Compare commits

...

31 Commits

Author SHA1 Message Date
xiaoju b8f9ffcb59 feat(workflow): migrate supervisor to ThreadReactor (Phase 2)
- Rewrite supervisor to use createThreadReactor + createLlmFn
- No direct fetch/HTTP calls in supervisor
- All 266 tests passing

Refs #139, relates #141
2026-05-09 02:26:39 +00:00
xiaoju a7171f05f6 feat(workflow): add ThreadReactor generic ReAct loop + migrate extract (Phase 1)
- New src/reactor/ module: createThreadReactor, createLlmFn, types
- Two-stage API: config (llm, systemPrompt, tools, toolHandler) + per-call (thread, input, schema)
- All tool failures are recoverable (returned to LLM as error message)
- Rewrite createExtract to use createThreadReactor
- Delete reactExtract old implementation
- Fix template test imports (START/END from runtime, validateWorkflowDescriptor from engine)

268 tests passing.

Refs #139, relates #140
2026-05-09 02:15:38 +00:00
xiaoju b53667a2aa Merge pull request 'refactor(workflow): move descriptor validation out of runtime' (#135) from refactor/runtime-descriptor-boundary into main 2026-05-08 15:05:24 +00:00
Scott Wei 5b60fa6454 refactor(workflow-runtime): flatten package layout and centralize types
Collapse bundle/cas/extract/util stubs into types.ts; move createWorkflow and Result helpers to src root.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-08 23:03:53 +08:00
xiaomo 2c0e744ebf Merge pull request 'perf(serve): SSE live pump reads incrementally' (#137) from fix/130-sse-incremental into main 2026-05-08 15:00:44 +00:00
xiaomo ae16f09688 Merge pull request 'feat(dashboard): hash routing + health check polling' (#138) from fix/128-dashboard-enhancements into main 2026-05-08 15:00:34 +00:00
xiaomo 73a3638ad9 Merge pull request 'fix(serve): error handling, CORS, body limit, CAS store reuse' (#136) from fix/120-serve-hardening into main 2026-05-08 15:00:32 +00:00
xingyue 7b0260cedd feat(dashboard): hash routing + health check polling
- Hash-based URL routing (#threads, #threads/{id}, #workflows)
  for bookmarkable/shareable thread links
- Health check polls every 10s with reconnecting state
- useHashRoute hook for clean route management

Closes #128
2026-05-08 18:16:09 +08:00
xingyue 61fc1cfe1b perf(serve): SSE live pump reads incrementally instead of full file
Use Bun.file().slice() to read only new bytes from the last known
offset instead of re-reading the entire JSONL file on every fs watch.

- readNewBytes() helper with byte-offset tracking
- Handles file truncation (resets offset)
- Early return when no new data

Closes #130
2026-05-08 18:14:04 +08:00
xingyue 6b1e728700 fix(serve): error handling, CORS, body limit, CAS store reuse
- Global error handler (app.onError → 500 JSON)
- JSON parse validation on POST routes (400)
- CORS restricted to localhost origins
- 1MB body size limit on POST (413)
- CAS store created once per route group, not per-request
- 6 new tests covering all changes

Closes #120
2026-05-08 18:11:59 +08:00
xiaomo dedab62c49 Merge pull request 'feat(dashboard): connect thread detail to SSE live stream' (#134) from feat/131-dashboard-sse into main 2026-05-08 09:53:10 +00:00
xingyue a44f1f34a8 feat(dashboard): connect thread detail to SSE live stream
Add useSSE hook that connects to /api/threads/:id/live via EventSource.
Thread detail page now shows records in real-time with auto-scroll.

- useSSE hook: EventSource connection, record accumulation, auto-reconnect
  with exponential backoff, cleanup on unmount
- Thread detail: Live badge, SSE-first with fetch fallback, smooth scroll
- Records clear on reconnect (server replays full file)

Closes #131, testing verified per #133
Refs: #118
2026-05-08 17:52:10 +08:00
Scott Wei 8ff6f7e778 refactor(workflow): move descriptor validation out of runtime
Keep @uncaged/workflow-runtime focused on bundle runtime capabilities by relocating descriptor validation implementation to @uncaged/workflow.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-08 17:45:15 +08:00
xiaoju e04e75bdee chore: remove stale self-referencing symlink
小橘 🍊(NEKO Team)
2026-05-08 09:35:32 +00:00
xiaoju c65c29c1b5 Merge pull request 'refactor(workflow): simplify extraction + thread runtime contract' (#132) from refactor/thread-context-runtime into main 2026-05-08 09:34:26 +00:00
Scott Wei cc3f2b576c refactor(workflow): decouple agent context from CAS and fix monorepo checks
Move CAS access into extract dependencies so AgentContext stays state-only, and clean up type/lint/check regressions across CLI/dashboard to keep full check green.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-08 17:30:07 +08:00
Scott Wei 884ff85205 refactor(workflow): remove dead extract retry export
Drop unused llmExtractWithRetry implementation and public exports.

Add solve-issue template coverage for tool_calls extraction path.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-08 17:10:31 +08:00
Scott Wei a11cc62a81 refactor(workflow-runtime): use full ThreadContext in WorkflowFn
Redefine WorkflowFn to accept a complete ThreadContext plus WorkflowRuntime dependencies, removing ThreadInput and WorkflowFnOptions.

Move thread context construction into engine executeThread, update runtime loop/agent paths, and align templates/docs/tests with template-only definition exports.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-08 17:08:01 +08:00
Scott Wei 34f5e655d1 refactor(workflow): unify extraction behind ExtractFn
Route createExtract through reactExtract with plain-JSON correction retry.

Remove WorkflowFnOptions.llmProvider, ExtractMode, RoleDefinition.extractMode, ResolveRoleMetaFn.

Runtime createWorkflow calls options.extract directly; engine passes extract only.

Update templates, CLI skill docs, and tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-08 17:08:01 +08:00
xiaomo 44fb0694aa Merge pull request 'feat(serve+dashboard): write endpoints, SSE live, run dialog' (#129) from feat/118-serve-write-sse into main 2026-05-08 09:01:09 +00:00
xingyue cdcaff15ab feat(serve+dashboard): write endpoints, SSE live, run dialog
Serve API:
- POST /api/threads — run a new thread
- POST /api/threads/:id/kill — kill thread
- POST /api/threads/:id/pause — pause thread
- POST /api/threads/:id/resume — resume thread
- GET /api/threads/:id/live — SSE stream of thread records

Dashboard:
- Run Thread dialog (select workflow, enter prompt, set maxRounds)
- Thread detail controls (pause/resume/kill buttons)
- postJson API helper for write operations

262 tests pass. Refs: #118
2026-05-08 16:07:02 +08:00
xiaomo 402479ddef Merge pull request 'feat(dashboard): workflow dashboard' (#127) from feat/118-dashboard into main 2026-05-08 07:22:00 +00:00
xingyue a28dd3050e fix(dashboard): remove unused onBack prop from Sidebar 2026-05-08 15:17:40 +08:00
xingyue ce0d0a962c feat(dashboard): workflow dashboard 2026-05-08 14:48:43 +08:00
xiaomo 46b552ec01 Merge pull request 'refactor: split @uncaged/workflow-runtime from engine' (#126) from refactor/121-split-workflow-runtime into main 2026-05-08 06:42:15 +00:00
xiaoju 587518ac09 refactor(workflow): cleanup engine re-exports, final verification (Phase 4)
- Remove all re-exports from @uncaged/workflow -> @uncaged/workflow-runtime
- Fix cli-workflow imports to use @uncaged/workflow-runtime for types
- Update bundle-validator to allow @uncaged/workflow-runtime imports
- Update init templates to reference @uncaged/workflow-runtime
- 378 tests passing, build + check clean

Refs #121, relates #125
2026-05-08 06:37:56 +00:00
xiaoju e9e4960714 refactor(workflow): migrate downstream packages to workflow-runtime (Phase 2+3)
- Verify createWorkflow in runtime has zero I/O imports
- Migrate agent-cursor, agent-hermes to pure workflow-runtime dependency
- Migrate agent-llm, util-agent, templates to dual dependency
  (runtime for types, engine for CAS/merkle/buildDescriptor)
- All 377 tests passing

Refs #121, relates #123 #124
2026-05-08 06:33:52 +00:00
xiaoju 495c000356 refactor(workflow): split @uncaged/workflow-runtime from engine (Phase 1)
Create packages/workflow-runtime with the minimal runtime subset:
- Types (WorkflowFn, RoleOutput, AgentBinding, etc.)
- createWorkflow (pure orchestration, zero I/O)
- validateWorkflowDescriptor
- Result/ok/err, START/END constants

Zero external dependencies (zod as peer only).
Zero node:fs/node:path imports.

Engine (@uncaged/workflow) now depends on workflow-runtime and
provides CAS/merkle/extract implementations via injection.

Refs #121, relates #122
2026-05-08 06:29:49 +00:00
xiaomo 7e662f9287 Merge pull request 'feat(cli): add serve command — Hono HTTP API server' (#119) from feat/118-serve-api into main 2026-05-08 03:12:44 +00:00
xingyue 3ed38c65ec feat(cli): add serve command — Hono HTTP API server
Adds `uncaged-workflow serve` command that exposes workflow data
via a local HTTP API for the upcoming Web UI (RFC #118 Phase 1).

Routes:
- GET /healthz — health check
- GET /api/workflows — list registered workflows
- GET /api/workflows/:name — show workflow details
- GET /api/workflows/:name/history — version history
- GET /api/threads — list threads (optional ?workflow= filter)
- GET /api/threads/running — list running threads
- GET /api/threads/:id — show thread records (parsed JSONL)
- GET /api/cas — list CAS hashes
- GET /api/cas/:hash — get CAS content
- POST /api/cas — store content, returns hash
- DELETE /api/cas/:hash — remove CAS entry
- POST /api/cas/gc — garbage collect

Default: 127.0.0.1:7860, configurable via --port/-p and --host.

