Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 5643a06a39 |
@@ -9,5 +9,3 @@ bunfig.toml
|
||||
xiaoju/
|
||||
solve-issue-entry.ts
|
||||
packages/workflow-template-develop/develop.esm.js
|
||||
.DS_Store
|
||||
*.py
|
||||
|
||||
+182
-392
@@ -1,478 +1,268 @@
|
||||
# uwf — Architecture
|
||||
# Uncaged workflow — Architecture
|
||||
|
||||
**Last updated:** 2026-05-19
|
||||
**Last updated:** 2026-05-09
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
A stateless workflow engine driven by a single-step CLI. Workflows are YAML definitions stored as CAS nodes; threads are immutable chains of CAS-linked step nodes. No daemon — each `uwf thread step` invocation runs one moderator→agent→extract cycle and exits.
|
||||
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.
|
||||
|
||||
The implementation lives in **6** active packages under `packages/`, plus two external CAS packages (`@uncaged/json-cas`, `@uncaged/json-cas-fs`). Legacy packages reside in `legacy-packages/` and are not part of the active stack.
|
||||
The implementation lives in **15** Bun workspace packages under `packages/`, using the `workspace:*` protocol.
|
||||
|
||||
## Package map
|
||||
|
||||
Grouped by responsibility (npm name → folder).
|
||||
|
||||
| Layer | Package | One-line role |
|
||||
|-------|---------|---------------|
|
||||
| Contract | `@uncaged/uwf-protocol` → `uwf-protocol` | Shared TypeScript types (`WorkflowPayload`, `StepNodePayload`, `ModeratorContext`, `WorkflowConfig`, etc.). No runtime deps beyond `@uncaged/json-cas-fs`. |
|
||||
| Shared infra | `@uncaged/workflow-util` → `workflow-util` | Crockford Base32, ULID generation, `createLogger`, frontmatter parsing/validation. |
|
||||
| Moderator | `@uncaged/uwf-moderator` → `uwf-moderator` | JSONata-based graph evaluator: given a `WorkflowPayload` and `ModeratorContext`, returns the next role or `$END`. |
|
||||
| Agent framework | `@uncaged/uwf-agent-kit` → `uwf-agent-kit` | `createAgent` entrypoint factory, context builder, frontmatter fast-path extractor, LLM extract fallback, output format instruction builder. |
|
||||
| Agent: Hermes | `@uncaged/uwf-agent-hermes` → `uwf-agent-hermes` | `uwf-hermes` CLI binary — spawns `hermes chat`, pipes prompt, captures session detail. |
|
||||
| CLI | `@uncaged/cli-uwf` → `cli-uwf` | `uwf` binary — thread lifecycle, workflow registry, CAS inspection, setup. |
|
||||
|-------|---------|----------------|
|
||||
| Contract | `@uncaged/workflow-protocol` → `workflow-protocol` | Shared TypeScript types and `Result` helpers; peer `zod` only — no other workspace deps. |
|
||||
| Author API | `@uncaged/workflow-runtime` → `workflow-runtime` | `createWorkflow` and re-exports of protocol workflow types for bundle authors. |
|
||||
| Shared infra | `@uncaged/workflow-util` → `workflow-util` | Base32/ULID, logger, storage root paths, global CAS dir, ref-field helpers. |
|
||||
| LLM plumbing | `@uncaged/workflow-reactor` → `workflow-reactor` | `createLlmFn`, `createThreadReactor`, and related tool-call types for threaded LLM invocation. |
|
||||
| CAS | `@uncaged/workflow-cas` → `workflow-cas` | `CasStore` implementation, XXH64 hashing, Merkle helpers over CAS payloads. |
|
||||
| Registry / bundles | `@uncaged/workflow-register` → `workflow-register` | Bundle validation & dynamic export extraction, `workflow.yaml` registry I/O, provider/model resolution. |
|
||||
| Engine | `@uncaged/workflow-execute` → `workflow-execute` | Thread execution, worker entry path, fork/GC, extract pipeline, `workflowAsAgent`. |
|
||||
| CLI | `@uncaged/cli-workflow` → `cli-workflow` | `uncaged-workflow` binary (depends on engine, registry, CAS, protocol, util, runtime). |
|
||||
| Agent adapters | `@uncaged/workflow-agent-cursor` → `workflow-agent-cursor` | `AgentFn` via `cursor-agent` CLI + workspace extraction. |
|
||||
| | `@uncaged/workflow-agent-hermes` → `workflow-agent-hermes` | `AgentFn` via `hermes chat` CLI. |
|
||||
| | `@uncaged/workflow-agent-llm` → `workflow-agent-llm` | `AgentFn` via OpenAI-compatible HTTP (`LlmProvider` from runtime). |
|
||||
| Agent shared | `@uncaged/workflow-util-agent` → `workflow-util-agent` | `buildAgentPrompt`, `spawnCli` for CLI-backed agents. |
|
||||
| Templates | `@uncaged/workflow-template-develop` → `workflow-template-develop` | Develop workflow definition, roles, descriptor builder. |
|
||||
| | `@uncaged/workflow-template-solve-issue` → `workflow-template-solve-issue` | Solve-issue workflow definition, roles, descriptor builder. |
|
||||
| Dashboard | `@uncaged/workflow-dashboard` → `workflow-dashboard` | Private Vite + React app (`src/main.tsx`); only `react` / `react-dom` dependencies — no workspace packages. |
|
||||
|
||||
### External dependencies
|
||||
## Dependency graph (workspace packages)
|
||||
|
||||
| Package | Role |
|
||||
|---------|------|
|
||||
| `@uncaged/json-cas` | Content-addressed store API, XXH64 hashing, JSON Schema registration and validation. |
|
||||
| `@uncaged/json-cas-fs` | Filesystem backend for `json-cas`. |
|
||||
| `jsonata` | JSONata expression evaluator (used by `uwf-moderator`). |
|
||||
| `commander` | CLI argument parsing (used by `cli-uwf`). |
|
||||
| `dotenv` | Loads `.env` files for API keys. |
|
||||
| `yaml` | YAML parse/stringify. |
|
||||
|
||||
## Dependency graph
|
||||
Bottom-up layering for the execution stack:
|
||||
|
||||
```mermaid
|
||||
flowchart BT
|
||||
subgraph External
|
||||
jcas["@uncaged/json-cas"]
|
||||
jcasfs["@uncaged/json-cas-fs"]
|
||||
end
|
||||
subgraph L0["Layer 0 — contract"]
|
||||
protocol["@uncaged/uwf-protocol"]
|
||||
protocol["@uncaged/workflow-protocol"]
|
||||
end
|
||||
subgraph L1["Layer 1 — shared"]
|
||||
subgraph L1["Layer 1 — on protocol"]
|
||||
runtime["@uncaged/workflow-runtime"]
|
||||
util["@uncaged/workflow-util"]
|
||||
moderator["@uncaged/uwf-moderator"]
|
||||
reactor["@uncaged/workflow-reactor"]
|
||||
end
|
||||
subgraph L2["Layer 2 — agent framework"]
|
||||
kit["@uncaged/uwf-agent-kit"]
|
||||
subgraph L2["Layer 2 — protocol + util"]
|
||||
cas["@uncaged/workflow-cas"]
|
||||
register["@uncaged/workflow-register"]
|
||||
end
|
||||
subgraph L3["Layer 3 — agent implementations"]
|
||||
hermes["@uncaged/uwf-agent-hermes"]
|
||||
subgraph L3["Layer 3 — engine"]
|
||||
execute["@uncaged/workflow-execute"]
|
||||
end
|
||||
subgraph L4["Layer 4 — CLI"]
|
||||
cli["@uncaged/cli-uwf"]
|
||||
cli["@uncaged/cli-workflow"]
|
||||
end
|
||||
protocol --> jcasfs
|
||||
runtime --> protocol
|
||||
util --> protocol
|
||||
moderator --> protocol
|
||||
kit --> protocol
|
||||
kit --> util
|
||||
kit --> jcas
|
||||
kit --> jcasfs
|
||||
hermes --> kit
|
||||
hermes --> jcas
|
||||
reactor --> protocol
|
||||
cas --> protocol
|
||||
cas --> util
|
||||
register --> protocol
|
||||
register --> util
|
||||
execute --> protocol
|
||||
execute --> runtime
|
||||
execute --> util
|
||||
execute --> cas
|
||||
execute --> reactor
|
||||
execute --> register
|
||||
cli --> protocol
|
||||
cli --> util
|
||||
cli --> kit
|
||||
cli --> moderator
|
||||
cli --> jcas
|
||||
cli --> jcasfs
|
||||
cli --> cas
|
||||
cli --> execute
|
||||
cli --> register
|
||||
cli --> runtime
|
||||
```
|
||||
|
||||
## Workflow definition
|
||||
**Adjacent consumers** (not in the main CLI stack):
|
||||
|
||||
Workflows are **YAML files** (not ESM bundles). `uwf workflow put <file.yaml>` parses the YAML, registers output schemas as JSON Schema CAS nodes, and stores the `WorkflowPayload` as a CAS node.
|
||||
- `@uncaged/workflow-util-agent` → `@uncaged/workflow-runtime`
|
||||
- `@uncaged/workflow-agent-llm` → `@uncaged/workflow-runtime`
|
||||
- `@uncaged/workflow-agent-cursor` → `@uncaged/workflow-runtime`, `@uncaged/workflow-util-agent`, `zod`
|
||||
- `@uncaged/workflow-agent-hermes` → `@uncaged/workflow-runtime`, `@uncaged/workflow-util-agent`
|
||||
- `@uncaged/workflow-template-develop` → `@uncaged/workflow-register`, `@uncaged/workflow-runtime`, `zod`
|
||||
- `@uncaged/workflow-template-solve-issue` → `@uncaged/workflow-register`, `@uncaged/workflow-runtime`, `zod` (dev-only workspace deps: `@uncaged/workflow-cas`, `@uncaged/workflow-execute` for tests/tooling per `package.json`)
|
||||
|
||||
Example (`examples/solve-issue.yaml`):
|
||||
## Package roles (detail)
|
||||
|
||||
```yaml
|
||||
name: "solve-issue"
|
||||
description: "End-to-end issue resolution"
|
||||
roles:
|
||||
planner:
|
||||
description: "Creates implementation plan"
|
||||
systemPrompt: "You are a planning agent. Analyze the issue and create a step-by-step plan."
|
||||
outputSchema:
|
||||
type: object
|
||||
properties:
|
||||
plan: { type: string }
|
||||
steps: { type: array, items: { type: string } }
|
||||
required: [plan, steps]
|
||||
developer:
|
||||
description: "Implements code changes"
|
||||
systemPrompt: "You are a developer agent. Implement the plan."
|
||||
outputSchema:
|
||||
type: object
|
||||
properties:
|
||||
filesChanged: { type: array, items: { type: string } }
|
||||
summary: { type: string }
|
||||
required: [filesChanged, summary]
|
||||
reviewer:
|
||||
description: "Reviews code changes"
|
||||
systemPrompt: "You are a code reviewer. Review the implementation."
|
||||
outputSchema:
|
||||
type: object
|
||||
properties:
|
||||
approved: { type: boolean }
|
||||
comments: { type: string }
|
||||
required: [approved, comments]
|
||||
conditions:
|
||||
notApproved:
|
||||
description: "Reviewer rejected the implementation"
|
||||
expression: "steps[-1].output.approved = false"
|
||||
graph:
|
||||
$START:
|
||||
- role: "planner"
|
||||
condition: null
|
||||
planner:
|
||||
- role: "developer"
|
||||
condition: null
|
||||
developer:
|
||||
- role: "reviewer"
|
||||
condition: null
|
||||
reviewer:
|
||||
- role: "developer"
|
||||
condition: "notApproved"
|
||||
- role: "$END"
|
||||
condition: null
|
||||
```
|
||||
|
||||
Key properties:
|
||||
|
||||
- **`roles`** — inline role definitions; each `outputSchema` is a JSON Schema (stored as its own CAS node on registration)
|
||||
- **`conditions`** — named JSONata expressions evaluated against the `ModeratorContext`
|
||||
- **`graph`** — `Record<Role | "$START", Transition[]>` — first matching transition wins; `condition: null` = fallback
|
||||
- **No agent binding** — agent selection is a deployment concern, configured in `config.yaml`
|
||||
- **No Zod** — all schemas are JSON Schema, validated through `@uncaged/json-cas`
|
||||
- **`workflow-protocol`** — Pure types (`WorkflowFn`, contexts, `CasStore` interface, descriptor shapes), `START` / `END`, `ok` / `err`. Depends only on peer `zod` for schema-related types in signatures.
|
||||
- **`workflow-runtime`** — Workflow author surface: `createWorkflow` from `src/create-workflow.js`, re-exports protocol types/constants used when authoring bundles.
|
||||
- **`workflow-util`** — Cross-cutting utilities: Crockford Base32, ULID, `createLogger`, `getDefaultWorkflowStorageRoot`, `getGlobalCasDir`, ref normalization; re-exports `ok`/`err` from protocol.
|
||||
- **`workflow-cas`** — Filesystem CAS (`createCasStore`), `hashString` / `hashWorkflowBundleBytes`, Merkle node serialization and helpers (`merkle.js`).
|
||||
- **`workflow-register`** — Bundle pipeline (`validateWorkflowBundle`, `extractBundleExports`, descriptor builders), registry YAML read/write, `resolveModel` / `splitProviderModelRef`.
|
||||
- **`workflow-execute`** — `executeThread`, supervisor/worker wiring (`engine/`), fork/GC/pause gate, `createExtract` + LLM extract helpers (`extract/`), `workflowAsAgent`. Imports `@uncaged/workflow-reactor` for LLM-backed extract/supervisor paths (`extract-fn.ts`, `supervisor.ts`).
|
||||
- **`workflow-reactor`** — `createLlmFn`, `createThreadReactor`, and thread tool-invocation types — consumed by `workflow-execute`.
|
||||
- **`cli-workflow`** — CLI commands and HTTP/dashboard-related wiring (`hono`, `yaml`); composes register + execute + CAS + util.
|
||||
- **`workflow-agent-*`** — Replaceable `AgentFn` implementations (Cursor / Hermes CLIs, or HTTP LLM).
|
||||
- **`workflow-util-agent`** — Shared prompt assembly and subprocess spawning for CLI agents.
|
||||
- **`workflow-template-*`** — Concrete `WorkflowDefinition` graphs + Zod role schemas + descriptor builders for publishing bundles.
|
||||
- **`workflow-dashboard`** — Standalone React UI; no published library entry matching `src/index.ts`.
|
||||
|
||||
## Three-phase engine loop
|
||||
|
||||
Each `uwf thread step` runs exactly one cycle: moderator → agent → extract. The CLI orchestrates this in `packages/cli-uwf/src/commands/thread.ts` (`cmdThreadStep`).
|
||||
Each role round is implemented in `packages/workflow-runtime/src/create-workflow.ts` (`advanceOneRound`): moderator → agent → extractor, with progressive context types from `@uncaged/workflow-protocol`.
|
||||
|
||||
```
|
||||
┌─→ Phase 1: MODERATOR
|
||||
│ Input: WorkflowPayload + ModeratorContext { start, steps[] }
|
||||
│ Engine: JSONata conditions evaluated against the graph
|
||||
│ Output: next role name | $END
|
||||
│ Context: ModeratorContext { threadId, depth, start, steps }
|
||||
│ Action: moderator(ctx) → role name | END
|
||||
│
|
||||
│ Phase 2: AGENT
|
||||
│ Input: thread-id + role (via argv)
|
||||
│ Engine: agent-kit builds context from CAS chain, prepends
|
||||
│ output format instruction to system prompt, spawns agent
|
||||
│ Output: raw string (frontmatter markdown)
|
||||
│ Context: AgentContext = ModeratorCtx + { currentRole: { name, systemPrompt } }
|
||||
│ Action: agent(ctx) → raw string
|
||||
│
|
||||
│ Phase 3: EXTRACT
|
||||
│ Input: raw agent output + role's outputSchema
|
||||
│ Engine: two-layer extract (frontmatter fast path → LLM fallback)
|
||||
│ Output: CasRef to structured output node
|
||||
│ Phase 3: EXTRACTOR
|
||||
│ Context: ExtractContext = AgentCtx + { agentContent }
|
||||
│ Action: runtime.extract(schema, extractPrompt, ctx) → typed meta
|
||||
│
|
||||
│ Persist: StepNode { start, prev, role, output, detail, agent }
|
||||
│ Update: threads.yaml head pointer
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
│ Merge: RoleStep { role, contentHash, meta, refs, timestamp }
|
||||
│ Append to steps
|
||||
└─────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### Context types
|
||||
### Context types (progressive)
|
||||
|
||||
Defined in `packages/uwf-protocol/src/types.ts`:
|
||||
Defined in `packages/workflow-protocol/src/types.ts`:
|
||||
|
||||
```typescript
|
||||
type StepContext = {
|
||||
role: string;
|
||||
output: unknown; // CAS node payload, expanded (not hash)
|
||||
detail: CasRef;
|
||||
agent: string;
|
||||
};
|
||||
|
||||
type ModeratorContext = {
|
||||
start: StartNodePayload; // { workflow: CasRef, prompt: string }
|
||||
steps: StepContext[]; // chronological, oldest first
|
||||
};
|
||||
|
||||
type AgentContext = ModeratorContext & {
|
||||
threadId: ThreadId;
|
||||
role: string;
|
||||
store: Store;
|
||||
workflow: WorkflowPayload;
|
||||
outputFormatInstruction: string;
|
||||
type ModeratorContext<M> = ThreadContext<M>;
|
||||
type AgentContext<M> = ModeratorContext<M> & {
|
||||
currentRole: { name: string; systemPrompt: string };
|
||||
};
|
||||
type ExtractContext<M> = AgentContext<M> & { agentContent: string };
|
||||
```
|
||||
|
||||
### Key properties
|
||||
|
||||
- **Moderator** — pure JSONata evaluation; no LLM call, no I/O beyond CAS reads. Evaluates `workflow.graph[currentRole]` transitions in order, returns first match.
|
||||
- **Agent** — receives `AgentContext` with thread history + role system prompt + output format instruction. Raw output is frontmatter markdown.
|
||||
- **Extractor** — two-layer: tries frontmatter fast-path first (zero LLM cost), falls back to LLM extract if frontmatter is absent or invalid.
|
||||
- **Stateless** — each `uwf thread step` is an atomic, self-contained operation. No in-memory state between steps.
|
||||
- **Moderator is synchronous and pure** — no I/O, no state mutation inside `createWorkflow`’s moderator call path.
|
||||
- **Agent receives `AgentContext`** — reads `ctx.currentRole.systemPrompt`; raw output becomes `agentContent` for extract.
|
||||
- **Extractor is `WorkflowRuntime.extract`** — supplied by the engine from registry-resolved LLM config (`workflow-execute`); stores agent body in CAS and yields `contentHash` + `refs` on each step (`create-workflow.ts`).
