Compare commits
15 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 52ffc7dcc1 | |||
| ac55a3e3d9 | |||
| edb979baa9 | |||
| 3d1850ddbe | |||
| 3c1f4a6dfa | |||
| f07a6daa30 | |||
| 0eeb4a8ed8 | |||
| a3fac708b6 | |||
| 52879c0028 | |||
| 8720eb19af | |||
| 9e4527bb89 | |||
| 5209cfa7ac | |||
| 155b879d29 | |||
| c1f04929f4 | |||
| 211f38bc8d |
@@ -41,7 +41,8 @@ roles:
|
||||
Before starting any work, ensure a clean worktree:
|
||||
1. `git checkout main && git pull` to get the latest code
|
||||
2. `git checkout -b fix/<issue-number>-<short-description>` to create a fresh branch
|
||||
- If bounced back from reviewer or tester, reuse the existing branch instead
|
||||
- If bounced back from reviewer or tester, reuse the existing branch and rebase onto latest main:
|
||||
`git checkout main && git pull && git checkout <branch> && git rebase main`
|
||||
|
||||
Then implement TDD:
|
||||
3. Read the test spec from CAS: `uwf cas get <plan hash>` (find the hash from the latest planner step's frontmatter.plan)
|
||||
|
||||
+1
-1
@@ -9,7 +9,7 @@
|
||||
"check": "bunx tsc --build && biome check . && bash scripts/lint-log-tags.sh",
|
||||
"typecheck": "bunx tsc --build",
|
||||
"format": "biome format --write .",
|
||||
"test": "bun run --filter '*' test",
|
||||
"test": "bun run --filter './packages/*' test",
|
||||
"changeset": "bunx changeset",
|
||||
"version": "bunx changeset version",
|
||||
"release": "bun run build && bun test && node scripts/publish-all.mjs"
|
||||
|
||||
@@ -266,12 +266,7 @@ describe("cmdThreadRead ### Content section", () => {
|
||||
|
||||
expect(markdown).toContain("### Content");
|
||||
expect(markdown).toContain("The assistant response text");
|
||||
|
||||
const contentIdx = markdown.indexOf("### Content");
|
||||
const outputIdx = markdown.indexOf("### Output");
|
||||
expect(contentIdx).toBeGreaterThanOrEqual(0);
|
||||
expect(outputIdx).toBeGreaterThanOrEqual(0);
|
||||
expect(contentIdx).toBeLessThan(outputIdx);
|
||||
expect(markdown).not.toContain("### Output");
|
||||
});
|
||||
|
||||
test("omits ### Content when detail has no matching assistant turns", async () => {
|
||||
@@ -314,7 +309,7 @@ describe("cmdThreadRead ### Content section", () => {
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
|
||||
expect(markdown).not.toContain("### Content");
|
||||
expect(markdown).toContain("### Output");
|
||||
expect(markdown).not.toContain("### Output");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -392,3 +387,87 @@ describe("cmdThreadStepDetails", () => {
|
||||
await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
// ── cmdThreadRead: ### Prompt deduplication ───────────────────────────────────
|
||||
|
||||
describe("cmdThreadRead ### Prompt deduplication", () => {
|
||||
async function makeThreadWithRoles(uwf: UwfStore, roles: string[]): Promise<string> {
|
||||
const roleMap: Record<string, unknown> = {};
|
||||
for (const r of [...new Set(roles)]) {
|
||||
roleMap[r] = {
|
||||
description: r,
|
||||
goal: `Goal for ${r}`,
|
||||
capabilities: [],
|
||||
procedure: "Do stuff.",
|
||||
output: "Output.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
};
|
||||
}
|
||||
const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "dedup-wf",
|
||||
description: "desc",
|
||||
roles: roleMap,
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
const startHash = await uwf.store.put(uwf.schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Start",
|
||||
});
|
||||
const outputHash = await uwf.store.put(uwf.schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
let prev: string | null = null;
|
||||
let stepHash = "";
|
||||
for (const role of roles) {
|
||||
stepHash = await uwf.store.put(uwf.schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: prev as CasRef | null,
|
||||
role,
|
||||
output: outputHash,
|
||||
detail: null,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
prev = stepHash;
|
||||
}
|
||||
return stepHash;
|
||||
}
|
||||
|
||||
test("same consecutive role shows ### Prompt once", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const headHash = await makeThreadWithRoles(uwf, ["writer", "writer"]);
|
||||
const threadId = "01JTEST0000000000000003" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: headHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
const count = (markdown.match(/### Prompt/g) ?? []).length;
|
||||
expect(count).toBe(1);
|
||||
});
|
||||
|
||||
test("different consecutive roles each show ### Prompt", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const headHash = await makeThreadWithRoles(uwf, ["planner", "coder"]);
|
||||
const threadId = "01JTEST0000000000000004" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: headHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
const count = (markdown.match(/### Prompt/g) ?? []).length;
|
||||
expect(count).toBe(2);
|
||||
});
|
||||
|
||||
test("non-consecutive same role shows ### Prompt twice", async () => {