Refs: #118
2026-05-08 11:07:13 +08:00
xiaoju 38f2b0eeb2 Merge pull request 'chore: bump all packages to 0.2.0' (#117) from chore/bump-0.2.0 into main 2026-05-08 02:55:49 +00:00
121 changed files with 3153 additions and 1348 deletions
+1 -1
View File
@@ -1,7 +1,7 @@
{
"$schema": "https://biomejs.dev/schemas/2.4.14/schema.json",
"files": {
"includes": ["**", "!**/dist", "!**/node_modules"]
"includes": ["**", "!**/dist", "!**/node_modules", "!packages/workflow/workflow"]
},
"assist": { "actions": { "source": { "organizeImports": "on" } } },
"formatter": {
+1
View File
@@ -5,6 +5,7 @@
"packages/*"
],
"scripts": {
"build": "bunx tsc --build",
"check": "bunx tsc --build && biome check .",
"typecheck": "bunx tsc --build",
"format": "biome format --write .",
@@ -3,7 +3,13 @@ import { mkdir, mkdtemp, readFile, rm, unlink, writeFile } from "node:fs/promise
import { tmpdir } from "node:os";
import { join } from "node:path";
import { getGlobalCasDir, getRegisteredWorkflow, readWorkflowRegistry } from "@uncaged/workflow";
import {
createContentMerkleNode,
getGlobalCasDir,
getRegisteredWorkflow,
readWorkflowRegistry,
serializeMerkleNode,
} from "@uncaged/workflow";
import { cmdCasGet, cmdCasList, cmdCasPut, cmdCasRm } from "../src/commands/cas/index.js";
import {
cmdAdd,
@@ -22,6 +28,10 @@ const fixtureDescriptor = `export const descriptor = { description: "fixture", r
const wfPutImport = `import { putContentMerkleNode } from "@uncaged/workflow";
`;
function casStoredForm(raw: string): string {
return serializeMerkleNode(createContentMerkleNode(raw));
}
describe("cli workflow commands", () => {
let prevEnv: string | undefined;
let storageRoot: string;
@@ -402,21 +412,23 @@ export const run = async function* (input, options) {
});
test("cas put/get/list/rm use global cas dir (thread id not required for storage)", async () => {
const put = await cmdCasPut(storageRoot, "phase doc");
const raw = "phase doc";
const stored = casStoredForm(raw);
const put = await cmdCasPut(storageRoot, raw);
expect(put.ok).toBe(true);
if (!put.ok) {
return;
}
const hash = put.value;
const blobPath = join(getGlobalCasDir(storageRoot), `${hash}.txt`);
expect(await readFile(blobPath, "utf8")).toBe("phase doc");
expect(await readFile(blobPath, "utf8")).toBe(stored);
const got = await cmdCasGet(storageRoot, hash);
expect(got.ok).toBe(true);
if (!got.ok) {
return;
}
expect(got.value).toBe("phase doc");
expect(got.value).toBe(stored);
const listed = await cmdCasList(storageRoot);
expect(listed.ok).toBe(true);
@@ -51,6 +51,7 @@ describe("init template", () => {
};
expect(pkg.type).toBe("module");
expect(pkg.dependencies["@uncaged/workflow"]).toBeDefined();
expect(pkg.dependencies["@uncaged/workflow-runtime"]).toBeDefined();
expect(pkg.dependencies.zod).toBeDefined();
expect(pkg.name).toContain("review-pr");
@@ -0,0 +1,181 @@
import { describe, expect, test } from "bun:test";
import { createContentMerkleNode, serializeMerkleNode } from "@uncaged/workflow";
import { createApp } from "../src/commands/serve/app.js";
function casStoredForm(raw: string): string {
return serializeMerkleNode(createContentMerkleNode(raw));
}
function buildApp(storageRoot: string) {
const app = createApp(storageRoot);
return {
fetch: (path: string, init?: RequestInit) =>
app.fetch(new Request(`http://localhost${path}`, init)),
};
}
describe("serve /healthz", () => {
test("returns ok", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/healthz");
expect(res.status).toBe(200);
const body = (await res.json()) as { ok: boolean };
expect(body.ok).toBe(true);
});
});
describe("serve /api/workflows", () => {
test("returns empty list for missing storage", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/workflows");
// Registry file won't exist, should return error
expect(res.status).toBe(200);
});
});
describe("serve /api/threads", () => {
test("returns empty list for missing storage", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/threads");
expect(res.status).toBe(200);
const body = (await res.json()) as { threads: unknown[] };
expect(body.threads).toEqual([]);
});
test("returns 404 for missing thread", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/threads/nonexistent-id");
expect(res.status).toBe(404);
});
});
describe("serve /api/threads/running", () => {
test("returns empty list for missing storage", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/threads/running");
expect(res.status).toBe(200);
const body = (await res.json()) as { threads: unknown[] };
expect(body.threads).toEqual([]);
});
});
describe("serve /api/cas", () => {
test("returns empty list for missing storage", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/cas");
expect(res.status).toBe(200);
const body = (await res.json()) as { hashes: unknown[] };
expect(body.hashes).toEqual([]);
});
test("returns 404 for missing hash", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/cas/nonexistent-hash");
expect(res.status).toBe(404);
});
});
describe("serve error handling", () => {
test("POST /api/threads with invalid JSON body → 400", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/threads", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: "not json",
});
expect(res.status).toBe(400);
const body = (await res.json()) as { error: string };
expect(body.error).toBe("invalid JSON body");
});
test("POST /api/cas with invalid JSON body → 400", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/cas", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: "not json",
});
expect(res.status).toBe(400);
const body = (await res.json()) as { error: string };
expect(body.error).toBe("invalid JSON body");
});
test("POST /api/threads with missing required fields → 400", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const res = await fetch("/api/threads", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ foo: "bar" }),
});
expect(res.status).toBe(400);
const body = (await res.json()) as { error: string };
expect(body.error).toContain("required");
});
test("global error handler returns 500 with JSON", async () => {
const app = createApp("/tmp/uncaged-serve-test-nonexistent");
app.get("/test-error", () => {
throw new Error("boom");
});
const res = await app.fetch(new Request("http://localhost/test-error"));
expect(res.status).toBe(500);
const body = (await res.json()) as { error: string };
expect(body.error).toBe("Internal server error");
});
});
describe("serve security", () => {
test("CORS headers present on responses", async () => {
const app = createApp("/tmp/uncaged-serve-test-nonexistent");
const res2 = await app.fetch(
new Request("http://localhost/healthz", {
headers: { Origin: "http://localhost:5173" },
}),
);
expect(res2.headers.get("Access-Control-Allow-Origin")).toBe("http://localhost:5173");
});
test("POST with body > 1MB → 413", async () => {
const { fetch } = buildApp("/tmp/uncaged-serve-test-nonexistent");
const largeBody = "x".repeat(1_048_577);
const res = await fetch("/api/cas", {
method: "POST",
headers: {
"Content-Type": "application/json",
"Content-Length": String(largeBody.length),
},
body: largeBody,
});
expect(res.status).toBe(413);
const body = (await res.json()) as { error: string };
expect(body.error).toBe("Payload too large");
});
});
describe("serve CAS round-trip", () => {
const tmpDir = `/tmp/uncaged-serve-cas-test-${Date.now()}`;
test("put then get", async () => {
const { fetch } = buildApp(tmpDir);
const putRes = await fetch("/api/cas", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ content: "hello world" }),
});
expect(putRes.status).toBe(201);
const putBody = (await putRes.json()) as { hash: string };
expect(typeof putBody.hash).toBe("string");
const getRes = await fetch(`/api/cas/${putBody.hash}`);
expect(getRes.status).toBe(200);
const getBody = (await getRes.json()) as { content: string };
expect(getBody.content).toBe(casStoredForm("hello world"));
// cleanup
const delRes = await fetch(`/api/cas/${putBody.hash}`, { method: "DELETE" });
expect(delRes.status).toBe(200);
});
});
+2
View File
@@ -6,7 +6,9 @@
"uncaged-workflow": "src/cli.ts"
},
"dependencies": {
"@uncaged/workflow-runtime": "workspace:*",
"@uncaged/workflow": "workspace:*",
"hono": "^4.12.18",
"yaml": "^2.8.4"
},
"scripts": {
@@ -4,6 +4,7 @@ import { getCommandRegistry } from "./cli-registry.js";
import { formatCliUsage as formatCliUsageWithGroups } from "./cli-usage.js";
import { createCasDispatcher } from "./commands/cas/index.js";
import { createInitDispatcher } from "./commands/init/index.js";
import { dispatchServe } from "./commands/serve/index.js";
import { createThreadDispatcher, dispatchLive, dispatchRun } from "./commands/thread/index.js";
import { createWorkflowDispatcher } from "./commands/workflow/index.js";
import { formatSkillIndex, formatSkillTopic, getSkillTopics } from "./skill.js";
@@ -71,6 +72,7 @@ const COMMAND_TABLE: Record<string, DispatchFn> = {
skill: dispatchSkill,
run: dispatchRun,
live: dispatchLive,
serve: dispatchServe,
};
export async function runCli(storageRoot: string, argv: string[]): Promise<number> {
+11
View File
@@ -57,6 +57,17 @@ export function formatCliUsage(
);
lines.push("");
lines.push("Server:");
lines.push(
...formatUsageCommandLines([
{
prefix: "serve [--port N] [--host ADDR]",
description: "Start HTTP API server (default: 127.0.0.1:7860)",
},
]),
);
lines.push("");
lines.push("Reference:");
const skillTopicNames = skillTopics.map((t) => t.name).join(", ");
lines.push(
@@ -7,6 +7,7 @@ export function templatePackageJson(templateName: string): string {
type: "module",
dependencies: {
"@uncaged/workflow": "^0.1.0",
"@uncaged/workflow-runtime": "^0.1.0",
zod: "^4.0.0",
},
},
@@ -31,7 +32,7 @@ export function templateTsconfigJson(): string {
}
export function templateRolesTs(): string {
return `import type { RoleDefinition } from "@uncaged/workflow";
return `import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const HELLO_TEMPLATE_DESCRIPTION =
@@ -58,7 +59,7 @@ export const greeterRole: RoleDefinition<HelloTemplateMeta["greeter"]> = {
}
export function templateModeratorTs(): string {
return `import { END, type Moderator, type ModeratorContext } from "@uncaged/workflow";
return `import { END, type Moderator, type ModeratorContext } from "@uncaged/workflow-runtime";
import type { HelloTemplateMeta } from "./roles.js";
@@ -74,7 +75,7 @@ export const helloTemplateModerator: Moderator<HelloTemplateMeta> = (
}
export function templateIndexTs(): string {
return `import type { WorkflowDefinition } from "@uncaged/workflow";
return `import type { WorkflowDefinition } from "@uncaged/workflow-runtime";
import { helloTemplateModerator } from "./moderator.js";
import {
@@ -107,7 +107,7 @@ Init 生成的骨架:\`templates/\` 下放可复用定义,\`workflows/\` 下
2. **编写 RoleDefinition**:为每个角色写 Zod \`schema\`,补齐 \`systemPrompt\` / \`extractPrompt\` / \`description\`
3. **编写 Moderator**:根据 \`ctx.steps\` 与业务状态返回下一个角色名或 \`END\`
4. **组装 WorkflowDefinition**:在模板 \`index\` 中导出 definition(以及必要的角色 / moderator 导出)。
5. **实例化**:在 workflow 包中使用 \`createWorkflow(def, binding)\`(或项目约定的封装)绑定 **AgentFn**;**ExtractFn** 由引擎从 **workflow.yaml** 注入 \`WorkflowFnOptions\`
5. **实例化**:在 workflow 包中使用 \`createWorkflow(def, binding)\`(或项目约定的封装)绑定 **AgentFn**;**ExtractFn** 由引擎从 **workflow.yaml** 注入 \`WorkflowRuntime\`
6. **构建**:打包为单个 **.esm.js** bundle,使用 **uncaged-workflow add** 注册。
## 4. 编码规范
@@ -0,0 +1,48 @@
import { Hono } from "hono";
import { cors } from "hono/cors";
import { createCasRoutes } from "./routes-cas.js";
import { createLiveRoutes } from "./routes-live.js";
import { createThreadRoutes } from "./routes-thread.js";
import { createWorkflowRoutes } from "./routes-workflow.js";
const MAX_BODY_SIZE = 1_048_576; // 1 MB
export function createApp(storageRoot: string): Hono {
const app = new Hono();
app.onError((_err, c) => {
return c.json({ error: "Internal server error" }, 500);
});
app.use(
"*",
cors({
origin: [
"http://localhost:5173",
"http://127.0.0.1:5173",
"http://localhost:7860",
"http://127.0.0.1:7860",
],
}),
);
app.use("*", async (c, next) => {
if (c.req.method === "POST") {
const contentLength = c.req.header("content-length");
if (contentLength !== undefined && Number(contentLength) > MAX_BODY_SIZE) {
return c.json({ error: "Payload too large" }, 413);
}
}
await next();
});
app.get("/healthz", (c) => c.json({ ok: true }));
app.route("/api/workflows", createWorkflowRoutes(storageRoot));
app.route("/api/threads", createThreadRoutes(storageRoot));
app.route("/api/threads", createLiveRoutes(storageRoot));
app.route("/api/cas", createCasRoutes(storageRoot));
return app;
}
@@ -0,0 +1,3 @@
export { createApp } from "./app.js";
export { dispatchServe, startServer } from "./serve.js";
export type { ServeOptions } from "./types.js";
@@ -0,0 +1,55 @@
import { createCasStore, garbageCollectCas, getGlobalCasDir } from "@uncaged/workflow";
import { Hono } from "hono";
export function createCasRoutes(storageRoot: string): Hono {
const app = new Hono();
const casDir = getGlobalCasDir(storageRoot);
const cas = createCasStore(casDir);
app.get("/", async (c) => {
const hashes = await cas.list();
return c.json({ hashes });
});
app.get("/:hash", async (c) => {
const content = await cas.get(c.req.param("hash"));
if (content === null) {
return c.json({ error: "not found" }, 404);
}
return c.json({ hash: c.req.param("hash"), content });
});
app.post("/", async (c) => {
let body: { content: string };
try {
body = (await c.req.json()) as { content: string };
} catch {
return c.json({ error: "invalid JSON body" }, 400);
}
if (typeof body.content !== "string") {
return c.json({ error: "content field required" }, 400);
}
const hash = await cas.put(body.content);
return c.json({ hash }, 201);
});
app.delete("/:hash", async (c) => {
const hash = c.req.param("hash");
const content = await cas.get(hash);
if (content === null) {
return c.json({ error: "not found" }, 404);
}
await cas.delete(hash);
return c.json({ ok: true });
});
app.post("/gc", async (c) => {
const result = await garbageCollectCas(storageRoot);
if (!result.ok) {
return c.json({ error: result.error }, 500);
}
return c.json(result.value);
});
return app;
}
@@ -0,0 +1,198 @@
import { statSync, watch } from "node:fs";
import { dirname, join } from "node:path";
import { Hono } from "hono";
import { streamSSE } from "hono/streaming";
import { resolveThreadDataPath } from "../../thread-scan.js";
type PumpState = {
contentOffset: number;
carry: string;
};
function fileSize(path: string): number {
try {
return statSync(path).size;
} catch {
return 0;
}
}
async function readNewBytes(path: string, state: PumpState): Promise<string | null> {
const size = fileSize(path);
if (size < state.contentOffset) {
// File was truncated — reset
state.contentOffset = 0;
state.carry = "";
}
if (size <= state.contentOffset) {
return null;
}
const blob = Bun.file(path).slice(state.contentOffset, size);
const chunk = await blob.text();
state.contentOffset = size;
return chunk;
}
function parseJsonLine(line: string): unknown {
try {
return JSON.parse(line) as unknown;
} catch {
return { raw: line };
}
}
function isWorkflowResult(record: unknown): boolean {
return (
record !== null &&
typeof record === "object" &&
"type" in (record as Record<string, unknown>) &&
(record as Record<string, unknown>).type === "workflow-result"
);
}
function parseNewLines(chunk: string, state: PumpState): string[] {
state.carry += chunk;
const parts = state.carry.split("\n");
state.carry = parts.pop() ?? "";
const lines: string[] = [];
for (const line of parts) {
const trimmed = line.trim();
if (trimmed !== "") {
lines.push(trimmed);
}
}
return lines;
}
export function createLiveRoutes(storageRoot: string): Hono {
const app = new Hono();
app.get("/:threadId/live", async (c) => {
const threadId = c.req.param("threadId");
const dataPath = await resolveThreadDataPath(storageRoot, threadId);
if (dataPath === null) {
return c.json({ error: `thread not found: ${threadId}` }, 404);
}
const resolvedDataPath = dataPath;
const infoPath = join(dirname(resolvedDataPath), `${threadId}.info.jsonl`);
return streamSSE(c, async (stream) => {
const dataState: PumpState = { contentOffset: 0, carry: "" };
const infoState: PumpState = { contentOffset: 0, carry: "" };
let eventId = 0;
async function pumpData(): Promise<boolean> {
let chunk: string | null;
try {
chunk = await readNewBytes(resolvedDataPath, dataState);
} catch {
return false;
}
if (chunk === null) {
return false;
}
const lines = parseNewLines(chunk, dataState);
for (const line of lines) {
const record = parseJsonLine(line);
eventId++;
await stream.writeSSE({
event: "record",
data: JSON.stringify(record),
id: String(eventId),
});
if (isWorkflowResult(record)) {
return true;
}
}
return false;
}
async function pumpInfo(): Promise<void> {
let chunk: string | null;
try {
chunk = await readNewBytes(infoPath, infoState);
} catch {
return;
}
if (chunk === null) {
return;
}
const lines = parseNewLines(chunk, infoState);
for (const line of lines) {
const record = parseJsonLine(line);
if (
typeof record === "object" &&
record !== null &&
"raw" in (record as Record<string, unknown>)
) {
continue;
}
eventId++;
await stream.writeSSE({
event: "info",
data: JSON.stringify(record),
id: String(eventId),
});
}
}
// Initial pump
const done = await pumpData();
await pumpInfo();
if (done) {
return;
}
// Watch for changes
const controller = new AbortController();
let completed = false;
const dataWatcher = watch(resolvedDataPath, async () => {
if (completed) return;
const finished = await pumpData();
if (finished) {
completed = true;
controller.abort();
}
});
let infoWatcher: ReturnType<typeof watch> | null = null;
try {
infoWatcher = watch(infoPath, async () => {
if (completed) return;
await pumpInfo();
});
} catch {
// info file may not exist
}
stream.onAbort(() => {
completed = true;
dataWatcher.close();
infoWatcher?.close();
});
// Keep stream alive until completion or client disconnect
await new Promise<void>((resolve) => {