|
||||
- **`extractPrompt` is a call parameter** on `RoleDefinition`, not implicit context state.
|
||||
|
||||
## Agent CLI protocol
|
||||
## Agent information sources
|
||||
|
||||
Each agent is an external command invoked by `uwf thread step`:
|
||||
An agent has exactly three information sources:
|
||||
|
||||
```bash
|
||||
<agent-cmd> <thread-id> <role>
|
||||
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 obtains it via `ExtractFn` (e.g. Cursor agent).
|
||||
|
||||
## Bundle contract
|
||||
|
||||
A workflow bundle is a single `.esm.js` file with two named exports (see `WorkflowFn` / `WorkflowDescriptor` in `packages/workflow-protocol/src/types.ts`):
|
||||
|
||||
```typescript
|
||||
export const descriptor: WorkflowDescriptor;
|
||||
export const run: WorkflowFn;
|
||||
|
||||
type WorkflowFn = (
|
||||
thread: ThreadContext,
|
||||
runtime: WorkflowRuntime,
|
||||
) => AsyncGenerator<RoleOutput, WorkflowCompletion>;
|
||||
```
|
||||
|
||||
Contract:
|
||||
1. `uwf thread step` determines the next role via the moderator
|
||||
2. Agent CLI is spawned with `(thread-id, role)` as positional args
|
||||
3. `uwf-agent-kit` (`createAgent`) handles the boilerplate:
|
||||
- Parses argv
|
||||
- Loads `.env` from storage root
|
||||
- Builds `AgentContext` by walking the CAS chain from `threads.yaml` head
|
||||
- Resolves the role's `outputSchema` and builds `outputFormatInstruction`
|
||||
- Calls the agent's `run` function
|
||||
- Runs two-layer extract on the raw output
|
||||
- Writes `StepNode` to CAS (output + detail + prev link)
|
||||
- Prints the new `StepNode` CAS hash to stdout
|
||||
4. `uwf thread step` reads stdout, updates `threads.yaml` head pointer, re-evaluates moderator for `done`
|
||||
5. Exit 0 = success, non-zero = failure
|
||||
`RoleOutput` carries `contentHash`, `meta`, and `refs` (agent text lives in CAS, addressed by hash).
|
||||
|
||||
Agent resolution priority: `--agent` CLI override → `config.yaml` per-workflow/role override → `config.yaml` `defaultAgent`.
|
||||
### Constraints
|
||||
|
||||
## Agent output format: frontmatter markdown (RFC #351)
|
||||
- Single `.esm.js` file
|
||||
- No dynamic `import()` in bundles (loader exempt in engine)
|
||||
- Portable bundle static imports are constrained by validation in `@uncaged/workflow-register` (`validateWorkflowBundle`)
|
||||
- XXH64 hash (Crockford Base32) = version ID
|
||||
|
||||
Agents produce **frontmatter markdown** — YAML frontmatter for structured meta, followed by a markdown body for content:
|
||||
### Why AsyncGenerator?
|
||||
|
||||
```markdown
|
||||
---
|
||||
status: done
|
||||
next: reviewer
|
||||
confidence: 0.9
|
||||
artifacts:
|
||||
- src/auth.ts
|
||||
scope: role
|
||||
---
|
||||
|
||||
## Implementation
|
||||
|
||||
Fixed the login redirect by updating the auth middleware...
|
||||
```
|
||||
|
||||
The `outputFormatInstruction` (built by `buildOutputFormatInstruction` in `uwf-agent-kit`) is prepended to the role's system prompt, so the deliverable format is the first thing the agent sees. It lists the expected frontmatter fields derived from the role's JSON Schema.
|
||||
|
||||
## Two-layer extract
|
||||
|
||||
Structured output extraction uses a two-layer strategy (`uwf-agent-kit`):
|
||||
|
||||
### Layer 1: frontmatter fast path (`frontmatter.ts`)
|
||||
|
||||
1. Parse YAML frontmatter from raw agent output (`parseFrontmatterMarkdown`)
|
||||
2. Validate required fields (`validateFrontmatter`)
|
||||
3. Build a candidate object from frontmatter fields (`status`, `next`, `confidence`, `artifacts`, `scope`)
|
||||
4. `store.put()` the candidate against the role's `outputSchema`
|
||||
5. Validate with `json-cas` schema validation
|
||||
6. If valid → return `outputHash` (zero LLM cost)
|
||||
|
||||
### Layer 2: LLM extract fallback (`extract.ts`)
|
||||
|
||||
If the fast path returns `null` (no frontmatter, invalid, or doesn't satisfy schema):
|
||||
|
||||
1. Resolve extract model alias from config (`modelOverrides.extract` → `models.extract` → `defaultModel`)
|
||||
2. Call OpenAI-compatible chat completion with JSON mode
|
||||
3. System prompt: "Extract structured data matching this JSON Schema: ..."
|
||||
4. User message: the raw agent output
|
||||
5. Parse response, `store.put()`, validate
|
||||
6. Return `outputHash`
|
||||
|
||||
## Prompt injection
|
||||
|
||||
`uwf-agent-kit` prepends two pieces of context to the agent's system prompt:
|
||||
|
||||
1. **Deliverable format instruction** — generated from the role's `outputSchema`, tells the agent exactly what frontmatter fields to produce and the expected format
|
||||
2. **Scope constraint** — "Focus exclusively on YOUR role's deliverable. Do not perform actions outside your role's scope."
|
||||
|
||||
This ensures agents produce parseable frontmatter output without requiring per-agent format knowledge.
|
||||
|
||||
## CAS node types
|
||||
|
||||
### Workflow
|
||||
|
||||
```yaml
|
||||
type: <workflow-schema-hash>
|
||||
payload:
|
||||
name: "solve-issue"
|
||||
description: "End-to-end issue resolution"
|
||||
roles:
|
||||
planner:
|
||||
description: "Creates implementation plan"
|
||||
systemPrompt: "You are a planning agent..."
|
||||
outputSchema: "5GWKR8TN1V3JA" # cas_ref → JSON Schema node
|
||||
conditions:
|
||||
notApproved:
|
||||
description: "Reviewer rejected"
|
||||
expression: "steps[-1].output.approved = false"
|
||||
graph:
|
||||
$START:
|
||||
- role: "planner"
|
||||
condition: null
|
||||
```
|
||||
|
||||
### StartNode
|
||||
|
||||
```yaml
|
||||
type: <start-node-schema-hash>
|
||||
payload:
|
||||
workflow: "4KNM2PXR3B1QW" # cas_ref → Workflow
|
||||
prompt: "Fix the login bug..."
|
||||
```
|
||||
|
||||
### StepNode
|
||||
|
||||
```yaml
|
||||
type: <step-node-schema-hash>
|
||||
payload:
|
||||
start: "4TNVW8KR2B3MA" # cas_ref → StartNode
|
||||
prev: "2MXBG6PN4A8JR" # cas_ref → previous StepNode (null for first step)
|
||||
role: "developer"
|
||||
output: "9KRVW3TN5F1QA" # cas_ref → structured output (validated against outputSchema)
|
||||
detail: "7BQST3VW9F2MA" # cas_ref → execution detail (raw turns, session data)
|
||||
agent: "uwf-hermes" # agent command used (plain string)
|
||||
```
|
||||
|
||||
### Chain structure
|
||||
|
||||
```
|
||||
threads.yaml: { "01J7K9...4T": "8FWKR3TN5V1QA" }
|
||||
│
|
||||
▼
|
||||
StepNode (step 3)
|
||||
├── start ──→ StartNode
|
||||
│ ├── workflow → Workflow (CAS)
|
||||
│ └── prompt: "Fix..."
|
||||
├── prev ──→ StepNode (step 2)
|
||||
│ ├── prev ──→ StepNode (step 1)
|
||||
│ │ └── prev: null
|
||||
│ └── ...
|
||||
├── role: "reviewer"
|
||||
├── output → CAS({ approved: true })
|
||||
├── detail → CAS(session turns)
|
||||
└── agent: "uwf-hermes"
|
||||
```
|
||||
- Each `yield` lets `workflow-execute` persist state, CAS rows, and enforce pause/abort
|
||||
- `return` supplies `WorkflowCompletion`
|
||||
- Fork replays historical steps into a new thread context
|
||||
- Bundle does not import the engine — only protocol/runtime types at build time
|
||||
|
||||
## Storage layout
|
||||
|
||||
```
|
||||
~/.uncaged/workflow/
|
||||
├── cas/ # json-cas filesystem store (all CAS nodes)
|
||||
├── config.yaml # Provider, model, agent configuration
|
||||
├── threads.yaml # Active thread head pointers: threadId → CasRef
|
||||
├── history.jsonl # Archived thread records
|
||||
├── registry.yaml # Workflow name → CAS hash mapping
|
||||
└── .env # API keys (loaded by dotenv)
|
||||
├── cas/ # Global content-addressed blobs (see getGlobalCasDir)
|
||||
├── bundles/
|
||||
│ ├── C9NMV6V2TQT81.esm.js # Crockford Base32 of XXH64
|
||||
│ ├── C9NMV6V2TQT81.yaml # Role descriptor sidecar (when present)
|
||||
│ └── C9NMV6V2TQT81/ # Per-hash bundle dir (alongside or instead of loose files)
|
||||
│ ├── threads.json # Active threads: threadId → { head, start, updatedAt }
|
||||
│ └── history/
|
||||
│ └── 2026-05-09.jsonl # Completed threads (one JSON object per line)
|
||||
├── logs/ # One folder per bundle hash
|
||||
│ └── C9NMV6V2TQT81/
|
||||
│ ├── 01KQXKW…YG.running # Present while worker executes this thread (optional)
|
||||
│ └── 01KQXKW…YG.info.jsonl # Debug log
|
||||
└── workflow.yaml # Registry
|
||||
```
|
||||
|
||||
### Mutable state
|
||||
|
||||
Only three files carry mutable state:
|
||||
|
||||
| File | Contents |
|
||||
|------|----------|
|
||||
| `threads.yaml` | `Record<ThreadId, CasRef>` — maps active thread IDs to head node hash |
|
||||
| `history.jsonl` | Append-only log of completed threads (`thread`, `workflow`, `head`, `completedAt`) |
|
||||
| `registry.yaml` | Workflow name → current CAS hash |
|
||||
|
||||
Everything else is immutable CAS content.
|
||||
|
||||
### ID encoding: Crockford Base32
|
||||
|
||||
- Case-insensitive, filesystem-safe, no ambiguous chars (0/O, 1/I/L)
|
||||
- CAS hash: XXH64 → 13-char Crockford Base32
|
||||
- Thread ID: ULID → 26-char Crockford Base32 (10 timestamp + 16 random)
|
||||
- Bundle hash: XXH64 → 13-char
|
||||
- Thread ID: ULID → 26-char (10 timestamp + 16 random)
|
||||
|
||||
### Config (`config.yaml`)
|
||||
### Registry (`workflow.yaml`)
|
||||
|
||||
```yaml
|
||||
providers:
|
||||
openrouter:
|
||||
baseUrl: "https://openrouter.ai/api/v1"
|
||||
apiKeyEnv: "OPENROUTER_API_KEY"
|
||||
Managed by `@uncaged/workflow-register` (`readWorkflowRegistry`, `writeWorkflowRegistry`, …). Shape includes workflow entries and a top-level `config` section used for extract/supervisor model resolution.
|
||||
|
||||
models:
|
||||
sonnet:
|
||||
provider: "openrouter"
|
||||
name: "anthropic/claude-sonnet-4"
|
||||
gpt4o-mini:
|
||||
provider: "openai"
|
||||
name: "gpt-4o-mini"
|
||||
### Thread storage (CAS + index)
|
||||
|
||||
agents:
|
||||
hermes:
|
||||
command: "uwf-hermes"
|
||||
args: []
|
||||
cursor:
|
||||
command: "uwf-cursor"
|
||||
args: []
|
||||
Thread execution state is a chain of immutable CAS nodes (`StartNode`, `StateNode`, content Merkle blobs). Per bundle:
|
||||
|
||||
defaultAgent: "hermes"
|
||||
agentOverrides:
|
||||
solve-issue:
|
||||
developer: "cursor"
|
||||
- **`threads.json`** — only in-flight threads (`head`, `start`, `updatedAt`).
|
||||
- **`history/{YYYY-MM-DD}.jsonl`** — completed threads (`threadId`, `head`, `start`, `completedAt`).
|
||||
- **CAS (`cas/`)** — payloads and refs for replay, GC, and fork sharing.
|
||||
|
||||
defaultModel: "sonnet"
|
||||
modelOverrides:
|
||||
extract: "gpt4o-mini"
|
||||
**`.info.jsonl`** — Structured debug log via `@uncaged/workflow-util` `createLogger`:
|
||||
|
||||
```jsonc
|
||||
{ "tag": "4KNMR2PX", "content": "Loading bundle...", "timestamp": ... }
|
||||
```
|
||||
|
||||
Tags are 8-char Crockford Base32 (40-bit random), one per call site. `grep "4KNMR2PX"` → code location.
|
||||
|
||||
## Execution model
|
||||
|
||||
- **No daemon.** `uncaged-workflow run <name>` starts a worker process (`workflow-execute` worker entry via `getWorkerHostScriptPath`)
|
||||
- Threads share bundle-scoped workers as implemented in CLI/engine
|
||||
- Pause/resume/abort via engine IPC and pause gate (`createThreadPauseGate`)
|
||||
|
||||
## CLI commands
|
||||
|
||||
Binary: `uwf`
|
||||
|
||||
### Thread commands
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf thread start <workflow> -p <prompt>` | Create a thread (StartNode → CAS, head → threads.yaml). No execution. |
|
||||
| `uwf thread step <thread-id> [--agent <cmd>]` | Execute one moderator→agent→extract cycle. |
|
||||
| `uwf thread show <thread-id>` | Show thread head pointer and done status. |
|
||||
| `uwf thread list [--all]` | List active threads (`--all` includes archived). |
|
||||
| `uwf thread steps <thread-id>` | List all steps in chronological order. |
|
||||
| `uwf thread read <thread-id> [--quota <chars>] [--before <hash>]` | Render thread as human-readable markdown. |
|
||||
| `uwf thread fork <step-hash>` | Fork a thread from a specific CAS node. |
|
||||
| `uwf thread step-details <step-hash>` | Dump full detail node as YAML. |
|
||||
| `uwf thread kill <thread-id>` | Terminate and archive a thread. |
|
||||
|
||||
### Workflow commands
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf workflow put <file.yaml>` | Register a workflow from YAML definition. |
|
||||
| `uwf workflow show <id>` | Show workflow by name or CAS hash. |
|
||||
| `uwf workflow list` | List registered workflows. |
|
||||
|
||||
### CAS commands
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf cas get <hash>` | Read a CAS node. |
|
||||
| `uwf cas put <type-hash> <data>` | Store a node, print its hash. |
|
||||
| `uwf cas has <hash>` | Check if a hash exists. |
|
||||
| `uwf cas refs <hash>` | List direct CAS references. |
|
||||
| `uwf cas walk <hash>` | Recursive traversal from a node. |
|
||||
| `uwf cas reindex` | Rebuild type index from all nodes. |
|
||||
| `uwf cas schema list` | List registered schemas. |
|
||||
| `uwf cas schema get <hash>` | Show a schema by type hash. |
|
||||
|
||||
### Setup
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `uwf setup [--provider --base-url --api-key --model --agent]` | Configure provider/model/agent (interactive if no flags). |
|
||||
|
||||
## Toolchain
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| **bun** | Package manager + runtime |
|
||||
| **TypeScript** | Type checking (strict mode) |
|
||||
| **Biome** | Lint + format |
|
||||
| **vitest** | Test runner |
|
||||
| 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 |
|
||||
|
||||
## Design decisions
|
||||
|
||||
| Decision | Rationale |
|
||||
|----------|-----------|
|
||||
| **YAML workflow definitions** | Human-readable, versionable, no build step required. JSON Schema inline in YAML, registered as CAS nodes on `workflow put`. |
|
||||
| **Stateless single-step CLI** | Each `uwf thread step` is atomic — no in-memory state, no daemon, no long-running process. OS handles lifecycle. |
|
||||
| **CAS-backed thread state** | Immutable linked nodes enable fork, replay, and GC without copying data. Content-addressed deduplication across threads. |
|
||||
| **JSONata moderator** | Declarative condition expressions evaluated against thread history. No LLM cost for routing decisions. |
|
||||
| **Frontmatter markdown output** | Agents produce structured meta (YAML frontmatter) alongside free-form content (markdown body). Enables zero-cost extraction when frontmatter is well-formed. |
|
||||
| **Two-layer extract** | Fast path avoids LLM calls when agents follow the format; LLM fallback handles messy output gracefully. |
|
||||
| **Prompt injection for format** | Output format instruction prepended to system prompt ensures agents produce parseable output without per-agent configuration. |
|
||||
| **JSON Schema (not Zod)** | Schemas are CAS-native data — storable, hashable, validatable through `json-cas`. No code generation, no runtime library dependency. |
|
||||
| **Agent as external command** | Agents are independent CLI binaries (`uwf-hermes`, `uwf-cursor`). Swappable per workflow/role via config. No tight coupling to the engine. |
|
||||
| **No daemon** | Process starts, does one step, exits. Simpler failure model, no connection management. |
|
||||
| **Crockford Base32** | Filesystem-safe, case-insensitive, readable, compact. |
|
||||
| **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; types live in `workflow-protocol` |
|
||||
| **`WorkflowRuntime.extract` + CAS `contentHash`** | Large agent bodies deduplicated globally; Merkle roots summarize threads |
|
||||
| **`workflow-reactor` split** | LLM tool-calling loop isolated from filesystem/registry concerns |
|
||||
| **Single-file ESM** | Hash = version, self-contained bundle |
|
||||
| **No daemon** | OS handles process lifecycle |
|
||||
| **Crockford Base32** | Filesystem-safe, readable, compact |
|
||||
| **15-package split** | Clear boundaries: protocol ↔ runtime author API ↔ util/CAS/register ↔ execute ↔ CLI ↔ agents/templates/UI |
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,387 +0,0 @@
|
||||
# 设计文档:office-agent 文档生成/编辑 Workflow 体系
|
||||
|
||||
**日期:** 2026-05-18
|
||||
|
||||
---
|
||||
|
||||
## 概述
|
||||
|
||||
在 monorepo 中新增三个包,实现通过 `office-agent` CLI 生成或编辑 Word 文档的完整 workflow 体系。
|
||||
|
||||
| 包 | npm name | 职责 |
|
||||
|---|---|---|
|
||||
| `workflow-template-document` | `@uncaged/workflow-template-document` | 纯结构:角色定义、meta schema、调度表、descriptor |
|
||||
