4, steps))).toBe(END);
|
||||
test("returns END for any unexpected last step (defensive)", () => {
|
||||
// A submitter step with a pseudo-unknown future status would still be
|
||||
// routed to END, since the moderator is a closed switch over known roles.
|
||||
expect(
|
||||
solveIssueModerator(
|
||||
makeCtx(20, [
|
||||
preparerStep(),
|
||||
developerStep(),
|
||||
submitterStep({ status: "submitted", prUrl: "https://example.com/pr/1" }),
|
||||
]),
|
||||
),
|
||||
).toBe(END);
|
||||
});
|
||||
});
|
||||
|
||||
describe("createSolveIssueRoles", () => {
|
||||
test("returns all four role callables", async () => {
|
||||
const agent = async () => '{"plan":"x","files":[],"approach":"y"}';
|
||||
const roles = createSolveIssueRoles({
|
||||
agent,
|
||||
workdir: "/tmp/repo",
|
||||
extract: null,
|
||||
});
|
||||
describe("createSolveIssueRun", () => {
|
||||
let restoreFetch: (() => void) | null = null;
|
||||
let casDir: string | undefined;
|
||||
|
||||
expect(typeof roles.planner).toBe("function");
|
||||
expect(typeof roles.coder).toBe("function");
|
||||
expect(typeof roles.reviewer).toBe("function");
|
||||
expect(typeof roles.committer).toBe("function");
|
||||
afterEach(async () => {
|
||||
restoreFetch?.();
|
||||
restoreFetch = null;
|
||||
if (casDir !== undefined) {
|
||||
await rm(casDir, { recursive: true, force: true }).catch(() => {});
|
||||
casDir = undefined;
|
||||
}
|
||||
});
|
||||
|
||||
const ctx = makeCtx(10, []);
|
||||
const plannerOut = await roles.planner(ctx);
|
||||
expect(plannerOut.meta.plan).toBe("");
|
||||
expect(Array.isArray(plannerOut.meta.files)).toBe(true);
|
||||
test("structured extraction yields preparer meta from mocked chat completions", async () => {
|
||||
const EXPECT_PREPARER_META: PreparerMeta = {
|
||||
repoPath: "/home/user/repos/test",
|
||||
defaultBranch: "main",
|
||||
conventions: null,
|
||||
toolchain: {
|
||||
packageManager: "bun",
|
||||
testCommand: "bun test",
|
||||
lintCommand: null,
|
||||
buildCommand: "bun run build",
|
||||
},
|
||||
};
|
||||
restoreFetch = installMockChatCompletions([EXPECT_PREPARER_META]);
|
||||
|
||||
casDir = await mkdtemp(join(tmpdir(), "solve-issue-cas-"));
|
||||
const cas = createCasStore(casDir);
|
||||
|
||||
// Override developer so the test does not spin up a child workflow.
|
||||
const run = createSolveIssueRun(
|
||||
{
|
||||
agent: async () => "",
|
||||
overrides: { developer: async () => "stub-root-hash" },
|
||||
},
|
||||
stubExtract,
|
||||
stubLlmProvider,
|
||||
);
|
||||
const gen = run(
|
||||
{ prompt: "task", steps: [] },
|
||||
{ threadId: "01TEST000000000000000000TR", maxRounds: 20, depth: 0, cas },
|
||||
);
|
||||
const first = await gen.next();
|
||||
expect(first.done).toBe(false);
|
||||
if (first.done) {
|
||||
throw new Error("expected yield");
|
||||
}
|
||||
expect(first.value.role).toBe("preparer");
|
||||
expect(first.value.meta).toEqual(EXPECT_PREPARER_META);
|
||||
});
|
||||
|
||||
test("per-role agent overrides default", async () => {
|
||||
const PREPARER_META: PreparerMeta = {
|
||||
repoPath: "/tmp/r",
|
||||
defaultBranch: "main",
|
||||
conventions: null,
|
||||
toolchain: { packageManager: null, testCommand: null, lintCommand: null, buildCommand: null },
|
||||
};
|
||||
const DEVELOPER_META: DeveloperMeta = {
|
||||
branch: "feat/x",
|
||||
commitSha: "abc1234",
|
||||
filesChanged: ["a.ts"],
|
||||
summary: "did the work",
|
||||
};
|
||||
const SUBMITTER_META: SubmitterMeta = {
|
||||
status: "submitted",
|
||||
prUrl: "https://github.com/example/repo/pull/2",
|
||||
};
|
||||
restoreFetch = installMockChatCompletions([PREPARER_META, DEVELOPER_META, SUBMITTER_META]);
|
||||
|
||||
casDir = await mkdtemp(join(tmpdir(), "solve-issue-cas-"));
|
||||
const cas = createCasStore(casDir);
|
||||
|
||||
const calls: string[] = [];
|
||||
const run = createSolveIssueRun(
|
||||
{
|
||||