if (completed) {
resolve();
return;
}
controller.signal.addEventListener("abort", () => resolve(), { once: true });
stream.onAbort(() => resolve());
});
dataWatcher.close();
infoWatcher?.close();
});
});
return app;
}
@@ -0,0 +1,98 @@
import { Hono } from "hono";
import { readTextFileIfExists } from "../../fs-utils.js";
import {
listHistoricalThreads,
listRunningThreads,
resolveThreadDataPath,
} from "../../thread-scan.js";
import { cmdKill, cmdPause, cmdResume } from "../thread/control.js";
import { cmdRun } from "../thread/run.js";
export function createThreadRoutes(storageRoot: string): Hono {
const app = new Hono();
app.get("/", async (c) => {
const nameFilter = c.req.query("workflow") ?? null;
const rows = await listHistoricalThreads(storageRoot, nameFilter);
return c.json({ threads: rows });
});
app.get("/running", async (c) => {
const rows = await listRunningThreads(storageRoot);
return c.json({ threads: rows });
});
app.get("/:threadId", async (c) => {
const threadId = c.req.param("threadId");
const dataPath = await resolveThreadDataPath(storageRoot, threadId);
if (dataPath === null) {
return c.json({ error: `thread not found: ${threadId}` }, 404);
}
const text = await readTextFileIfExists(dataPath);
if (text === null) {
return c.json({ error: `thread data missing: ${threadId}` }, 404);
}
const lines = text.trim().split("\n");
const records = lines.map((line) => {
try {
return JSON.parse(line) as unknown;
} catch {
return { raw: line };
}
});
return c.json({ threadId, records });
});
app.post("/", async (c) => {
let body: Record<string, unknown>;
try {
body = (await c.req.json()) as Record<string, unknown>;
} catch {
return c.json({ error: "invalid JSON body" }, 400);
}
const name = body.workflow;
const prompt = body.prompt;
const maxRounds = typeof body.maxRounds === "number" ? body.maxRounds : 10;
if (typeof name !== "string" || typeof prompt !== "string") {
return c.json({ error: "workflow (string) and prompt (string) are required" }, 400);
}
const result = await cmdRun(storageRoot, name, prompt, maxRounds);
if (!result.ok) {
return c.json({ error: result.error }, 400);
}
return c.json({ threadId: result.value.threadId }, 201);
});
app.post("/:threadId/kill", async (c) => {
const threadId = c.req.param("threadId");
const result = await cmdKill(storageRoot, threadId);
if (!result.ok) {
return c.json({ error: result.error }, 400);
}
return c.json({ ok: true });
});
app.post("/:threadId/pause", async (c) => {
const threadId = c.req.param("threadId");
const result = await cmdPause(storageRoot, threadId);
if (!result.ok) {
return c.json({ error: result.error }, 400);
}
return c.json({ ok: true });
});
app.post("/:threadId/resume", async (c) => {
const threadId = c.req.param("threadId");
const result = await cmdResume(storageRoot, threadId);
if (!result.ok) {
return c.json({ error: result.error }, 400);
}
return c.json({ ok: true });
});
return app;
}
@@ -0,0 +1,55 @@
import {
getRegisteredWorkflow,
listRegisteredWorkflowNames,
readWorkflowRegistry,
} from "@uncaged/workflow";
import { Hono } from "hono";
export function createWorkflowRoutes(storageRoot: string): Hono {
const app = new Hono();
app.get("/", async (c) => {
const reg = await readWorkflowRegistry(storageRoot);
if (!reg.ok) {
return c.json({ error: reg.error.message }, 500);
}
const names = listRegisteredWorkflowNames(reg.value);
const workflows = names.map((name) => {
const entry = reg.value.workflows[name];
return {
name,
hash: entry?.hash ?? null,
timestamp: entry?.timestamp ?? null,
};
});
return c.json({ workflows });
});
app.get("/:name", async (c) => {
const reg = await readWorkflowRegistry(storageRoot);
if (!reg.ok) {
return c.json({ error: reg.error.message }, 500);
}
const name = c.req.param("name");
const entry = getRegisteredWorkflow(reg.value, name);
if (entry === null) {
return c.json({ error: `workflow not found: ${name}` }, 404);
}
return c.json({ name, ...entry });
});
app.get("/:name/history", async (c) => {
const reg = await readWorkflowRegistry(storageRoot);
if (!reg.ok) {
return c.json({ error: reg.error.message }, 500);
}
const name = c.req.param("name");
const entry = getRegisteredWorkflow(reg.value, name);
if (entry === null) {
return c.json({ error: `workflow not found: ${name}` }, 404);
}
return c.json({ name, history: entry.history });
});
return app;
}
@@ -0,0 +1,69 @@
import { err, ok, type Result } from "@uncaged/workflow";
import { serve } from "bun";
import { printCliLine } from "../../cli-output.js";
import { createApp } from "./app.js";
import type { ServeOptions } from "./types.js";
export function startServer(storageRoot: string, options: ServeOptions): void {
const app = createApp(storageRoot);
const server = serve({
fetch: app.fetch,
port: options.port,
hostname: options.hostname,
});
printCliLine(`uncaged-workflow API server listening on http://${server.hostname}:${server.port}`);
}
function parsePortValue(value: string | undefined): Result<number, string> {
if (value === undefined) {
return err("--port requires a value");
}
const parsed = Number.parseInt(value, 10);
if (!Number.isFinite(parsed) || parsed < 0 || parsed > 65535) {
return err(`invalid port: ${value}`);
}
return ok(parsed);
}
function parseServeArgv(argv: string[]): Result<ServeOptions, string> {
let port = 7860;
let hostname = "127.0.0.1";
for (let i = 0; i < argv.length; i++) {
const arg = argv[i];
if (arg === "--port" || arg === "-p") {
const portResult = parsePortValue(argv[i + 1]);
if (!portResult.ok) {
return portResult;
}
port = portResult.value;
i++;
} else if (arg === "--host") {
const next = argv[i + 1];
if (next === undefined) {
return err("--host requires a value");
}
hostname = next;
i++;
}
}
return ok({ port, hostname });
}
export async function dispatchServe(storageRoot: string, argv: string[]): Promise<number> {
const parsed = parseServeArgv(argv);
if (!parsed.ok) {
printCliLine(`error: ${parsed.error}`);
return 1;
}
startServer(storageRoot, parsed.value);
// Keep process alive
await new Promise(() => {});
return 0;
}
@@ -0,0 +1,4 @@
export type ServeOptions = {
port: number;
hostname: string;
};
@@ -9,8 +9,8 @@ import {
getGlobalCasDir,
tryParseRoleStepRecord,
tryParseWorkflowResultRecord,
type WorkflowCompletion,
} from "@uncaged/workflow";
import type { WorkflowCompletion } from "@uncaged/workflow-runtime";
import { dimGreyLine, highlightLiveRole } from "../../cli-color.js";
import { printCliError, printCliLine } from "../../cli-output.js";
-1
View File
@@ -203,7 +203,6 @@ Each role has:
| \`extractPrompt\` | string | Instruction for extracting structured meta |
| \`schema\` | ZodSchema | Validates the extracted meta |
| \`extractRefs\` | fn or null | Extracts CAS hashes from meta for DAG linking |
| \`extractMode\` | "single" | Extraction mode |
## Development Workflow
+1 -1
View File
@@ -17,6 +17,6 @@
"rootDir": "src",
"types": ["bun-types"]
},
"references": [{ "path": "../workflow" }],
"references": [{ "path": "../workflow-runtime" }, { "path": "../workflow" }],
"include": ["src/**/*.ts"]
}
+24
View File
@@ -0,0 +1,24 @@
# @uncaged/workflow-dashboard
Web dashboard for the Uncaged Workflow engine. Connects to the local
`uncaged-workflow serve` API to display threads, workflows, and CAS data.
## Development
```bash
# Start the local API server (in another terminal)
uncaged-workflow serve
# Start the dashboard dev server
bun run dev
```
Opens at http://localhost:5173. Vite proxies `/api/*` to `localhost:7860`.
## Build
```bash
bun run build
```
Output goes to `dist/` — static files ready for CF Pages or any host.
+12
View File
@@ -0,0 +1,12 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Workflow Dashboard</title>
</head>
<body>
<div id="root"></div>
<script type="module" src="/src/main.tsx"></script>
</body>
</html>
+24
View File
@@ -0,0 +1,24 @@
{
"name": "@uncaged/workflow-dashboard",
"version": "0.1.0",
"private": true,
"type": "module",
"scripts": {
"dev": "vite",
"build": "vite build",
"preview": "vite preview"
},
"dependencies": {
"react": "^19.2.6",
"react-dom": "^19.2.6"
},
"devDependencies": {
"@tailwindcss/vite": "^4.2.4",
"@types/react": "^19.2.14",
"@types/react-dom": "^19.2.3",
"@vitejs/plugin-react": "^6.0.1",
"tailwindcss": "^4.2.4",
"typescript": "^6.0.3",
"vite": "^8.0.11"
}
}
+84
View File
@@ -0,0 +1,84 @@
const BASE = "/api";
async function postJson<T>(path: string, body: unknown): Promise<T> {
const res = await fetch(`${BASE}${path}`, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify(body),
});
if (!res.ok) {
const err = (await res.json().catch(() => ({ error: res.statusText }))) as { error: string };
throw new Error(err.error || `API ${res.status}`);
}
return res.json() as Promise<T>;
}
async function fetchJson<T>(path: string): Promise<T> {
const res = await fetch(`${BASE}${path}`);
if (!res.ok) {
throw new Error(`API ${res.status}: ${path}`);
}
return res.json() as Promise<T>;
}
export type WorkflowSummary = {
name: string;
currentHash: string;
versions: number;
};
export type ThreadSummary = {
threadId: string;
workflow: string | null;
hash: string | null;
startedAt: string | null;
status: string | null;
};
export type ThreadRecord = {
type: string;
role: string | null;
content: string | null;
timestamp: number | null;
[key: string]: unknown;
};
export function listWorkflows(): Promise<{ workflows: WorkflowSummary[] }> {
return fetchJson("/workflows");
}
export function listThreads(): Promise<{ threads: ThreadSummary[] }> {
return fetchJson("/threads");
}
export function listRunningThreads(): Promise<{ threads: ThreadSummary[] }> {
return fetchJson("/threads/running");
}
export function getThread(id: string): Promise<{ records: ThreadRecord[] }> {
return fetchJson(`/threads/${id}`);
}
export function runThread(
workflow: string,
prompt: string,
maxRounds: number = 10,
): Promise<{ threadId: string }> {
return postJson("/threads", { workflow, prompt, maxRounds });
}
export function killThread(threadId: string): Promise<{ ok: boolean }> {
return postJson(`/threads/${threadId}/kill`, {});
}
export function pauseThread(threadId: string): Promise<{ ok: boolean }> {
return postJson(`/threads/${threadId}/pause`, {});
}
export function resumeThread(threadId: string): Promise<{ ok: boolean }> {
return postJson(`/threads/${threadId}/resume`, {});
}
export function getHealth(): Promise<{ ok: boolean }> {
return fetchJson("/healthz");
}
+38
View File
@@ -0,0 +1,38 @@
import { useState } from "react";
import { RunDialog } from "./components/run-dialog.tsx";
import { Sidebar } from "./components/sidebar.tsx";
import { StatusBar } from "./components/status-bar.tsx";
import { ThreadDetail } from "./components/thread-detail.tsx";
import { ThreadList } from "./components/thread-list.tsx";
import { WorkflowList } from "./components/workflow-list.tsx";
import { useHashRoute } from "./use-hash-route.ts";
export function App() {
const { view, threadId, setView, setThreadId } = useHashRoute();
const [showRun, setShowRun] = useState(false);
return (
<div className="flex h-screen">
<Sidebar view={view} onViewChange={setView} />
<main className="flex-1 overflow-hidden flex flex-col">
<StatusBar onRun={() => setShowRun(true)} />
<div className="flex-1 overflow-auto p-6">
{view === "threads" && threadId === null && <ThreadList onSelect={setThreadId} />}
{view === "threads" && threadId !== null && (
<ThreadDetail threadId={threadId} onBack={() => setThreadId(null)} />
)}
{view === "workflows" && <WorkflowList />}
</div>
</main>
{showRun && (
<RunDialog
onClose={() => setShowRun(false)}
onCreated={(id) => {
setShowRun(false);
setThreadId(id);
}}
/>
)}
</div>
);
}
@@ -0,0 +1,147 @@
import { useState } from "react";
import { listWorkflows, runThread } from "../api.ts";
import { useFetch } from "../hooks.ts";
type Props = {
onClose: () => void;
onCreated: (threadId: string) => void;
};
export function RunDialog({ onClose, onCreated }: Props) {
const workflows = useFetch(() => listWorkflows(), []);
const [workflow, setWorkflow] = useState("");
const [prompt, setPrompt] = useState("");
const [maxRounds, setMaxRounds] = useState(10);
const [submitting, setSubmitting] = useState(false);
const [error, setError] = useState<string | null>(null);
async function handleSubmit(e: React.FormEvent) {
e.preventDefault();
if (!workflow || !prompt) return;
setSubmitting(true);
setError(null);
try {
const result = await runThread(workflow, prompt, maxRounds);
onCreated(result.threadId);
} catch (err) {
setError(err instanceof Error ? err.message : String(err));
setSubmitting(false);
}
}
return (
<div
className="fixed inset-0 flex items-center justify-center z-50"
style={{ background: "rgba(0,0,0,0.6)" }}
>
<div
className="w-full max-w-lg p-6 rounded-lg border"
style={{ background: "var(--color-surface)", borderColor: "var(--color-border)" }}
>
<h3 className="text-lg font-semibold mb-4">Run Thread</h3>
<form onSubmit={handleSubmit} className="space-y-4">
<div>
<label
htmlFor="run-workflow"
className="text-sm block mb-1"
style={{ color: "var(--color-text-muted)" }}
>
Workflow
</label>
<select
id="run-workflow"
value={workflow}
onChange={(e) => setWorkflow(e.target.value)}
className="w-full px-3 py-2 rounded border text-sm"
style={{
background: "var(--color-bg)",
borderColor: "var(--color-border)",
color: "var(--color-text)",
}}
>
<option value="">Select a workflow...</option>
{workflows.status === "ok" &&
workflows.data.workflows.map((w) => (
<option key={w.name} value={w.name}>
{w.name}
</option>
))}
</select>
</div>
<div>
<label
htmlFor="run-prompt"
className="text-sm block mb-1"
style={{ color: "var(--color-text-muted)" }}
>
Prompt
</label>
<textarea
id="run-prompt"
value={prompt}
onChange={(e) => setPrompt(e.target.value)}
rows={4}
className="w-full px-3 py-2 rounded border text-sm"
style={{
background: "var(--color-bg)",
borderColor: "var(--color-border)",
color: "var(--color-text)",
}}
placeholder="Enter the task prompt..."
/>
</div>
<div>
<label
htmlFor="run-max-rounds"
className="text-sm block mb-1"
style={{ color: "var(--color-text-muted)" }}
>
Max Rounds
</label>
<input
id="run-max-rounds"
type="number"
value={maxRounds}
onChange={(e) => setMaxRounds(Number(e.target.value))}
min={1}
max={100}
className="w-24 px-3 py-2 rounded border text-sm"
style={{
background: "var(--color-bg)",
borderColor: "var(--color-border)",
color: "var(--color-text)",
}}
/>
</div>
{error && (
<p className="text-sm" style={{ color: "var(--color-error)" }}>
{error}
</p>
)}
<div className="flex gap-2 justify-end">
<button
type="button"
onClick={onClose}
className="px-4 py-2 text-sm rounded border"
style={{ borderColor: "var(--color-border)", color: "var(--color-text-muted)" }}
>
Cancel
</button>
<button
type="submit"
disabled={submitting || !workflow || !prompt}
className="px-4 py-2 text-sm rounded"
style={{
background: submitting ? "var(--color-accent-dim)" : "var(--color-accent)",
color: "#fff",
opacity: !workflow || !prompt ? 0.5 : 1,
}}
>
{submitting ? "Starting..." : "Run"}
</button>
</div>
</form>
</div>
</div>
);
}
@@ -0,0 +1,43 @@
type Props = {
view: "threads" | "workflows";
onViewChange: (v: "threads" | "workflows") => void;
};
export function Sidebar({ view, onViewChange }: Props) {
const items = [
{ key: "threads" as const, label: "Threads", icon: "⚡" },
{ key: "workflows" as const, label: "Workflows", icon: "📦" },
];
return (
<aside
className="w-56 border-r flex flex-col"
style={{ borderColor: "var(--color-border)", background: "var(--color-surface)" }}
>
<div className="p-4 border-b" style={{ borderColor: "var(--color-border)" }}>
<h1 className="text-lg font-semibold" style={{ color: "var(--color-accent)" }}>
Workflow
</h1>
<p className="text-xs mt-1" style={{ color: "var(--color-text-muted)" }}>
Dashboard
</p>
</div>
<nav className="flex-1 p-2 space-y-1">
{items.map((item) => (
<button
type="button"
key={item.key}
onClick={() => onViewChange(item.key)}
className="w-full text-left px-3 py-2 rounded text-sm transition-colors"
style={{
background: view === item.key ? "var(--color-accent-dim)" : "transparent",
color: view === item.key ? "#fff" : "var(--color-text-muted)",
}}
>
{item.icon} {item.label}
</button>
))}
</nav>
</aside>
);
}
@@ -0,0 +1,65 @@
import { useCallback, useEffect, useRef, useState } from "react";
import { getHealth } from "../api.ts";
type HealthStatus = "connected" | "disconnected" | "reconnecting";
type Props = {
onRun: () => void;
};
function statusLabel(status: HealthStatus): { text: string; color: string } {
if (status === "connected") {
return { text: "● Connected", color: "var(--color-success)" };
}
if (status === "reconnecting") {
return { text: "● Reconnecting...", color: "var(--color-warning, #f59e0b)" };
}
return { text: "● Offline", color: "var(--color-error)" };
}
export function StatusBar({ onRun }: Props) {
const [status, setStatus] = useState<HealthStatus>("disconnected");
const wasConnectedRef = useRef(false);
const checkHealth = useCallback(async () => {
try {
await getHealth();
wasConnectedRef.current = true;
setStatus("connected");
} catch {
if (wasConnectedRef.current) {
setStatus("reconnecting");
} else {
setStatus("disconnected");
}
}
}, []);
useEffect(() => {
checkHealth();
const interval = setInterval(checkHealth, 10_000);
return () => clearInterval(interval);
}, [checkHealth]);
const label = statusLabel(status);
return (
<div
className="flex items-center justify-between px-6 py-2 text-xs border-b"
style={{ borderColor: "var(--color-border)", background: "var(--color-surface)" }}
>
<div className="flex items-center gap-4">
<span style={{ color: "var(--color-text-muted)" }}>Local API: 127.0.0.1:7860</span>
<button
type="button"
onClick={onRun}
className="px-3 py-1 rounded text-xs font-medium"
style={{ background: "var(--color-accent)", color: "#fff" }}
>
Run Thread
</button>
</div>
<span style={{ color: label.color }}>{label.text}</span>
</div>
);
}
@@ -0,0 +1,143 @@
import { useEffect, useRef, useState } from "react";
import { getThread, killThread, pauseThread, resumeThread } from "../api.ts";