|
||||
const uwf = await makeUwfStore(tmpDir);
|
||||
const headHash = await makeThreadWithRoles(uwf, ["roleA", "roleB", "roleA"]);
|
||||
const threadId = "01JTEST0000000000000005" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: headHash });
|
||||
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
|
||||
const count = (markdown.match(/### Prompt/g) ?? []).length;
|
||||
expect(count).toBe(2);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,367 @@
|
||||
import { mkdir, mkdtemp, rm, writeFile } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { createFsStore } from "@uncaged/json-cas-fs";
|
||||
import type { CasRef, WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
import { afterEach, beforeEach, describe, expect, test } from "vitest";
|
||||
import { stringify } from "yaml";
|
||||
import { cmdThreadStart } from "../commands/thread.js";
|
||||
import { registerUwfSchemas } from "../schemas.js";
|
||||
import type { UwfStore } from "../store.js";
|
||||
import { loadWorkflowRegistry, saveWorkflowRegistry } from "../store.js";
|
||||
|
||||
// ── helpers ───────────────────────────────────────────────────────────────────
|
||||
|
||||
async function makeUwfStore(storageRoot: string): Promise<UwfStore> {
|
||||
const casDir = join(storageRoot, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
return { storageRoot, store, schemas };
|
||||
}
|
||||
|
||||
async function storeWorkflow(uwf: UwfStore, name: string): Promise<CasRef> {
|
||||
const payload: WorkflowPayload = {
|
||||
name,
|
||||
description: "Test workflow",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
};
|
||||
return await uwf.store.put(uwf.schemas.workflow, payload);
|
||||
}
|
||||
|
||||
async function createWorkflowYaml(name: string, version: string | null = null): Promise<string> {
|
||||
const payload: WorkflowPayload = {
|
||||
name,
|
||||
description: version !== null ? `Test workflow (${version})` : "Test workflow",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
};
|
||||
const yaml = stringify(payload);
|
||||
return yaml;
|
||||
}
|
||||
|
||||
// ── fixture ───────────────────────────────────────────────────────────────────
|
||||
|
||||
let tmpDir: string;
|
||||
let storageRoot: string;
|
||||
let projectRoot: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-wf-resolve-test-"));
|
||||
storageRoot = join(tmpDir, "storage");
|
||||
projectRoot = join(tmpDir, "project");
|
||||
await mkdir(storageRoot, { recursive: true });
|
||||
await mkdir(projectRoot, { recursive: true });
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
// ── Strategy 1: CAS Hash Resolution ───────────────────────────────────────────
|
||||
|
||||
describe("Strategy 1: CAS Hash Resolution", () => {
|
||||
test("should resolve valid 13-char Crockford Base32 hash", async () => {
|
||||
const uwf = await makeUwfStore(storageRoot);
|
||||
const hash = await storeWorkflow(uwf, "test-workflow");
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, hash, "test prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toBe(hash);
|
||||
expect(result.thread).toMatch(/^[0-9A-HJKMNP-TV-Z]{26}$/);
|
||||
});
|
||||
|
||||
test("should fail on invalid hash format (non-Crockford characters)", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
|
||||
await expect(
|
||||
cmdThreadStart(storageRoot, "123456789ABCD", "prompt", projectRoot),
|
||||
).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("should fail on valid-format hash not present in CAS", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const fakeHash = "0000000000000"; // valid format, doesn't exist
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, fakeHash, "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("should reject 40-char hex hash (legacy format not supported)", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const hexHash = "a".repeat(40);
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, hexHash, "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
// ── Strategy 2: File Path Resolution ──────────────────────────────────────────
|
||||
|
||||
describe("Strategy 2: File Path Resolution", () => {
|
||||
test("should load workflow from absolute file path", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const yamlPath = join(tmpDir, "test-workflow.yaml");
|
||||
await writeFile(yamlPath, await createWorkflowYaml("test-workflow"));
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
const uwf = await makeUwfStore(storageRoot);
|
||||
const node = uwf.store.get(result.workflow);
|
||||
expect(node).not.toBeNull();
|
||||
if (node !== null) {
|
||||
expect((node.payload as WorkflowPayload).name).toBe("test-workflow");
|
||||
}
|
||||
});
|
||||
|
||||
test("should load workflow from relative file path", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const yamlPath = "test-workflow.yaml";
|
||||
await writeFile(join(projectRoot, yamlPath), await createWorkflowYaml("test-workflow"));