| `workflow-agent-office` | `@uncaged/workflow-agent-office` | writer 角色执行器:调用 `office-agent` CLI |
|
||||
| `workflow-agent-docx-diff` | `@uncaged/workflow-agent-docx-diff` | differ 角色执行器:调用 `docx-diff` CLI |
|
||||
|
||||
Template 只定义结构,不含执行逻辑。执行器与 template 解耦。
|
||||
|
||||
---
|
||||
|
||||
## 一、`workflow-template-document`
|
||||
|
||||
### Thread 启动输入
|
||||
|
||||
```typescript
|
||||
// src/types.ts
|
||||
type DocumentStartInput = {
|
||||
prompt: string; // 用户指令
|
||||
inputDocx: string | null; // null = 生成模式;本机绝对路径 = 编辑模式
|
||||
};
|
||||
```
|
||||
|
||||
start.content 为 JSON `{ prompt, inputDocx }` 或纯文本(fallback:generate 模式,整段作为 prompt)。
|
||||
|
||||
### 角色与 Meta
|
||||
|
||||
`WriterMeta` 使用 discriminated union,在 schema 层区分两种模式:
|
||||
|
||||
```typescript
|
||||
const writerMetaSchema = z.discriminatedUnion("mode", [
|
||||
z.object({
|
||||
mode: z.literal("generate"),
|
||||
outputDocx: z.string(), // 生成产物绝对路径
|
||||
sourceDocx: z.null(),
|
||||
}),
|
||||
z.object({
|
||||
mode: z.literal("edit"),
|
||||
outputDocx: z.string(), // 修改后产物:<outputDir>/modified.docx
|
||||
sourceDocx: z.string(), // 原始副本:<outputDir>/original.docx
|
||||
}),
|
||||
]);
|
||||
type WriterMeta = z.infer<typeof writerMetaSchema>;
|
||||
|
||||
// differ:仅编辑模式执行
|
||||
const differMetaSchema = z.object({
|
||||
sourceDocx: z.string(),
|
||||
modifiedDocx: z.string(),
|
||||
diffDocx: z.string(),
|
||||
});
|
||||
type DifferMeta = z.infer<typeof differMetaSchema>;
|
||||
```
|
||||
|
||||
两个角色的 `systemPrompt` 均为 `""`。
|
||||
|
||||
### 调度表
|
||||
|
||||
```
|
||||
START → writer ──(mode = "edit")──→ differ → END
|
||||
↘(mode = "generate")→ END
|
||||
```
|
||||
|
||||
### 公开导出
|
||||
|
||||
template 导出两个对象供消费方使用:
|
||||
|
||||
- `documentWorkflowDefinition: WorkflowDefinition<DocumentMeta>` — 传入 `createWorkflow` 的 `def` 参数
|
||||
- `buildDocumentDescriptor(): WorkflowDescriptor` — bundle 导出用
|
||||
|
||||
```typescript
|
||||
// bundle 侧用法
|
||||
export const descriptor = buildDocumentDescriptor();
|
||||
export const run = createWorkflow(documentWorkflowDefinition, { adapter, overrides });
|
||||
```
|
||||
|
||||
### 包文件结构
|
||||
|
||||
```
|
||||
packages/workflow-template-document/
|
||||
src/
|
||||
types.ts # DocumentStartInput
|
||||
roles/
|
||||
writer.ts # writerMetaSchema, WriterMeta, writerRole
|
||||
differ.ts # differMetaSchema, DifferMeta, differRole
|
||||
index.ts
|
||||
roles.ts # DocumentMeta, documentRoles
|
||||
moderator.ts # writerIsEditMode condition + documentTable
|
||||
definition.ts # documentWorkflowDefinition
|
||||
descriptor.ts # buildDocumentDescriptor()
|
||||
index.ts
|
||||
__tests__/
|
||||
moderator.test.ts
|
||||
package.json
|
||||
tsconfig.json
|
||||
```
|
||||
|
||||
### 依赖
|
||||
|
||||
```json
|
||||
{
|
||||
"@uncaged/workflow-protocol": "workspace:^",
|
||||
"@uncaged/workflow-runtime": "workspace:^",
|
||||
"@uncaged/workflow-register": "workspace:^",
|
||||
"zod": "^4.0.0"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 二、`workflow-agent-office`
|
||||
|
||||
### office-agent CLI 接口
|
||||
|
||||
```bash
|
||||
# 生成模式:在 CWD 生成 output.docx
|
||||
office-agent create "<prompt>" -o output.docx
|
||||
|
||||
# 编辑模式:在 CWD 对 modified.docx 进行修改(覆写)
|
||||
office-agent edit modified.docx "<instruction>"
|
||||
```
|
||||
|
||||
- 两个命令均为阻塞调用(CLI 内部消费 SSE,退出即完成)
|
||||
- 输出文件落到调用方设定的 CWD
|
||||
- 退出码 0 = 成功,非零 = 失败
|
||||
|
||||
### 文件命名约定
|
||||
|
||||
| 模式 | 文件 | 路径 |
|
||||
|---|---|---|
|
||||
| generate | 输出 | `<outputDir>/output.docx` |
|
||||
| edit | 原始副本(workflow-owned 快照) | `<outputDir>/original.docx` |
|
||||
| edit | 修改后产物 | `<outputDir>/modified.docx` |
|
||||
|
||||
edit 模式先将 `inputDocx` 复制为 `original.docx`(不可变快照),再复制为 `modified.docx`,对 `modified.docx` 调用 CLI。agent 覆写 `modified.docx`,`original.docx` 保持不变。differ 对比这两个 workflow-owned 文件,不依赖用户原始路径。
|
||||
|
||||
### 执行流程
|
||||
|
||||
**生成模式(`inputDocx = null`):**
|
||||
1. `mkdir -p <outputDir>`(`<config.outputDir>/<ctx.threadId>`)
|
||||
2. `const command = config.command ?? "office-agent"`
|
||||
3. `spawnCli(command, ["create", prompt, "-o", "output.docx"], { cwd: outputDir, timeoutMs })`
|
||||
4. 验证 `outputDir/output.docx` 存在
|
||||
5. 返回 `JSON.stringify({ mode: "generate", outputDocx, sourceDocx: null })`
|
||||
|
||||
**编辑模式(`inputDocx ≠ null`):**
|
||||
1. `mkdir -p <outputDir>`
|
||||
2. `copyFile(inputDocx, <outputDir>/original.docx)`
|
||||
3. `copyFile(inputDocx, <outputDir>/modified.docx)`
|
||||
4. `const command = config.command ?? "office-agent"`
|
||||
5. `spawnCli(command, ["edit", "modified.docx", prompt], { cwd: outputDir, timeoutMs })`
|
||||
6. 验证 `outputDir/modified.docx` 存在
|
||||
7. 返回 `JSON.stringify({ mode: "edit", outputDocx: modifiedPath, sourceDocx: originalPath })`
|
||||
|
||||
### AdapterFn 实现(直接实现,不经过 runtime.extract)
|
||||
|
||||
CLI 产出确定性 JSON,直接 `schema.parse(JSON.parse(raw))` 跳过 LLM extraction:
|
||||
|
||||
```typescript
|
||||
export function createOfficeAgent(config: OfficeAgentConfig): AdapterFn {
|
||||
return <T>(_systemPrompt: string, schema: z.ZodType<T>) =>
|
||||
async (ctx: ThreadContext, _runtime: WorkflowRuntime): Promise<RoleResult<T>> => {
|
||||
const { prompt, inputDocx } = parseStartInput(ctx.start.content);
|
||||
const raw = await runOfficeAgent(config, ctx.threadId, prompt, inputDocx);
|
||||
const meta = schema.parse(JSON.parse(raw)) as T;
|
||||
return { meta, childThread: null };
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
`_systemPrompt` 为 writer 角色的 systemPrompt(空字符串),实际指令从 `ctx.start.content` 解析。
|
||||
|
||||
### 配置
|
||||
|
||||
```typescript
|
||||
type OfficeAgentConfig = {
|
||||
outputDir: string; // 输出根目录,runner 在此下按 threadId 建子目录
|
||||
command: string | null; // null → runner 内 resolve 为 "office-agent"
|
||||
timeout: number | null; // null → 不设超时;单位 ms
|
||||
};
|
||||
```
|
||||
|
||||
### 错误处理
|
||||
|
||||
```typescript
|
||||
if (!result.ok) {
|
||||
const e = result.error;
|
||||
if (e.kind === "non_zero_exit")
|
||||
throw new Error(`office-agent failed (exit ${e.exitCode}): ${e.stderr}`);
|
||||
if (e.kind === "timeout")
|
||||
throw new Error("office-agent: timed out");
|
||||
// "spawn_failed"
|
||||
throw new Error(`office-agent: spawn failed: ${e.message}`);
|
||||
}
|
||||
if (!existsSync(expectedPath))
|
||||
throw new Error(`office-agent: output file not found: ${expectedPath}`);
|
||||
```
|
||||
|
||||
### packageDescriptor
|
||||
|
||||
```typescript
|
||||
// src/package-descriptor.ts
|
||||
export const packageDescriptor: PackageDescriptor = {
|
||||
name: "@uncaged/workflow-agent-office",
|
||||
version: "0.1.0",
|
||||
capabilities: ["office-agent-cli", "docx-generate", "docx-edit"],
|
||||
configSchema: {
|
||||
type: "object",
|
||||
required: ["outputDir"],
|
||||
properties: {
|
||||
outputDir: { type: "string", description: "Root directory for workflow outputs." },
|
||||
command: { anyOf: [{ type: "string" }, { type: "null" }], description: "Path to office-agent CLI; null uses PATH." },
|
||||
timeout: { anyOf: [{ type: "number" }, { type: "null" }], description: "Timeout in ms; null means no limit." },
|
||||
},
|
||||
additionalProperties: false,
|
||||
},
|
||||
};
|
||||
```
|
||||
|
||||
### 包文件结构
|
||||
|
||||
```
|
||||
packages/workflow-agent-office/
|
||||
src/
|
||||
types.ts # OfficeAgentConfig, OfficeAgentOpt
|
||||
runner.ts # runOfficeAgent()(spawnCli 封装 + 文件验证)
|
||||
agent.ts # createOfficeAgent(): AdapterFn
|
||||
package-descriptor.ts # packageDescriptor
|
||||
index.ts
|
||||
__tests__/
|
||||
runner.test.ts
|
||||
agent.test.ts
|
||||
package.json
|
||||
tsconfig.json
|
||||
```
|
||||
|
||||
### 依赖
|
||||
|
||||
```json
|
||||
{
|
||||
"@uncaged/workflow-protocol": "workspace:^",
|
||||
"@uncaged/workflow-util": "workspace:^",
|
||||
"@uncaged/workflow-util-agent": "workspace:^"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 三、`workflow-agent-docx-diff`
|
||||
|
||||
`differ` 角色专用执行器。从 `ctx.steps` 读取 `WriterMeta`,调用本地 `docx-diff` CLI。
|
||||
|
||||
### docx-diff 退出码约定
|
||||
|
||||
| 退出码 | 含义 | runner 处理 |
|
||||
|---|---|---|
|
||||
| 0 | 无差异 | 正常,验证 diffDocx 存在 |
|
||||
| 1 | 有差异 | 正常(显式处理为成功),验证 diffDocx 存在 |
|
||||
| 2+ | 错误 | throw |
|
||||
|
||||
runner 收到 `SpawnCliError { kind: "non_zero_exit", exitCode: 1 }` 时视为成功,验证文件后继续;`exitCode >= 2` 才 throw。
|
||||
|
||||
### 执行流程
|
||||
|
||||
```
|
||||
1. 从 ctx.steps 找到 writer 步骤,读取 WriterMeta
|
||||
2. 验证 mode === "edit"(否则 throw)
|
||||
3. diffDocx = join(dirname(writer.outputDocx), "diff.docx")
|
||||
4. const command = config.command ?? "docx-diff"
|
||||
5. spawnCli(command,
|
||||
[writer.sourceDocx, writer.outputDocx, "--output", "docx", "--out-file", diffDocx],
|
||||
{ cwd: null, timeoutMs: null })
|
||||
exit 0 或 1 → 验证 diffDocx 存在
|
||||
exit 2+ → throw
|
||||
6. 返回 JSON.stringify({ sourceDocx, modifiedDocx: writer.outputDocx, diffDocx })
|
||||
```
|
||||
|
||||
### AdapterFn 实现(直接实现,不经过 runtime.extract)
|
||||
|
||||
```typescript
|
||||
export function createDocxDiffAgent(config: DocxDiffAgentConfig = { command: null }): AdapterFn {
|
||||
return <T>(_prompt: string, schema: z.ZodType<T>) =>
|
||||
async (ctx: ThreadContext, _runtime: WorkflowRuntime): Promise<RoleResult<T>> => {
|
||||
const writerStep = ctx.steps.find(s => s.role === "writer");
|
||||
if (!writerStep) throw new Error("differ: no writer step found");
|
||||
const writerMeta = writerStep.meta as WriterMeta;
|
||||
if (writerMeta.mode !== "edit")
|
||||
throw new Error("differ: writer did not run in edit mode");
|
||||
const raw = await runDocxDiff(config, writerMeta);
|
||||
const meta = schema.parse(JSON.parse(raw)) as T;
|
||||
return { meta, childThread: null };
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
### 配置
|
||||
|
||||
```typescript
|
||||
type DocxDiffAgentConfig = {
|
||||
command: string | null; // null → runner 内 resolve 为 "docx-diff"
|
||||
};
|
||||
```
|
||||
|
||||
### packageDescriptor
|
||||
|
||||
```typescript
|
||||
export const packageDescriptor: PackageDescriptor = {
|
||||
name: "@uncaged/workflow-agent-docx-diff",
|
||||
version: "0.1.0",
|
||||
capabilities: ["docx-diff-cli", "docx-diff-report"],
|
||||
configSchema: {
|
||||
type: "object",
|
||||
properties: {
|
||||
command: { anyOf: [{ type: "string" }, { type: "null" }], description: "Path to docx-diff CLI; null uses PATH." },
|
||||
},
|
||||
additionalProperties: false,
|
||||
},
|
||||
};
|
||||
```
|
||||
|
||||
### 包文件结构
|
||||
|
||||
```
|
||||
packages/workflow-agent-docx-diff/
|
||||
src/
|
||||
types.ts # DocxDiffAgentConfig
|
||||
runner.ts # runDocxDiff()(exit 1 处理 + 文件验证)
|
||||
agent.ts # createDocxDiffAgent(): AdapterFn
|
||||
package-descriptor.ts # packageDescriptor
|
||||
index.ts
|
||||
__tests__/
|
||||
runner.test.ts
|
||||
agent.test.ts
|
||||
package.json
|
||||
tsconfig.json
|
||||
```
|
||||
|
||||
### 依赖
|
||||
|
||||
```json
|
||||
{
|
||||
"@uncaged/workflow-protocol": "workspace:^",
|
||||
"@uncaged/workflow-util-agent": "workspace:^",
|
||||
"@uncaged/workflow-template-document": "workspace:^"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 四、外部 bundle(外部 workspace 消费)
|
||||
|
||||
```typescript
|
||||
import { createOfficeAgent } from "@uncaged/workflow-agent-office";
|
||||
import { createDocxDiffAgent } from "@uncaged/workflow-agent-docx-diff";
|
||||
import {
|
||||
buildDocumentDescriptor,
|
||||
documentWorkflowDefinition,
|
||||
} from "@uncaged/workflow-template-document";
|
||||
import { createWorkflow } from "@uncaged/workflow-runtime";
|
||||
import { getDefaultWorkflowStorageRoot } from "@uncaged/workflow-util";
|
||||
import { join } from "node:path";
|
||||
|
||||
const outputDir = join(getDefaultWorkflowStorageRoot(), "outputs");
|
||||
|
||||
export const descriptor = buildDocumentDescriptor();
|
||||
export const run = createWorkflow(documentWorkflowDefinition, {
|
||||
adapter: createOfficeAgent({ outputDir, command: null, timeout: null }),
|
||||
overrides: { differ: createDocxDiffAgent() },
|
||||
});
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 不在范围内
|
||||
|
||||
- 重试逻辑(失败直接 throw)
|
||||
- office-agent server 的启停管理(假设 server 已在运行)
|
||||
- docx-diff HTML/terminal 格式输出(仅 docx)
|
||||
- 跨机器执行(`inputDocx` 须为本机有效绝对路径)
|
||||
@@ -1,22 +0,0 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { packageDescriptor } from "../src/package-descriptor.js";
|
||||
import { createDocxDiffAgent } from "../src/agent.js";
|
||||
|
||||
describe("createDocxDiffAgent", () => {
|
||||
test("returns an AdapterFn (function)", () => {
|
||||
const agent = createDocxDiffAgent({ command: null });
|
||||
expect(typeof agent).toBe("function");
|
||||
});
|
||||
|
||||
test("AdapterFn returns a RoleFn (function)", () => {
|
||||
const agent = createDocxDiffAgent({ command: null });
|
||||
const roleFn = agent("", expect.anything() as never);
|
||||
expect(typeof roleFn).toBe("function");
|
||||
});
|
||||
});
|
||||
|
||||
describe("packageDescriptor", () => {
|
||||
test("has correct name", () => {
|
||||
expect(packageDescriptor.name).toBe("@uncaged/workflow-agent-docx-diff");
|
||||
});
|
||||
});
|
||||
@@ -1,113 +0,0 @@
|
||||
import { mkdirSync, writeFileSync } from "node:fs";
|
||||
import { join } from "node:path";
|
||||
import { tmpdir } from "node:os";
|
||||
import { describe, expect, mock, test } from "bun:test";
|
||||
import { ok, err } from "@uncaged/workflow-util";
|
||||
import type { SpawnCliConfig } from "@uncaged/workflow-util-agent";
|
||||
import { runDocxDiff } from "../src/runner.js";
|
||||
|
||||
type MockSpawnResult = Awaited<ReturnType<typeof import("@uncaged/workflow-util-agent").spawnCli>>;
|
||||
|
||||
function makeSpawn(result: MockSpawnResult) {
|
||||
return mock(async (_cmd: string, _args: string[], _opts: SpawnCliConfig) => result);
|
||||
}
|
||||
|
||||
function tempDir(): string {
|
||||
const dir = join(tmpdir(), `diff-test-${Date.now()}`);
|
||||
mkdirSync(dir, { recursive: true });
|
||||
return dir;
|
||||
}
|
||||
|
||||
describe("runDocxDiff", () => {
|
||||
test("exit 0: success, returns DifferMeta JSON", async () => {
|
||||
const dir = tempDir();
|
||||
const sourceDocx = join(dir, "original.docx");
|
||||
const modifiedDocx = join(dir, "modified.docx");
|
||||
const diffDocx = join(dir, "diff.docx");
|
||||
writeFileSync(sourceDocx, "");
|
||||
writeFileSync(modifiedDocx, "");
|
||||
|
||||
const spawnFn = makeSpawn(ok("") as MockSpawnResult);
|
||||
// simulate docx-diff creating the diff file
|
||||
writeFileSync(diffDocx, "");
|
||||
|
||||
const raw = await runDocxDiff(
|
||||
{ command: "docx-diff" },
|
||||
sourceDocx,
|
||||
modifiedDocx,
|
||||
diffDocx,
|
||||
spawnFn,
|
||||
);
|
||||
const meta = JSON.parse(raw);
|
||||
expect(meta.sourceDocx).toBe(sourceDocx);
|
||||
expect(meta.modifiedDocx).toBe(modifiedDocx);
|
||||
expect(meta.diffDocx).toBe(diffDocx);
|
||||
|
||||
expect(spawnFn.mock.calls[0][1]).toEqual([
|
||||
sourceDocx,
|
||||
modifiedDocx,
|
||||
"--output",
|
||||
"docx",
|
||||
"--out-file",
|
||||
diffDocx,
|
||||
]);
|
||||
});
|
||||
|
||||
test("exit 1 (changes found): treated as success", async () => {
|
||||
const dir = tempDir();
|
||||
const sourceDocx = join(dir, "s.docx");
|
||||
const modifiedDocx = join(dir, "m.docx");
|
||||
const diffDocx = join(dir, "diff.docx");
|
||||
writeFileSync(sourceDocx, "");
|
||||
writeFileSync(modifiedDocx, "");
|
||||
writeFileSync(diffDocx, "");
|
||||
|
||||
const spawnFn = makeSpawn(
|
||||
err({ kind: "non_zero_exit", exitCode: 1, stdout: "", stderr: "" }) as MockSpawnResult,
|
||||
);
|
||||
|
||||
await expect(
|
||||
runDocxDiff({ command: "docx-diff" }, sourceDocx, modifiedDocx, diffDocx, spawnFn),
|
||||
).resolves.toBeDefined();
|
||||
});
|
||||
|
||||
test("exit 2: throws error", async () => {
|
||||
const dir = tempDir();
|
||||
const spawnFn = makeSpawn(
|
||||
err({ kind: "non_zero_exit", exitCode: 2, stdout: "", stderr: "fatal error" }) as MockSpawnResult,
|
||||
);
|
||||
|
||||
await expect(
|
||||
runDocxDiff({ command: null }, "s.docx", "m.docx", "diff.docx", spawnFn),
|
||||
).rejects.toThrow("docx-diff failed");
|
||||
});
|
||||
|
||||
test("timeout: throws error", async () => {
|
||||
const spawnFn = makeSpawn(err({ kind: "timeout" }) as MockSpawnResult);
|
||||
|
||||
await expect(
|
||||
runDocxDiff({ command: null }, "s.docx", "m.docx", "diff.docx", spawnFn),
|
||||
).rejects.toThrow("timed out");
|
||||
});
|
||||
|
||||
test("throws when diff file not created", async () => {