agent: async () => {
|
||||
calls.push("default");
|
||||
return "";
|
||||
},
|
||||
overrides: {
|
||||
preparer: async () => {
|
||||
calls.push("preparer");
|
||||
return "";
|
||||
},
|
||||
developer: async () => {
|
||||
calls.push("developer");
|
||||
return "stub-root-hash";
|
||||
},
|
||||
submitter: async () => {
|
||||
calls.push("submitter");
|
||||
return "";
|
||||
},
|
||||
},
|
||||
},
|
||||
stubExtract,
|
||||
stubLlmProvider,
|
||||
);
|
||||
const gen = run(
|
||||
{ prompt: "task", steps: [] },
|
||||
{ threadId: "01TEST000000000000000000TR", maxRounds: 20, depth: 0, cas },
|
||||
);
|
||||
await gen.next();
|
||||
expect(calls).toEqual(["preparer"]);
|
||||
|
||||
calls.length = 0;
|
||||
await gen.next();
|
||||
expect(calls).toEqual(["developer"]);
|
||||
|
||||
calls.length = 0;
|
||||
await gen.next();
|
||||
expect(calls).toEqual(["submitter"]);
|
||||
});
|
||||
|
||||
test("developer defaults to workflowAsAgent override (caller override still wins)", async () => {
|
||||
const PREPARER_META: PreparerMeta = {
|
||||
repoPath: "/tmp/r",
|
||||
defaultBranch: "main",
|
||||
conventions: null,
|
||||
toolchain: { packageManager: null, testCommand: null, lintCommand: null, buildCommand: null },
|
||||
};
|
||||
const DEVELOPER_META: DeveloperMeta = {
|
||||
branch: "feat/y",
|
||||
commitSha: "def5678",
|
||||
filesChanged: ["b.ts"],
|
||||
summary: "more work",
|
||||
};
|
||||
restoreFetch = installMockChatCompletions([PREPARER_META, DEVELOPER_META]);
|
||||
|
||||
casDir = await mkdtemp(join(tmpdir(), "solve-issue-cas-"));
|
||||
const cas = createCasStore(casDir);
|
||||
|
||||
let developerInvocations = 0;
|
||||
const run = createSolveIssueRun(
|
||||
{
|
||||
agent: async () => "",
|
||||
overrides: {
|
||||
developer: async () => {
|
||||
developerInvocations += 1;
|
||||
return "stub-root-hash";
|
||||
},
|
||||
},
|
||||
},
|
||||
stubExtract,
|
||||
stubLlmProvider,
|
||||
);
|
||||
const gen = run(
|
||||
{ prompt: "task", steps: [] },
|
||||
{ threadId: "01TEST000000000000000000TR", maxRounds: 20, depth: 0, cas },
|
||||
);
|
||||
// preparer
|
||||
await gen.next();
|
||||
// developer (caller override should be invoked, NOT workflowAsAgent default)
|
||||
const devYield = await gen.next();
|
||||
expect(devYield.done).toBe(false);
|
||||
if (devYield.done) {
|
||||
throw new Error("expected yield");
|
||||
}
|
||||
expect(devYield.value.role).toBe("developer");
|
||||
expect(devYield.value.meta).toEqual(DEVELOPER_META);
|
||||
expect(developerInvocations).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe("buildSolveIssueDescriptor", () => {
|
||||
test("lists all roles with schemas that validate", () => {
|
||||
test("lists preparer, developer, submitter with schemas that validate", () => {
|
||||
const descriptor = buildSolveIssueDescriptor();
|
||||
const validated = validateWorkflowDescriptor(descriptor);
|
||||
expect(validated.ok).toBe(true);
|
||||
@@ -130,12 +396,11 @@ describe("buildSolveIssueDescriptor", () => {
|
||||
throw new Error(validated.error);
|
||||
}
|
||||
expect(Object.keys(validated.value.roles).sort()).toEqual([
|
||||
"coder",
|
||||
"committer",
|
||||
"planner",
|
||||
"reviewer",
|
||||
"developer",
|
||||
"preparer",
|
||||
"submitter",
|
||||
]);
|
||||
for (const key of ["planner", "coder", "reviewer", "committer"] as const) {
|
||||
for (const key of ["preparer", "developer", "submitter"] as const) {
|
||||
const role = validated.value.roles[key];
|
||||
expect(role).toBeDefined();
|
||||
expect(typeof role.schema).toBe("object");
|
||||
|
||||
@@ -10,11 +10,8 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow": "workspace:*",
|
||||
"@uncaged/workflow-agent-cursor": "workspace:*",
|
||||
"@uncaged/workflow-role-committer": "workspace:*",
|
||||
"@uncaged/workflow-role-llm": "workspace:*",
|
||||
"@uncaged/workflow-role-reviewer": "workspace:*",
|
||||