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
});
|
||||
|
||||
test("should fail when file path does not exist", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
|
||||
await expect(
|
||||
cmdThreadStart(storageRoot, "./nonexistent.yaml", "prompt", projectRoot),
|
||||
).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("should fail on invalid YAML syntax in file", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const yamlPath = join(tmpDir, "bad-syntax.yaml");
|
||||
await writeFile(yamlPath, "invalid: yaml: : :");
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("should fail on valid YAML with invalid WorkflowPayload shape", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const yamlPath = join(tmpDir, "invalid-workflow.yaml");
|
||||
await writeFile(yamlPath, "name: test\n# missing roles, conditions, and graph");
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("should enforce filename matches workflow name", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const yamlPath = join(tmpDir, "solve-issue.yaml");
|
||||
await writeFile(yamlPath, await createWorkflowYaml("wrong-name"));
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, yamlPath, "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
// ── Strategy 3: Local Discovery (Parent Traversal) ────────────────────────────
|
||||
|
||||
describe("Strategy 3: Local Discovery", () => {
|
||||
test("should find workflow in current directory .workflow/", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const workflowDir = join(projectRoot, ".workflow");
|
||||
await mkdir(workflowDir, { recursive: true });
|
||||
await writeFile(join(workflowDir, "solve-issue.yaml"), await createWorkflowYaml("solve-issue"));
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
const uwf = await makeUwfStore(storageRoot);
|
||||
const node = uwf.store.get(result.workflow);
|
||||
expect(node).not.toBeNull();
|
||||
if (node !== null) {
|
||||
expect((node.payload as WorkflowPayload).name).toBe("solve-issue");
|
||||
}
|
||||
});
|
||||
|
||||
test("should find workflow in parent directory .workflow/", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const workflowDir = join(projectRoot, ".workflow");
|
||||
await mkdir(workflowDir, { recursive: true });
|
||||
await writeFile(join(workflowDir, "solve-issue.yaml"), await createWorkflowYaml("solve-issue"));
|
||||
|
||||
const subdir = join(projectRoot, "packages", "cli-workflow", "src");
|
||||
await mkdir(subdir, { recursive: true });
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", subdir);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
});
|
||||
|
||||
test("should stop at filesystem root when traversing", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const deepPath = join(tmpDir, "deep", "path", "that", "does", "not", "have", "workflow");
|
||||
await mkdir(deepPath, { recursive: true });
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, "nonexistent", "prompt", deepPath)).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("should prefer .workflow/ over .workflows/ directory", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const workflowDir = join(projectRoot, ".workflow");
|
||||
const workflowsDir = join(projectRoot, ".workflows");
|
||||
await mkdir(workflowDir, { recursive: true });
|
||||
await mkdir(workflowsDir, { recursive: true });
|
||||
|
||||
await writeFile(
|
||||
join(workflowDir, "solve-issue.yaml"),
|
||||
await createWorkflowYaml("solve-issue", "1"),
|
||||
);
|
||||
await writeFile(
|
||||
join(workflowsDir, "solve-issue.yaml"),
|
||||
await createWorkflowYaml("solve-issue", "2"),
|
||||
);
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
|
||||
|
||||
const uwf = await makeUwfStore(storageRoot);
|
||||
const node = uwf.store.get(result.workflow);
|
||||
expect(node).not.toBeNull();
|
||||
if (node !== null) {
|
||||
expect((node.payload as WorkflowPayload).description).toBe("Test workflow (1)");
|
||||
}
|
||||
});
|
||||
|
||||
test("should support .yml extension in local discovery", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const workflowDir = join(projectRoot, ".workflow");
|
||||
await mkdir(workflowDir, { recursive: true });
|
||||
await writeFile(join(workflowDir, "solve-issue.yml"), await createWorkflowYaml("solve-issue"));
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
});
|
||||
});
|
||||
|
||||
// ── Strategy 4: Global Registry Fallback ──────────────────────────────────────
|
||||
|
||||
describe("Strategy 4: Global Registry Resolution", () => {
|
||||
test("should resolve workflow from global registry when not found locally", async () => {
|
||||
const uwf = await makeUwfStore(storageRoot);
|
||||
const hash = await storeWorkflow(uwf, "deploy-pipeline");
|
||||
const registry = await loadWorkflowRegistry(storageRoot);
|
||||
registry["deploy-pipeline"] = hash;
|
||||
await saveWorkflowRegistry(storageRoot, registry);
|
||||
|
||||