|
||||
const dir = tempDir();
|
||||
const spawnFn = makeSpawn(ok("") as MockSpawnResult);
|
||||
// do NOT create diffDocx
|
||||
|
||||
await expect(
|
||||
runDocxDiff({ command: null }, "s.docx", "m.docx", join(dir, "missing.docx"), spawnFn),
|
||||
).rejects.toThrow("diff file not found");
|
||||
});
|
||||
|
||||
test("uses PATH docx-diff when command is null", async () => {
|
||||
const dir = tempDir();
|
||||
const diffDocx = join(dir, "diff.docx");
|
||||
writeFileSync(diffDocx, "");
|
||||
const spawnFn = makeSpawn(ok("") as MockSpawnResult);
|
||||
|
||||
await runDocxDiff({ command: null }, "s.docx", "m.docx", diffDocx, spawnFn);
|
||||
|
||||
expect(spawnFn.mock.calls[0][0]).toBe("docx-diff");
|
||||
});
|
||||
});
|
||||
@@ -1,29 +0,0 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-agent-docx-diff",
|
||||
"version": "0.1.0",
|
||||
"files": ["src", "dist", "package.json"],
|
||||
"type": "module",
|
||||
"types": "src/index.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"bun": "./src/index.ts",
|
||||
"types": "./dist/index.d.ts",
|
||||
"import": "./dist/index.js"
|
||||
}
|
||||
},
|
||||
"scripts": {
|
||||
"test": "bun test"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow-runtime": "workspace:^",
|
||||
"@uncaged/workflow-util-agent": "workspace:^",
|
||||
"@uncaged/workflow-template-document": "workspace:^",
|
||||
"zod": "^4.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@uncaged/workflow-util": "workspace:^"
|
||||
},
|
||||
"publishConfig": {
|
||||
"access": "public"
|
||||
}
|
||||
}
|
||||
@@ -1,29 +0,0 @@
|
||||
import * as z from "zod/v4";
|
||||
import { dirname, join } from "node:path";
|
||||
import type { AdapterFn, RoleResult, ThreadContext, WorkflowRuntime } from "@uncaged/workflow-runtime";
|
||||
import type { WriterMeta } from "@uncaged/workflow-template-document";
|
||||
import { runDocxDiff } from "./runner.js";
|
||||
import type { DocxDiffAgentConfig } from "./types.js";
|
||||
|
||||
export function createDocxDiffAgent(config: DocxDiffAgentConfig): AdapterFn {
|
||||
return <T>(_prompt: string, schema: z.ZodType<T>) =>
|
||||
async (ctx: ThreadContext, _runtime: WorkflowRuntime): Promise<RoleResult<T>> => {
|
||||
const writerStep = ctx.steps.find((s) => s.role === "writer");
|
||||
if (writerStep === undefined) throw new Error("differ: no writer step found");
|
||||
|
||||
const writerMeta = writerStep.meta as WriterMeta;
|
||||
if (writerMeta.mode !== "edit")
|
||||
throw new Error("differ: writer did not run in edit mode");
|
||||
|
||||
const diffDocx = join(dirname(writerMeta.outputDocx), "diff.docx");
|
||||
const raw = await runDocxDiff(
|
||||
config,
|
||||
writerMeta.sourceDocx,
|
||||
writerMeta.outputDocx,
|
||||
diffDocx,
|
||||
);
|
||||
|
||||
const meta = schema.parse(JSON.parse(raw)) as T;
|
||||
return { meta, childThread: null };
|
||||
};
|
||||
}
|
||||
@@ -1,3 +0,0 @@
|
||||
export { createDocxDiffAgent } from "./agent.js";
|
||||
export { packageDescriptor } from "./package-descriptor.js";
|
||||
export type { DocxDiffAgentConfig } from "./types.js";
|
||||
@@ -1,17 +0,0 @@
|
||||
import type { PackageDescriptor } from "@uncaged/workflow-runtime";
|
||||
|
||||
export const packageDescriptor: PackageDescriptor = {
|
||||
name: "@uncaged/workflow-agent-docx-diff",
|
||||
version: "0.1.0",
|
||||
capabilities: ["docx-diff-cli", "docx-diff-report"],
|
||||
configSchema: {
|
||||
type: "object",
|
||||
properties: {
|
||||
command: {
|
||||
anyOf: [{ type: "string" }, { type: "null" }],
|
||||
description: "Path to docx-diff CLI binary; null uses PATH.",
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
},
|
||||
};
|
||||
@@ -1,47 +0,0 @@
|
||||
import { stat } from "node:fs/promises";
|
||||
import { spawnCli } from "@uncaged/workflow-util-agent";
|
||||
import type { SpawnCliError } from "@uncaged/workflow-util-agent";
|
||||
import type { DocxDiffAgentConfig } from "./types.js";
|
||||
|
||||
type SpawnCliFn = typeof spawnCli;
|
||||
|
||||
function throwSpawnError(e: SpawnCliError): never {
|
||||
if (e.kind === "non_zero_exit")
|
||||
throw new Error(`docx-diff failed (exit ${e.exitCode}): ${e.stderr}`);
|
||||
if (e.kind === "timeout")
|
||||
throw new Error("docx-diff: timed out");
|
||||
throw new Error(`docx-diff: spawn failed: ${e.message}`);
|
||||
}
|
||||
|
||||
export async function runDocxDiff(
|
||||
config: DocxDiffAgentConfig,
|
||||
sourceDocx: string,
|
||||
modifiedDocx: string,
|
||||
diffDocx: string,
|
||||
spawnCliFn: SpawnCliFn = spawnCli,
|
||||
): Promise<string> {
|
||||
const command = config.command ?? "docx-diff";
|
||||
const result = await spawnCliFn(
|
||||
command,
|
||||
[sourceDocx, modifiedDocx, "--output", "docx", "--out-file", diffDocx],
|
||||
{ cwd: null, timeoutMs: null },
|
||||
);
|
||||
|
||||
if (!result.ok) {
|
||||
const e = result.error;
|
||||
// exit 1 = changes found (normal for docx-diff)
|
||||
if (e.kind === "non_zero_exit" && e.exitCode === 1) {
|
||||
// fall through to file check
|
||||
} else {
|
||||
throwSpawnError(e);
|
||||
}
|
||||
}
|
||||
|
||||
try {
|
||||
await stat(diffDocx);
|
||||
} catch {
|
||||
throw new Error(`docx-diff: diff file not found: ${diffDocx}`);
|
||||
}
|
||||
|
||||
return JSON.stringify({ sourceDocx, modifiedDocx, diffDocx });
|
||||
}
|
||||
@@ -1,3 +0,0 @@
|
||||
export type DocxDiffAgentConfig = {
|
||||
command: string | null;
|
||||
};
|
||||
@@ -1,15 +0,0 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [
|
||||
{ "path": "../workflow-protocol" },
|
||||
{ "path": "../workflow-runtime" },
|
||||
{ "path": "../workflow-util-agent" },
|
||||
{ "path": "../workflow-template-document" }
|
||||
]
|
||||
}
|
||||
@@ -1,27 +0,0 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { packageDescriptor } from "../src/package-descriptor.js";
|
||||
import { createOfficeAgent } from "../src/agent.js";
|
||||
|
||||
describe("createOfficeAgent", () => {
|
||||
test("returns an AdapterFn (function)", () => {
|
||||
const agent = createOfficeAgent({ outputDir: "/tmp", command: null, timeout: null });
|
||||
expect(typeof agent).toBe("function");
|
||||
});
|
||||
|
||||
test("AdapterFn returns a RoleFn (function)", () => {
|
||||
const agent = createOfficeAgent({ outputDir: "/tmp", command: null, timeout: null });
|
||||
const roleFn = agent("", expect.anything() as never);
|
||||
expect(typeof roleFn).toBe("function");
|
||||
});
|
||||
});
|
||||
|
||||
describe("packageDescriptor", () => {
|
||||
test("has correct name", () => {
|
||||
expect(packageDescriptor.name).toBe("@uncaged/workflow-agent-office");
|
||||
});
|
||||
|
||||
test("has outputDir in configSchema required", () => {
|
||||
const schema = packageDescriptor.configSchema as { required: string[] };
|
||||
expect(schema.required).toContain("outputDir");
|
||||
});
|
||||
});
|
||||
@@ -1,129 +0,0 @@
|
||||
import { mkdirSync, writeFileSync } from "node:fs";
|
||||
import { join } from "node:path";
|
||||
import { tmpdir } from "node:os";
|
||||
import { describe, expect, mock, test } from "bun:test";
|
||||
import { ok, err } from "@uncaged/workflow-util";
|
||||
import type { SpawnCliConfig } from "@uncaged/workflow-util-agent";
|
||||
import { editDocument, generateDocument } from "../src/runner.js";
|
||||
|
||||
type MockSpawnResult = Awaited<ReturnType<typeof import("@uncaged/workflow-util-agent").spawnCli>>;
|
||||
|
||||
function makeSpawn(result: MockSpawnResult) {
|
||||
return mock(async (_cmd: string, _args: string[], _opts: SpawnCliConfig) => result);
|
||||
}
|
||||
|
||||
function tempDir(): string {
|
||||
const dir = join(tmpdir(), `office-test-${Date.now()}`);
|
||||
mkdirSync(dir, { recursive: true });
|
||||
return dir;
|
||||
}
|
||||
|
||||
describe("generateDocument", () => {
|
||||
test("calls office-agent create with correct args and returns outputDocx path", async () => {
|
||||
const base = tempDir();
|
||||
const spawnFn = makeSpawn(ok("agent reply") as MockSpawnResult);
|
||||
// Simulate CLI creating the file
|
||||
const outFile = join(base, "thread1", "output.docx");
|
||||
mkdirSync(join(base, "thread1"), { recursive: true });
|
||||
writeFileSync(outFile, "");
|
||||
|
||||
const result = await generateDocument(
|
||||
{ outputDir: base, command: "office-agent", timeout: null },
|
||||
"thread1",
|
||||
"Write a report",
|
||||
spawnFn,
|
||||
);
|
||||
|
||||
expect(result.outputDocx).toBe(outFile);
|
||||
expect(result.sourceDocx).toBeNull();
|
||||
expect(spawnFn.mock.calls[0][0]).toBe("office-agent");
|
||||
expect(spawnFn.mock.calls[0][1]).toEqual(["create", "Write a report", "-o", "output.docx"]);
|
||||
expect(spawnFn.mock.calls[0][2].cwd).toBe(join(base, "thread1"));
|
||||
});
|
||||
|
||||
test("uses PATH office-agent when command is null", async () => {
|
||||
const base = tempDir();
|
||||
const spawnFn = makeSpawn(ok("") as MockSpawnResult);
|
||||
mkdirSync(join(base, "t2"), { recursive: true });
|
||||
writeFileSync(join(base, "t2", "output.docx"), "");
|
||||
|
||||
await generateDocument(
|
||||
{ outputDir: base, command: null, timeout: null },
|
||||
"t2",
|
||||
"Generate",
|
||||
spawnFn,
|
||||
);
|
||||
|
||||
expect(spawnFn.mock.calls[0][0]).toBe("office-agent");
|
||||
});
|
||||
|
||||
test("throws on non_zero_exit", async () => {
|
||||
const base = tempDir();
|
||||
const spawnFn = makeSpawn(
|
||||
err({ kind: "non_zero_exit", exitCode: 1, stdout: "", stderr: "error" }) as MockSpawnResult,
|
||||
);
|
||||
|
||||
await expect(
|
||||
generateDocument({ outputDir: base, command: null, timeout: null }, "t3", "fail", spawnFn),
|
||||
).rejects.toThrow("office-agent failed (exit 1)");
|
||||
});
|
||||
|
||||
test("throws on timeout", async () => {
|
||||
const base = tempDir();
|
||||
const spawnFn = makeSpawn(err({ kind: "timeout" }) as MockSpawnResult);
|
||||
|
||||
await expect(
|
||||
generateDocument({ outputDir: base, command: null, timeout: null }, "t4", "slow", spawnFn),
|
||||
).rejects.toThrow("office-agent: timed out");
|
||||
});
|
||||
|
||||
test("throws when output file not created", async () => {
|
||||
const base = tempDir();
|
||||
const spawnFn = makeSpawn(ok("") as MockSpawnResult);
|
||||
// Do NOT create output.docx
|
||||
|
||||
await expect(
|
||||
generateDocument({ outputDir: base, command: null, timeout: null }, "t5", "no file", spawnFn),
|
||||
).rejects.toThrow("output file not found");
|
||||
});
|
||||
});
|
||||
|
||||
describe("editDocument", () => {
|
||||
test("copies input to original.docx and modified.docx, calls edit, returns paths", async () => {
|
||||
const base = tempDir();
|
||||
// Create a fake inputDocx
|
||||
const inputFile = join(base, "source.docx");
|
||||
writeFileSync(inputFile, "original content");
|
||||
|
||||
const spawnFn = makeSpawn(ok("") as MockSpawnResult);
|
||||
// Simulate CLI overwriting modified.docx
|
||||
const outDir = join(base, "te1");
|
||||
mkdirSync(outDir, { recursive: true });
|
||||
writeFileSync(join(outDir, "modified.docx"), "modified content");
|
||||
|
||||
const result = await editDocument(
|
||||
{ outputDir: base, command: "office-agent", timeout: null },
|
||||
"te1",
|
||||
"Edit the doc",
|
||||
inputFile,
|
||||
spawnFn,
|
||||
);
|
||||
|
||||
expect(result.outputDocx).toBe(join(outDir, "modified.docx"));
|
||||
expect(result.sourceDocx).toBe(join(outDir, "original.docx"));
|
||||
expect(spawnFn.mock.calls[0][1]).toEqual(["edit", "modified.docx", "Edit the doc"]);
|
||||
});
|
||||
|
||||
test("throws on spawn_failed", async () => {
|
||||
const base = tempDir();
|
||||
const inputFile = join(base, "src.docx");
|
||||
writeFileSync(inputFile, "");
|
||||
const spawnFn = makeSpawn(
|
||||
err({ kind: "spawn_failed", message: "not found" }) as MockSpawnResult,
|
||||
);
|
||||
|
||||
await expect(
|
||||
editDocument({ outputDir: base, command: null, timeout: null }, "te2", "edit", inputFile, spawnFn),
|
||||
).rejects.toThrow("spawn failed");
|
||||
});
|
||||
});
|
||||
@@ -1,25 +0,0 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-agent-office",
|
||||
"version": "0.1.0",
|
||||
"files": ["src", "dist", "package.json"],
|
||||
"type": "module",
|
||||
"types": "src/index.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"bun": "./src/index.ts",
|
||||
"types": "./dist/index.d.ts",
|
||||
"import": "./dist/index.js"
|
||||
}
|
||||
},
|
||||
"scripts": {
|
||||
"test": "bun test"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow-runtime": "workspace:^",
|
||||
"@uncaged/workflow-util": "workspace:^",
|
||||
"@uncaged/workflow-util-agent": "workspace:^"
|
||||
},
|
||||
"publishConfig": {
|
||||
"access": "public"
|
||||
}
|
||||
}
|
||||
@@ -1,44 +0,0 @@
|
||||
import * as z from "zod/v4";
|
||||
import type { AdapterFn, RoleResult, ThreadContext, WorkflowRuntime } from "@uncaged/workflow-runtime";
|
||||
import { createLogger } from "@uncaged/workflow-util";
|
||||
import { editDocument, generateDocument } from "./runner.js";
|
||||
import type { OfficeAgentConfig } from "./types.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
type ParsedInput = { prompt: string; inputDocx: string | null };
|
||||
|
||||
function parseStartInput(content: string): ParsedInput {
|
||||
try {
|
||||
const parsed = JSON.parse(content) as Record<string, unknown>;
|
||||
if (typeof parsed.prompt === "string") {
|
||||
return {
|
||||
prompt: parsed.prompt,
|
||||
inputDocx: typeof parsed.inputDocx === "string" ? parsed.inputDocx : null,
|
||||
};
|
||||
}
|
||||
} catch {
|
||||
// not JSON — treat whole content as prompt, generate mode
|
||||
}
|
||||
return { prompt: content, inputDocx: null };
|
||||
}
|
||||
|
||||
export function createOfficeAgent(config: OfficeAgentConfig): AdapterFn {
|
||||
return <T>(_systemPrompt: string, schema: z.ZodType<T>) =>
|
||||
async (ctx: ThreadContext, _runtime: WorkflowRuntime): Promise<RoleResult<T>> => {
|
||||
const { prompt, inputDocx } = parseStartInput(ctx.start.content);
|
||||
log("8FQKP3NV", `office-agent: mode=${inputDocx === null ? "generate" : "edit"} thread=${ctx.threadId}`);
|
||||
|
||||
let raw: string;
|
||||
if (inputDocx === null) {
|
||||
const result = await generateDocument(config, ctx.threadId, prompt);
|
||||
raw = JSON.stringify({ mode: "generate", outputDocx: result.outputDocx, sourceDocx: null });
|
||||
} else {
|
||||
const result = await editDocument(config, ctx.threadId, prompt, inputDocx);
|
||||
raw = JSON.stringify({ mode: "edit", outputDocx: result.outputDocx, sourceDocx: result.sourceDocx });
|
||||
}
|
||||
|
||||
const meta = schema.parse(JSON.parse(raw)) as T;
|
||||
return { meta, childThread: null };
|
||||
};
|
||||
}
|
||||
@@ -1,3 +0,0 @@
|
||||
export { createOfficeAgent } from "./agent.js";
|
||||
export { packageDescriptor } from "./package-descriptor.js";
|
||||
export type { OfficeAgentConfig } from "./types.js";
|
||||
@@ -1,26 +0,0 @@
|
||||
import type { PackageDescriptor } from "@uncaged/workflow-runtime";
|
||||
|
||||
export const packageDescriptor: PackageDescriptor = {
|
||||
name: "@uncaged/workflow-agent-office",
|
||||
version: "0.1.0",
|
||||
capabilities: ["office-agent-cli", "docx-generate", "docx-edit"],
|
||||
configSchema: {
|
||||
type: "object",
|
||||
required: ["outputDir"],
|
||||
properties: {
|
||||
outputDir: {
|
||||
type: "string",
|
||||
description: "Root directory for workflow outputs; subdirs are created per threadId.",
|
||||
},
|
||||
command: {
|
||||
anyOf: [{ type: "string" }, { type: "null" }],
|
||||
description: "Path to office-agent CLI binary; null uses PATH.",
|
||||
},
|
||||
timeout: {
|
||||
anyOf: [{ type: "number" }, { type: "null" }],
|
||||
description: "Timeout in milliseconds; null means no limit.",
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
},
|
||||
};
|
||||
@@ -1,65 +0,0 @@
|
||||
import { copyFile, mkdir, stat } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import { spawnCli } from "@uncaged/workflow-util-agent";
|
||||
import type { SpawnCliError } from "@uncaged/workflow-util-agent";
|
||||
import type { OfficeAgentConfig } from "./types.js";
|
||||
|
||||
type SpawnCliFn = typeof spawnCli;
|
||||
|
||||
function throwSpawnError(e: SpawnCliError): never {
|
||||
if (e.kind === "non_zero_exit")
|
||||
throw new Error(`office-agent failed (exit ${e.exitCode}): ${e.stderr}`);
|
||||
if (e.kind === "timeout")
|
||||
throw new Error("office-agent: timed out");
|
||||
throw new Error(`office-agent: spawn failed: ${e.message}`);