import { useFetch } from "../hooks.ts";
import { useSSE } from "../use-sse.ts";
type Props = {
threadId: string;
onBack: () => void;
};
export function ThreadDetail({ threadId, onBack }: Props) {
const sse = useSSE(threadId);
const { status, data, error } = useFetch(() => getThread(threadId), [threadId]);
const [actionStatus, setActionStatus] = useState<string | null>(null);
const recordsEndRef = useRef<HTMLDivElement>(null);
const liveActive = sse.connected && !sse.completed;
const records = liveActive
? sse.records
: status === "ok"
? data.records
: ([] as typeof sse.records);
// biome-ignore lint/correctness/useExhaustiveDependencies: scroll when the rendered record list grows
useEffect(() => {
recordsEndRef.current?.scrollIntoView({ behavior: "smooth" });
}, [records.length]);
async function handleAction(action: "kill" | "pause" | "resume") {
setActionStatus(`${action}ing...`);
try {
const fn = action === "kill" ? killThread : action === "pause" ? pauseThread : resumeThread;
await fn(threadId);
setActionStatus(`${action} sent ✓`);
} catch (e) {
setActionStatus(`${action} failed: ${e instanceof Error ? e.message : String(e)}`);
}
}
return (
<div>
<div className="flex items-center justify-between mb-4">
<button
type="button"
onClick={onBack}
className="text-sm hover:underline"
style={{ color: "var(--color-accent)" }}
>
Back to threads
</button>
<div className="flex gap-2">
<button
type="button"
onClick={() => handleAction("pause")}
className="px-3 py-1 text-xs rounded border"
style={{ borderColor: "var(--color-warning)", color: "var(--color-warning)" }}
>
Pause
</button>
<button
type="button"
onClick={() => handleAction("resume")}
className="px-3 py-1 text-xs rounded border"
style={{ borderColor: "var(--color-success)", color: "var(--color-success)" }}
>
Resume
</button>
<button
type="button"
onClick={() => handleAction("kill")}
className="px-3 py-1 text-xs rounded border"
style={{ borderColor: "var(--color-error)", color: "var(--color-error)" }}
>
Kill
</button>
</div>
</div>
<h2 className="text-xl font-semibold mb-2 font-mono flex items-center gap-2 flex-wrap">
<span>{threadId}</span>
{sse.connected && (
<span
className="text-xs font-medium px-2 py-0.5 rounded"
style={{ background: "var(--color-success)", color: "var(--color-bg)" }}
>
Live
</span>
)}
</h2>
{actionStatus && (
<p className="text-xs mb-4" style={{ color: "var(--color-text-muted)" }}>
{actionStatus}
</p>
)}
{status === "loading" && !liveActive && records.length === 0 && (
<p style={{ color: "var(--color-text-muted)" }}>Loading...</p>
)}
{status === "error" && !liveActive && (
<p style={{ color: "var(--color-error)" }}>Error: {error}</p>
)}
{(status === "ok" || liveActive || records.length > 0) && (
<div className="space-y-3">
{records.map((r) => (
<div
key={`${threadId}-${r.type}-${String(r.timestamp)}-${r.role ?? ""}-${r.content ?? ""}`}
className="p-3 rounded border text-sm"
style={{ background: "var(--color-surface)", borderColor: "var(--color-border)" }}
>
<div className="flex items-center gap-2 mb-1">
<span
className="text-xs px-1.5 py-0.5 rounded font-mono"
style={{ background: "var(--color-border)", color: "var(--color-accent)" }}
>
{r.type}
</span>
{r.role && (
<span className="text-xs" style={{ color: "var(--color-text-muted)" }}>
{r.role}
</span>
)}
{r.timestamp !== null && (
<span className="text-xs ml-auto" style={{ color: "var(--color-text-muted)" }}>
{new Date(r.timestamp).toLocaleTimeString()}
</span>
)}
</div>
{r.content && (
<pre
className="whitespace-pre-wrap text-xs mt-1"
style={{ color: "var(--color-text)" }}
>
{typeof r.content === "string" ? r.content : JSON.stringify(r.content, null, 2)}
</pre>
)}
</div>
))}
<div ref={recordsEndRef} aria-hidden />
</div>
)}
</div>
);
}
@@ -0,0 +1,69 @@
import { listThreads } from "../api.ts";
import { useFetch } from "../hooks.ts";
type Props = {
onSelect: (id: string) => void;
};
export function ThreadList({ onSelect }: Props) {
const { status, data, error } = useFetch(() => listThreads(), []);
if (status === "loading")
return <p style={{ color: "var(--color-text-muted)" }}>Loading threads...</p>;
if (status === "error") return <p style={{ color: "var(--color-error)" }}>Error: {error}</p>;
const threads = data.threads;
return (
<div>
<h2 className="text-xl font-semibold mb-4">Threads</h2>
{threads.length === 0 ? (
<p style={{ color: "var(--color-text-muted)" }}>No threads found.</p>
) : (
<div className="space-y-2">
{threads.map((t) => (
<button
type="button"
key={t.threadId}
onClick={() => onSelect(t.threadId)}
className="w-full text-left p-4 rounded-lg border transition-colors hover:border-[var(--color-accent-dim)]"
style={{ background: "var(--color-surface)", borderColor: "var(--color-border)" }}
>
<div className="flex items-center justify-between">
<code className="text-sm font-mono" style={{ color: "var(--color-accent)" }}>
{t.threadId}
</code>
{t.status && (
<span
className="text-xs px-2 py-0.5 rounded"
style={{
background:
t.status === "running"
? "var(--color-success)"
: t.status === "failed"
? "var(--color-error)"
: "var(--color-text-muted)",
color: "#000",
}}
>
{t.status}
</span>
)}
</div>
{t.workflow && (
<p className="text-sm mt-1" style={{ color: "var(--color-text-muted)" }}>
{t.workflow}
</p>
)}
{t.startedAt && (
<p className="text-xs mt-1" style={{ color: "var(--color-text-muted)" }}>
{t.startedAt}
</p>
)}
</button>
))}
</div>
)}
</div>
);
}
@@ -0,0 +1,44 @@
import { listWorkflows } from "../api.ts";
import { useFetch } from "../hooks.ts";
export function WorkflowList() {
const { status, data, error } = useFetch(() => listWorkflows(), []);
if (status === "loading")
return <p style={{ color: "var(--color-text-muted)" }}>Loading workflows...</p>;
if (status === "error") return <p style={{ color: "var(--color-error)" }}>Error: {error}</p>;
const workflows = data.workflows;
return (
<div>
<h2 className="text-xl font-semibold mb-4">Workflows</h2>
{workflows.length === 0 ? (
<p style={{ color: "var(--color-text-muted)" }}>No workflows registered.</p>
) : (
<div className="space-y-2">
{workflows.map((w) => (
<div
key={w.name}
className="p-4 rounded-lg border"
style={{ background: "var(--color-surface)", borderColor: "var(--color-border)" }}
>
<div className="flex items-center justify-between">
<span className="font-medium">{w.name}</span>
<span className="text-xs" style={{ color: "var(--color-text-muted)" }}>
{w.versions} version{w.versions !== 1 ? "s" : ""}
</span>
</div>
<code
className="text-xs mt-1 block font-mono"
style={{ color: "var(--color-accent)" }}
>
{w.currentHash}
</code>
</div>
))}
</div>
)}
</div>
);
}
+37
View File
@@ -0,0 +1,37 @@
import { useEffect, useState } from "react";
type FetchState<T> =
| { status: "loading"; data: null; error: null }
| { status: "ok"; data: T; error: null }
| { status: "error"; data: null; error: string };
export function useFetch<T>(fetcher: () => Promise<T>, deps: unknown[] = []): FetchState<T> {
const [state, setState] = useState<FetchState<T>>({
status: "loading",
data: null,
error: null,
});
useEffect(() => {
let cancelled = false;
setState({ status: "loading", data: null, error: null });
fetcher()
.then((data) => {
if (!cancelled) setState({ status: "ok", data, error: null });
})
.catch((err: unknown) => {
if (!cancelled)
setState({
status: "error",
data: null,
error: err instanceof Error ? err.message : String(err),
});
});
return () => {
cancelled = true;
};
// biome-ignore lint/correctness/useExhaustiveDependencies: this helper intentionally accepts caller-provided dependency arrays
}, deps);
return state;
}
+21
View File
@@ -0,0 +1,21 @@
@import "tailwindcss";
:root {
--color-bg: #0a0a0f;
--color-surface: #12121a;
--color-border: #1e1e2e;
--color-text: #e4e4ef;
--color-text-muted: #6b6b8a;
--color-accent: #7c6df0;
--color-accent-dim: #5a4db8;
--color-success: #34d399;
--color-warning: #fbbf24;
--color-error: #f87171;
}
body {
margin: 0;
background: var(--color-bg);
color: var(--color-text);
font-family: "Inter", system-ui, -apple-system, sans-serif;
}
+13
View File
@@ -0,0 +1,13 @@
import { StrictMode } from "react";
import { createRoot } from "react-dom/client";
import "./index.css";
import { App } from "./app.tsx";
const root = document.getElementById("root");
if (root) {
createRoot(root).render(
<StrictMode>
<App />
</StrictMode>,
);
}
+64
View File
@@ -0,0 +1,64 @@
import { useCallback, useEffect, useState } from "react";
type View = "threads" | "workflows";
type HashRoute = {
view: View;
threadId: string | null;
};
function parseHash(hash: string): HashRoute {
const raw = hash.replace(/^#\/?/, "");
if (raw.startsWith("threads/")) {
const id = raw.slice("threads/".length);
if (id.length > 0) {
return { view: "threads", threadId: id };
}
}
if (raw === "workflows") {
return { view: "workflows", threadId: null };
}
return { view: "threads", threadId: null };
}
function buildHash(route: HashRoute): string {
if (route.view === "workflows") {
return "#workflows";
}
if (route.threadId !== null) {
return `#threads/${route.threadId}`;
}
return "#threads";
}
export function useHashRoute(): {
view: View;
threadId: string | null;
setView: (v: View) => void;
setThreadId: (id: string | null) => void;
} {
const [route, setRoute] = useState<HashRoute>(() => parseHash(window.location.hash));
useEffect(() => {
function onHashChange(): void {
setRoute(parseHash(window.location.hash));
}
window.addEventListener("hashchange", onHashChange);
return () => window.removeEventListener("hashchange", onHashChange);
}, []);
const navigate = useCallback((next: HashRoute) => {
const hash = buildHash(next);
window.location.hash = hash;
setRoute(next);
}, []);
const setView = useCallback((v: View) => navigate({ view: v, threadId: null }), [navigate]);
const setThreadId = useCallback(
(id: string | null) => navigate({ view: "threads", threadId: id }),
[navigate],
);
return { view: route.view, threadId: route.threadId, setView, setThreadId };
}
+161
View File
@@ -0,0 +1,161 @@
import {
type Dispatch,
type MutableRefObject,
type SetStateAction,
useEffect,
useRef,
useState,
} from "react";
import type { ThreadRecord } from "./api.ts";
export type UseSSEReturn = {
records: ThreadRecord[];
connected: boolean;
completed: boolean;
};
function isWorkflowResult(record: ThreadRecord): boolean {
return record.type === "workflow-result";
}
function parseRecord(data: string): ThreadRecord | null {
try {
return JSON.parse(data) as ThreadRecord;
} catch {
return null;
}
}
type RecordEventContext = {
cancelled: boolean;
completedRef: MutableRefObject<boolean>;
setRecords: Dispatch<SetStateAction<ThreadRecord[]>>;
setCompleted: (value: boolean) => void;
setConnected: (value: boolean) => void;
cleanupEs: () => void;
};
function handleRecordEvent(ev: Event, ctx: RecordEventContext): void {
if (ctx.cancelled) {
return;
}
const msg = ev as MessageEvent;
const raw = typeof msg.data === "string" ? msg.data : "";
const parsed = parseRecord(raw);
if (parsed === null) {
return;
}
ctx.setRecords((prev) => [...prev, parsed]);
if (!isWorkflowResult(parsed)) {
return;
}
ctx.completedRef.current = true;
ctx.setCompleted(true);
ctx.setConnected(false);
ctx.cleanupEs();
}
export function useSSE(threadId: string | null): UseSSEReturn {
const [records, setRecords] = useState<ThreadRecord[]>([]);
const [connected, setConnected] = useState(false);
const [completed, setCompleted] = useState(false);
const completedRef = useRef(false);
const reconnectAttemptsRef = useRef(0);
useEffect(() => {
if (threadId === null) {
completedRef.current = false;
reconnectAttemptsRef.current = 0;
setRecords([]);
setConnected(false);
setCompleted(false);
return;
}
const tid = threadId;
completedRef.current = false;
reconnectAttemptsRef.current = 0;
setRecords([]);
setConnected(false);
setCompleted(false);
let es: EventSource | null = null;
let reconnectTimer: ReturnType<typeof setTimeout> | null = null;
let cancelled = false;
function cleanupEs(): void {
if (es !== null) {
es.close();
es = null;
}
}
function scheduleReconnect(): void {
if (cancelled || completedRef.current) {
return;
}
const delayMs = Math.min(1000 * 2 ** reconnectAttemptsRef.current, 8000);
reconnectAttemptsRef.current += 1;
reconnectTimer = setTimeout(() => {
reconnectTimer = null;
if (!cancelled && !completedRef.current) {
connect();
}
}, delayMs);
}
function connect(): void {
if (cancelled || completedRef.current) {
return;
}
cleanupEs();
const url = `/api/threads/${encodeURIComponent(tid)}/live`;
es = new EventSource(url);
es.onopen = () => {
if (cancelled) {
return;
}
reconnectAttemptsRef.current = 0;
setConnected(true);
setRecords([]);
};
es.addEventListener("record", (ev: Event) =>
handleRecordEvent(ev, {
cancelled,
completedRef,
setRecords,
setCompleted,
setConnected,
cleanupEs,
}),
);
es.onerror = () => {
if (cancelled || completedRef.current) {
return;
}
setConnected(false);
cleanupEs();
scheduleReconnect();
};
}
connect();
return () => {
cancelled = true;
if (reconnectTimer !== null) {
clearTimeout(reconnectTimer);
}
cleanupEs();
};
}, [threadId]);
return { records, connected, completed };
}
+17
View File
@@ -0,0 +1,17 @@
{
"compilerOptions": {
"target": "ES2022",
"lib": ["ES2022", "DOM", "DOM.Iterable"],
"module": "ESNext",
"moduleResolution": "bundler",
"strict": true,
"jsx": "react-jsx",
"esModuleInterop": true,
"skipLibCheck": true,
"forceConsistentCasingInFileNames": true,
"resolveJsonModule": true,
"isolatedModules": true,
"noEmit": true
},
"include": ["src"]
}
+17
View File
@@ -0,0 +1,17 @@
import tailwindcss from "@tailwindcss/vite";
import react from "@vitejs/plugin-react";
import { defineConfig } from "vite";
// biome-ignore lint/style/noDefaultExport: Vite loads config from default export.
export default defineConfig({
plugins: [react(), tailwindcss()],
server: {
port: 5173,
proxy: {
"/api": {
target: "http://127.0.0.1:7860",
changeOrigin: true,
},
},
},
});
@@ -1,5 +1,5 @@
import { describe, expect, test } from "bun:test";
import type { ExtractContext, ExtractFn } from "@uncaged/workflow";
import type { ExtractContext, ExtractFn } from "@uncaged/workflow-runtime";
import type * as z from "zod/v4";
import { createCursorAgent, validateCursorAgentConfig } from "../src/index.js";
+1 -1
View File
@@ -8,7 +8,7 @@
"test": "bun test"
},
"dependencies": {
"@uncaged/workflow": "workspace:*",
"@uncaged/workflow-runtime": "workspace:*",
"@uncaged/workflow-util-agent": "workspace:*",
"zod": "^4.0.0"
}
+1 -1
View File
@@ -1,4 +1,4 @@
import type { AgentFn, ExtractContext } from "@uncaged/workflow";
import type { AgentFn, ExtractContext } from "@uncaged/workflow-runtime";
import { buildAgentPrompt, type SpawnCliError, spawnCli } from "@uncaged/workflow-util-agent";
import * as z from "zod/v4";
+1 -1
View File
@@ -1,4 +1,4 @@
import type { ExtractFn } from "@uncaged/workflow";
import type { ExtractFn } from "@uncaged/workflow-runtime";
export type CursorAgentConfig = {
model: string | null;
@@ -1,4 +1,4 @@
import { err, ok, type Result } from "@uncaged/workflow";
import { err, ok, type Result } from "@uncaged/workflow-runtime";
import type { CursorAgentConfig } from "./types.js";
+1 -1
View File
@@ -8,7 +8,7 @@
"test": "bun test"
},
"dependencies": {
"@uncaged/workflow": "workspace:*",
"@uncaged/workflow-runtime": "workspace:*",
"@uncaged/workflow-util-agent": "workspace:*"
}
}
+1 -1
View File
@@ -1,4 +1,4 @@
import type { AgentFn } from "@uncaged/workflow";
import type { AgentFn } from "@uncaged/workflow-runtime";
import { buildAgentPrompt, type SpawnCliError, spawnCli } from "@uncaged/workflow-util-agent";
import type { HermesAgentConfig } from "./types.js";
@@ -1,4 +1,4 @@
import { err, ok, type Result } from "@uncaged/workflow";
import { err, ok, type Result } from "@uncaged/workflow-runtime";
import type { HermesAgentConfig } from "./types.js";
@@ -1,15 +1,9 @@
import { describe, expect, test } from "bun:test";
import { mkdtempSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { createCasStore, START, type ThreadContext } from "@uncaged/workflow";
import { type AgentContext, START } from "@uncaged/workflow-runtime";
import { createLlmAdapter } from "../src/create-llm-adapter.js";
const casDir = mkdtempSync(join(tmpdir(), "wf-llm-adapter-cas-"));
const testCas = createCasStore(casDir);
function makeCtx(userContent: string): ThreadContext {
function makeCtx(userContent: string): AgentContext {
return {
start: {
role: START,
@@ -21,7 +15,6 @@ function makeCtx(userContent: string): ThreadContext {
steps: [],
threadId: "01TEST000000000000000000TR",
currentRole: { name: "planner", systemPrompt: "system instructions" },
cas: testCas,
};
}
+2 -1
View File
@@ -8,6 +8,7 @@
"test": "bun test"
},
"dependencies": {
"@uncaged/workflow": "workspace:*"
"@uncaged/workflow": "workspace:*",
"@uncaged/workflow-runtime": "workspace:*"
}
}
@@ -5,7 +5,7 @@ import {
type LlmProvider,
ok,
type Result,
} from "@uncaged/workflow";
} from "@uncaged/workflow-runtime";
/** OpenAI chat completion message shape (passed to `/chat/completions`). */
export type LlmMessage = { role: "system" | "user" | "assistant"; content: string };
+16
View File
@@ -0,0 +1,16 @@
{
"name": "@uncaged/workflow-runtime",
"version": "0.2.0",
"type": "module",
"main": "src/index.ts",
"types": "src/index.ts",
"scripts": {
"test": "bun test"
},
"peerDependencies": {
"zod": "^4.0.0"
},
"devDependencies": {
"zod": "^4.0.0"
}
}
@@ -0,0 +1,170 @@
import type * as z from "zod/v4";
import {
type AgentBinding,
type AgentContext,
type AgentFn,
type CasStore,
END,
type ExtractContext,
type ModeratorContext,
type RoleDefinition,
type RoleMeta,
type RoleOutput,
type RoleStep,
START,
type ThreadContext,
type WorkflowCompletion,
type WorkflowDefinition,
type WorkflowFn,
type WorkflowRuntime,
} from "./types.js";
function isRoleNext<M extends RoleMeta>(
next: (keyof M & string) | typeof END,
): next is keyof M & string {
return next !== END;
}
function resolveExtractedRefs(
roleDef: RoleDefinition<Record<string, unknown>>,