const isolatedRoot = join(tmpDir, "isolated");
|
||||
await mkdir(isolatedRoot, { recursive: true });
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, "deploy-pipeline", "prompt", isolatedRoot);
|
||||
|
||||
expect(result.workflow).toBe(hash);
|
||||
});
|
||||
|
||||
test("should fail when workflow not found in any strategy", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, "nonexistent", "prompt", tmpDir)).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
// ── Strategy Priority Order ───────────────────────────────────────────────────
|
||||
|
||||
describe("Resolution Priority", () => {
|
||||
test("should use explicit file path over local discovery", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
|
||||
// Setup: Create workflow in .workflow/ AND as explicit file
|
||||
const workflowDir = join(projectRoot, ".workflow");
|
||||
await mkdir(workflowDir, { recursive: true });
|
||||
await writeFile(
|
||||
join(workflowDir, "solve-issue.yaml"),
|
||||
await createWorkflowYaml("solve-issue", "discovery"),
|
||||
);
|
||||
|
||||
const explicitPath = join(projectRoot, "custom-solve-issue.yaml");
|
||||
await writeFile(explicitPath, await createWorkflowYaml("custom-solve-issue", "explicit"));
|
||||
|
||||
// Execute with explicit path
|
||||
const result = await cmdThreadStart(storageRoot, explicitPath, "prompt", projectRoot);
|
||||
|
||||
const uwf = await makeUwfStore(storageRoot);
|
||||
const node = uwf.store.get(result.workflow);
|
||||
expect(node).not.toBeNull();
|
||||
if (node !== null) {
|
||||
expect((node.payload as WorkflowPayload).description).toBe("Test workflow (explicit)");
|
||||
}
|
||||
});
|
||||
|
||||
test("should use local discovery over global registry", async () => {
|
||||
const uwf = await makeUwfStore(storageRoot);
|
||||
|
||||
// Setup: Register globally
|
||||
const globalHash = await storeWorkflow(uwf, "solve-issue");
|
||||
const registry = await loadWorkflowRegistry(storageRoot);
|
||||
registry["solve-issue"] = globalHash;
|
||||
await saveWorkflowRegistry(storageRoot, registry);
|
||||
|
||||
// Setup: Create local .workflow/
|
||||
const workflowDir = join(projectRoot, ".workflow");
|
||||
await mkdir(workflowDir, { recursive: true });
|
||||
const localYaml = await createWorkflowYaml("solve-issue", "local");
|
||||
await writeFile(join(workflowDir, "solve-issue.yaml"), localYaml);
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, "solve-issue", "prompt", projectRoot);
|
||||
|
||||
const uwf2 = await makeUwfStore(storageRoot);
|
||||
const node = uwf2.store.get(result.workflow);
|
||||
expect(node).not.toBeNull();
|
||||
if (node !== null) {
|
||||
expect((node.payload as WorkflowPayload).description).toBe("Test workflow (local)");
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
// ── Edge Cases ────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("Edge Cases", () => {
|
||||
test("should treat '13-char-string.yaml' as file path, not CAS hash", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const fileName = "0123456789ABC.yaml"; // 13 chars + .yaml
|
||||
await writeFile(join(projectRoot, fileName), await createWorkflowYaml("0123456789ABC"));
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, fileName, "prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
});
|
||||
|
||||
test("should handle workflow names containing slashes as file paths", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const filePath = "subdir/solve-issue.yaml";
|
||||
const fullPath = join(projectRoot, filePath);
|
||||
await mkdir(join(projectRoot, "subdir"), { recursive: true });
|
||||
await writeFile(fullPath, await createWorkflowYaml("solve-issue"));
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, filePath, "prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
});
|
||||
|
||||
test("should handle absolute paths correctly", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
const absPath = join(tmpDir, "abs-workflow.yaml");
|
||||
await writeFile(absPath, await createWorkflowYaml("abs-workflow"));
|
||||
|
||||
const result = await cmdThreadStart(storageRoot, absPath, "prompt", projectRoot);
|
||||
|
||||
expect(result.workflow).toMatch(/^[0-9A-HJKMNP-TV-Z]{13}$/);
|
||||
});
|
||||
|
||||
test("should fail on empty workflow ID", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, "", "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
|
||||
test("should fail on whitespace-only workflow ID", async () => {
|
||||
await makeUwfStore(storageRoot);
|
||||
|
||||
await expect(cmdThreadStart(storageRoot, " ", "prompt", projectRoot)).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
@@ -137,6 +137,75 @@ function apiKeyEnvName(providerName: string): string {
|
||||
return `${providerName.toUpperCase().replace(/[^A-Z0-9]/g, "_")}_API_KEY`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Discover uwf-* agent binaries in PATH.
|
||||
* Returns sorted list of binary names (e.g., ["uwf-hermes", "uwf-claude-code"]).