|
||||
}
|
||||
|
||||
async function assertFileExists(path: string): Promise<void> {
|
||||
try {
|
||||
await stat(path);
|
||||
} catch {
|
||||
throw new Error(`office-agent: output file not found: ${path}`);
|
||||
}
|
||||
}
|
||||
|
||||
export async function generateDocument(
|
||||
config: OfficeAgentConfig,
|
||||
threadId: string,
|
||||
prompt: string,
|
||||
spawnCliFn: SpawnCliFn = spawnCli,
|
||||
): Promise<{ outputDocx: string; sourceDocx: null }> {
|
||||
const outputDir = join(config.outputDir, threadId);
|
||||
await mkdir(outputDir, { recursive: true });
|
||||
const command = config.command ?? "office-agent";
|
||||
const result = await spawnCliFn(command, ["create", prompt, "-o", "output.docx"], {
|
||||
cwd: outputDir,
|
||||
timeoutMs: config.timeout,
|
||||
});
|
||||
if (!result.ok) throwSpawnError(result.error);
|
||||
const outputDocx = join(outputDir, "output.docx");
|
||||
await assertFileExists(outputDocx);
|
||||
return { outputDocx, sourceDocx: null };
|
||||
}
|
||||
|
||||
export async function editDocument(
|
||||
config: OfficeAgentConfig,
|
||||
threadId: string,
|
||||
prompt: string,
|
||||
inputDocx: string,
|
||||
spawnCliFn: SpawnCliFn = spawnCli,
|
||||
): Promise<{ outputDocx: string; sourceDocx: string }> {
|
||||
const outputDir = join(config.outputDir, threadId);
|
||||
await mkdir(outputDir, { recursive: true });
|
||||
const originalDocx = join(outputDir, "original.docx");
|
||||
const modifiedDocx = join(outputDir, "modified.docx");
|
||||
await copyFile(inputDocx, originalDocx);
|
||||
await copyFile(inputDocx, modifiedDocx);
|
||||
const command = config.command ?? "office-agent";
|
||||
const result = await spawnCliFn(command, ["edit", "modified.docx", prompt], {
|
||||
cwd: outputDir,
|
||||
timeoutMs: config.timeout,
|
||||
});
|
||||
if (!result.ok) throwSpawnError(result.error);
|
||||
await assertFileExists(modifiedDocx);
|
||||
return { outputDocx: modifiedDocx, sourceDocx: originalDocx };
|
||||
}
|
||||
@@ -1,5 +0,0 @@
|
||||
export type OfficeAgentConfig = {
|
||||
outputDir: string;
|
||||
command: string | null;
|
||||
timeout: number | null;
|
||||
};
|
||||
@@ -1,15 +0,0 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [
|
||||
{ "path": "../workflow-protocol" },
|
||||
{ "path": "../workflow-runtime" },
|
||||
{ "path": "../workflow-util" },
|
||||
{ "path": "../workflow-util-agent" }
|
||||
]
|
||||
}
|
||||
@@ -1,87 +0,0 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { tableToModerator } from "@uncaged/workflow-protocol/moderator-table.js";
|
||||
import { validateWorkflowDescriptor } from "@uncaged/workflow-register";
|
||||
import { END, type ModeratorContext, type RoleStep, START } from "@uncaged/workflow-runtime";
|
||||
import { buildDocumentDescriptor } from "../src/descriptor.js";
|
||||
import { documentTable } from "../src/moderator.js";
|
||||
import type { DifferMeta, WriterMeta } from "../src/roles/index.js";
|
||||
import type { DocumentMeta } from "../src/roles.js";
|
||||
|
||||
const documentModerator = tableToModerator(documentTable);
|
||||
|
||||
function makeCtx(
|
||||
steps: ModeratorContext<DocumentMeta>["steps"],
|
||||
): ModeratorContext<DocumentMeta> {
|
||||
return {
|
||||
threadId: "01TEST000000000000000000TR",
|
||||
depth: 0,
|
||||
bundleHash: "TESTHASH00001",
|
||||
start: { role: START, content: "", meta: {}, timestamp: 0, parentState: null },
|
||||
steps,
|
||||
};
|
||||
}
|
||||
|
||||
function writerGenerateStep(): RoleStep<DocumentMeta> {
|
||||
return {
|
||||
role: "writer",
|
||||
contentHash: "STUBHASHWRITER001",
|
||||
meta: { mode: "generate", outputDocx: "/out/output.docx", sourceDocx: null } satisfies WriterMeta,
|
||||
refs: [],
|
||||
timestamp: 1,
|
||||
};
|
||||
}
|
||||
|
||||
function writerEditStep(): RoleStep<DocumentMeta> {
|
||||
return {
|
||||
role: "writer",
|
||||
contentHash: "STUBHASHWRITER002",
|
||||
meta: { mode: "edit", outputDocx: "/out/modified.docx", sourceDocx: "/out/original.docx" } satisfies WriterMeta,
|
||||
refs: [],
|
||||
timestamp: 1,
|
||||
};
|
||||
}
|
||||
|
||||
function differStep(): RoleStep<DocumentMeta> {
|
||||
return {
|
||||
role: "differ",
|
||||
contentHash: "STUBHASHDIFF001",
|
||||
meta: {
|
||||
sourceDocx: "/out/original.docx",
|
||||
modifiedDocx: "/out/modified.docx",
|
||||
diffDocx: "/out/diff.docx",
|
||||
} satisfies DifferMeta,
|
||||
refs: [],
|
||||
timestamp: 2,
|
||||
};
|
||||
}
|
||||
|
||||
describe("documentTable", () => {
|
||||
test("START → writer", () => {
|
||||
expect(documentModerator(makeCtx([]))).toBe("writer");
|
||||
});
|
||||
|
||||
test("writer (generate) → END", () => {
|
||||
expect(documentModerator(makeCtx([writerGenerateStep()]))).toBe(END);
|
||||
});
|
||||
|
||||
test("writer (edit) → differ", () => {
|
||||
expect(documentModerator(makeCtx([writerEditStep()]))).toBe("differ");
|
||||
});
|
||||
|
||||
test("differ → END", () => {
|
||||
expect(documentModerator(makeCtx([writerEditStep(), differStep()]))).toBe(END);
|
||||
});
|
||||
});
|
||||
|
||||
describe("buildDocumentDescriptor", () => {
|
||||
test("descriptor passes validation", () => {
|
||||
const descriptor = buildDocumentDescriptor();
|
||||
expect(() => validateWorkflowDescriptor(descriptor)).not.toThrow();
|
||||
});
|
||||
|
||||
test("descriptor has writer and differ roles", () => {
|
||||
const descriptor = buildDocumentDescriptor();
|
||||
expect(Object.keys(descriptor.roles)).toContain("writer");
|
||||
expect(Object.keys(descriptor.roles)).toContain("differ");
|
||||
});
|
||||
});
|
||||
@@ -1,28 +0,0 @@
|
||||
{
|
||||
"name": "@uncaged/workflow-template-document",
|
||||
"version": "0.1.0",
|
||||
"files": ["src", "dist", "package.json"],
|
||||
"type": "module",
|
||||
"types": "src/index.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"bun": "./src/index.ts",
|
||||
"types": "./dist/index.d.ts",
|
||||
"import": "./dist/index.js"
|
||||
}
|
||||
},
|
||||
"scripts": {
|
||||
"test": "bun test"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/workflow-register": "workspace:^",
|
||||
"@uncaged/workflow-runtime": "workspace:^",
|
||||
"zod": "^4.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@uncaged/workflow-protocol": "workspace:^"
|
||||
},
|
||||
"publishConfig": {
|
||||
"access": "public"
|
||||
}
|
||||
}
|
||||
@@ -1,11 +0,0 @@
|
||||
import { buildDescriptor } from "@uncaged/workflow-register";
|
||||
import { documentTable } from "./moderator.js";
|
||||
import { DOCUMENT_WORKFLOW_DESCRIPTION, documentRoles } from "./roles.js";
|
||||
|
||||
export function buildDocumentDescriptor() {
|
||||
return buildDescriptor({
|
||||
description: DOCUMENT_WORKFLOW_DESCRIPTION,
|
||||
roles: documentRoles,
|
||||
table: documentTable,
|
||||
});
|
||||
}
|
||||
@@ -1,27 +0,0 @@
|
||||
import type { WorkflowDefinition } from "@uncaged/workflow-runtime";
|
||||
import { documentTable } from "./moderator.js";
|
||||
import { DOCUMENT_WORKFLOW_DESCRIPTION, type DocumentMeta, documentRoles } from "./roles.js";
|
||||
|
||||
export { buildDocumentDescriptor } from "./descriptor.js";
|
||||
export { documentTable } from "./moderator.js";
|
||||
export {
|
||||
type DifferMeta,
|
||||
differMetaSchema,
|
||||
differRole,
|
||||
type WriterMeta,
|
||||
writerMetaSchema,
|
||||
writerRole,
|
||||
} from "./roles/index.js";
|
||||
export {
|
||||
DOCUMENT_WORKFLOW_DESCRIPTION,
|
||||
type DocumentMeta,
|
||||
type DocumentRoles,
|
||||
documentRoles,
|
||||
} from "./roles.js";
|
||||
export type { DocumentStartInput } from "./types.js";
|
||||
|
||||
export const documentWorkflowDefinition: WorkflowDefinition<DocumentMeta> = {
|
||||
description: DOCUMENT_WORKFLOW_DESCRIPTION,
|
||||
roles: documentRoles,
|
||||
table: documentTable,
|
||||
};
|
||||
@@ -1,27 +0,0 @@
|
||||
import {
|
||||
END,
|
||||
type ModeratorCondition,
|
||||
type ModeratorTable,
|
||||
START,
|
||||
} from "@uncaged/workflow-runtime";
|
||||
import type { WriterMeta } from "./roles/writer.js";
|
||||
import type { DocumentMeta } from "./roles.js";
|
||||
|
||||
const writerIsEditMode: ModeratorCondition<DocumentMeta> = {
|
||||
name: "writerIsEditMode",
|
||||
description: "Writer ran in edit mode and produced a modified document",
|
||||
check: (ctx) => {
|
||||
const writerStep = ctx.steps.find((s) => s.role === "writer");
|
||||
if (writerStep === undefined) return false;
|
||||
return (writerStep.meta as WriterMeta).mode === "edit";
|
||||
},
|
||||
};
|
||||
|
||||
export const documentTable: ModeratorTable<DocumentMeta> = {
|
||||
[START]: [{ condition: "FALLBACK", role: "writer" }],
|
||||
writer: [
|
||||
{ condition: writerIsEditMode, role: "differ" },
|
||||
{ condition: "FALLBACK", role: END },
|
||||
],
|
||||
differ: [{ condition: "FALLBACK", role: END }],
|
||||
};
|
||||
@@ -1,20 +0,0 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow-runtime";
|
||||
import { type DifferMeta, differRole } from "./roles/differ.js";
|
||||
import { type WriterMeta, writerRole } from "./roles/writer.js";
|
||||
|
||||
export const DOCUMENT_WORKFLOW_DESCRIPTION =
|
||||
"Generates a new Word document from a prompt, or edits an existing one and produces a diff report.";
|
||||
|
||||
export type DocumentMeta = {
|
||||
writer: WriterMeta;
|
||||
differ: DifferMeta;
|
||||
};
|
||||
|
||||
export type DocumentRoles = {
|
||||
[K in keyof DocumentMeta]: RoleDefinition<DocumentMeta[K]>;
|
||||
};
|
||||
|
||||
export const documentRoles: DocumentRoles = {
|
||||
writer: writerRole,
|
||||
differ: differRole,
|
||||
};
|
||||
@@ -1,16 +0,0 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow-runtime";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const differMetaSchema = z.object({
|
||||
sourceDocx: z.string(),
|
||||
modifiedDocx: z.string(),
|
||||
diffDocx: z.string(),
|
||||
});
|
||||
|
||||
export type DifferMeta = z.infer<typeof differMetaSchema>;
|
||||
|
||||
export const differRole: RoleDefinition<DifferMeta> = {
|
||||
description: "Produces a Word-format diff report of the writer's changes (edit mode only).",
|
||||
systemPrompt: "",
|
||||
schema: differMetaSchema,
|
||||
};
|
||||
@@ -1,4 +0,0 @@
|
||||
export type { DifferMeta } from "./differ.js";
|
||||
export { differMetaSchema, differRole } from "./differ.js";
|
||||
export type { WriterMeta } from "./writer.js";
|
||||
export { writerMetaSchema, writerRole } from "./writer.js";
|
||||
@@ -1,23 +0,0 @@
|
||||
import type { RoleDefinition } from "@uncaged/workflow-runtime";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
export const writerMetaSchema = z.discriminatedUnion("mode", [
|
||||
z.object({
|
||||
mode: z.literal("generate"),
|
||||
outputDocx: z.string(),
|
||||
sourceDocx: z.null(),
|
||||
}),
|
||||
z.object({
|
||||
mode: z.literal("edit"),
|
||||
outputDocx: z.string(),
|
||||
sourceDocx: z.string(),
|
||||
}),
|
||||
]);
|
||||
|
||||
export type WriterMeta = z.infer<typeof writerMetaSchema>;
|
||||
|
||||
export const writerRole: RoleDefinition<WriterMeta> = {
|
||||
description: "Generates or modifies a Word document via an external agent.",
|
||||
systemPrompt: "",
|
||||
schema: writerMetaSchema,
|
||||
};
|
||||
@@ -1,4 +0,0 @@
|
||||
export type DocumentStartInput = {
|
||||
prompt: string;
|
||||
inputDocx: string | null;
|
||||
};
|
||||
@@ -1,14 +0,0 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"composite": true
|
||||
},
|
||||
"include": ["src/**/*.ts"],
|
||||
"references": [
|
||||
{ "path": "../workflow-protocol" },
|
||||
{ "path": "../workflow-runtime" },
|
||||
{ "path": "../workflow-register" }
|
||||
]
|
||||
}
|
||||
@@ -1,80 +0,0 @@
|
||||
import { describe, expect, test } from "vitest";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
import { buildOutputFormatInstruction } from "../src/build-output-format-instruction.js";
|
||||
|
||||
describe("buildOutputFormatInstruction", () => {
|
||||
test("always includes the frontmatter example block", () => {
|
||||
const schema = z.object({ status: z.string() });
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("## Deliverable Format");
|
||||
expect(result).toContain("status:");
|
||||
expect(result).toContain("confidence:");
|
||||
expect(result).toContain("artifacts:");
|
||||
expect(result).toContain("scope:");
|
||||
});
|
||||
|
||||
test("always includes scope reminder", () => {
|
||||
const schema = z.object({ status: z.string() });
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("Focus exclusively on YOUR role's deliverable");
|
||||
expect(result).toContain("Do not perform actions outside your role's scope");
|
||||
});
|
||||
|
||||
test("lists fields from a flat ZodObject schema", () => {
|
||||
const schema = z.object({
|
||||
title: z.string(),
|
||||
phases: z.array(z.string()),
|
||||
reason: z.union([z.string(), z.null()]),
|
||||
});
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("`title`");
|
||||
expect(result).toContain("`phases`");
|
||||
expect(result).toContain("`reason`");
|
||||
});
|
||||
|
||||
test("lists union of fields from a discriminated union schema", () => {
|
||||
const schema = z.discriminatedUnion("status", [
|
||||
z.object({ status: z.literal("planned"), phases: z.array(z.string()) }),
|
||||
z.object({ status: z.literal("aborted"), reason: z.string() }),
|
||||
]);
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("`status`");
|
||||
expect(result).toContain("`phases`");
|
||||
expect(result).toContain("`reason`");
|
||||
});
|
||||
|
||||
test("lists fields from a plain ZodUnion schema", () => {
|
||||
const schema = z.union([
|
||||
z.object({ kind: z.literal("a"), valueA: z.string() }),
|
||||
z.object({ kind: z.literal("b"), valueB: z.number() }),
|
||||
]);
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("`kind`");
|
||||
expect(result).toContain("`valueA`");
|
||||
expect(result).toContain("`valueB`");
|
||||
});
|
||||
|
||||
test("falls back gracefully for a non-object schema (no field list crash)", () => {
|
||||
const schema = z.string();
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("## Deliverable Format");
|
||||
expect(result).toContain("schema fields will be extracted automatically");
|
||||
});
|
||||
|
||||
test("marks frontmatter as the primary deliverable", () => {
|
||||
const schema = z.object({ done: z.boolean() });
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("primary deliverable");
|
||||
});
|
||||
|
||||
test("no field is listed more than once for a union with overlapping keys", () => {
|
||||
const schema = z.union([
|
||||
z.object({ status: z.literal("a"), shared: z.string() }),
|
||||
z.object({ status: z.literal("b"), shared: z.string() }),
|
||||
]);
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
const matches = [...result.matchAll(/`shared`/g)];
|
||||
expect(matches.length).toBe(1);
|
||||
});
|
||||
});
|
||||
@@ -1,238 +0,0 @@
|
||||
import { describe, expect, test, vi } from "vitest";
|
||||
|
||||
const mock = vi.fn;
|
||||
|
||||
import type { CasStore } from "@uncaged/workflow-cas";
|
||||
import type { ThreadContext, WorkflowRuntime } from "@uncaged/workflow-runtime";
|
||||
import * as z from "zod/v4";
|
||||
|
||||
import { createAgentAdapter } from "../src/index.js";
|
||||
|
||||
// ── Minimal test fixtures ─────────────────────────────────────────────────────
|
||||
|
||||
function makeCtx(): ThreadContext {
|
||||
return {
|
||||
threadId: "01TEST000000000000000000TR",
|
||||
depth: 0,
|
||||
bundleHash: "TESTHASH00001",
|
||||
start: {
|
||||
role: "START" as const,
|
||||
content: "test task",
|
||||
meta: {},
|
||||
timestamp: 1,
|
||||
parentState: null,
|
||||
},
|
||||
steps: [],
|
||||
};
|
||||
}
|
||||
|
||||
function makeCas(): CasStore & { store: Map<string, string> } {
|
||||
const store = new Map<string, string>();
|
||||
let seq = 0;
|
||||
return {
|
||||
store,
|
||||
async put(content: string) {
|
||||
const hash = `HASH${String(++seq).padStart(9, "0")}`;
|
||||
store.set(hash, content);
|
||||
return hash;
|
||||
},
|
||||
async get(hash: string) {
|
||||
return store.get(hash) ?? null;
|
||||
},
|
||||
async delete(hash: string) {
|
||||
store.delete(hash);
|
||||
},
|
||||
async list() {
|
||||
return [...store.keys()];
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
// ── Frontmatter-compatible schema ─────────────────────────────────────────────
|
||||
|
||||
// Schema that maps directly to AgentFrontmatter fields so happy path works.