meta: unknown,
): string[] {
const extractRefsFn = roleDef.extractRefs;
if (extractRefsFn === null || typeof extractRefsFn !== "function") {
return [];
}
return extractRefsFn(meta as Record<string, unknown>);
}
async function putContentBlob(store: CasStore, raw: string): Promise<string> {
return store.put(raw);
}
function agentForRole(binding: AgentBinding, roleName: string): AgentFn {
const overrides = binding.overrides;
const overrideFn: AgentFn | undefined =
overrides !== null ? overrides[roleName as keyof typeof overrides] : undefined;
return overrideFn !== undefined ? overrideFn : binding.agent;
}
type AdvanceOutcome<M extends RoleMeta> =
| { kind: "complete"; completion: WorkflowCompletion }
| { kind: "yield"; output: RoleOutput; step: RoleStep<M> };
async function advanceOneRound<M extends RoleMeta>(
def: Pick<WorkflowDefinition<M>, "roles" | "moderator">,
binding: AgentBinding,
params: {
thread: ModeratorContext<M>;
runtime: WorkflowRuntime;
},
): Promise<AdvanceOutcome<M>> {
const { thread, runtime } = params;
const modCtx: ModeratorContext<M> = thread;
const next = def.moderator(modCtx);
if (!isRoleNext(next)) {
return {
kind: "complete",
completion: { returnCode: 0, summary: "completed: moderator returned END" },
};
}
const roleDef = def.roles[next];
if (roleDef === undefined) {
return { kind: "complete", completion: { returnCode: 1, summary: `unknown role: ${next}` } };
}
const agentCtx: AgentContext<M> = {
...modCtx,
currentRole: { name: next, systemPrompt: roleDef.systemPrompt },
};
const agent = agentForRole(binding, next);
const raw = await agent(agentCtx as unknown as AgentContext);
const extractCtx: ExtractContext<M> = {
...agentCtx,
agentContent: raw,
};
const meta = await runtime.extract(
roleDef.schema as z.ZodType<Record<string, unknown>>,
roleDef.extractPrompt,
extractCtx as unknown as ExtractContext,
);
const contentHash = await putContentBlob(runtime.cas, raw);
const refsFromMeta = resolveExtractedRefs(
roleDef as unknown as RoleDefinition<Record<string, unknown>>,
meta,
);
const refs = refsFromMeta.includes(contentHash) ? refsFromMeta : [...refsFromMeta, contentHash];
const step = {
role: next,
contentHash,
meta,
refs,
timestamp: Date.now(),
} as RoleStep<M>;
return {
kind: "yield",
output: {
role: step.role,
contentHash: step.contentHash,
meta: step.meta,
refs: step.refs,
},
step,
};
}
/**
* Binds pure role definitions + moderator to runtime agents.
* Assign with `export const run = createWorkflow(def, binding)`.
*
* Structured meta extraction is delegated to {@link WorkflowRuntime.extract}, which the
* engine resolves from the workflow registry's `extract` scene.
*/
export function createWorkflow<M extends RoleMeta>(
def: Pick<WorkflowDefinition<M>, "roles" | "moderator">,
binding: AgentBinding,
): WorkflowFn {
return async function* workflowLoop(
thread: ThreadContext,
runtime: WorkflowRuntime,
): AsyncGenerator<RoleOutput, WorkflowCompletion> {
if (thread.start.role !== START) {
throw new Error(`workflow loop expected start role to be ${START}`);
}
const maxRounds = thread.start.meta.maxRounds;
let currentThread = thread as ModeratorContext<M>;
while (true) {
if (currentThread.steps.length >= maxRounds) {
return {
returnCode: 0,
summary: `completed: reached maxRounds (${maxRounds})`,
};
}
const outcome = await advanceOneRound(def, binding, {
thread: currentThread,
runtime,
});
if (outcome.kind === "complete") {
return outcome.completion;
}
yield outcome.output;
currentThread = {
...currentThread,
steps: [...currentThread.steps, outcome.step],
};
}
};
}
+29
View File
@@ -0,0 +1,29 @@
export { createWorkflow } from "./create-workflow.js";
export { err, ok } from "./result.js";
export type {
AgentBinding,
AgentContext,
AgentFn,
CasStore,
ExtractContext,
ExtractFn,
LlmProvider,
Moderator,
ModeratorContext,
Result,
RoleDefinition,
RoleMeta,
RoleOutput,
RoleStep,
StartStep,
ThreadContext,
WorkflowCompletion,
WorkflowDefinition,
WorkflowDescriptor,
WorkflowFn,
WorkflowResult,
WorkflowRoleDescriptor,
WorkflowRoleSchema,
WorkflowRuntime,
} from "./types.js";
export { END, START } from "./types.js";
+9
View File
@@ -0,0 +1,9 @@
import type { Result } from "./types.js";
export function ok<T>(value: T): Result<T, never> {
return { ok: true, value };
}
export function err<E>(error: E): Result<never, E> {
return { ok: false, error };
}
@@ -1,12 +1,33 @@
import type * as z from "zod/v4";
import type { CasStore } from "./cas/index.js";
import type { ExtractFn } from "./extract/types.js";
/** Sentinel values for automaton control flow. */
export const START = "__start__" as const;
export const END = "__end__" as const;
export type CasStore = {
put(content: string): Promise<string>;
get(hash: string): Promise<string | null>;
delete(hash: string): Promise<void>;
list(): Promise<string[]>;
};
/** JSON Schema fragment describing one role's `meta` shape (subset supported by code generation). */
export type WorkflowRoleSchema = Record<string, unknown>;
export type WorkflowRoleDescriptor = {
description: string;
schema: WorkflowRoleSchema;
};
/** Workflow metadata exported as `export const descriptor` from `.esm.js` bundles. */
export type WorkflowDescriptor = {
description: string;
roles: Record<string, WorkflowRoleDescriptor>;
};
/** Expected success/failure outcome without throwing for recoverable errors. */
export type Result<T, E = Error> = { ok: true; value: T } | { ok: false; error: E };
/** Maps role names → their meta types. Single generic drives all inference. */
export type RoleMeta = Record<string, Record<string, unknown>>;
@@ -17,9 +38,6 @@ export type LlmProvider = {
model: string;
};
/** How the engine runs meta extraction for a role after the agent phase. */
export type ExtractMode = "single" | "react";
/** What each generator yield produces — one role's output (engine adds `timestamp` when persisting). */
export type RoleOutput = {
role: string;
@@ -36,35 +54,23 @@ export type WorkflowCompletion = {
summary: string;
};
/** Final thread outcome from {@link executeThread}, including Merkle thread root CAS hash. */
/** Final thread outcome from executeThread, including Merkle thread root CAS hash. */
export type WorkflowResult = WorkflowCompletion & {
rootHash: string;
};
/** Input to a workflow — prompt plus optional historical steps for fork/resume. */
export type ThreadInput = {
prompt: string;
steps: RoleOutput[];
};
/** Options passed to a workflow bundle's `run` export (engine-provided). */
export type WorkflowFnOptions = {
threadId: string;
maxRounds: number;
/** Nesting depth for workflow-as-agent chains; root threads use `0`. */
depth: number;
/** Runtime dependencies passed to a workflow bundle's `run` export (engine-provided). */
export type WorkflowRuntime = {
/** Global CAS store for Merkle content blobs (role step bodies). */
cas: CasStore;
/** Structured meta extraction; resolved from workflow.yaml `extract` scene by the engine. */
extract: ExtractFn;
/** Provider for `extractMode: "react"` roles; same backing config as `extract`. */
llmProvider: LlmProvider | null;
};
/** Bundle contract — named export `run` is a function returning an AsyncGenerator. */
export type WorkflowFn = (
input: ThreadInput,
options: WorkflowFnOptions,
thread: ThreadContext,
runtime: WorkflowRuntime,
) => AsyncGenerator<RoleOutput, WorkflowCompletion>;
/** Engine start frame: initial prompt + thread identity. */
@@ -86,22 +92,24 @@ export type RoleStep<M extends RoleMeta> = {
};
}[keyof M & string];
/** Phase 1: Moderator decides next role. */
export type ModeratorContext<M extends RoleMeta = RoleMeta> = {
/** Thread runtime context shared by moderator/agent/extractor phases. */
export type ThreadContext<M extends RoleMeta = RoleMeta> = {
threadId: string;
/** Same as `WorkflowFnOptions.depth` for the active thread. */
/** Nesting depth for workflow-as-agent chains; root threads use `0`. */
depth: number;
start: StartStep;
steps: RoleStep<M>[];
};
/** Phase 1: Moderator decides next role. */
export type ModeratorContext<M extends RoleMeta = RoleMeta> = ThreadContext<M>;
/** Phase 2: Agent executes — knows its role and prompt. */
export type AgentContext<M extends RoleMeta = RoleMeta> = ModeratorContext<M> & {
currentRole: {
name: string;
systemPrompt: string;
};
cas: CasStore;
};
/** Phase 3: Extractor runs — has agent output; the extraction instruction is a separate argument to the extract function. */
@@ -109,16 +117,19 @@ export type ExtractContext<M extends RoleMeta = RoleMeta> = AgentContext<M> & {
agentContent: string;
};
/** Alias — most external consumers see the agent-phase context. */
export type ThreadContext<M extends RoleMeta = RoleMeta> = AgentContext<M>;
export type ExtractFn = <T extends Record<string, unknown>>(
schema: z.ZodType<T>,
prompt: string,
ctx: ExtractContext,
) => Promise<T>;
/** Raw string output from an LLM/CLI adapter; meta is extracted by the engine. */
export type AgentFn = (ctx: AgentContext) => Promise<string>;
/** Runtime agent assignment (optional per-role overrides). */
/** Runtime agent assignment (explicit null when no per-role overrides). */
export type AgentBinding = {
agent: AgentFn;
overrides?: Partial<Record<string, AgentFn>>;
overrides: Partial<Record<string, AgentFn>> | null;
};
/** Role wiring: prompts, schema, and human-readable description. */
@@ -129,7 +140,6 @@ export type RoleDefinition<Meta extends Record<string, unknown>> = {
schema: z.ZodType<Meta>;
/** When non-null, produces CAS hashes to persist on this role's steps (see `RoleOutput.refs`). */
extractRefs: ((meta: Meta) => string[]) | null;
extractMode: ExtractMode;
};
/**
@@ -148,3 +158,8 @@ export type WorkflowDefinition<M extends RoleMeta> = {
roles: { [K in keyof M & string]: RoleDefinition<M[K]> };
moderator: Moderator<M>;
};
/** Internal outcome of advancing one moderator round inside {@link createWorkflow}. */
export type AdvanceOutcome<M extends RoleMeta> =
| { kind: "complete"; completion: WorkflowCompletion }
| { kind: "yield"; output: RoleOutput; step: RoleStep<M> };
+21
View File
@@ -0,0 +1,21 @@
{
"compilerOptions": {
"target": "ES2022",
"lib": ["ES2022"],
"module": "NodeNext",
"moduleResolution": "NodeNext",
"strict": true,
"exactOptionalPropertyTypes": true,
"esModuleInterop": true,
"skipLibCheck": true,
"forceConsistentCasingInFileNames": true,
"declaration": true,
"declarationMap": true,
"sourceMap": true,
"composite": true,
"outDir": "dist",
"rootDir": "src",
"types": ["bun-types"]
},
"include": ["src/**/*.ts"]
}
+4 -5
View File
@@ -2,7 +2,7 @@
Reference **develop** workflow template: plan phases, implement in a loop, review, test, then commit.
Export a `WorkflowDefinition` and `createDevelopRun` so a host can bind agents/LLM and run the same graph the bundled `.esm.js` would use. Use `buildDevelopDescriptor()` when assembling `descriptor` metadata for a bundle.
Export a pure `WorkflowDefinition` (`developWorkflowDefinition`) and role/moderator pieces. Workflow instantiation (`createWorkflow(definition, binding)`) happens in the workflow instance layer, not in this template package.
## Install
@@ -15,10 +15,10 @@ In this monorepo: `workspace:*` for `@uncaged/workflow-template-develop` and `@u
## Usage
```typescript
import { createDevelopRun, developWorkflowDefinition } from "@uncaged/workflow-template-develop";
import { createWorkflow } from "@uncaged/workflow";
import { developWorkflowDefinition } from "@uncaged/workflow-template-develop";
const run = createDevelopRun(binding, extract, llmProvider);
// run(...) executes the develop moderator graph with your AgentBinding
const run = createWorkflow(developWorkflowDefinition, binding);
```
## Roles
@@ -46,7 +46,6 @@ Also exported: role factories/meta schemas (`plannerRole`, `coderRole`, …), `D
| Export | Description |
|--------|-------------|
| `createDevelopRun` | `createWorkflow(developWorkflowDefinition, …)` factory |
| `developWorkflowDefinition` | `description`, `roles`, `developModerator` |
| `developModerator` | `Moderator<DevelopMeta>` |
| `buildDevelopDescriptor` | `buildDescriptor({ … })` for bundle metadata |
@@ -1,11 +1,6 @@
import { describe, expect, test } from "bun:test";
import {
END,
type ModeratorContext,
type RoleStep,
START,
validateWorkflowDescriptor,
} from "@uncaged/workflow";
import { validateWorkflowDescriptor } from "@uncaged/workflow";
import { END, type ModeratorContext, type RoleStep, START } from "@uncaged/workflow-runtime";
import { buildDevelopDescriptor } from "../src/descriptor.js";
import { developModerator } from "../src/index.js";
import type { CommitterMeta, PlannerMeta } from "../src/roles/index.js";
@@ -9,6 +9,7 @@
},
"dependencies": {
"@uncaged/workflow": "workspace:*",
"@uncaged/workflow-runtime": "workspace:*",
"zod": "^4.0.0"
}
}
@@ -1,9 +1,4 @@
import {
type AgentBinding,
createWorkflow,
type WorkflowDefinition,
type WorkflowFn,
} from "@uncaged/workflow";
import type { WorkflowDefinition } from "@uncaged/workflow-runtime";
import { developModerator } from "./moderator.js";
import { DEVELOP_WORKFLOW_DESCRIPTION, type DevelopMeta, developRoles } from "./roles.js";
@@ -40,7 +35,3 @@ export const developWorkflowDefinition: WorkflowDefinition<DevelopMeta> = {
roles: developRoles,
moderator: developModerator,
};
export function createDevelopRun(binding: AgentBinding): WorkflowFn {
return createWorkflow(developWorkflowDefinition, binding);
}
@@ -1,5 +1,5 @@
import type { Moderator, ModeratorContext } from "@uncaged/workflow";
import { END } from "@uncaged/workflow";
import type { Moderator, ModeratorContext } from "@uncaged/workflow-runtime";
import { END } from "@uncaged/workflow-runtime";
import type { DevelopMeta } from "./roles.js";
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import { type CoderMeta, coderRole } from "./roles/coder.js";
import { type CommitterMeta, committerRole } from "./roles/committer.js";
import { type PlannerMeta, plannerRole } from "./roles/planner.js";
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const coderMetaSchema = z.object({
@@ -31,5 +31,4 @@ export const coderRole: RoleDefinition<CoderMeta> = {
"Extract completedPhase: the planner phase hash finished this round (exact hash string from the plan). If multiple phases were finished in one round, use the last finished phase hash. Extract filesChanged and a summary of the work.",
schema: coderMetaSchema,
extractRefs: (meta) => [meta.completedPhase],
extractMode: "single",
};
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const committerMetaSchema = z.discriminatedUnion("status", [
@@ -32,5 +32,4 @@ export const committerRole: RoleDefinition<CommitterMeta> = {
"Extract the commit result: committed (with branch and SHA), recoverable failure, or unrecoverable failure. Include error details and log references if applicable.",
schema: committerMetaSchema,
extractRefs: null,
extractMode: "single",
};
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const phaseSchema = z.object({
@@ -48,5 +48,4 @@ export const plannerRole: RoleDefinition<PlannerMeta> = {
"Extract the implementation phases from the agent's output. Each phase has a hash (the CAS content-hash returned by the cas put command) and a title (one-line summary).",
schema: plannerMetaSchema,
extractRefs: (meta) => meta.phases.map((p) => p.hash),
extractMode: "single",
};
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const reviewerMetaSchema = z.discriminatedUnion("status", [
@@ -41,5 +41,4 @@ export const reviewerRole: RoleDefinition<ReviewerMeta> = {
"Extract the review verdict: approved or rejected. If rejected, list the blocking issues.",
schema: reviewerMetaSchema,
extractRefs: null,
extractMode: "single",
};
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const testerMetaSchema = z.discriminatedUnion("status", [
@@ -23,5 +23,4 @@ export const testerRole: RoleDefinition<TesterMeta> = {
"Extract the verification result: passed with summary details, or failed with details of what broke.",
schema: testerMetaSchema,
extractRefs: null,
extractMode: "single",
};
@@ -2,7 +2,7 @@
Reference **solve-issue** workflow template: prepare a repo, delegate implementation to the **develop** workflow, then submit (e.g. open a PR).
`createSolveIssueRun` wires the `developer` role to `workflowAsAgent("develop")` by default; `binding.overrides.developer` wins if you pass one (for tests or custom hosts).
This package exports a pure `WorkflowDefinition` (`solveIssueWorkflowDefinition`). Workflow instantiation (`createWorkflow(definition, binding)`) and any role-specific agent wiring (for example delegating `developer` to `workflowAsAgent("develop")`) are done in the workflow instance layer.
## Install
@@ -15,9 +15,10 @@ In this monorepo: `workspace:*` for this package and `@uncaged/workflow`.
## Usage
```typescript
import { createSolveIssueRun, solveIssueWorkflowDefinition } from "@uncaged/workflow-template-solve-issue";
import { createWorkflow } from "@uncaged/workflow";
import { solveIssueWorkflowDefinition } from "@uncaged/workflow-template-solve-issue";
const run = createSolveIssueRun(binding, extract, llmProvider);
const run = createWorkflow(solveIssueWorkflowDefinition, binding);
```
## Roles
@@ -41,7 +42,6 @@ Also exported: `preparerRole`, `developerRole`, `submitterRole` and their Zod me
| Export | Description |
|--------|-------------|
| `createSolveIssueRun` | Merges `developer` override with `workflowAsAgent("develop")`, then `createWorkflow` |
| `solveIssueWorkflowDefinition` | `description`, `roles`, `solveIssueModerator` |
| `solveIssueModerator` | Linear `Moderator<SolveIssueMeta>` |
| `buildSolveIssueDescriptor` | Descriptor helper for bundles |
@@ -5,15 +5,13 @@ import { join } from "node:path";
import {
createCasStore,
createExtract,
END,
type ModeratorContext,
type RoleStep,
START,
createWorkflow,
validateWorkflowDescriptor,
} from "@uncaged/workflow";
import { END, type ModeratorContext, type RoleStep, START } from "@uncaged/workflow-runtime";
