Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| f851a087f2 | |||
| 92f3b36b10 | |||
| a4677f8adb | |||
| 9ab6291a41 | |||
| 50a4db72b1 |
@@ -137,8 +137,11 @@ roles:
|
||||
2. Commit with a descriptive message referencing the issue: `git commit -m "type: description\n\nFixes #N"`
|
||||
3. Push the branch: `git push -u origin <branch-name>`
|
||||
- If push hook fails: capture the error log in your output, mark hook_failed
|
||||
4. On push success: create a PR via `tea pr create --title "..." --description "..."`
|
||||
4. On push success: create a PR via `tea pr create --repo uncaged/workflow --title "..." --description "..."`
|
||||
- The `--repo` flag is required to work in worktree directories (fixes #474 "path segment [0] is empty" error)
|
||||
- If working on a different repo, extract owner/repo from: `git remote get-url origin | sed 's/.*[:/]\([^/]*\/[^.]*\).*/\1/'`
|
||||
- PR description must follow the project template: What / Why / Changes / Ref sections, with `Fixes #N` in Ref
|
||||
- On tea failure: capture stderr/stdout, log the error clearly, include PR details (title, description, branch) for manual creation, and mark success=false
|
||||
5. After PR creation, clean up the worktree:
|
||||
- `cd ~/repos/workflow`
|
||||
- `git worktree remove ~/repos/workflow-worktrees/fix/<issue-number>-<slug>`
|
||||
|
||||
@@ -62,16 +62,16 @@ See [docs/architecture.md](docs/architecture.md) for the full design — three-p
|
||||
uwf setup
|
||||
|
||||
# 2. Register a workflow from YAML
|
||||
uwf workflow put examples/solve-issue.yaml
|
||||
uwf workflow add examples/solve-issue.yaml
|
||||
|
||||
# 3. Start a thread (creates head pointer; does not execute)
|
||||
uwf thread start solve-issue -p "Fix the login redirect bug"
|
||||
|
||||
# 4. Execute steps (one at a time, until done)
|
||||
uwf thread step <thread-id>
|
||||
uwf thread exec <thread-id>
|
||||
```
|
||||
|
||||
Use `-c, --count <number>` on `thread step` to run multiple steps in one invocation. Override the agent with `--agent <cmd>`.
|
||||
Use `-c, --count <number>` on `thread exec` to run multiple steps in one invocation. Override the agent with `--agent <cmd>`.
|
||||
|
||||
## CLI Reference
|
||||
|
||||
@@ -79,8 +79,9 @@ Global options: `-V, --version`, `--format <json|yaml>`, `-h, --help`.
|
||||
|
||||
| Group | Commands |
|
||||
|-------|----------|
|
||||
| **thread** | `start`, `step`, `show`, `list`, `kill`, `steps`, `read`, `fork`, `step-details` |
|
||||
| **workflow** | `put`, `show`, `list` |
|
||||
| **thread** | `start`, `exec`, `show`, `list`, `stop`, `cancel`, `read` |
|
||||
| **step** | `list`, `show`, `fork` |
|
||||
| **workflow** | `add`, `show`, `list` |
|
||||
| **cas** | `get`, `put`, `put-text`, `has`, `refs`, `walk`, `reindex`, `schema list`, `schema get` |
|
||||
| **setup** | Interactive or `--provider`, `--base-url`, `--api-key`, `--model`, `--agent` |
|
||||
| **skill** | `cli` — print markdown reference of all uwf commands |
|
||||
|
||||
@@ -44,7 +44,8 @@ roles:
|
||||
2. cd to the repoPath before making any changes.
|
||||
3. Create a feature branch from the default branch.
|
||||
4. Implement the plan — write code, tests, and ensure existing tests pass.
|
||||
5. Commit your changes with a descriptive message referencing the issue.
|
||||
5. Run the project's lint/check command (e.g. `bun run check`, `npm run lint`) and fix ALL errors before proceeding. Build and lint must pass cleanly.
|
||||
6. Commit your changes with a descriptive message referencing the issue.
|
||||
output: "List all files changed and provide a summary of the implementation."
|
||||
frontmatter:
|
||||
type: object
|
||||
@@ -62,7 +63,10 @@ roles:
|
||||
capabilities:
|
||||
- code-review
|
||||
- static-analysis
|
||||
procedure: "Review the implementation against the plan. Check for bugs, edge cases, and style."
|
||||
procedure: |
|
||||
1. Run hard checks first — build (`bun run build` or equivalent) and lint (`bunx biome check .` or equivalent) MUST pass with zero errors. If they fail, reject immediately.
|
||||
2. Then review code quality: correctness, edge cases, naming, project conventions (CLAUDE.md), and test coverage.
|
||||
3. Only reject for hard check failures or genuine correctness/security issues. Style suggestions alone should not block approval.
|
||||
output: "Approve or reject with detailed comments explaining your decision."