|
||||
*/
|
||||
async function _discoverAgents(): Promise<string[]> {
|
||||
try {
|
||||
// Use which -a to find all uwf-* binaries in PATH
|
||||
const proc = Bun.spawn(["which", "-a", "uwf-hermes", "uwf-claude-code", "uwf-cursor"], {
|
||||
stdout: "pipe",
|
||||
stderr: "pipe",
|
||||
});
|
||||
|
||||
const text = await new Response(proc.stdout).text();
|
||||
await proc.exited;
|
||||
|
||||
if (proc.exitCode !== 0) {
|
||||
// Try alternative approach: search PATH directories manually
|
||||
const pathEnv = process.env.PATH || "";
|
||||
const pathDirs = pathEnv.split(":").filter((d) => d.length > 0);
|
||||
const agents = new Set<string>();
|
||||
|
||||
for (const dir of pathDirs) {
|
||||
try {
|
||||
if (!existsSync(dir)) continue;
|
||||
const { readdirSync, statSync } = await import("node:fs");
|
||||
const entries = readdirSync(dir);
|
||||
|
||||
for (const entry of entries) {
|
||||
if (!entry.startsWith("uwf-") || entry === "uwf") continue;
|
||||
const fullPath = join(dir, entry);
|
||||
try {
|
||||
const stat = statSync(fullPath);
|
||||
// Check if executable (owner, group, or other has execute bit)
|
||||
if (stat.isFile() && (stat.mode & 0o111) !== 0) {
|
||||
agents.add(entry);
|
||||
}
|
||||
} catch {
|
||||
// Skip if can't stat
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
// Skip inaccessible directories
|
||||
}
|
||||
}
|
||||
|
||||
return Array.from(agents).sort();
|
||||
}
|
||||
|
||||
// Parse which output - each line is a path to a binary
|
||||
const paths = text
|
||||
.trim()
|
||||
.split("\n")
|
||||
.filter((line) => line.length > 0);
|
||||
const agents = new Set<string>();
|
||||
|
||||
for (const path of paths) {
|
||||
const basename = path.split("/").pop();
|
||||
if (basename?.startsWith("uwf-") && basename !== "uwf") {
|
||||
agents.add(basename);
|
||||
}
|
||||
}
|
||||
|
||||
return Array.from(agents).sort();
|
||||
} catch {
|
||||
// If all fails, return empty array
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Merge setup args into config.yaml structure. Non-destructive — preserves existing entries.
|
||||
*/
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
import { execFileSync } from "node:child_process";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { access, readFile } from "node:fs/promises";
|
||||
import { dirname, isAbsolute, resolve as resolvePath } from "node:path";
|
||||
import type { Store as CasStore, JSONSchema } from "@uncaged/json-cas";
|
||||
import { getSchema, validate } from "@uncaged/json-cas";
|
||||
import { getEnvPath, loadWorkflowConfig } from "@uncaged/workflow-agent-kit";
|
||||
@@ -30,12 +31,10 @@ import { parse, stringify } from "yaml";
|
||||
import {
|
||||
appendThreadHistory,
|
||||
createUwfStore,
|
||||
discoverProjectWorkflows,
|
||||
findThreadInHistory,
|
||||
loadThreadHistory,
|
||||
loadThreadsIndex,
|
||||
loadWorkflowRegistry,
|
||||
resolveProjectWorkflowFile,
|
||||
resolveWorkflowHash,
|
||||
saveThreadsIndex,
|
||||
type ThreadHistoryLine,
|
||||
@@ -82,6 +81,83 @@ function fail(message: string): never {
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a string looks like a file path (contains path separators or has .yaml/.yml extension).
|
||||
*/
|
||||
function isFilePath(input: string): boolean {
|
||||
return (
|
||||
input.includes("/") || input.includes("\\") || input.endsWith(".yaml") || input.endsWith(".yml")
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a workflow file exists at the given path.
|
||||
*/
|
||||
async function workflowFileExists(dir: string, name: string, ext: string): Promise<string | null> {
|
||||
const candidate = resolvePath(dir, `${name}${ext}`);
|
||||
try {
|
||||
await access(candidate);
|
||||
return candidate;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Search for a workflow file in a given directory (checks both .workflow/ and .workflows/).
|
||||
*/
|
||||
async function findWorkflowInDir(dir: string, name: string): Promise<string | null> {
|
||||
// Check .workflow/ directory first (preferred)
|
||||
for (const ext of [".yaml", ".yml"]) {
|
||||
const result = await workflowFileExists(resolvePath(dir, ".workflow"), name, ext);
|
||||
if (result !== null) {
|
||||
return result;
|
||||
}
|
||||
}
|
||||
|
||||
// Check .workflows/ directory as fallback (legacy)
|
||||
for (const ext of [".yaml", ".yml"]) {
|
||||
const result = await workflowFileExists(resolvePath(dir, ".workflows"), name, ext);
|
||||
if (result !== null) {
|
||||
return result;
|
||||
}
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Traverse parent directories looking for `.workflow/<name>.yaml` or `.workflow/<name>.yml`.
|
||||
* Returns the absolute path if found, otherwise null.
|
||||
* Stops at filesystem root or .git directory.