import { buildSolveIssueDescriptor } from "../src/descriptor.js";
import type { DeveloperMeta } from "../src/developer.js";
import { createSolveIssueRun, solveIssueModerator } from "../src/index.js";
import { solveIssueModerator, solveIssueWorkflowDefinition } from "../src/index.js";
import type { PreparerMeta, SubmitterMeta } from "../src/roles/index.js";
import type { SolveIssueMeta } from "../src/roles.js";
@@ -24,46 +22,7 @@ function jsonResponse(payload: Record<string, unknown>): Response {
});
}
function readToolListFromBody(init: RequestInit | undefined): readonly Record<string, unknown>[] {
if (init === undefined || init.body === undefined || init.body === null) {
return [];
}
const body = JSON.parse(String(init.body)) as Record<string, unknown>;
const tools = body.tools;
if (!Array.isArray(tools)) {
return [];
}
return tools.filter((t): t is Record<string, unknown> => t !== null && typeof t === "object");
}
function singleToolName(tools: readonly Record<string, unknown>[]): string {
if (tools.length === 0) {
return "extract";
}
const fn = tools[0].function as Record<string, unknown> | undefined;
return typeof fn?.name === "string" ? fn.name : "extract";
}
function buildSingleModeResponse(args: Record<string, unknown>, toolName: string): Response {
return jsonResponse({
choices: [
{
message: {
tool_calls: [
{
type: "function",
function: { name: toolName, arguments: JSON.stringify(args) },
},
],
},
},
],
});
}
function buildReactModeResponse(args: Record<string, unknown>): Response {
// reactExtract accepts a plain-JSON assistant message and validates it
// directly against the schema, so we skip the cas_get / extract tool dance.
function buildPlainJsonResponse(args: Record<string, unknown>): Response {
return jsonResponse({
choices: [{ message: { content: JSON.stringify(args) } }],
});
@@ -74,18 +33,59 @@ function installMockChatCompletions(sequence: ReadonlyArray<Record<string, unkno
let i = 0;
const mockFetch = async (
_input: Parameters<typeof fetch>[0],
init?: RequestInit,
_init?: RequestInit,
): Promise<Response> => {
const args = sequence[i] ?? sequence[sequence.length - 1];
if (args === undefined) {
throw new Error("installMockChatCompletions: empty sequence");
}
i += 1;
const tools = readToolListFromBody(init);
if (tools.length > 1) {
return buildReactModeResponse(args);
return buildPlainJsonResponse(args);
};
globalThis.fetch = Object.assign(mockFetch, {
preconnect: origFetch.preconnect.bind(origFetch),
}) as typeof fetch;
return () => {
globalThis.fetch = origFetch;
};
}
function buildToolCallResponse(args: Record<string, unknown>): Response {
return jsonResponse({
choices: [
{
message: {
tool_calls: [
{
id: "tc_extract_1",
type: "function",
function: {
name: "extract",
arguments: JSON.stringify(args),
},
},
],
},
},
],
});
}
function installMockToolCallCompletions(
sequence: ReadonlyArray<Record<string, unknown>>,
): () => void {
const origFetch = globalThis.fetch;
let i = 0;
const mockFetch = async (
_input: Parameters<typeof fetch>[0],
_init?: RequestInit,
): Promise<Response> => {
const args = sequence[i] ?? sequence[sequence.length - 1];
if (args === undefined) {
throw new Error("installMockToolCallCompletions: empty sequence");
}
return buildSingleModeResponse(args, singleToolName(tools));
i += 1;
return buildToolCallResponse(args);
};
globalThis.fetch = Object.assign(mockFetch, {
preconnect: origFetch.preconnect.bind(origFetch),
@@ -161,17 +161,30 @@ function submitterStep(meta: SubmitterMeta): RoleStep<SolveIssueMeta> {
};
}
const stubExtract = createExtract({
baseUrl: "http://127.0.0.1:9",
apiKey: "",
model: "test",
});
function createStubExtract(casDir: string) {
return createExtract(
{
baseUrl: "http://127.0.0.1:9",
apiKey: "",
model: "test",
},
{ cas: createCasStore(casDir) },
);
}
const stubLlmProvider = {
baseUrl: "http://127.0.0.1:9",
apiKey: "",
model: "test",
};
function makeThread(prompt: string) {
return {
threadId: "01TEST000000000000000000TR",
depth: 0,
start: {
role: START,
content: prompt,
meta: { maxRounds: 20 },
timestamp: Date.now(),
},
steps: [],
};
}
describe("solveIssueModerator", () => {
test("routes initial → preparer → developer → submitter → END", () => {
@@ -219,7 +232,7 @@ describe("solveIssueModerator", () => {
});
});
describe("createSolveIssueRun", () => {
describe("solveIssueWorkflowDefinition + createWorkflow", () => {
let restoreFetch: (() => void) | null = null;
let casDir: string | undefined;
@@ -249,22 +262,48 @@ describe("createSolveIssueRun", () => {
casDir = await mkdtemp(join(tmpdir(), "solve-issue-cas-"));
const cas = createCasStore(casDir);
// Override developer so the test does not spin up a child workflow.
const run = createSolveIssueRun({
const run = createWorkflow(solveIssueWorkflowDefinition, {
agent: async () => "",
overrides: { developer: async () => "stub-root-hash" },
});
const gen = run(
{ prompt: "task", steps: [] },
{
threadId: "01TEST000000000000000000TR",
maxRounds: 20,
depth: 0,
cas,
extract: stubExtract,
llmProvider: stubLlmProvider,
const gen = run(makeThread("task"), {
cas,
extract: createStubExtract(casDir),
});
const first = await gen.next();
expect(first.done).toBe(false);
if (first.done) {
throw new Error("expected yield");
}
expect(first.value.role).toBe("preparer");
expect(first.value.meta).toEqual(EXPECT_PREPARER_META);
});
test("structured extraction also accepts tool_calls extraction path", async () => {
const EXPECT_PREPARER_META: PreparerMeta = {
repoPath: "/home/user/repos/tool-call",
defaultBranch: "main",
conventions: null,
toolchain: {
packageManager: "bun",
testCommand: "bun test",
lintCommand: null,
buildCommand: "bun run build",
},
);
};
restoreFetch = installMockToolCallCompletions([EXPECT_PREPARER_META]);
casDir = await mkdtemp(join(tmpdir(), "solve-issue-cas-"));
const cas = createCasStore(casDir);
const run = createWorkflow(solveIssueWorkflowDefinition, {
agent: async () => "",
overrides: { developer: async () => "stub-root-hash" },
});
const gen = run(makeThread("task"), {
cas,
extract: createStubExtract(casDir),
});
const first = await gen.next();
expect(first.done).toBe(false);
if (first.done) {
@@ -297,7 +336,7 @@ describe("createSolveIssueRun", () => {
const cas = createCasStore(casDir);
const calls: string[] = [];
const run = createSolveIssueRun({
const run = createWorkflow(solveIssueWorkflowDefinition, {
agent: async () => {
calls.push("default");
return "";
@@ -317,17 +356,10 @@ describe("createSolveIssueRun", () => {
},
},
});
const gen = run(
{ prompt: "task", steps: [] },
{
threadId: "01TEST000000000000000000TR",
maxRounds: 20,
depth: 0,
cas,
extract: stubExtract,
llmProvider: stubLlmProvider,
},
);
const gen = run(makeThread("task"), {
cas,
extract: createStubExtract(casDir),
});
await gen.next();
expect(calls).toEqual(["preparer"]);
@@ -339,58 +371,6 @@ describe("createSolveIssueRun", () => {
await gen.next();
expect(calls).toEqual(["submitter"]);
});
test("developer defaults to workflowAsAgent override (caller override still wins)", async () => {
const PREPARER_META: PreparerMeta = {
repoPath: "/tmp/r",
defaultBranch: "main",
conventions: null,
toolchain: { packageManager: null, testCommand: null, lintCommand: null, buildCommand: null },
};
const DEVELOPER_META: DeveloperMeta = {
branch: "feat/y",
commitSha: "def5678",
filesChanged: ["b.ts"],
summary: "more work",
};
restoreFetch = installMockChatCompletions([PREPARER_META, DEVELOPER_META]);
casDir = await mkdtemp(join(tmpdir(), "solve-issue-cas-"));
const cas = createCasStore(casDir);
let developerInvocations = 0;
const run = createSolveIssueRun({
agent: async () => "",
overrides: {
developer: async () => {
developerInvocations += 1;
return "stub-root-hash";
},
},
});
const gen = run(
{ prompt: "task", steps: [] },
{
threadId: "01TEST000000000000000000TR",
maxRounds: 20,
depth: 0,
cas,
extract: stubExtract,
llmProvider: stubLlmProvider,
},
);
// preparer
await gen.next();
// developer (caller override should be invoked, NOT workflowAsAgent default)
const devYield = await gen.next();
expect(devYield.done).toBe(false);
if (devYield.done) {
throw new Error("expected yield");
}
expect(devYield.value.role).toBe("developer");
expect(devYield.value.meta).toEqual(DEVELOPER_META);
expect(developerInvocations).toBe(1);
});
});
describe("buildSolveIssueDescriptor", () => {
@@ -32,8 +32,7 @@ describe("submitterRole", () => {
expect(submitterRole.systemPrompt).toContain("pull request");
});
test("uses single extract mode without refs", () => {
expect(submitterRole.extractMode).toBe("single");
test("has no refs extractor", () => {
expect(submitterRole.extractRefs).toBeNull();
});
});
@@ -9,6 +9,7 @@
},
"dependencies": {
"@uncaged/workflow": "workspace:*",
"@uncaged/workflow-runtime": "workspace:*",
"zod": "^4.0.0"
}
}
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const developerMetaSchema = z.object({
@@ -33,5 +33,4 @@ export const developerRole: RoleDefinition<DeveloperMeta> = {
extractPrompt: DEVELOPER_EXTRACT_PROMPT,
schema: developerMetaSchema,
extractRefs: () => [],
extractMode: "react",
};
@@ -1,10 +1,4 @@
import {
type AgentBinding,
createWorkflow,
type WorkflowDefinition,
type WorkflowFn,
workflowAsAgent,
} from "@uncaged/workflow";
import type { WorkflowDefinition } from "@uncaged/workflow-runtime";
import { solveIssueModerator } from "./moderator.js";
import { SOLVE_ISSUE_WORKFLOW_DESCRIPTION, type SolveIssueMeta, solveIssueRoles } from "./roles.js";
@@ -36,22 +30,3 @@ export const solveIssueWorkflowDefinition: WorkflowDefinition<SolveIssueMeta> =
roles: solveIssueRoles,
moderator: solveIssueModerator,
};
/**
* Build the solve-issue {@link WorkflowFn}.
*
* The `developer` role always delegates to the registered `develop` workflow via
* {@link workflowAsAgent}; if the caller supplies their own `developer` override in
* `binding.overrides`, it takes precedence so tests and custom hosts can stub it.
*/
export function createSolveIssueRun(binding: AgentBinding): WorkflowFn {
const developerOverride = binding.overrides?.developer ?? workflowAsAgent("develop");
const mergedBinding: AgentBinding = {
agent: binding.agent,
overrides: {
...(binding.overrides ?? {}),
developer: developerOverride,
},
};
return createWorkflow(solveIssueWorkflowDefinition, mergedBinding);
}
@@ -1,5 +1,5 @@
import type { Moderator } from "@uncaged/workflow";
import { END } from "@uncaged/workflow";
import type { Moderator } from "@uncaged/workflow-runtime";
import { END } from "@uncaged/workflow-runtime";
import type { SolveIssueMeta } from "./roles.js";
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import { type DeveloperMeta, developerRole } from "./developer.js";
import { type PreparerMeta, preparerRole } from "./roles/preparer.js";
import { type SubmitterMeta, submitterRole } from "./roles/submitter.js";
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
const toolchainSchema = z.object({
@@ -48,5 +48,4 @@ export const preparerRole: RoleDefinition<PreparerMeta> = {
"Extract repoPath (absolute path), defaultBranch, conventions (summary string or null), and toolchain (packageManager, testCommand, lintCommand, buildCommand — each string or null).",
schema: preparerMetaSchema,
extractRefs: null,
extractMode: "single",
};
@@ -1,4 +1,4 @@
import type { RoleDefinition } from "@uncaged/workflow";
import type { RoleDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
export const submitterMetaSchema = z.discriminatedUnion("status", [
@@ -40,5 +40,4 @@ export const submitterRole: RoleDefinition<SubmitterMeta> = {
extractPrompt: SUBMITTER_EXTRACT_PROMPT,
schema: submitterMetaSchema,
extractRefs: null,
extractMode: "single",
};
@@ -1,12 +1,9 @@
import { afterEach, beforeEach, describe, expect, test } from "bun:test";
import { mkdtemp, rm } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { createCasStore, putContentMerkleNode, START, type ThreadContext } from "@uncaged/workflow";
import { describe, expect, test } from "bun:test";
import { type AgentContext, START } from "@uncaged/workflow-runtime";
import { buildAgentPrompt } from "../src/index.js";
function startTask(content: string): ThreadContext["start"] {
function startTask(content: string): AgentContext["start"] {
return {
role: START,
content,
@@ -16,25 +13,13 @@ function startTask(content: string): ThreadContext["start"] {
}
describe("buildAgentPrompt", () => {
let casRoot: string;
beforeEach(async () => {
casRoot = await mkdtemp(join(tmpdir(), "wf-build-prompt-cas-"));
});
afterEach(async () => {
await rm(casRoot, { recursive: true, force: true });
});
test("includes system prompt and full task; omits tools when there are no steps", async () => {
const cas = createCasStore(casRoot);
const ctx: ThreadContext = {
const ctx: AgentContext = {
start: startTask("fix the bug"),
depth: 0,
steps: [],
threadId: "01TEST000000000000000000TR",
currentRole: { name: START, systemPrompt: "You are an agent." },
cas,
};
const text = await buildAgentPrompt(ctx);
expect(text).toContain("You are an agent.");
@@ -43,15 +28,13 @@ describe("buildAgentPrompt", () => {
expect(text).not.toContain("## Tools");
});
test("single step shows full content and meta, and includes tools", async () => {
const cas = createCasStore(casRoot);
const onlyHash = await putContentMerkleNode(cas, "only step full body");
const ctx: ThreadContext = {
test("single step shows hash and meta, and includes tools", async () => {
const onlyHash = "01HASHSINGLESTEP0000000001";
const ctx: AgentContext = {
start: startTask("user task"),
depth: 0,
threadId: "01TEST000000000000000000TR",
currentRole: { name: "coder", systemPrompt: "Be helpful." },
cas,
steps: [
{
role: "coder",
@@ -66,22 +49,20 @@ describe("buildAgentPrompt", () => {
expect(text).toContain("## Task");
expect(text).toContain("user task");
expect(text).toContain("## Step: coder");
expect(text).toContain("only step full body");
expect(text).toContain(`ContentHash: ${onlyHash}`);
expect(text).toContain('Meta: {"files":["a.ts"]}');
expect(text).toContain("## Tools");
expect(text).toContain("uncaged-workflow thread 01TEST000000000000000000TR");
});
test("two or more steps: previous steps are meta-only; latest step is full", async () => {
const cas = createCasStore(casRoot);
const plannerHash = await putContentMerkleNode(cas, "PLANNER_SECRET_FULL_TEXT");
const coderHash = await putContentMerkleNode(cas, "last step full content");
const ctx: ThreadContext = {
test("two or more steps: previous steps are meta-only; latest step includes hash", async () => {
const plannerHash = "01HASHPLANNER0000000000001";
const coderHash = "01HASHCODER0000000000000001";
const ctx: AgentContext = {
start: startTask("first message full: task content here"),
depth: 0,
threadId: "01TEST000000000000000000TR",
currentRole: { name: "coder", systemPrompt: "System." },
cas,
steps: [
{
role: "planner",
@@ -104,25 +85,22 @@ describe("buildAgentPrompt", () => {
expect(text).toContain("## Previous Steps");
expect(text).toContain("### Step 1: planner");
expect(text).toContain('Summary: {"plan":"short"}');
expect(text).not.toContain("PLANNER_SECRET_FULL_TEXT");
expect(text).toContain("## Latest Step: coder");
expect(text).toContain("last step full content");
expect(text).toContain(`ContentHash: ${coderHash}`);
expect(text).toContain('Meta: {"done":true}');
expect(text).toContain("## Tools");
expect(text).toContain("uncaged-workflow thread 01TEST000000000000000000TR");
});
test("middle steps show meta summary only, not full content", async () => {
const cas = createCasStore(casRoot);
const ha = await putContentMerkleNode(cas, "HIDDEN_A");
const hb = await putContentMerkleNode(cas, "HIDDEN_B_MIDDLE");
const hc = await putContentMerkleNode(cas, "VISIBLE_LAST");
const ctx: ThreadContext = {
test("middle steps show meta summary only and latest shows hash", async () => {
const ha = "01HASHA00000000000000000001";
const hb = "01HASHB00000000000000000001";
const hc = "01HASHC00000000000000000001";
const ctx: AgentContext = {
start: startTask("start"),
depth: 0,
threadId: "01TEST000000000000000000TR",
currentRole: { name: "c", systemPrompt: "S" },
cas,
steps: [
{
role: "a",
@@ -148,11 +126,9 @@ describe("buildAgentPrompt", () => {
],
};
const text = await buildAgentPrompt(ctx);
expect(text).not.toContain("HIDDEN_A");
expect(text).not.toContain("HIDDEN_B_MIDDLE");
expect(text).toContain('Summary: {"n":1}');
expect(text).toContain('Summary: {"n":2}');
expect(text).toContain("VISIBLE_LAST");
expect(text).toContain(`ContentHash: ${hc}`);
expect(text).toContain("## Latest Step: c");
});
});
+2 -1
View File
@@ -14,6 +14,7 @@
"test": "bun test"
},
"dependencies": {
"@uncaged/workflow": "workspace:*"
"@uncaged/workflow": "workspace:*",
"@uncaged/workflow-runtime": "workspace:*"
}
}
@@ -1,13 +1,4 @@
import type { AgentContext } from "@uncaged/workflow";
import { getContentMerklePayload } from "@uncaged/workflow";
async function resolveStepText(ctx: AgentContext, contentHash: string): Promise<string> {
const text = await getContentMerklePayload(ctx.cas, contentHash);
if (text === null) {
throw new Error(`buildAgentPrompt: missing CAS blob for ${contentHash}`);
}
return text;
}
import type { AgentContext } from "@uncaged/workflow-runtime";
/** Builds the full agent prompt: system instructions plus summarized thread history. */
export async function buildAgentPrompt(ctx: AgentContext): Promise<string> {
@@ -24,12 +15,10 @@ export async function buildAgentPrompt(ctx: AgentContext): Promise<string> {
if (steps.length === 1) {
const s = steps[0];
const body = await resolveStepText(ctx, s.contentHash);
lines.push("");
lines.push(`## Step: ${s.role}`);
lines.push("");
lines.push(body);
lines.push("");
lines.push(`ContentHash: ${s.contentHash}`);
lines.push(`Meta: ${JSON.stringify(s.meta)}`);
} else {
lines.push("");
@@ -41,12 +30,10 @@ export async function buildAgentPrompt(ctx: AgentContext): Promise<string> {
lines.push(`Summary: ${JSON.stringify(s.meta)}`);
}
const last = steps[steps.length - 1];
const lastBody = await resolveStepText(ctx, last.contentHash);