|
||||
const FrontmatterSchema = z.object({
|
||||
status: z.union([
|
||||
z.literal("done"),
|
||||
z.literal("needs_input"),
|
||||
z.literal("in_progress"),
|
||||
z.literal("failed"),
|
||||
z.null(),
|
||||
]),
|
||||
next: z.union([z.string(), z.null()]),
|
||||
confidence: z.union([z.number(), z.null()]),
|
||||
artifacts: z.array(z.string()),
|
||||
scope: z.union([z.literal("role"), z.literal("thread")]),
|
||||
});
|
||||
|
||||
type FrontmatterMeta = z.infer<typeof FrontmatterSchema>;
|
||||
|
||||
// ── Happy path ────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("createAgentAdapter — happy path (valid frontmatter satisfies schema)", () => {
|
||||
test("returns meta from frontmatter without calling runtime.extract", async () => {
|
||||
const cas = makeCas();
|
||||
const extractMock = mock(async () => {
|
||||
throw new Error("runtime.extract must not be called in happy path");
|
||||
});
|
||||
const runtime: WorkflowRuntime = { cas, extract: extractMock as WorkflowRuntime["extract"] };
|
||||
|
||||
const rawOutput = [
|
||||
"---",
|
||||
"status: done",
|
||||
"next: reviewer",
|
||||
"confidence: 0.9",
|
||||
"artifacts: [src/foo.ts]",
|
||||
"scope: role",
|
||||
"---",
|
||||
"",
|
||||
"## Summary",
|
||||
"Work is complete.",
|
||||
].join("\n");
|
||||
|
||||
const agentFn = mock(async (_ctx: ThreadContext, _opts: null) => rawOutput);
|
||||
const extractOpts = mock(async () => null);
|
||||
|
||||
const adapter = createAgentAdapter<null>(agentFn, extractOpts);
|
||||
const roleFn = adapter<FrontmatterMeta>("test prompt", FrontmatterSchema);
|
||||
const result = await roleFn(makeCtx(), runtime);
|
||||
|
||||
// Meta must come from frontmatter
|
||||
expect(result.meta.status).toBe("done");
|
||||
expect(result.meta.next).toBe("reviewer");
|
||||
expect(result.meta.confidence).toBe(0.9);
|
||||
expect(result.meta.artifacts).toEqual(["src/foo.ts"]);
|
||||
expect(result.meta.scope).toBe("role");
|
||||
expect(result.childThread).toBeNull();
|
||||
|
||||
// LLM extract must NOT have been called
|
||||
expect(extractMock).not.toHaveBeenCalled();
|
||||
|
||||
// CAS should store the body (without frontmatter) as the CAS node payload
|
||||
const storedContent = [...cas.store.values()][0] ?? "";
|
||||
expect(storedContent).toContain("## Summary");
|
||||
expect(storedContent).toContain("Work is complete.");
|
||||
// The frontmatter block itself must not appear in the stored payload
|
||||
expect(storedContent).not.toContain("status: done\n");
|
||||
});
|
||||
|
||||
test("body stored in CAS does not include the frontmatter block", async () => {
|
||||
const cas = makeCas();
|
||||
const runtime: WorkflowRuntime = {
|
||||
cas,
|
||||
extract: mock(async () => {
|
||||
throw new Error("must not be called");
|
||||
}) as WorkflowRuntime["extract"],
|
||||
};
|
||||
|
||||
const rawOutput =
|
||||
"---\nstatus: done\nnext: null\nconfidence: null\nscope: role\n---\n\nThe actual work content here.";
|
||||
|
||||
const adapter = createAgentAdapter<null>(
|
||||
mock(async () => rawOutput),
|
||||
mock(async () => null),
|
||||
);
|
||||
const roleFn = adapter<FrontmatterMeta>("prompt", FrontmatterSchema);
|
||||
await roleFn(makeCtx(), runtime);
|
||||
|
||||
// CAS node wraps content as `payload: <body>`; check the payload contains only body
|
||||
const stored = [...cas.store.values()][0] ?? "";
|
||||
expect(stored).toContain("The actual work content here.");
|
||||
// The frontmatter block must be stripped
|
||||
expect(stored).not.toContain("status: done");
|
||||
});
|
||||
});
|
||||
|
||||
// ── Fallback path ─────────────────────────────────────────────────────────────
|
||||
|
||||
describe("createAgentAdapter — fallback path (no frontmatter)", () => {
|
||||
test("calls runtime.extract when output has no frontmatter block", async () => {
|
||||
const cas = makeCas();
|
||||
const expectedMeta: FrontmatterMeta = {
|
||||
status: "done",
|
||||
next: null,
|
||||
confidence: null,
|
||||
artifacts: [],
|
||||
scope: "role",
|
||||
};
|
||||
|
||||
const extractFn = mock(async (_schema: unknown, _hash: string) => ({
|
||||
meta: expectedMeta as Record<string, unknown>,
|
||||
contentPayload: "plain text output",
|
||||
refs: [],
|
||||
}));
|
||||
const runtime: WorkflowRuntime = { cas, extract: extractFn as WorkflowRuntime["extract"] };
|
||||
|
||||
const rawOutput = "This is plain markdown without any frontmatter.";
|
||||
const adapter = createAgentAdapter<null>(
|
||||
mock(async () => rawOutput),
|
||||
mock(async () => null),
|
||||
);
|
||||
const roleFn = adapter<FrontmatterMeta>("prompt", FrontmatterSchema);
|
||||
const result = await roleFn(makeCtx(), runtime);
|
||||
|
||||
// runtime.extract must have been called once
|
||||
expect(extractFn).toHaveBeenCalledTimes(1);
|
||||
expect(result.meta).toEqual(expectedMeta);
|
||||
expect(result.childThread).toBeNull();
|
||||
|
||||
// CAS should store the full raw output (as CAS node payload)
|
||||
const stored = [...cas.store.values()][0] ?? "";
|
||||
expect(stored).toContain(rawOutput);
|
||||
});
|
||||
|
||||
test("falls back to runtime.extract when frontmatter is structurally invalid", async () => {
|
||||
const cas = makeCas();
|
||||
const expectedMeta: FrontmatterMeta = {
|
||||
status: null,
|
||||
next: null,
|
||||
confidence: null,
|
||||
artifacts: [],
|
||||
scope: "role",
|
||||
};
|
||||
const extractFn = mock(async () => ({
|
||||
meta: expectedMeta as Record<string, unknown>,
|
||||
contentPayload: "",
|
||||
refs: [],
|
||||
}));
|
||||
const runtime: WorkflowRuntime = { cas, extract: extractFn as WorkflowRuntime["extract"] };
|
||||
|
||||
// confidence out of range — validateFrontmatter will reject
|
||||
const rawOutput = "---\nstatus: done\nconfidence: 1.5\nscope: role\n---\n\nBody.";
|
||||
const adapter = createAgentAdapter<null>(
|
||||
mock(async () => rawOutput),
|
||||
mock(async () => null),
|
||||
);
|
||||
const roleFn = adapter<FrontmatterMeta>("prompt", FrontmatterSchema);
|
||||
await roleFn(makeCtx(), runtime);
|
||||
|
||||
expect(extractFn).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
test("falls back when frontmatter fields do not satisfy schema", async () => {
|
||||
const cas = makeCas();
|
||||
|
||||
// Schema requires a mandatory non-null string field that frontmatter cannot provide
|
||||
const StrictSchema = z.object({
|
||||
requiredField: z.string(),
|
||||
});
|
||||
|
||||
const extractFn = mock(async () => ({
|
||||
meta: { requiredField: "from-llm" } as Record<string, unknown>,
|
||||
contentPayload: "",
|
||||
refs: [],
|
||||
}));
|
||||
const runtime: WorkflowRuntime = { cas, extract: extractFn as WorkflowRuntime["extract"] };
|
||||
|
||||
const rawOutput = "---\nstatus: done\nscope: role\n---\n\nBody.";
|
||||
const adapter = createAgentAdapter<null>(
|
||||
mock(async () => rawOutput),
|
||||
mock(async () => null),
|
||||
);
|
||||
const roleFn = adapter<{ requiredField: string }>("prompt", StrictSchema);
|
||||
await roleFn(makeCtx(), runtime);
|
||||
|
||||
// frontmatter has no `requiredField`, so schema parse fails → fallback
|
||||
expect(extractFn).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
});
|
||||
@@ -1,79 +0,0 @@
|
||||
import type * as z from "zod/v4";
|
||||
|
||||
type ZodSchema = z.ZodType;
|
||||
|
||||
/**
|
||||
* Extract the top-level field names from a Zod schema.
|
||||
*
|
||||
* Handles:
|
||||
* - ZodObject → its `.shape` keys
|
||||
* - ZodDiscriminatedUnion / ZodUnion → union of all variant shapes
|
||||
*
|
||||
* Returns an empty array for schemas that have no inspectable shape
|
||||
* (e.g. primitives, ZodAny).
|
||||
*/
|
||||
function extractSchemaFields(schema: ZodSchema): string[] {
|
||||
const def = schema.def as {
|
||||
type: string;
|
||||
shape?: Record<string, ZodSchema>;
|
||||
options?: ZodSchema[];
|
||||
};
|
||||
|
||||
if (def.type === "object" && def.shape !== undefined) {
|
||||
return Object.keys(def.shape);
|
||||
}
|
||||
|
||||
if ((def.type === "discriminated_union" || def.type === "union") && Array.isArray(def.options)) {
|
||||
const fieldSet = new Set<string>();
|
||||
for (const option of def.options) {
|
||||
for (const field of extractSchemaFields(option as ZodSchema)) {
|
||||
fieldSet.add(field);
|
||||
}
|
||||
}
|
||||
return [...fieldSet];
|
||||
}
|
||||
|
||||
return [];
|
||||
}
|
||||
|
||||
/**
|
||||
* Build a concise output format instruction block for an agent role.
|
||||
*
|
||||
* The instruction describes the expected frontmatter markdown format and lists
|
||||
* the meta fields derived from `schema`. It is injected at the top of the
|
||||
* system prompt so the deliverable format is the first thing the agent sees.
|
||||
*
|
||||
* Focus on YOUR role's deliverable. Do not perform actions outside your role's scope.
|
||||
*/
|
||||
export function buildOutputFormatInstruction(schema: ZodSchema): string {
|
||||
const fields = extractSchemaFields(schema);
|
||||
|
||||
const fieldList =
|
||||
fields.length > 0
|
||||
? fields.map((f) => ` - \`${f}\``).join("\n")
|
||||
: " (schema fields will be extracted automatically)";
|
||||
|
||||
return `## Deliverable Format
|
||||
|
||||
Your response MUST begin with a YAML frontmatter block followed by your markdown work:
|
||||
|
||||
\`\`\`
|
||||
---
|
||||
status: done # done | needs_input | in_progress | failed
|
||||
next: <role-name> # suggested next role, or omit
|
||||
confidence: 0.9 # 0.0–1.0, your self-assessed confidence
|
||||
artifacts: # list of file paths or CAS hashes you produced
|
||||
- path/to/file.ts
|
||||
scope: role # role | thread
|
||||
---
|
||||
|
||||
... your markdown work here ...
|
||||
\`\`\`
|
||||
|
||||
The frontmatter is the **primary deliverable** — the engine reads it directly.
|
||||
Your meta output must satisfy these fields:
|
||||
|
||||
${fieldList}
|
||||
|
||||
Focus exclusively on YOUR role's deliverable. Do not perform actions outside your role's scope.`;
|
||||
}
|
||||
@@ -1,109 +0,0 @@
|
||||
import { putContentNodeWithRefs } from "@uncaged/workflow-cas";
|
||||
import type {
|
||||
AdapterFn,
|
||||
AgentFn,
|
||||
RoleResult,
|
||||
ThreadContext,
|
||||
WorkflowRuntime,
|
||||
} from "@uncaged/workflow-runtime";
|
||||
import {
|
||||
createLogger,
|
||||
parseFrontmatterMarkdown,
|
||||
validateFrontmatter,
|
||||
} from "@uncaged/workflow-util";
|
||||
import type * as z from "zod/v4";
|
||||
import { buildOutputFormatInstruction } from "./build-output-format-instruction.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
export type ExtractOptionsFn<Opt> = (
|
||||
ctx: ThreadContext,
|
||||
prompt: string,
|
||||
runtime: WorkflowRuntime,
|
||||
) => Promise<Opt>;
|
||||
|
||||
/**
|
||||
* Try to satisfy `schema` from frontmatter fields alone.
|
||||
*
|
||||
* Returns the parsed value on success, or `null` when the frontmatter does not
|
||||
* cover all required fields of the schema. Never throws.
|
||||
*/
|
||||
function tryFrontmatterMeta<T>(
|
||||
raw: string,
|
||||
schema: z.ZodType<T>,
|
||||
): { meta: T; body: string } | null {
|
||||
const { frontmatter, body } = parseFrontmatterMarkdown(raw);
|
||||
|
||||
if (frontmatter === null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
const validationErrors = validateFrontmatter(frontmatter);
|
||||
if (validationErrors.length > 0) {
|
||||
log(
|
||||
"4KNMR2PX",
|
||||
`frontmatter validation errors: ${validationErrors.map((e) => e.message).join("; ")}`,
|
||||
);
|
||||
return null;
|
||||
}
|
||||
|
||||
// Coerce frontmatter into the plain object shape the schema expects.
|
||||
const candidate: Record<string, unknown> = {
|
||||
status: frontmatter.status,
|
||||
next: frontmatter.next,
|
||||
confidence: frontmatter.confidence,
|
||||
artifacts: frontmatter.artifacts,
|
||||
scope: frontmatter.scope,
|
||||
};
|
||||
|
||||
const result = schema.safeParse(candidate);
|
||||
if (!result.success) {
|
||||
log("7BQST3VW", "frontmatter does not satisfy schema; falling back to extract");
|
||||
return null;
|
||||
}
|
||||
|
||||
return { meta: result.data, body };
|
||||
}
|
||||
|
||||
/**
|
||||
* Bridges {@link AgentFn} to {@link AdapterFn}.