|
||||
*/
|
||||
async function findWorkflowInParents(startDir: string, name: string): Promise<string | null> {
|
||||
let currentDir = resolvePath(startDir);
|
||||
const root = resolvePath("/");
|
||||
|
||||
while (true) {
|
||||
const found = await findWorkflowInDir(currentDir, name);
|
||||
if (found !== null) {
|
||||
return found;
|
||||
}
|
||||
|
||||
// Stop at filesystem root
|
||||
if (currentDir === root) {
|
||||
break;
|
||||
}
|
||||
|
||||
// Move to parent directory
|
||||
const parentDir = dirname(currentDir);
|
||||
if (parentDir === currentDir) {
|
||||
// Reached filesystem root
|
||||
break;
|
||||
}
|
||||
currentDir = parentDir;
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
async function materializeLocalWorkflow(uwf: UwfStore, filePath: string): Promise<CasRef> {
|
||||
let text: string;
|
||||
try {
|
||||
@@ -123,18 +199,41 @@ async function resolveWorkflowCasRef(
|
||||
workflowId: string,
|
||||
projectRoot: string,
|
||||
): Promise<CasRef> {
|
||||
// Project-local resolution: check .workflows/<workflowId>.yaml first
|
||||
const localEntries = await discoverProjectWorkflows(projectRoot);
|
||||
const localFile = resolveProjectWorkflowFile(localEntries, workflowId);
|
||||
if (localFile !== null) {
|
||||
return materializeLocalWorkflow(uwf, localFile);
|
||||
// Validate input
|
||||
const trimmed = workflowId.trim();
|
||||
if (trimmed === "") {
|
||||
fail("workflow ID cannot be empty");
|
||||
}
|
||||
|
||||
// Global registry fallback
|
||||
// Strategy 1: Direct CAS hash
|
||||
if (isCasRef(trimmed)) {
|
||||
const node = uwf.store.get(trimmed);
|
||||
if (node === null) {
|
||||
fail(`CAS node not found: ${trimmed}`);
|
||||
}
|
||||
if (node.type !== uwf.schemas.workflow) {
|
||||
fail(`node ${trimmed} is not a Workflow (type ${node.type})`);
|
||||
}
|
||||
return trimmed;
|
||||
}
|
||||
|
||||
// Strategy 2: Explicit file path (relative or absolute)
|
||||
if (isFilePath(trimmed)) {
|
||||
const absolutePath = isAbsolute(trimmed) ? trimmed : resolvePath(projectRoot, trimmed);
|
||||
return materializeLocalWorkflow(uwf, absolutePath);
|
||||
}
|
||||
|
||||
// Strategy 3: Local discovery (parent directory traversal)
|
||||
const localPath = await findWorkflowInParents(projectRoot, trimmed);
|
||||
if (localPath !== null) {
|
||||
return materializeLocalWorkflow(uwf, localPath);
|
||||
}
|
||||
|
||||
// Strategy 4: Global registry fallback
|
||||
const registry = await loadWorkflowRegistry(storageRoot);
|
||||
const hash = resolveWorkflowHash(registry, workflowId);
|
||||
const hash = resolveWorkflowHash(registry, trimmed);
|
||||
if (!isCasRef(hash)) {
|
||||
fail(`workflow not found: ${workflowId}`);
|
||||
fail(`workflow not found: ${trimmed}`);
|
||||
}
|
||||
const node = uwf.store.get(hash);
|
||||
if (node === null) {
|
||||
@@ -440,7 +539,7 @@ function collectOrderedSteps(
|
||||
}
|
||||
|
||||
function formatYaml(value: unknown): string {
|
||||
return stringify(value).trimEnd();
|
||||
return stringify(value, { aliasDuplicateObjects: false }).trimEnd();
|
||||
}
|
||||
|
||||
function formatCompactStep(index: number, item: OrderedStepItem, outputYaml: string): string {
|
||||
@@ -556,11 +655,11 @@ function formatThreadReadMarkdown(options: {
|
||||
|
||||
// Step blocks
|
||||
const startIndex = candidates.length - selected.length;
|
||||
const shownPromptRoles = new Set<string>();
|
||||
for (let i = 0; i < selected.length; i++) {
|
||||
const item = selected[i];
|
||||
if (item === undefined) continue;
|
||||
const stepNum = startIndex + i + 1;
|
||||
const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
|
||||
const ts = new Date(item.timestamp)
|
||||
.toISOString()
|
||||
.replace("T", " ")
|
||||
@@ -570,9 +669,10 @@ function formatThreadReadMarkdown(options: {
|
||||
`**Agent:** ${item.payload.agent} | **Time:** ${ts}`,
|
||||
];
|
||||
const roleDef = workflow.roles[item.payload.role];
|
||||
if (roleDef) {
|
||||
if (roleDef && !shownPromptRoles.has(item.payload.role)) {
|
||||
const prompt = roleDef.goal;
|
||||
stepLines.push("", "### Prompt", "", prompt);
|
||||
shownPromptRoles.add(item.payload.role);
|
||||
}
|
||||
if (item.payload.detail) {
|
||||
const content = extractLastAssistantContent(uwf, item.payload.detail);
|
||||
@@ -580,7 +680,6 @@ function formatThreadReadMarkdown(options: {
|
||||
stepLines.push("", "### Content", "", content);
|
||||
}
|
||||
}
|
||||
stepLines.push("", "### Output", "", "```yaml", outputYaml, "```");
|
||||
parts.push(stepLines.join("\n"));
|
||||
}
|
||||
|
||||
|
||||
@@ -7,6 +7,6 @@ export function formatOutput(data: unknown, format: OutputFormat): string {
|
||||
case "json":
|
||||
return JSON.stringify(data);
|
||||
case "yaml":
|
||||
return stringify(data).trimEnd();
|
||||
return stringify(data, { aliasDuplicateObjects: false }).trimEnd();
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,10 +13,28 @@ import { storeBuiltinDetail } from "./detail.js";
|
||||
import type { ChatMessage } from "./llm/index.js";
|
||||
import { BUILTIN_CONTINUE_MAX_TURNS, BUILTIN_MAX_TURNS, runBuiltinLoop } from "./loop.js";
|
||||
import { buildBuiltinMessages } from "./prompt.js";
|
||||
import { initSessionDir, removeSession } from "./session.js";
|
||||
import { initSessionDir } from "./session.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
const FRONTMATTER_FENCE = "---";
|
||||
|
||||
/**
|
||||
* Strip any text before the first `---` fence.