lines.push("");
lines.push(`## Latest Step: ${last.role}`);
lines.push("");
lines.push(lastBody);
lines.push("");
lines.push(`ContentHash: ${last.contentHash}`);
lines.push(`Meta: ${JSON.stringify(last.meta)}`);
}
@@ -1,6 +1,6 @@
import { spawn } from "node:child_process";
import { err, ok, type Result } from "@uncaged/workflow";
import { err, ok, type Result } from "@uncaged/workflow-runtime";
export type SpawnCliError =
| { kind: "non_zero_exit"; exitCode: number | null; stdout: string; stderr: string }
+1 -1
View File
@@ -29,7 +29,7 @@ import { createWorkflow, readWorkflowRegistry, executeThread } from "@uncaged/wo
| **Registry** | `readWorkflowRegistry`, `writeWorkflowRegistry`, `registerWorkflowVersion`, `workflowRegistryPath`, YAML helpers |
| **CAS** | `createCasStore`, Merkle helpers (`putStepMerkleNode`, `getContentMerklePayload`, …), `hashWorkflowBundleBytes` |
| **Engine** | `createWorkflow`, `executeThread`, `parseThreadDataJsonl`, fork helpers, `garbageCollectCas` |
| **Extract / LLM tools** | `llmExtract`, `reactExtract`, `createExtract`, `getExtractProvider` |
| **Extract / LLM tools** | `llmExtract`, `createExtract`, `createThreadReactor`, `createLlmFn`, `getExtractProvider` |
| **Agent bridge** | `workflowAsAgent` — expose a registered workflow as an agent-backed role |
| **Utilities** | `createLogger`, ULID / Crockford Base32 codecs, `getDefaultWorkflowStorageRoot`, paths |
@@ -1,9 +1,8 @@
import { describe, expect, test } from "bun:test";
import { END } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
import { buildDescriptor } from "../src/bundle/build-descriptor.js";
import { validateWorkflowDescriptor } from "../src/bundle/workflow-descriptor.js";
import { END } from "../src/types.js";
describe("buildDescriptor", () => {
test("produces a descriptor that validates and includes JSON schemas per role", () => {
@@ -23,7 +22,6 @@ describe("buildDescriptor", () => {
extractPrompt: "Extract title and count from the analysis.",
schema,
extractRefs: null,
extractMode: "single",
},
},
moderator: () => END,
@@ -39,6 +39,16 @@ export const run = async function* (_input, options) {
expect(r.ok).toBe(true);
});
test("allows static import of @uncaged/workflow-runtime", () => {
const source = `${minimalDescriptor}import { createWorkflow } from "@uncaged/workflow-runtime";
import { putContentMerkleNode } from "@uncaged/workflow";
export const run = createWorkflow({ description: "x", roles: {}, moderator: () => "END" }, {});
`;
const r = validateWorkflowBundle({ filePath: "/tmp/w.esm.js", source });
expect(r.ok).toBe(true);
});
test("rejects wrong filename suffix", () => {
const r = validateWorkflowBundle({
filePath: "/tmp/w.js",
+21 -9
View File
@@ -5,6 +5,11 @@ import { join } from "node:path";
import { createCasStore } from "../src/cas/cas.js";
import { hashString } from "../src/cas/hash.js";
import { createContentMerkleNode, serializeMerkleNode } from "../src/cas/merkle.js";
function casStoredForm(raw: string): string {
return serializeMerkleNode(createContentMerkleNode(raw));
}
describe("createCasStore", () => {
let casDir: string;
@@ -19,25 +24,30 @@ describe("createCasStore", () => {
test("put returns consistent hash for same content", async () => {
const cas = createCasStore(casDir);
const h1 = await cas.put("hello world");
const h2 = await cas.put("hello world");
const raw = "hello world";
const stored = casStoredForm(raw);
const h1 = await cas.put(raw);
const h2 = await cas.put(raw);
expect(h1).toBe(h2);
expect(h1).toBe(hashString(stored));
expect(h1).toHaveLength(13);
});
test("put returns hash matching hashString", async () => {
test("put returns hash matching hashString of merkle-stored form", async () => {
const cas = createCasStore(casDir);
const content = "some content to store";
const stored = casStoredForm(content);
const h = await cas.put(content);
expect(h).toBe(hashString(content));
expect(h).toBe(hashString(stored));
});
test("get returns stored content", async () => {
test("get returns merkle-serialized blob for raw puts", async () => {
const cas = createCasStore(casDir);
const content = "line1\nline2\nline3";
const stored = casStoredForm(content);
const h = await cas.put(content);
const retrieved = await cas.get(h);
expect(retrieved).toBe(content);
expect(retrieved).toBe(stored);
});
test("get returns null for missing hash", async () => {
@@ -76,11 +86,13 @@ describe("createCasStore", () => {
test("put is idempotent — same content written twice causes no error", async () => {
const cas = createCasStore(casDir);
const h1 = await cas.put("idempotent");
const h2 = await cas.put("idempotent");
const raw = "idempotent";
const stored = casStoredForm(raw);
const h1 = await cas.put(raw);
const h2 = await cas.put(raw);
expect(h1).toBe(h2);
const content = await cas.get(h1);
expect(content).toBe("idempotent");
expect(content).toBe(stored);
});
test("different content produces different hashes", async () => {
+18 -61
View File
@@ -2,8 +2,8 @@ import { afterEach, describe, expect, test } from "bun:test";
import { mkdir, mkdtemp, readFile, rm, writeFile } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { END } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
import { createCasStore } from "../src/cas/cas.js";
import {
createContentMerkleNode,
@@ -13,7 +13,6 @@ import {
} from "../src/cas/merkle.js";
import { createWorkflow } from "../src/engine/create-workflow.js";
import { executeThread } from "../src/engine/engine.js";
import { END } from "../src/types.js";
import { createLogger } from "../src/util/logger.js";
const plannerMetaSchema = z.object({
@@ -34,41 +33,17 @@ function installMockChatCompletions(sequence: ReadonlyArray<Record<string, unkno
const origFetch = globalThis.fetch;
let i = 0;
const mockFetch = async (
input: Parameters<typeof fetch>[0],
init?: RequestInit,
_input: Parameters<typeof fetch>[0],
_init?: RequestInit,
): Promise<Response> => {
const args = sequence[i] ?? sequence[sequence.length - 1];
if (args === undefined) {
throw new Error("installMockChatCompletions: empty sequence");
}
i += 1;
void input;
const body = init?.body ? (JSON.parse(String(init.body)) as Record<string, unknown>) : {};
const tools = body.tools;
const firstTool =
Array.isArray(tools) && tools.length > 0 && tools[0] !== null && typeof tools[0] === "object"
? (tools[0] as Record<string, unknown>)
: null;
const fn =
firstTool !== null ? (firstTool.function as Record<string, unknown> | undefined) : undefined;
const toolName = typeof fn?.name === "string" ? fn.name : "extract";
return new Response(
JSON.stringify({
choices: [
{
message: {
tool_calls: [
{
type: "function",
function: {
name: toolName,
arguments: JSON.stringify(args),
},
},
],
},
},
],
choices: [{ message: { content: JSON.stringify(args) } }],
}),
{ status: 200, headers: { "Content-Type": "application/json" } },
);
@@ -126,10 +101,10 @@ async function writeRegistryYaml(storageRoot: string, yaml: string): Promise<voi
await writeFile(join(storageRoot, "workflow.yaml"), yaml, "utf8");
}
/** Extract rounds use tool_calls; supervisor uses plain `content` (no tools). */
/** Extract and supervisor both run via {@link createThreadReactor}; differentiate by `body.model`. */
function installMockExtractThenSupervisor(params: {
extractArgs: ReadonlyArray<Record<string, unknown>>;
supervisorContent: string;
supervisorDecision: "continue" | "stop";
onSupervisorCall?: () => void;
}): () => void {
const origFetch = globalThis.fetch;
@@ -139,35 +114,18 @@ function installMockExtractThenSupervisor(params: {
init?: RequestInit,
): Promise<Response> => {
const body = init?.body ? (JSON.parse(String(init.body)) as Record<string, unknown>) : {};
const tools = body.tools;
const hasTools = Array.isArray(tools) && tools.length > 0;
if (hasTools) {
const model = typeof body.model === "string" ? body.model : "";
const isSupervisor = model.startsWith("supervisor-");
if (!isSupervisor) {
const args =
params.extractArgs[extractI] ?? params.extractArgs[params.extractArgs.length - 1];
if (args === undefined) {
throw new Error("installMockExtractThenSupervisor: empty extractArgs");
}
extractI += 1;
const firstTool = tools[0] as Record<string, unknown>;
const fn = firstTool.function as Record<string, unknown> | undefined;
const toolName = typeof fn?.name === "string" ? fn.name : "extract";
return new Response(
JSON.stringify({
choices: [
{
message: {
tool_calls: [
{
type: "function",
function: {
name: toolName,
arguments: JSON.stringify(args),
},
},
],
},
},
],
choices: [{ message: { content: JSON.stringify(args) } }],
}),
{ status: 200, headers: { "Content-Type": "application/json" } },
);
@@ -175,7 +133,9 @@ function installMockExtractThenSupervisor(params: {
params.onSupervisorCall?.();
return new Response(
JSON.stringify({
choices: [{ message: { content: params.supervisorContent } }],
choices: [
{ message: { content: JSON.stringify({ decision: params.supervisorDecision }) } },
],
}),
{ status: 200, headers: { "Content-Type": "application/json" } },
);
@@ -197,7 +157,6 @@ const demoWorkflow = createWorkflow<DemoMeta>(
extractPrompt: "Extract plan text and affected files list.",
schema: plannerMetaSchema,
extractRefs: null,
extractMode: "single",
},
coder: {
description: "Demo coder",
@@ -205,7 +164,6 @@ const demoWorkflow = createWorkflow<DemoMeta>(
extractPrompt: "Extract the code diff summary.",
schema: coderMetaSchema,
extractRefs: null,
extractMode: "single",
},
},
moderator: (ctx) => {
@@ -348,7 +306,7 @@ describe("executeThread", () => {
}
});
test("pre-filled ThreadInput.steps skips roles already present", async () => {
test("pre-filled input.steps skips roles already present", async () => {
restoreFetch = installMockChatCompletions([{ diff: "+ok" }]);
const root = await mkdtemp(join(tmpdir(), "wf-engine-fork-"));
@@ -554,7 +512,7 @@ describe("executeThread", () => {
}
});
test("extractMode react traverses CAS DAG via cas_get during extraction", async () => {
test("extract traverses CAS DAG via cas_get during extraction", async () => {
const dagMetaSchema = z.object({ leafPayload: z.string() });
type DagDemoMeta = { walker: z.infer<typeof dagMetaSchema> };
@@ -664,12 +622,11 @@ describe("executeThread", () => {
"Set leafPayload to the string payload of the content Merkle node under the root.",
schema: dagMetaSchema,
extractRefs: null,
extractMode: "react",
},
},
moderator: (ctx) => (ctx.steps.length === 0 ? "walker" : END),
},
{ agent: async () => dagRootHash },
{ agent: async () => dagRootHash, overrides: null },
);
const threadId = "01KQXKW18CT8G75T53R8F4G7YG";
@@ -719,7 +676,7 @@ describe("executeThread", () => {
test("supervisor stops thread when interval elapses and model returns stop", async () => {
restoreFetch = installMockExtractThenSupervisor({
extractArgs: [{ plan: "do-it", files: ["a.ts"] }, { diff: "+ok" }],
supervisorContent: "stop",
supervisorDecision: "stop",
});
const root = await mkdtemp(join(tmpdir(), "wf-engine-sup-stop-"));
@@ -770,7 +727,7 @@ describe("executeThread", () => {
let supervisorCalls = 0;
restoreFetch = installMockExtractThenSupervisor({
extractArgs: [{ plan: "do-it", files: ["a.ts"] }, { diff: "+ok" }],
supervisorContent: "stop",
supervisorDecision: "stop",
onSupervisorCall: () => {
supervisorCalls += 1;
},
@@ -2,13 +2,12 @@ import { afterEach, describe, expect, test } from "bun:test";
import { mkdir, mkdtemp, readFile, rm, writeFile } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { END } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
import { createCasStore } from "../src/cas/cas.js";
import { createWorkflow } from "../src/engine/create-workflow.js";
import { executeThread } from "../src/engine/engine.js";
import { buildForkPlan, parseThreadDataJsonl } from "../src/engine/fork-thread.js";
import { END } from "../src/types.js";
import { createLogger } from "../src/util/logger.js";
const phaseSchema = z.object({
@@ -28,41 +27,17 @@ function installMockChatCompletions(sequence: ReadonlyArray<Record<string, unkno
const origFetch = globalThis.fetch;
let i = 0;
const mockFetch = async (
input: Parameters<typeof fetch>[0],
init?: RequestInit,
_input: Parameters<typeof fetch>[0],
_init?: RequestInit,
): Promise<Response> => {
const args = sequence[i] ?? sequence[sequence.length - 1];
if (args === undefined) {
throw new Error("installMockChatCompletions: empty sequence");
}
i += 1;
void input;
const body = init?.body ? (JSON.parse(String(init.body)) as Record<string, unknown>) : {};
const tools = body.tools;
const firstTool =
Array.isArray(tools) && tools.length > 0 && tools[0] !== null && typeof tools[0] === "object"
? (tools[0] as Record<string, unknown>)
: null;
const fn =
firstTool !== null ? (firstTool.function as Record<string, unknown> | undefined) : undefined;
const toolName = typeof fn?.name === "string" ? fn.name : "extract";
return new Response(
JSON.stringify({
choices: [
{
message: {
tool_calls: [
{
type: "function",
function: {
name: toolName,
arguments: JSON.stringify(args),
},
},
],
},
},
],
choices: [{ message: { content: JSON.stringify(args) } }],
}),
{ status: 200, headers: { "Content-Type": "application/json" } },
);
@@ -95,13 +70,13 @@ const refsDemoWorkflow = createWorkflow<RefsDemoMeta>(
extractPrompt: "Extract phases with CAS hashes.",
schema: plannerMetaSchema,
extractRefs: (meta) => meta.phases.map((p) => p.hash),
extractMode: "single",
},
},
moderator: (ctx) => (ctx.steps.length === 0 ? "planner" : END),
},
{
agent: async () => "plan-output",
overrides: null,
},
);
+78 -54
View File
@@ -1,6 +1,6 @@
import { afterEach, describe, expect, test } from "bun:test";
import { parseSupervisorDecisionText, runSupervisor } from "../src/engine/supervisor.js";
import { runSupervisor } from "../src/engine/supervisor.js";
import type { WorkflowConfig } from "../src/registry/index.js";
import type { LogFn } from "../src/util/index.js";
@@ -20,28 +20,23 @@ function supervisorOnlyConfig(): WorkflowConfig {
};
}
describe("parseSupervisorDecisionText", () => {
test("reads continue and stop case-insensitively", () => {
expect(parseSupervisorDecisionText("continue")).toBe("continue");
expect(parseSupervisorDecisionText("CONTINUE")).toBe("continue");
expect(parseSupervisorDecisionText("stop")).toBe("stop");
expect(parseSupervisorDecisionText("STOP.")).toBe("stop");
function jsonResponse(body: Record<string, unknown>, status = 200): Response {
return new Response(JSON.stringify(body), {
status,
headers: { "Content-Type": "application/json" },
});
}
test("finds token inside a sentence", () => {
expect(parseSupervisorDecisionText("Answer: continue")).toBe("continue");
expect(parseSupervisorDecisionText("I recommend stop now")).toBe("stop");
});
test("when both appear, earlier token wins", () => {
expect(parseSupervisorDecisionText("continue then stop")).toBe("continue");
expect(parseSupervisorDecisionText("stop then continue")).toBe("stop");
});
test("defaults to continue when unclear", () => {
expect(parseSupervisorDecisionText("maybe later")).toBe("continue");
});
});
function installFetchMock(impl: (init?: RequestInit) => Promise<Response>): () => void {
const origFetch = globalThis.fetch;
globalThis.fetch = Object.assign(
async (_input: Parameters<typeof fetch>[0], init?: RequestInit) => impl(init),
{ preconnect: origFetch.preconnect.bind(origFetch) },
) as typeof fetch;
return () => {
globalThis.fetch = origFetch;
};
}
describe("runSupervisor", () => {
let restoreFetch: (() => void) | null = null;
@@ -52,16 +47,9 @@ describe("runSupervisor", () => {
});
test("returns continue when supervisor model cannot be resolved (no fetch)", async () => {
const origFetch = globalThis.fetch;
restoreFetch = () => {
globalThis.fetch = origFetch;
};
globalThis.fetch = Object.assign(
async () => {
throw new Error("fetch should not run when supervisor is not configured");
},
{ preconnect: origFetch.preconnect.bind(origFetch) },
) as typeof fetch;
restoreFetch = installFetchMock(async () => {
throw new Error("fetch should not run when supervisor is not configured");
});
const config: WorkflowConfig = {
maxDepth: 1,
@@ -87,21 +75,27 @@ describe("runSupervisor", () => {
expect(r.value).toBe("continue");
});
test("returns stop from chat/completions assistant content", async () => {
const origFetch = globalThis.fetch;
restoreFetch = () => {
globalThis.fetch = origFetch;
};
globalThis.fetch = Object.assign(
async () =>
new Response(
JSON.stringify({
choices: [{ message: { content: "stop" } }],
}),
{ status: 200, headers: { "Content-Type": "application/json" } },
),
{ preconnect: origFetch.preconnect.bind(origFetch) },
) as typeof fetch;
test("returns stop from structured tool call", async () => {
restoreFetch = installFetchMock(async () =>
jsonResponse({
choices: [
{
message: {
tool_calls: [
{
id: "t1",
type: "function",
function: {
name: "supervisor_decision",
arguments: JSON.stringify({ decision: "stop" }),
},
},
],
},
},
],
}),
);
const r = await runSupervisor({
config: supervisorOnlyConfig(),
@@ -116,14 +110,44 @@ describe("runSupervisor", () => {
expect(r.value).toBe("stop");
});
test("returns err on invalid JSON body", async () => {
const origFetch = globalThis.fetch;
restoreFetch = () => {
globalThis.fetch = origFetch;
};
globalThis.fetch = Object.assign(async () => new Response("not-json", { status: 200 }), {
preconnect: origFetch.preconnect.bind(origFetch),
}) as typeof fetch;
test("returns continue from plain JSON content (reactor short-circuit)", async () => {
restoreFetch = installFetchMock(async () =>
jsonResponse({
choices: [{ message: { content: '{"decision":"continue"}' } }],
}),
);
const r = await runSupervisor({
config: supervisorOnlyConfig(),
prompt: "do Y",
recentSteps: [],
logger: noopLogger,
});
expect(r.ok).toBe(true);
if (!r.ok) {
return;
}
expect(r.value).toBe("continue");
});
test("returns err when reactor cannot validate the schema within max rounds", async () => {
restoreFetch = installFetchMock(async () =>
jsonResponse({