"@uncaged/workflow-util-role": "workspace:*",
|
||||
"@uncaged/workflow-role-preparer": "workspace:*",
|
||||
"@uncaged/workflow-role-submitter": "workspace:*",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,34 +1,12 @@
|
||||
import { committerMetaSchema } from "@uncaged/workflow-role-committer";
|
||||
import { reviewerMetaSchema } from "@uncaged/workflow-role-reviewer";
|
||||
import { buildDescriptorFromRoles } from "@uncaged/workflow-util-role";
|
||||
import { buildDescriptor } from "@uncaged/workflow";
|
||||
|
||||
import { coderMetaSchema, plannerMetaSchema } from "./roles.js";
|
||||
import { solveIssueModerator } from "./moderator.js";
|
||||
import { SOLVE_ISSUE_WORKFLOW_DESCRIPTION, solveIssueRoles } from "./roles.js";
|
||||
|
||||
export function buildSolveIssueDescriptor() {
|
||||
return buildDescriptorFromRoles({
|
||||
description:
|
||||
"Plan, implement, review, and commit changes to resolve an issue end-to-end (planner → coder → reviewer → committer).",
|
||||
roles: {
|
||||
planner: {
|
||||
name: "planner",
|
||||
schema: plannerMetaSchema,
|
||||
description: "Analyzes the issue and proposes plan, files, and approach.",
|
||||
},
|
||||
coder: {
|
||||
name: "coder",
|
||||
schema: coderMetaSchema,
|
||||
description: "Implements the planner output and summarizes touched files.",
|
||||
},
|
||||
reviewer: {
|
||||
name: "reviewer",
|
||||
schema: reviewerMetaSchema,
|
||||
description: "Runs git diff checks and sets approved when the change is ready.",
|
||||
},
|
||||
committer: {
|
||||
name: "committer",
|
||||
schema: committerMetaSchema,
|
||||
description: "Creates branch, commits, and pushes when review passes.",
|
||||
},
|
||||
},
|
||||
return buildDescriptor({
|
||||
description: SOLVE_ISSUE_WORKFLOW_DESCRIPTION,
|
||||
roles: solveIssueRoles,
|
||||
moderator: solveIssueModerator,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const developerMetaSchema = z.object({
|
||||
branch: z.string(),
|
||||
commitSha: z.string(),
|
||||
filesChanged: z.array(z.string()),
|
||||
summary: z.string(),
|
||||
});
|
||||
|
||||
export type DeveloperMeta = z.infer<typeof developerMetaSchema>;
|
||||
|
||||
const DEVELOPER_SYSTEM = `You are the **developer**. You delegate the implementation work to the \`develop\` workflow.
|
||||
|
||||
The actual implementation (planning → coding → reviewing → testing → committing) is handled by a child workflow that runs in your place. Your output is the Merkle DAG root hash of that child thread.
|
||||
|
||||
Pass through the task and let the child workflow do the work.`;
|
||||
|
||||
const DEVELOPER_EXTRACT_PROMPT = `The agent output is the root CAS hash of a child workflow thread. Use the cas_get tool to traverse the Merkle DAG and extract the developer summary.
|
||||
|
||||
Procedure:
|
||||
1. cas_get(<rootHash>) — the root node lists all child step hashes (planner, coder, reviewer, tester, committer).
|
||||
2. Find the committer step. cas_get its hash to read the committer's meta — extract branch and commitSha from there.
|
||||
3. Find every coder step. cas_get each to read the coder's filesChanged. Union all filesChanged across coder steps.
|
||||
4. Compose a short human-readable summary describing what the develop child workflow accomplished (drawn from the coder summaries, or a synthesis of them).
|
||||
|
||||
Return: { branch, commitSha, filesChanged, summary }.`;
|
||||
|
||||
export const developerRole: RoleDefinition<DeveloperMeta> = {
|
||||
description:
|
||||
"Delegates the actual implementation to the develop workflow (workflow-as-agent). Produces a summary by traversing the child thread's Merkle DAG.",
|
||||
systemPrompt: DEVELOPER_SYSTEM,
|
||||
extractPrompt: DEVELOPER_EXTRACT_PROMPT,
|
||||
schema: developerMetaSchema,
|
||||
extractRefs: () => [],
|
||||
extractMode: "react",
|
||||
};
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user