|
||||
* LLMs sometimes emit preamble text before the frontmatter block.
|
||||
*/
|
||||
function stripPreamble(text: string): string {
|
||||
if (text.startsWith(FRONTMATTER_FENCE)) {
|
||||
return text;
|
||||
}
|
||||
const idx = text.indexOf(`\n${FRONTMATTER_FENCE}\n`);
|
||||
if (idx !== -1) {
|
||||
log("6GWRP3QX", `stripped ${idx + 1} chars of preamble before frontmatter`);
|
||||
return text.slice(idx + 1);
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
type SessionRecord = {
|
||||
sessionId: string;
|
||||
model: string;
|
||||
@@ -48,6 +66,7 @@ async function runBuiltinWithMessages(
|
||||
session: SessionRecord,
|
||||
store: Store,
|
||||
maxTurns: number,
|
||||
noTools: boolean,
|
||||
): Promise<AgentRunResult> {
|
||||
const loopResult = await runBuiltinLoop({
|
||||
provider,
|
||||
@@ -56,13 +75,13 @@ async function runBuiltinWithMessages(
|
||||
maxTurns,
|
||||
storageRoot,
|
||||
sessionId: session.sessionId,
|
||||
noTools,
|
||||
});
|
||||
|
||||
session.messages = loopResult.messages;
|
||||
|
||||
if (loopResult.turnCount === 0) {
|
||||
log("5RWTK9NB", "no turns produced, returning empty output");
|
||||
await removeSession(storageRoot, session.sessionId);
|
||||
return { output: "", detailHash: "", sessionId: session.sessionId };
|
||||
}
|
||||
|
||||
@@ -75,10 +94,7 @@ async function runBuiltinWithMessages(
|
||||
session.startedAtMs,
|
||||
);
|
||||
|
||||
// Clean up session jsonl
|
||||
await removeSession(storageRoot, session.sessionId);
|
||||
|
||||
return { output: loopResult.finalText, detailHash, sessionId: session.sessionId };
|
||||
return { output: stripPreamble(loopResult.finalText), detailHash, sessionId: session.sessionId };
|
||||
}
|
||||
|
||||
async function runBuiltin(ctx: AgentContext): Promise<AgentRunResult> {
|
||||
@@ -105,6 +121,7 @@ async function runBuiltin(ctx: AgentContext): Promise<AgentRunResult> {
|
||||
session,
|
||||
ctx.store,
|
||||
BUILTIN_MAX_TURNS,
|
||||
false,
|
||||
);
|
||||
}
|
||||
|
||||
@@ -127,6 +144,7 @@ async function continueBuiltin(
|
||||
session,
|
||||
store,
|
||||
BUILTIN_CONTINUE_MAX_TURNS,
|
||||
true,
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -96,8 +96,17 @@ function serializeMessage(message: ChatMessage): Record<string, unknown> {
|
||||
export async function chatCompletionWithTools(
|
||||
provider: ResolvedLlmProvider,
|
||||
messages: ChatMessage[],
|
||||
tools: OpenAiToolDefinition[],
|
||||
tools: OpenAiToolDefinition[] | null,
|
||||
): Promise<LlmAssistantResponse> {
|
||||
const body: Record<string, unknown> = {
|
||||
model: provider.model,
|
||||
messages: messages.map(serializeMessage),
|
||||
};
|
||||
if (tools !== null && tools.length > 0) {
|
||||
body.tools = tools;
|
||||
body.tool_choice = "auto";
|
||||
}
|
||||
|
||||
let response: Response;
|
||||
try {
|
||||
response = await fetch(chatUrl(provider.baseUrl), {
|
||||
@@ -106,12 +115,7 @@ export async function chatCompletionWithTools(
|
||||
Authorization: `Bearer ${provider.apiKey}`,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: provider.model,
|
||||
messages: messages.map(serializeMessage),
|
||||
tools,
|
||||
tool_choice: "auto",
|
||||
}),
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
|
||||
@@ -23,6 +23,8 @@ export type RunBuiltinLoopOptions = {
|
||||
maxTurns: number;
|
||||
storageRoot: string;
|
||||
sessionId: string;
|
||||
/** When true, do not provide tools — force LLM to emit text only. */
|
||||
noTools: boolean;
|
||||
};
|
||||
|
||||
export type RunBuiltinLoopResult = {
|
||||
@@ -73,13 +75,17 @@ export async function runBuiltinLoop(
|
||||
options: RunBuiltinLoopOptions,
|
||||
): Promise<RunBuiltinLoopResult> {
|
||||
const messages = [...options.messages];
|
||||
const openAiTools = builtinToolsToOpenAi(getBuiltinTools());
|
||||
const openAiTools = options.noTools ? [] : builtinToolsToOpenAi(getBuiltinTools());