choices: [{ message: { content: "not-json" } }],
}),
);
const r = await runSupervisor({
config: supervisorOnlyConfig(),
prompt: "p",
recentSteps: [],
logger: noopLogger,
});
expect(r.ok).toBe(false);
});
test("returns err on HTTP failure", async () => {
restoreFetch = installFetchMock(async () => new Response("boom", { status: 500 }));
const r = await runSupervisor({
config: supervisorOnlyConfig(),
@@ -2,12 +2,12 @@ import { afterEach, describe, expect, test } from "bun:test";
import { mkdtemp, rm } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
import type { LlmProvider } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
import { createCasStore } from "../src/cas/cas.js";
import { createContentMerkleNode, serializeMerkleNode } from "../src/cas/merkle.js";
import { reactExtract } from "../src/extract/react-extract.js";
import type { LlmProvider } from "../src/types.js";
import { extractFunctionToolFromZodSchema } from "../src/extract/llm-extract.js";
import { createLlmFn, createThreadReactor } from "../src/reactor/index.js";
const metaSchema = z.object({ seen: z.string() });
@@ -17,7 +17,57 @@ const provider: LlmProvider = {
model: "test",
};
describe("reactExtract", () => {
const CAS_GET_TOOL_DEFINITION = {
type: "function" as const,
function: {
name: "cas_get",
description: "Read CAS node",
parameters: {
type: "object",
properties: {
hash: { type: "string", description: "hash" },
},
required: ["hash"],
},
},
};
type ThreadCtx = { cas: ReturnType<typeof createCasStore> };
function createTestReactor() {
const llm = createLlmFn(provider);
return createThreadReactor<ThreadCtx>({
llm,
maxRounds: 10,
staticTools: [CAS_GET_TOOL_DEFINITION],
structuredToolFromSchema: (schema) => {
const t = extractFunctionToolFromZodSchema(schema);
return {
name: t.name,
tool: {
type: "function" as const,
function: {
name: t.name,
description: t.description,
parameters: t.parameters,
},
},
};
},
systemPromptForStructuredTool: (structuredToolName) =>
`Extract metadata. Use cas_get when needed. Call ${structuredToolName} with JSON args matching the schema, or reply with plain JSON.`,
toolHandler: async (call, thread) => {
if (call.function.name !== "cas_get") {
return `unexpected tool ${call.function.name}`;
}
const ta = JSON.parse(call.function.arguments) as { hash: string };
const blob = await thread.cas.get(ta.hash);
return blob === null ? "null" : blob;
},
});
}
describe("createThreadReactor (extract-shaped)", () => {
let restoreFetch: (() => void) | null = null;
afterEach(() => {
@@ -26,7 +76,7 @@ describe("reactExtract", () => {
});
test("cas_get rounds then extract tool yields validated meta", async () => {
const casDir = await mkdtemp(join(tmpdir(), "react-extract-"));
const casDir = await mkdtemp(join(tmpdir(), "thread-reactor-"));
const cas = createCasStore(casDir);
try {
const blob = serializeMerkleNode(createContentMerkleNode("needle"));
@@ -88,12 +138,12 @@ describe("reactExtract", () => {
{ preconnect: origFetch.preconnect.bind(origFetch) },
) as typeof fetch;
const reactor = createTestReactor();
const text = `## Agent Output\n${h}\n## Extraction Instruction\nExtract seen from CAS.`;
const result = await reactExtract({
text,
const result = await reactor({
thread: { cas },
input: text,
schema: metaSchema,
provider,
cas,
});
expect(result.ok).toBe(true);
@@ -108,7 +158,7 @@ describe("reactExtract", () => {
});
test("stops after max tool rounds when model keeps calling cas_get", async () => {
const casDir = await mkdtemp(join(tmpdir(), "react-extract-max-"));
const casDir = await mkdtemp(join(tmpdir(), "thread-reactor-max-"));
const cas = createCasStore(casDir);
try {
const blob = serializeMerkleNode(createContentMerkleNode("x"));
@@ -147,11 +197,11 @@ describe("reactExtract", () => {
{ preconnect: origFetch.preconnect.bind(origFetch) },
) as typeof fetch;
const result = await reactExtract({
text: "## Agent Output\nnoop\n## Extraction Instruction\nExtract seen.",
const reactor = createTestReactor();
const result = await reactor({
thread: { cas },
input: "## Agent Output\nnoop\n## Extraction Instruction\nExtract seen.",
schema: metaSchema,
provider,
cas,
});
expect(result.ok).toBe(false);
@@ -166,7 +216,7 @@ describe("reactExtract", () => {
});
test("passthrough JSON assistant message without tool calls", async () => {
const casDir = await mkdtemp(join(tmpdir(), "react-extract-pass-"));
const casDir = await mkdtemp(join(tmpdir(), "thread-reactor-pass-"));
const cas = createCasStore(casDir);
try {
const origFetch = globalThis.fetch;
@@ -190,11 +240,11 @@ describe("reactExtract", () => {
{ preconnect: origFetch.preconnect.bind(origFetch) },
) as typeof fetch;
const result = await reactExtract({
text: "## Agent Output\nok\n## Extraction Instruction\nExtract.",
const reactor = createTestReactor();
const result = await reactor({
thread: { cas },
input: "## Agent Output\nok\n## Extraction Instruction\nExtract.",
schema: metaSchema,
provider,
cas,
});
expect(result.ok).toBe(true);
@@ -2,8 +2,8 @@ import { afterEach, describe, expect, test } from "bun:test";
import { mkdir, mkdtemp, readdir, readFile, rm, writeFile } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { END } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
import { createCasStore } from "../src/cas/cas.js";
import { hashWorkflowBundleBytes } from "../src/cas/hash.js";
import { getContentMerklePayload, parseMerkleNode } from "../src/cas/merkle.js";
@@ -14,7 +14,6 @@ import {
registerWorkflowVersion,
writeWorkflowRegistry,
} from "../src/registry/registry.js";
import { END } from "../src/types.js";
import { createLogger } from "../src/util/logger.js";
import { workflowAsAgent } from "../src/workflow-as-agent.js";
@@ -28,41 +27,17 @@ function installMockChatCompletions(sequence: ReadonlyArray<Record<string, unkno
const origFetch = globalThis.fetch;
let i = 0;
const mockFetch = async (
input: Parameters<typeof fetch>[0],
init?: RequestInit,
_input: Parameters<typeof fetch>[0],
_init?: RequestInit,
): Promise<Response> => {
const args = sequence[i] ?? sequence[sequence.length - 1];
if (args === undefined) {
throw new Error("installMockChatCompletions: empty sequence");
}
i += 1;
void input;
const body = init?.body ? (JSON.parse(String(init.body)) as Record<string, unknown>) : {};
const tools = body.tools;
const firstTool =
Array.isArray(tools) && tools.length > 0 && tools[0] !== null && typeof tools[0] === "object"
? (tools[0] as Record<string, unknown>)
: null;
const fn =
firstTool !== null ? (firstTool.function as Record<string, unknown> | undefined) : undefined;
const toolName = typeof fn?.name === "string" ? fn.name : "extract";
return new Response(
JSON.stringify({
choices: [
{
message: {
tool_calls: [
{
type: "function",
function: {
name: toolName,
arguments: JSON.stringify(args),
},
},
],
},
},
],
choices: [{ message: { content: JSON.stringify(args) } }],
}),
{ status: 200, headers: { "Content-Type": "application/json" } },
);
@@ -97,11 +72,11 @@ export const descriptor = {
},
},
};
export async function* run(input, options) {
const cas = options.cas;
export async function* run(thread, runtime) {
const cas = runtime.cas;
const h = await putContentMerkleNode(cas, "child-body");
yield { role: "agent", contentHash: h, meta: {}, refs: [h] };
return { returnCode: 0, summary: "child-done:" + input.prompt };
return { returnCode: 0, summary: "child-done:" + thread.start.content };
}
`;
@@ -148,12 +123,11 @@ describe("workflowAsAgent integration", () => {
extractPrompt: "extract done flag",
schema: callerMetaSchema,
extractRefs: null,
extractMode: "single",
},
},
moderator: (ctx) => (ctx.steps.length === 0 ? "caller" : END),
},
{ agent: workflowAsAgent("child-wf", { storageRoot: root }) },
{ agent: workflowAsAgent("child-wf", { storageRoot: root }), overrides: null },
);
const threadId = "01KQXKW18CT8G75T53R8F4G7YG";
@@ -2,7 +2,7 @@ import { describe, expect, test } from "bun:test";
import { mkdir, mkdtemp, rm, writeFile } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { type AgentContext, START } from "@uncaged/workflow-runtime";
import { createCasStore } from "../src/cas/cas.js";
import { hashWorkflowBundleBytes } from "../src/cas/hash.js";
import { parseMerkleNode } from "../src/cas/merkle.js";
@@ -11,7 +11,6 @@ import {
registerWorkflowVersion,
writeWorkflowRegistry,
} from "../src/registry/registry.js";
import { type AgentContext, START } from "../src/types.js";
import { workflowAsAgent } from "../src/workflow-as-agent.js";
function makeAgentCtx(params: {
@@ -35,7 +34,6 @@ function makeAgentCtx(params: {
name: "caller",
systemPrompt: "caller",
},
cas: createCasStore(join(params.storageRoot, "agent-ctx-cas")),
};
}
@@ -50,11 +48,11 @@ export const descriptor = {
},
},
};
export async function* run(input, options) {
const cas = options.cas;
export async function* run(thread, runtime) {
const cas = runtime.cas;
const h = await putContentMerkleNode(cas, "child-body");
yield { role: "agent", contentHash: h, meta: {}, refs: [h] };
return { returnCode: 0, summary: "child-done:" + input.prompt };
return { returnCode: 0, summary: "child-done:" + thread.start.content };
}
`;
+1
View File
@@ -8,6 +8,7 @@
"test": "bun test"
},
"dependencies": {
"@uncaged/workflow-runtime": "workspace:*",
"acorn": "^8.16.0",
"xxhashjs": "^0.2.2",
"yaml": "^2.8.4"
@@ -1,6 +1,5 @@
import type { RoleMeta, WorkflowDefinition } from "@uncaged/workflow-runtime";
import * as z from "zod/v4";
import type { RoleMeta, WorkflowDefinition } from "../types.js";
import type { WorkflowDescriptor, WorkflowRoleSchema } from "./types.js";
function stripJsonSchemaMeta(json: Record<string, unknown>): WorkflowRoleSchema {
@@ -38,7 +38,7 @@ function isAllowedImportSpecifier(spec: string): boolean {
if (spec.startsWith(".") || spec.startsWith("/") || spec.startsWith("file:")) {
return false;
}
if (spec === "@uncaged/workflow") {
if (spec === "@uncaged/workflow" || spec === "@uncaged/workflow-runtime") {
return true;
}
return isBuiltin(spec);
@@ -1,4 +1,4 @@
import type { WorkflowFn } from "../types.js";
import type { WorkflowFn } from "@uncaged/workflow-runtime";
import { err, ok, type Result } from "../util/index.js";
import { importWorkflowBundleModule } from "./bundle-import-env.js";
import { ensureUncagedWorkflowSymlink } from "./ensure-uncaged-workflow-symlink.js";
+6 -14
View File
@@ -1,18 +1,10 @@
import type { WorkflowFn } from "../types.js";
import type { WorkflowDescriptor, WorkflowFn } from "@uncaged/workflow-runtime";
/** JSON Schema fragment describing one role's `meta` shape (subset supported by code generation). */
export type WorkflowRoleSchema = Record<string, unknown>;
export type WorkflowRoleDescriptor = {
description: string;
schema: WorkflowRoleSchema;
};
/** Workflow metadata exported as `export const descriptor` from `.esm.js` bundles. */
export type WorkflowDescriptor = {
description: string;
roles: Record<string, WorkflowRoleDescriptor>;
};
export type {
WorkflowDescriptor,
WorkflowRoleDescriptor,
WorkflowRoleSchema,
} from "@uncaged/workflow-runtime";
export type WorkflowBundleValidationInput = {
/** Absolute or relative path (used for `.esm.js` suffix checks). */
+14 -2
View File
@@ -2,8 +2,19 @@ import { mkdir, readdir, readFile, rename, unlink, writeFile } from "node:fs/pro
import { join } from "node:path";
import { hashString } from "./hash.js";
import { createContentMerkleNode, parseMerkleNode, serializeMerkleNode } from "./merkle.js";
import type { CasStore } from "./types.js";
/** Raw strings become content merkle YAML; already-valid merkle documents pass through. */
function normalizeCasPutContent(content: string): string {
try {
parseMerkleNode(content);
return content;
} catch {
return serializeMerkleNode(createContentMerkleNode(content));
}
}
export function createCasStore(casDir: string): CasStore {
async function ensureDir(): Promise<void> {
await mkdir(casDir, { recursive: true });
@@ -15,11 +26,12 @@ export function createCasStore(casDir: string): CasStore {
return {
async put(content: string): Promise<string> {
const hash = hashString(content);
const toStore = normalizeCasPutContent(content);
const hash = hashString(toStore);
await ensureDir();
const target = filePath(hash);
const tmp = `${target}.tmp.${Date.now()}`;
await writeFile(tmp, content, "utf8");
await writeFile(tmp, toStore, "utf8");
await rename(tmp, target);
return hash;
},
+2 -3
View File
@@ -77,10 +77,9 @@ export async function putThreadMerkleNode(
return store.put(serializeMerkleNode(node));
}
/** Serializes a content Merkle node and stores it in CAS; returns its hash. */
/** Stores agent/content text via CAS; {@link createCasStore} wraps raw strings as merkle content nodes. */
export async function putContentMerkleNode(store: CasStore, content: string): Promise<string> {
const yamlText = serializeMerkleNode(createContentMerkleNode(content));
return store.put(yamlText);
return store.put(content);
}
/** Loads a CAS blob and returns the payload string for a `content` Merkle node. */
+1 -6
View File
@@ -1,9 +1,4 @@
export type CasStore = {
put(content: string): Promise<string>;
get(hash: string): Promise<string | null>;
delete(hash: string): Promise<void>;
list(): Promise<string[]>;
};
export type { CasStore } from "@uncaged/workflow-runtime";
export type MerkleNodeType = "content" | "step" | "thread";
+6 -173
View File
@@ -1,175 +1,8 @@
import { putContentMerkleNode } from "../cas/index.js";
import { buildExtractUserContent, reactExtract } from "../extract/index.js";
import {
type AgentBinding,
type AgentContext,
END,
type ExtractContext,
type ModeratorContext,
type RoleDefinition,
type RoleMeta,
type RoleOutput,
type RoleStep,
START,
type ThreadInput,
type WorkflowCompletion,
type WorkflowDefinition,
type WorkflowFn,
type WorkflowFnOptions,
} from "../types.js";
import { mergeRefsWithContentHash } from "../util/index.js";
function isRoleNext<M extends RoleMeta>(
next: (keyof M & string) | typeof END,
): next is keyof M & string {
return next !== END;
}
function resolveExtractedRefs(
roleDef: RoleDefinition<Record<string, unknown>>,
meta: unknown,
): string[] {
const extractRefsFn = roleDef.extractRefs;
if (extractRefsFn === null || typeof extractRefsFn !== "function") {
return [];
}
return extractRefsFn(meta as Record<string, unknown>);
}
async function resolveRoleMeta<M extends RoleMeta>(
roleDef: RoleDefinition<Record<string, unknown>>,
extractCtx: ExtractContext<M>,
options: WorkflowFnOptions,
): Promise<Record<string, unknown>> {
if (roleDef.extractMode === "react") {
if (options.llmProvider === null) {
throw new Error(
'createWorkflow: WorkflowFnOptions.llmProvider is required when a role uses extractMode "react"',
);
}
const text = await buildExtractUserContent(
extractCtx as unknown as ExtractContext,
roleDef.extractPrompt,
);
const reactResult = await reactExtract({
text,
schema: roleDef.schema,
provider: options.llmProvider,
cas: options.cas,
});
if (!reactResult.ok) {
throw new Error(`react extract failed: ${reactResult.error}`);
}
return reactResult.value as Record<string, unknown>;
}
return (await options.extract(
roleDef.schema,
roleDef.extractPrompt,
extractCtx as unknown as ExtractContext,
)) as Record<string, unknown>;
}
/**
* Binds pure role definitions + moderator to runtime agents.
* Assign with `export const run = createWorkflow(def, binding)`.
* The engine supplies {@link WorkflowFnOptions.extract} and {@link WorkflowFnOptions.llmProvider} from workflow.yaml.
* Re-export of {@link createWorkflow} from `@uncaged/workflow-runtime`.
*
* The runtime's `createWorkflow` already binds role definitions + agents to a workflow loop
* and delegates structured meta extraction to `WorkflowRuntime.extract`, which the engine
* supplies (resolved from the `extract` scene in workflow.yaml).
*/
export function createWorkflow<M extends RoleMeta>(
def: Pick<WorkflowDefinition<M>, "roles" | "moderator">,
binding: AgentBinding,
): WorkflowFn {
return async function* workflowLoop(
input: ThreadInput,
options: WorkflowFnOptions,
): AsyncGenerator<RoleOutput, WorkflowCompletion> {
const nowMs = Date.now();
const start: ModeratorContext<M>["start"] = {
role: START,
content: input.prompt,
meta: { maxRounds: options.maxRounds },
timestamp: nowMs,
};
const baseTs = Date.now();
let steps: RoleStep<M>[] = input.steps.map((out, i) => ({
role: out.role,
contentHash: out.contentHash,
meta: out.meta,
refs: out.refs,
timestamp: baseTs + i,
})) as RoleStep<M>[];
while (true) {
if (steps.length >= options.maxRounds) {
return {
returnCode: 0,
summary: `completed: reached maxRounds (${options.maxRounds})`,
};
}
const modCtx: ModeratorContext<M> = {
threadId: options.threadId,
depth: options.depth,
start,
steps,
};
const next = def.moderator(modCtx);
if (!isRoleNext(next)) {
return { returnCode: 0, summary: "completed: moderator returned END" };
}
const roleDef = def.roles[next];
if (roleDef === undefined) {
return { returnCode: 1, summary: `unknown role: ${next}` };
}
const agentCtx: AgentContext<M> = {
...modCtx,
currentRole: { name: next, systemPrompt: roleDef.systemPrompt },
cas: options.cas,
};
const agent = binding.overrides?.[next] ?? binding.agent;
const raw = await agent(agentCtx as unknown as AgentContext);
const extractCtx: ExtractContext<M> = {
...agentCtx,
agentContent: raw,
};
const meta = await resolveRoleMeta(
roleDef as unknown as RoleDefinition<Record<string, unknown>>,
extractCtx,
options,
);
const contentHash = await putContentMerkleNode(options.cas, raw);
const refs = mergeRefsWithContentHash(
resolveExtractedRefs(roleDef as unknown as RoleDefinition<Record<string, unknown>>, meta),
contentHash,
);
const ts = Date.now();
const step = {
role: next,
contentHash,
meta,
refs,
timestamp: ts,
} as RoleStep<M>;
yield {
role: step.role,
contentHash: step.contentHash,
meta: step.meta,
refs: step.refs,
};
steps = [...steps, step];
}
};
}
export { createWorkflow } from "@uncaged/workflow-runtime";

Some files were not shown because too many files have changed in this diff Show More