|
||||
*
|
||||
* Happy path (zero LLM cost):
|
||||
* 1. extract(ctx, prompt, runtime) → Opt
|
||||
* 2. agent(ctx, options) → raw string
|
||||
* 3. Parse raw as frontmatter markdown
|
||||
* 4. If frontmatter is valid AND satisfies `schema` → use as meta directly
|
||||
* CAS stores the body (without frontmatter block)
|
||||
*
|
||||
* Fallback (safety net):
|
||||
* 4b. Store full raw in CAS
|
||||
* 5b. runtime.extract(schema, contentHash) → typed meta via LLM
|
||||
*/
|
||||
export function createAgentAdapter<Opt>(
|
||||
agent: AgentFn<Opt>,
|
||||
extract: ExtractOptionsFn<Opt>,
|
||||
): AdapterFn {
|
||||
return <T>(prompt: string, schema: z.ZodType<T>) => {
|
||||
const augmentedPrompt = `${buildOutputFormatInstruction(schema)}\n\n${prompt}`;
|
||||
return async (ctx: ThreadContext, runtime: WorkflowRuntime): Promise<RoleResult<T>> => {
|
||||
const options = await extract(ctx, augmentedPrompt, runtime);
|
||||
const raw = await agent(ctx, options);
|
||||
|
||||
const frontmatterResult = tryFrontmatterMeta(raw, schema);
|
||||
|
||||
if (frontmatterResult !== null) {
|
||||
log("3VXPW8QR", "frontmatter satisfied schema — skipping LLM extract");
|
||||
await putContentNodeWithRefs(runtime.cas, frontmatterResult.body, []);
|
||||
return { meta: frontmatterResult.meta, childThread: null };
|
||||
}
|
||||
|
||||
log("8MTNJ5YK", "no valid frontmatter — falling back to runtime.extract");
|
||||
const contentHash = await putContentNodeWithRefs(runtime.cas, raw, []);
|
||||
const extracted = await runtime.extract(
|
||||
schema as z.ZodType<Record<string, unknown>>,
|
||||
contentHash,
|
||||
);
|
||||
return { meta: extracted.meta as T, childThread: null };
|
||||
};
|
||||
};
|
||||
}
|
||||
@@ -11,8 +11,8 @@
|
||||
"uwf": "./src/cli.ts"
|
||||
},
|
||||
"dependencies": {
|
||||
"@uncaged/json-cas": "^0.3.0",
|
||||
"@uncaged/json-cas-fs": "^0.3.0",
|
||||
"@uncaged/json-cas": "^0.1.3",
|
||||
"@uncaged/json-cas-fs": "^0.1.2",
|
||||
"@uncaged/uwf-agent-kit": "workspace:^",
|
||||
"@uncaged/uwf-moderator": "workspace:^",
|
||||
"@uncaged/uwf-protocol": "workspace:^",
|
||||
@@ -22,12 +22,9 @@
|
||||
"yaml": "^2.8.4"
|
||||
},
|
||||
"scripts": {
|
||||
"test": "vitest run"
|
||||
"test": "bun test"
|
||||
},
|
||||
"publishConfig": {
|
||||
"access": "public"
|
||||
},
|
||||
"devDependencies": {
|
||||
"vitest": "^4.1.6"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,391 +0,0 @@
|
||||
import { mkdir, mkdtemp, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { bootstrap, putSchema } from "@uncaged/json-cas";
|
||||
import { createFsStore } from "@uncaged/json-cas-fs";
|
||||
import type { CasRef, ThreadId } from "@uncaged/uwf-protocol";
|
||||
import { afterEach, beforeEach, describe, expect, test } from "vitest";
|
||||
import {
|
||||
cmdThreadRead,
|
||||
cmdThreadStepDetails,
|
||||
extractLastAssistantContent,
|
||||
THREAD_READ_DEFAULT_QUOTA,
|
||||
} from "../commands/thread.js";
|
||||
import { registerUwfSchemas } from "../schemas.js";
|
||||
import type { UwfStore } from "../store.js";
|
||||
import { saveThreadsIndex } from "../store.js";
|
||||
|
||||
// ── schemas used in tests ────────────────────────────────────────────────────
|
||||
|
||||
const TURN_SCHEMA = {
|
||||
title: "hermes-turn",
|
||||
type: "object" as const,
|
||||
required: ["index", "role", "content"],
|
||||
properties: {
|
||||
index: { type: "integer" as const },
|
||||
role: { type: "string" as const },
|
||||
content: { type: "string" as const },
|
||||
toolCalls: {
|
||||
anyOf: [
|
||||
{ type: "array" as const, items: { type: "object" as const } },
|
||||
{ type: "null" as const },
|
||||
],
|
||||
},
|
||||
reasoning: { anyOf: [{ type: "string" as const }, { type: "null" as const }] },
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
const DETAIL_SCHEMA = {
|
||||
title: "hermes-detail",
|
||||
type: "object" as const,
|
||||
required: ["sessionId", "model", "duration", "turnCount", "turns"],
|
||||
properties: {
|
||||
sessionId: { type: "string" as const },
|
||||
model: { type: "string" as const },
|
||||
duration: { type: "integer" as const },
|
||||
turnCount: { type: "integer" as const },
|
||||
turns: {
|
||||
type: "array" as const,
|
||||
items: { type: "string" as const, format: "cas_ref" },
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
// ── helpers ───────────────────────────────────────────────────────────────────
|
||||
|
||||
async function makeUwfStore(storageRoot: string): Promise<UwfStore> {
|
||||
const casDir = join(storageRoot, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
return { storageRoot, store, schemas };
|
||||
}
|
||||
|
||||
async function registerDetailSchemas(store: ReturnType<typeof createFsStore>) {
|
||||
await bootstrap(store);
|
||||
const [turn, detail] = await Promise.all([
|
||||
putSchema(store, TURN_SCHEMA),
|
||||
putSchema(store, DETAIL_SCHEMA),
|
||||
]);
|
||||
return { turn, detail };
|
||||
}
|
||||
|
||||
// ── fixture ───────────────────────────────────────────────────────────────────
|
||||
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-test-"));
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
// ── extractLastAssistantContent ───────────────────────────────────────────────
|
||||
|
||||
describe("extractLastAssistantContent", () => {
|
||||
test("returns last non-empty assistant content from turns", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const schemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const turn1 = await uwf.store.put(schemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "intermediate",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const turn2 = await uwf.store.put(schemas.turn, {
|
||||
index: 1,
|
||||
role: "tool",
|
||||
content: "ok",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const turn3 = await uwf.store.put(schemas.turn, {
|
||||
index: 2,
|
||||
role: "assistant",
|
||||
content: "final answer",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
|
||||
const detailHash = await uwf.store.put(schemas.detail, {
|
||||
sessionId: "s1",
|
||||
model: "m1",
|
||||
duration: 1000,
|
||||
turnCount: 3,
|
||||
turns: [turn1, turn2, turn3],
|
||||
});
|
||||
|
||||
expect(extractLastAssistantContent(uwf, detailHash)).toBe("final answer");
|
||||
});
|
||||
|
||||
test("returns null when detail node does not exist in store", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
expect(extractLastAssistantContent(uwf, "nonexistent00" as CasRef)).toBeNull();
|
||||
});
|
||||
|
||||
test("returns null when turns array is empty", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const schemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const detailHash = await uwf.store.put(schemas.detail, {
|
||||
sessionId: "s2",
|
||||
model: "m2",
|
||||
duration: 0,
|
||||
turnCount: 0,
|
||||
turns: [],
|
||||
});
|
||||
|
||||
expect(extractLastAssistantContent(uwf, detailHash)).toBeNull();
|
||||
});
|
||||
|
||||
test("returns null when all assistant turns have empty content", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const schemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const turn1 = await uwf.store.put(schemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
|
||||
const detailHash = await uwf.store.put(schemas.detail, {
|
||||
sessionId: "s3",
|
||||
model: "m3",
|
||||
duration: 0,
|
||||
turnCount: 1,
|
||||
turns: [turn1],
|
||||
});
|
||||
|
||||
expect(extractLastAssistantContent(uwf, detailHash)).toBeNull();
|
||||
});
|
||||
|
||||
test("skips whitespace-only assistant content and returns earlier match", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const schemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const turn1 = await uwf.store.put(schemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "real content",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const turn2 = await uwf.store.put(schemas.turn, {
|
||||
index: 1,
|
||||
role: "assistant",
|
||||
content: " ",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
|
||||
const detailHash = await uwf.store.put(schemas.detail, {
|
||||
sessionId: "s4",
|
||||
model: "m4",
|
||||
duration: 0,
|
||||
turnCount: 2,
|
||||
turns: [turn1, turn2],
|
||||
});
|
||||
|
||||
expect(extractLastAssistantContent(uwf, detailHash)).toBe("real content");
|
||||
});
|
||||
});
|
||||
|
||||
// ── cmdThreadRead: ### Content section ───────────────────────────────────────
|
||||
|
||||
describe("cmdThreadRead ### Content section", () => {
|
||||
test("includes ### Content before ### Output when detail has assistant turns", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const detailSchemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
writer: {
|
||||
description: "Write",
|
||||
systemPrompt: "You are a writer.",
|
||||
outputSchema: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Write something",
|
||||
});
|
||||
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const turnHash = await uwf.store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "The assistant response text",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await uwf.store.put(detailSchemas.detail, {
|
||||
sessionId: "sx",
|
||||
model: "mx",
|
||||
duration: 500,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "writer",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-hermes",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000000001" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
expect(markdown).toContain("### Content");
|
||||
expect(markdown).toContain("The assistant response text");
|
||||
|
||||
const contentIdx = markdown.indexOf("### Content");
|
||||
const outputIdx = markdown.indexOf("### Output");
|
||||
expect(contentIdx).toBeGreaterThanOrEqual(0);
|
||||
expect(outputIdx).toBeGreaterThanOrEqual(0);
|
||||
expect(contentIdx).toBeLessThan(outputIdx);
|
||||
});
|
||||
|
||||
test("omits ### Content when detail has no matching assistant turns", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "test-wf2",
|
||||
description: "desc",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Do stuff",
|
||||
});
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
// A detail ref that doesn't exist in the store → extractLastAssistantContent returns null
|
||||
const missingDetailRef = "missingdetail0" as CasRef;
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: missingDetailRef,
|
||||
agent: "uwf-hermes",
|
||||
});
|
||||
|
||||
const threadId = "01JTEST0000000000000000002" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
expect(markdown).not.toContain("### Content");
|
||||
expect(markdown).toContain("### Output");
|
||||
});
|
||||
});
|
||||
|
||||
// ── cmdThreadStepDetails ──────────────────────────────────────────────────────
|
||||
|
||||
describe("cmdThreadStepDetails", () => {
|
||||
test("returns expanded detail node with turns inlined", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const detailSchemas = await registerDetailSchemas(uwf.store);
|
||||
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "wf",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "p",
|
||||
});
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const turnHash = await uwf.store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "done",
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await uwf.store.put(detailSchemas.detail, {
|
||||
sessionId: "sess42",
|
||||
model: "gpt-4o",
|
||||
duration: 3000,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
|
||||
const stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "coder",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-hermes",
|
||||
});
|
||||
|
||||
const result = await cmdThreadStepDetails(tmpDir, stepHash);
|
||||
|
||||
expect(result).toMatchObject({
|
||||
sessionId: "sess42",
|
||||
model: "gpt-4o",
|
||||
duration: 3000,
|
||||
turnCount: 1,
|
||||
});
|
||||
|
||||
const expanded = result as Record<string, unknown>;
|
||||
expect(Array.isArray(expanded.turns)).toBe(true);
|
||||
const turns = expanded.turns as unknown[];
|
||||
expect(turns).toHaveLength(1);
|
||||
expect(turns[0]).toMatchObject({
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: "done",
|
||||
});
|
||||
});
|
||||
|
||||
test("throws when step hash does not exist", async () => {
|
||||
await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
+55
-127
@@ -1,34 +1,28 @@
|
||||
#!/usr/bin/env bun
|
||||
|
||||
import type { ThreadId } from "@uncaged/uwf-protocol";
|
||||
import { Command } from "commander";
|
||||
import { stringify as yamlStringify } from "yaml";
|
||||
|
||||
import {
|
||||
cmdThreadKill,
|
||||
cmdThreadList,
|
||||
cmdThreadShow,
|
||||
cmdThreadStart,
|
||||
cmdThreadStep,
|
||||
} from "./commands/thread.js";
|
||||
import { cmdWorkflowList, cmdWorkflowPut, cmdWorkflowShow } from "./commands/workflow.js";
|
||||
import { cmdSetup, cmdSetupInteractive } from "./commands/setup.js";
|
||||
import {
|
||||
cmdCasCat,
|
||||
cmdCasGet,
|
||||
cmdCasHas,
|
||||
cmdCasPut,
|
||||
cmdCasRefs,
|
||||
cmdCasReindex,
|
||||
cmdCasSchemaGet,
|
||||
cmdCasSchemaList,
|
||||
cmdCasWalk,
|
||||
} from "./commands/cas.js";
|
||||
import { cmdSetup, cmdSetupInteractive } from "./commands/setup.js";
|
||||
import {
|
||||
cmdThreadFork,
|
||||
cmdThreadKill,
|
||||
cmdThreadList,
|
||||
cmdThreadRead,
|
||||
cmdThreadShow,
|
||||
cmdThreadStart,
|
||||
cmdThreadStep,
|
||||
cmdThreadStepDetails,
|
||||
cmdThreadSteps,
|
||||
THREAD_READ_DEFAULT_QUOTA,
|
||||
} from "./commands/thread.js";
|
||||
import { cmdWorkflowList, cmdWorkflowPut, cmdWorkflowShow } from "./commands/workflow.js";
|
||||
import { formatOutput, type OutputFormat } from "./format.js";
|
||||
import { resolveStorageRoot } from "./store.js";
|
||||
import { type OutputFormat, formatOutput } from "./format.js";
|
||||
|
||||
function writeOutput(data: unknown): void {
|
||||
const fmt = program.opts().format as OutputFormat;
|
||||
@@ -150,71 +144,6 @@ thread
|
||||
});
|
||||
});
|
||||
|
||||
thread
|
||||
.command("steps")
|
||||
.description("List all steps in a thread")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.action((threadId: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdThreadSteps(storageRoot, threadId);
|
||||
writeOutput(result);
|
||||
});
|
||||
});
|
||||
|
||||
thread
|
||||
.command("read")
|
||||
.description("Read thread context as human-readable markdown")
|
||||
.argument("<thread-id>", "Thread ULID")
|
||||
.option("--quota <chars>", "Max output characters", String(THREAD_READ_DEFAULT_QUOTA))
|
||||
.option("--before <step-hash>", "Load steps before this hash (exclusive)")
|
||||
.option("--start", "Include start step in output")
|
||||
.action(
|
||||
(threadId: string, opts: { quota: string; before: string | undefined; start: boolean }) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const quota = Number.parseInt(opts.quota, 10);
|
||||
if (!Number.isFinite(quota) || quota < 1) {
|
||||
process.stderr.write("invalid --quota: must be a positive integer\n");
|
||||
process.exit(1);
|
||||
}
|
||||
const before = opts.before ?? null;
|
||||
const markdown = await cmdThreadRead(
|
||||
storageRoot,
|
||||
threadId as ThreadId,
|
||||
quota,
|
||||
before,
|
||||
opts.start ?? false,
|
||||
);
|
||||
process.stdout.write(markdown.endsWith("\n") ? markdown : `${markdown}\n`);
|
||||
});
|
||||
},
|
||||
);
|
||||
|
||||
thread
|
||||
.command("fork")
|
||||
.description("Fork a thread from a specific step")
|
||||
.argument("<step-hash>", "CAS hash of the StartNode or StepNode to fork from")
|
||||
.action((stepHash: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const result = await cmdThreadFork(storageRoot, stepHash);
|
||||
writeOutput(result);
|
||||
});
|
||||
});
|
||||
|
||||
thread
|
||||
.command("step-details")
|
||||
.description("Dump the full detail node of a step as YAML")
|
||||
.argument("<step-hash>", "CAS hash of the StepNode")
|
||||
.action((stepHash: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
const detail = await cmdThreadStepDetails(storageRoot, stepHash);
|
||||
process.stdout.write(yamlStringify(detail));
|
||||
});
|
||||
});
|
||||
|
||||
program
|
||||
.command("setup")
|
||||
.description("Configure provider, model, and agent")
|
||||
@@ -223,48 +152,57 @@ program
|
||||
.option("--api-key <key>", "API key")
|
||||
.option("--model <name>", "Default model name")
|
||||
.option("--agent <name>", "Default agent alias")
|
||||
.action(
|
||||
(opts: {
|
||||
provider?: string;
|
||||
baseUrl?: string;
|
||||
apiKey?: string;
|
||||
model?: string;
|
||||
agent?: string;
|
||||
}) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
if (opts.provider && opts.baseUrl && opts.apiKey && opts.model) {
|
||||
const result = await cmdSetup({
|
||||
provider: opts.provider,
|
||||
baseUrl: opts.baseUrl,
|
||||
apiKey: opts.apiKey,
|
||||
model: opts.model,
|
||||
agent: opts.agent ?? undefined,
|
||||
storageRoot,
|
||||
});
|
||||
writeOutput(result);
|
||||
} else if (!opts.provider && !opts.baseUrl && !opts.apiKey && !opts.model) {
|
||||
await cmdSetupInteractive(storageRoot);
|
||||
} else {
|
||||
throw new Error(
|
||||
"Non-interactive setup requires all of: --provider, --base-url, --api-key, --model",
|
||||
);
|
||||
}
|
||||
});
|
||||
},
|
||||
);
|
||||
.action((opts: {
|
||||
provider?: string;
|
||||
baseUrl?: string;
|
||||
apiKey?: string;
|
||||
model?: string;
|
||||
agent?: string;
|
||||
}) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
if (opts.provider && opts.baseUrl && opts.apiKey && opts.model) {
|
||||
const result = await cmdSetup({
|
||||
provider: opts.provider,
|
||||
baseUrl: opts.baseUrl,
|
||||
apiKey: opts.apiKey,
|
||||
model: opts.model,
|
||||
agent: opts.agent ?? undefined,
|
||||
storageRoot,
|
||||
});
|
||||
writeOutput(result);
|
||||
} else if (!opts.provider && !opts.baseUrl && !opts.apiKey && !opts.model) {
|
||||
await cmdSetupInteractive(storageRoot);
|
||||
} else {
|
||||
throw new Error(
|
||||
"Non-interactive setup requires all of: --provider, --base-url, --api-key, --model",
|
||||
);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
const cas = program.command("cas").description("Content-addressable storage operations");
|
||||
|
||||
cas
|
||||
.command("get")
|
||||
.description("Read a CAS node (type + payload; use --timestamp to include timestamp)")
|
||||
.description("Read a CAS node as JSON")
|
||||
.argument("<hash>", "CAS hash (13 char)")
|
||||
.option("--timestamp", "Include timestamp in output")
|
||||
.action((hash: string, opts: { timestamp?: boolean }) => {
|
||||
.action((hash: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
writeOutput(await cmdCasGet(storageRoot, hash, opts));
|
||||
writeOutput(await cmdCasGet(storageRoot, hash));
|
||||
});
|
||||
});
|
||||
|
||||
cas
|
||||
.command("cat")
|
||||
.description("Output a CAS node (--payload for payload only)")
|
||||
.argument("<hash>", "CAS hash (13 char)")
|
||||
.option("--payload", "Output only the payload")
|
||||
.action((hash: string, opts: { payload?: boolean }) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
writeOutput(await cmdCasCat(storageRoot, hash, opts));
|
||||
});
|
||||
});
|
||||
|
||||
@@ -313,16 +251,6 @@ cas
|
||||
});
|
||||
});
|
||||
|
||||
cas
|
||||
.command("reindex")
|
||||
.description("Rebuild type index from all CAS nodes")
|
||||
.action(() => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
writeOutput(await cmdCasReindex(storageRoot));
|
||||
});
|
||||
});
|
||||
|
||||
const casSchema = cas.command("schema").description("CAS schema operations");
|
||||
|
||||
casSchema
|
||||
|
||||
@@ -28,18 +28,26 @@ function readJsonArg(fileOrInline: string): unknown {
|
||||
export async function cmdCasGet(
|
||||
storageRoot: string,
|
||||
hash: string,
|
||||
opts: { timestamp?: boolean },
|
||||
): Promise<unknown> {
|
||||
const store = openStore(storageRoot);
|
||||
const node = store.get(hash);
|
||||
if (node === null) {
|
||||
throw new Error(`Node not found: ${hash}`);
|
||||
}
|
||||
if (opts.timestamp) {
|
||||
return node;
|
||||
return node;
|
||||
}
|
||||
|
||||
export async function cmdCasCat(
|
||||
storageRoot: string,
|
||||
hash: string,
|
||||
opts: { payload?: boolean },
|
||||
): Promise<unknown> {
|
||||
const store = openStore(storageRoot);
|
||||
const node = store.get(hash);
|
||||
if (node === null) {
|
||||
throw new Error(`Node not found: ${hash}`);
|
||||
}
|
||||
const { timestamp: _, ...rest } = node as Record<string, unknown>;
|
||||
return rest;
|
||||
return opts.payload ? node.payload : node;
|
||||
}
|
||||
|
||||
export async function cmdCasPut(
|
||||
@@ -100,10 +108,10 @@ export async function cmdCasSchemaList(
|
||||
// Include meta-schema itself
|
||||
entries.push({ hash: metaHash, title: "(meta-schema)" });
|
||||
|
||||
for (const hash of store.listByType(metaHash)) {
|
||||
for (const hash of store.list()) {
|
||||
if (hash === metaHash) continue;
|
||||
const node = store.get(hash);
|
||||
if (node !== null) {
|
||||
if (node !== null && node.type === metaHash) {
|
||||
const schema = node.payload as JSONSchema;
|
||||
const title =
|
||||
(schema.title as string | undefined) ??