|
||||
let finalText = "";
|
||||
let turnCount = 0;
|
||||
|
||||
for (let turn = 0; turn < options.maxTurns; turn++) {
|
||||
log("8K2M4N7P", `builtin loop turn ${turn + 1}/${options.maxTurns}`);
|
||||
const response = await chatCompletionWithTools(options.provider, messages, openAiTools);
|
||||
const response = await chatCompletionWithTools(
|
||||
options.provider,
|
||||
messages,
|
||||
openAiTools.length > 0 ? openAiTools : null,
|
||||
);
|
||||
|
||||
const assistantMessage: ChatMessage = {
|
||||
role: "assistant",
|
||||
@@ -89,14 +95,27 @@ export async function runBuiltinLoop(
|
||||
messages.push(assistantMessage);
|
||||
|
||||
if (response.toolCalls === null || response.toolCalls.length === 0) {
|
||||
finalText = response.content ?? "";
|
||||
const text = response.content ?? "";
|
||||
await appendTurn(options.storageRoot, options.sessionId, {
|
||||
role: "assistant",
|
||||
content: response.content ?? "",
|
||||
content: text,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
turnCount += 1;
|
||||
|
||||
// If tools are available but LLM stopped calling them without producing
|
||||
// frontmatter, nudge it to continue working or output frontmatter.
|
||||
if (!options.noTools && !text.trimStart().startsWith("---") && turn < options.maxTurns - 1) {
|
||||
log("7FXQM2KN", "text-only turn without frontmatter, nudging LLM to continue");
|
||||
const nudge =
|
||||
"You stopped calling tools but your response does not start with the required `---` YAML frontmatter. " +
|
||||
"Either continue using tools to complete your work, or output your final response starting with `---`.";
|
||||
messages.push({ role: "user", content: nudge });
|
||||
continue;
|
||||
}
|
||||
|
||||
finalText = text;
|
||||
break;
|
||||
}
|
||||
|
||||
|
||||
@@ -59,6 +59,21 @@ export function buildBuiltinMessages(ctx: AgentContext): ChatMessage[] {
|
||||
}
|
||||
systemParts.push(rolePrompt);
|
||||
|
||||
systemParts.push(
|
||||
"",
|
||||
"## Workflow",
|
||||
"",
|
||||
`Your working directory is: ${process.cwd()}`,
|
||||
"",
|
||||
"You have tools available (read_file, write_file, run_command). " +
|
||||
"Use them to complete your task — read files, run commands, make changes as needed. " +
|
||||
"Your task is described in the user message below — do NOT use uwf or workflow CLI commands to discover your task. " +
|
||||
"When you are done, output your final response with the YAML frontmatter block as specified above. " +
|
||||
"Do NOT output the frontmatter until you have completed all necessary work. " +
|
||||
"CRITICAL: Your final output MUST start with the `---` fence on the very first line — " +
|
||||
"no preamble text, no explanation before it. The parser requires `---` at position 0.",
|
||||
);
|
||||
|
||||
const messages: ChatMessage[] = [{ role: "system", content: systemParts.join("\n") }];
|
||||
|
||||
const roleVisitIndices: number[] = [];
|
||||
|
||||
@@ -49,6 +49,7 @@ export function buildClaudeCodePrompt(ctx: AgentContext): string {
|
||||
if (historyBlock !== "") {
|
||||
parts.push("", historyBlock);
|
||||
}
|
||||
parts.push("", "## Current Instruction", "", ctx.edgePrompt);
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
@@ -132,6 +133,8 @@ async function processClaudeOutput(stdout: string, store: Store): Promise<AgentR
|
||||
async function runClaudeCode(ctx: AgentContext): Promise<AgentRunResult> {
|
||||
const fullPrompt = buildClaudeCodePrompt(ctx);
|
||||
|
||||
log("K7R2M4N8", `prompt for role=${ctx.role} (length=${fullPrompt.length}):\n${fullPrompt}`);
|
||||
|
||||
// Try resuming a cached session for re-entry scenarios (e.g. reviewer reject → developer re-entry).
|
||||
if (!ctx.isFirstVisit) {
|
||||
const cachedSessionId = await getCachedSessionId(ctx.threadId, ctx.role);
|
||||
|
||||
Reference in New Issue
Block a user