|
||||
@@ -115,17 +123,6 @@ export async function cmdCasSchemaList(
|
||||
return entries;
|
||||
}
|
||||
|
||||
export async function cmdCasReindex(
|
||||
storageRoot: string,
|
||||
): Promise<{ status: string }> {
|
||||
const indexDir = join(storageRoot, "cas", "_index");
|
||||
const { rmSync } = await import("node:fs");
|
||||
rmSync(indexDir, { recursive: true, force: true });
|
||||
// Re-open store to trigger migration rebuild
|
||||
openStore(storageRoot);
|
||||
return { status: "reindexed" };
|
||||
}
|
||||
|
||||
export async function cmdCasSchemaGet(
|
||||
storageRoot: string,
|
||||
hash: string,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { execFileSync } from "node:child_process";
|
||||
import type { Store as CasStore, JSONSchema } from "@uncaged/json-cas";
|
||||
import { getSchema, validate } from "@uncaged/json-cas";
|
||||
|
||||
import { validate } from "@uncaged/json-cas";
|
||||
import { getEnvPath, loadWorkflowConfig } from "@uncaged/uwf-agent-kit";
|
||||
import { evaluate } from "@uncaged/uwf-moderator";
|
||||
import type {
|
||||
@@ -8,23 +8,18 @@ import type {
|
||||
AgentConfig,
|
||||
CasRef,
|
||||
ModeratorContext,
|
||||
StartEntry,
|
||||
StartNodePayload,
|
||||
StartOutput,
|
||||
StepContext,
|
||||
StepEntry,
|
||||
StepNodePayload,
|
||||
StepOutput,
|
||||
ThreadForkOutput,
|
||||
ThreadId,
|
||||
ThreadListItem,
|
||||
ThreadStepsOutput,
|
||||
WorkflowConfig,
|
||||
WorkflowPayload,
|
||||
} from "@uncaged/uwf-protocol";
|
||||
import { generateUlid } from "@uncaged/workflow-util";
|
||||
import { config as loadDotenv } from "dotenv";
|
||||
import { stringify } from "yaml";
|
||||
|
||||
import {
|
||||
appendThreadHistory,
|
||||
@@ -41,7 +36,6 @@ import {
|
||||
import { isCasRef } from "../validate.js";
|
||||
|
||||
const END_ROLE = "$END";
|
||||
export const THREAD_READ_DEFAULT_QUOTA = 4000;
|
||||
|
||||
type ChainState = {
|
||||
startHash: CasRef;
|
||||
@@ -50,12 +44,6 @@ type ChainState = {
|
||||
headIsStart: boolean;
|
||||
};
|
||||
|
||||
type OrderedStepItem = {
|
||||
hash: CasRef;
|
||||
payload: StepNodePayload;
|
||||
timestamp: number;
|
||||
};
|
||||
|
||||
export type KillOutput = {
|
||||
thread: ThreadId;
|
||||
archived: boolean;
|
||||
@@ -274,247 +262,6 @@ function expandOutput(uwf: UwfStore, outputRef: CasRef): unknown {
|
||||
return node.payload;
|
||||
}
|
||||
|
||||
/**
|
||||
* Recursively expand all cas_ref fields in a CAS node's payload,
|
||||
* replacing hash strings with the referenced node's expanded payload.
|
||||
*/
|
||||
function expandDeep(store: CasStore, hash: CasRef, visited?: Set<string>): unknown {
|
||||
const seen = visited ?? new Set<string>();
|
||||
if (seen.has(hash)) return hash; // cycle guard
|
||||
seen.add(hash);
|
||||
|
||||
const node = store.get(hash);
|
||||
if (node === null) return hash;
|
||||
|
||||
const schema = getSchema(store, node.type);
|
||||
if (schema === null) return node.payload;
|
||||
|
||||
return expandValue(store, schema, node.payload, seen);
|
||||
}
|
||||
|
||||
function expandValue(
|
||||
store: CasStore,
|
||||
schema: JSONSchema,
|
||||
value: unknown,
|
||||
visited: Set<string>,
|
||||
): unknown {
|
||||
// If this field is a cas_ref, expand it
|
||||
if (schema.format === "cas_ref") {
|
||||
if (typeof value === "string") {
|
||||
return expandDeep(store, value as CasRef, visited);
|
||||
}
|
||||
return value;
|
||||
}
|
||||
|
||||
// anyOf (nullable refs)
|
||||
if (Array.isArray(schema.anyOf)) {
|
||||
for (const sub of schema.anyOf as JSONSchema[]) {
|
||||
if (sub.format === "cas_ref" && typeof value === "string") {
|
||||
return expandDeep(store, value as CasRef, visited);
|
||||
}
|
||||
}
|
||||
return value;
|
||||
}
|
||||
|
||||
// Array of cas_ref items
|
||||
if (schema.type === "array" && schema.items && Array.isArray(value)) {
|
||||
const itemSchema = schema.items as JSONSchema;
|
||||
return (value as unknown[]).map((item) => expandValue(store, itemSchema, item, visited));
|
||||
}
|
||||
|
||||
// Object with properties
|
||||
if (value !== null && typeof value === "object" && !Array.isArray(value) && schema.properties) {
|
||||
const props = schema.properties as Record<string, JSONSchema>;
|
||||
const obj = value as Record<string, unknown>;
|
||||
const result: Record<string, unknown> = {};
|
||||
for (const [key, val] of Object.entries(obj)) {
|
||||
const propSchema = props[key];
|
||||
result[key] = propSchema ? expandValue(store, propSchema, val, visited) : val;
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
return value;
|
||||
}
|
||||
|
||||
function collectOrderedSteps(
|
||||
uwf: UwfStore,
|
||||
headHash: CasRef,
|
||||
chain: ChainState,
|
||||
): OrderedStepItem[] {
|
||||
let hash: CasRef | null = headHash;
|
||||
const hashToNode = new Map<string, { payload: StepNodePayload; timestamp: number }>();
|
||||
while (hash !== null) {
|
||||
const node = uwf.store.get(hash);
|
||||
if (node === null || node.type !== uwf.schemas.stepNode) {
|
||||
break;
|
||||
}
|
||||
const payload = node.payload as StepNodePayload;
|
||||
hashToNode.set(hash, { payload, timestamp: node.timestamp });
|
||||
hash = payload.prev;
|
||||
}
|
||||
|
||||
let cur: CasRef | null = chain.headIsStart ? null : headHash;
|
||||
const ordered: OrderedStepItem[] = [];
|
||||
while (cur !== null) {
|
||||
const entry = hashToNode.get(cur);
|
||||
if (entry === undefined) {
|
||||
break;
|
||||
}
|
||||
ordered.push({ hash: cur, ...entry });
|
||||
cur = entry.payload.prev;
|
||||
}
|
||||
ordered.reverse();
|
||||
return ordered;
|
||||
}
|
||||
|
||||
function formatYaml(value: unknown): string {
|
||||
return stringify(value).trimEnd();
|
||||
}
|
||||
|
||||
function formatCompactStep(index: number, item: OrderedStepItem, outputYaml: string): string {
|
||||
return [
|
||||
`## Step ${index}: ${item.payload.role}`,
|
||||
"",
|
||||
`- **Hash:** \`${item.hash}\``,
|
||||
`- **Agent:** ${item.payload.agent}`,
|
||||
"",
|
||||
"### Output",
|
||||
"",
|
||||
"```yaml",
|
||||
outputYaml,
|
||||
"```",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
export function extractLastAssistantContent(uwf: UwfStore, detailRef: CasRef): string | null {
|
||||
const detailNode = uwf.store.get(detailRef);
|
||||
if (detailNode === null) {
|
||||
return null;
|
||||
}
|
||||
const detail = detailNode.payload as Record<string, unknown>;
|
||||
const turns = detail.turns;
|
||||
if (!Array.isArray(turns) || turns.length === 0) {
|
||||
return null;
|
||||
}
|
||||
for (let i = turns.length - 1; i >= 0; i--) {
|
||||
const turnRef = turns[i];
|
||||
if (typeof turnRef !== "string") {
|
||||
continue;
|
||||
}
|
||||
const turnNode = uwf.store.get(turnRef as CasRef);
|
||||
if (turnNode === null) {
|
||||
continue;
|
||||
}
|
||||
const turn = turnNode.payload as Record<string, unknown>;
|
||||
if (
|
||||
turn.role === "assistant" &&
|
||||
typeof turn.content === "string" &&
|
||||
turn.content.trim() !== ""
|
||||
) {
|
||||
return turn.content;
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
function formatThreadReadMarkdown(options: {
|
||||
threadId: ThreadId;
|
||||
workflowName: string;
|
||||
workflowHash: CasRef;
|
||||
prompt: string;
|
||||
ordered: OrderedStepItem[];
|
||||
uwf: UwfStore;
|
||||
workflow: WorkflowPayload;
|
||||
quota: number;
|
||||
before: CasRef | null;
|
||||
showStart: boolean;
|
||||
}): string {
|
||||
const { ordered, uwf, workflow, quota, before, showStart } = options;
|
||||
|
||||
// Determine which steps to consider
|
||||
let candidates = ordered;
|
||||
if (before !== null) {
|
||||
const idx = candidates.findIndex((s) => s.hash === before);
|
||||
if (idx === -1) {
|
||||
fail(`step ${before} not found in thread ${options.threadId}`);
|
||||
}
|
||||
candidates = candidates.slice(0, idx);
|
||||
}
|
||||
|
||||
// Walk backward from newest, accumulating chars until quota exceeded
|
||||
const selected: OrderedStepItem[] = [];
|
||||
let totalChars = 0;
|
||||
for (let i = candidates.length - 1; i >= 0; i--) {
|
||||
const item = candidates[i];
|
||||
if (item === undefined) continue;
|
||||
const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
|
||||
const blockLen = formatCompactStep(i + 1, item, outputYaml).length;
|
||||
selected.unshift(item);
|
||||
totalChars += blockLen;
|
||||
if (totalChars > quota) break;
|
||||
}
|
||||
|
||||
const skippedCount = candidates.length - selected.length;
|
||||
const parts: string[] = [];
|
||||
|
||||
// Start section
|
||||
if (before === null || showStart) {
|
||||
parts.push(
|
||||
[
|
||||
`# Thread \`${options.threadId}\``,
|
||||
"",
|
||||
`**Workflow:** ${options.workflowName} (\`${options.workflowHash}\`)`,
|
||||
"",
|
||||
"## Task",
|
||||
"",
|
||||
options.prompt,
|
||||
].join("\n"),
|
||||
);
|
||||
}
|
||||
|
||||
// Skip hint
|
||||
if (skippedCount > 0 && selected.length > 0) {
|
||||
const firstSelected = selected[0];
|
||||
if (firstSelected !== undefined) {
|
||||
parts.push(
|
||||
`*(${skippedCount} earlier step${skippedCount > 1 ? "s" : ""}, load with \`uwf thread read ${options.threadId} --before ${firstSelected.hash}\`)*`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// Step blocks
|
||||
const startIndex = candidates.length - selected.length;
|
||||
for (let i = 0; i < selected.length; i++) {
|
||||
const item = selected[i];
|
||||
if (item === undefined) continue;
|
||||
const stepNum = startIndex + i + 1;
|
||||
const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
|
||||
const ts = new Date(item.timestamp)
|
||||
.toISOString()
|
||||
.replace("T", " ")
|
||||
.replace(/\.\d+Z$/, "");
|
||||
const stepLines = [
|
||||
`## Step ${stepNum}: ${item.payload.role} \`${item.hash}\``,
|
||||
`**Agent:** ${item.payload.agent} | **Time:** ${ts}`,
|
||||
];
|
||||
const roleDef = workflow.roles[item.payload.role];
|
||||
if (roleDef) {
|
||||
stepLines.push("", "### Prompt", "", roleDef.systemPrompt);
|
||||
}
|
||||
if (item.payload.detail) {
|
||||
const content = extractLastAssistantContent(uwf, item.payload.detail);
|
||||
if (content !== null) {
|
||||
stepLines.push("", "### Content", "", content);
|
||||
}
|
||||
}
|
||||
stepLines.push("", "### Output", "", "```yaml", outputYaml, "```");
|
||||
parts.push(stepLines.join("\n"));
|
||||
}
|
||||
|
||||
return parts.join("\n\n---\n\n");
|
||||
}
|
||||
|
||||
function buildModeratorContext(uwf: UwfStore, chain: ChainState): ModeratorContext {
|
||||
const chronological = [...chain.stepsNewestFirst].reverse();
|
||||
const steps: StepContext[] = chronological.map((step) => ({
|
||||
@@ -690,132 +437,6 @@ export async function cmdThreadStep(
|
||||
};
|
||||
}
|
||||
|
||||
async function resolveHeadHash(storageRoot: string, threadId: ThreadId): Promise<CasRef> {
|
||||
const index = await loadThreadsIndex(storageRoot);
|
||||
const activeHead = index[threadId];
|
||||
if (activeHead !== undefined) {
|
||||
return activeHead;
|
||||
}
|
||||
const hist = await findThreadInHistory(storageRoot, threadId);
|
||||
if (hist !== null) {
|
||||
return hist.head;
|
||||
}
|
||||
fail(`thread not found: ${threadId}`);
|
||||
}
|
||||
|
||||
export async function cmdThreadSteps(
|
||||
storageRoot: string,
|
||||
threadId: ThreadId,
|
||||
): Promise<ThreadStepsOutput> {
|
||||
const headHash = await resolveHeadHash(storageRoot, threadId);
|
||||
const uwf = await createUwfStore(storageRoot);
|
||||
const chain = walkChain(uwf, headHash);
|
||||
|
||||
const startNode = uwf.store.get(chain.startHash);
|
||||
if (startNode === null) {
|
||||
fail(`StartNode not found: ${chain.startHash}`);
|
||||
}
|
||||
|
||||
const startEntry: StartEntry = {
|
||||
hash: chain.startHash,
|
||||
workflow: chain.start.workflow,
|
||||
prompt: chain.start.prompt,
|
||||
timestamp: startNode.timestamp,
|
||||
};
|
||||
|
||||
const stepEntries: StepEntry[] = [];
|
||||
const ordered = collectOrderedSteps(uwf, headHash, chain);
|
||||
|
||||
for (const item of ordered) {
|
||||
stepEntries.push({
|
||||
hash: item.hash,
|
||||
role: item.payload.role,
|
||||
output: expandOutput(uwf, item.payload.output),
|
||||
detail: item.payload.detail,
|
||||
agent: item.payload.agent,
|
||||
timestamp: item.timestamp,
|
||||
});
|
||||
}
|
||||
|
||||
return {
|
||||
thread: threadId,
|
||||
workflow: chain.start.workflow,
|
||||
steps: [startEntry, ...stepEntries],
|
||||
};
|
||||
}
|
||||
|
||||
export async function cmdThreadRead(
|
||||
storageRoot: string,
|
||||
threadId: ThreadId,
|
||||
quota: number = THREAD_READ_DEFAULT_QUOTA,
|
||||
before: CasRef | null = null,
|
||||
showStart: boolean = false,
|
||||
): Promise<string> {
|
||||
const headHash = await resolveHeadHash(storageRoot, threadId);
|
||||
const uwf = await createUwfStore(storageRoot);
|
||||
const chain = walkChain(uwf, headHash);
|
||||
const workflow = loadWorkflowPayload(uwf, chain.start.workflow);
|
||||
const ordered = collectOrderedSteps(uwf, headHash, chain);
|
||||
|
||||
return formatThreadReadMarkdown({
|
||||
threadId,
|
||||
workflowName: workflow.name,
|
||||
workflowHash: chain.start.workflow,
|
||||
prompt: chain.start.prompt,
|
||||
ordered,
|
||||
uwf,
|
||||
workflow,
|
||||
quota,
|
||||
before,
|
||||
showStart,
|
||||
});
|
||||
}
|
||||
|
||||
export async function cmdThreadFork(
|
||||
storageRoot: string,
|
||||
stepHash: CasRef,
|
||||
): Promise<ThreadForkOutput> {
|
||||
const uwf = await createUwfStore(storageRoot);
|
||||
const node = uwf.store.get(stepHash);
|
||||
if (node === null) {
|
||||
fail(`CAS node not found: ${stepHash}`);
|
||||
}
|
||||
if (node.type !== uwf.schemas.startNode && node.type !== uwf.schemas.stepNode) {
|
||||
fail(`node ${stepHash} is not a StartNode or StepNode`);
|
||||
}
|
||||
|
||||
const newThreadId = generateUlid(Date.now()) as ThreadId;
|
||||
const index = await loadThreadsIndex(storageRoot);
|
||||
index[newThreadId] = stepHash;
|
||||
await saveThreadsIndex(storageRoot, index);
|
||||
|
||||
return {
|
||||
thread: newThreadId,
|
||||
forkedFrom: {
|
||||
step: stepHash,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
export async function cmdThreadStepDetails(
|
||||
storageRoot: string,
|
||||
stepHash: CasRef,
|
||||
): Promise<unknown> {
|
||||
const uwf = await createUwfStore(storageRoot);
|
||||
const node = uwf.store.get(stepHash);
|
||||
if (node === null) {
|
||||
fail(`CAS node not found: ${stepHash}`);
|
||||
}
|
||||
if (node.type !== uwf.schemas.stepNode) {
|
||||
fail(`node ${stepHash} is not a StepNode`);
|
||||
}
|
||||
const payload = node.payload as StepNodePayload;
|
||||
if (!payload.detail) {
|
||||
fail(`step ${stepHash} has no detail`);
|
||||
}
|
||||
return expandDeep(uwf.store, payload.detail);
|
||||
}
|
||||
|
||||
export async function cmdThreadKill(storageRoot: string, threadId: ThreadId): Promise<KillOutput> {
|
||||
const index = await loadThreadsIndex(storageRoot);
|
||||
const head = index[threadId];
|
||||
|
||||
@@ -1,7 +0,0 @@
|
||||
import { defineConfig } from "vitest/config";
|
||||
|
||||
export default defineConfig({
|
||||
test: {
|
||||
include: ["src/__tests__/**/*.test.ts"],
|
||||
},
|
||||
});
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user