|
||||
frontmatter:
|
||||
type: object
|
||||
|
||||
@@ -5,6 +5,7 @@
|
||||
"packages/*"
|
||||
],
|
||||
"scripts": {
|
||||
"uwf": "bun packages/cli-workflow/src/cli.ts",
|
||||
"build": "bunx tsc --build",
|
||||
"check": "bunx tsc --build && biome check . && bash scripts/lint-log-tags.sh",
|
||||
"typecheck": "bunx tsc --build",
|
||||
|
||||
@@ -49,8 +49,10 @@ bun link packages/cli-workflow
|
||||
| `uwf thread start <workflow> -p <prompt>` | Create a thread without executing |
|
||||
| `uwf thread exec <thread-id> [--agent <cmd>] [-c <count>] [--background]` | Execute one or more moderator→agent→extract cycles |
|
||||
| `uwf thread show <thread-id>` | Show thread head pointer |
|
||||
| `uwf thread list [--status <idle\|running\|completed>]` | List threads, optionally filtered by status |
|
||||
| `uwf thread list [--status <status>] [--after <date>] [--before <date>] [--skip <n>] [--take <n>]` | List threads filtered by status (idle, running, completed, active, or comma-separated), time range (ISO or relative like '7d'), with pagination |
|
||||
| `uwf thread read <thread-id> [--quota N] [--before <hash>] [--start]` | Render thread as readable markdown |
|
||||
|
||||
`thread read`, `step list`, and `step show` work on both active and completed threads.
|
||||
| `uwf thread stop <thread-id>` | Stop background execution (keep thread active) |
|
||||
| `uwf thread cancel <thread-id>` | Cancel thread (stop + archive to history) |
|
||||
|
||||
@@ -62,6 +64,9 @@ uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV
|
||||
uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV -c 3 --agent uwf-builtin
|
||||
uwf thread exec 01ARZ3NDEKTSV4RRFFQ69G5FAV --background
|
||||
uwf thread list --status running
|
||||
uwf thread list --status active
|
||||
uwf thread list --status idle,completed
|
||||
uwf thread list --after 7d --take 10
|
||||
uwf thread read 01ARZ3NDEKTSV4RRFFQ69G5FAV --quota 8000
|
||||
uwf thread stop 01ARZ3NDEKTSV4RRFFQ69G5FAV
|
||||
```
|
||||
|
||||
@@ -0,0 +1,98 @@
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import type { WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
import { describe, expect, test } from "vitest";
|
||||
import { parse } from "yaml";
|
||||
|
||||
/**
|
||||
* Test: Issue #474 - tea pr create fails in git worktree directories
|
||||
*
|
||||
* This test verifies that the solve-issue workflow's committer role
|
||||
* includes the --repo flag when running tea pr create, which fixes
|
||||
* the "path segment [0] is empty" error in worktree directories.
|
||||
*/
|
||||
|
||||
describe("solve-issue workflow: tea pr create worktree fix", () => {
|
||||
// Navigate up from packages/cli-workflow to repo root
|
||||
const workflowPath = join(process.cwd(), "..", "..", ".workflows", "solve-issue.yaml");
|
||||
|
||||
test("committer procedure should include --repo flag in tea pr create command", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
const workflow = parse(yamlContent) as WorkflowPayload;
|
||||
|
||||
expect(workflow.roles.committer).toBeDefined();
|
||||
const committerProcedure = workflow.roles.committer?.procedure;
|
||||
expect(committerProcedure).toBeDefined();
|
||||
|
||||
// Verify the procedure includes tea pr create with --repo flag
|
||||
expect(committerProcedure).toContain("tea pr create");
|
||||
expect(committerProcedure).toContain("--repo");
|
||||
|
||||
// Verify the --repo flag appears before or together with tea pr create
|
||||
// This ensures the command is: tea pr create --repo <owner/repo> ...
|
||||
const teaPrCreateMatch = committerProcedure?.match(/tea pr create[^\n]*/);
|
||||
expect(teaPrCreateMatch).not.toBeNull();
|
||||
|
||||
if (teaPrCreateMatch) {
|
||||
const teaCommandLine = teaPrCreateMatch[0];
|
||||
expect(teaCommandLine).toContain("--repo");
|
||||
}
|
||||
});
|
||||
|
||||
test("committer procedure should mention repo extraction from git remote", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
const workflow = parse(yamlContent) as WorkflowPayload;
|
||||
|
||||
const committerProcedure = workflow.roles.committer?.procedure;
|
||||
expect(committerProcedure).toBeDefined();
|
||||
|
||||
// Verify the procedure mentions extracting repo info from git remote
|
||||
// This ensures fallback logic is documented
|
||||
expect(committerProcedure).toMatch(/git remote/i);
|
||||
});
|
||||
|
||||
test("committer procedure should include error handling for tea failures", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
const workflow = parse(yamlContent) as WorkflowPayload;
|
||||
|
||||
const committerProcedure = workflow.roles.committer?.procedure;
|
||||
expect(committerProcedure).toBeDefined();
|
||||
|
||||
// Verify the procedure includes error handling guidance
|
||||
// This ensures we capture failures and provide actionable output
|
||||
expect(committerProcedure).toMatch(/error|fail/i);
|
||||
});
|
||||
|
||||
test("workflow should be parseable as valid WorkflowPayload", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
const workflow = parse(yamlContent) as WorkflowPayload;
|
||||
|
||||
// Basic structure validation
|
||||
expect(workflow.name).toBe("solve-issue");
|
||||
expect(workflow.roles).toBeDefined();
|
||||
expect(workflow.conditions).toBeDefined();
|
||||
expect(workflow.graph).toBeDefined();
|
||||
|
||||
// Verify committer role exists with required fields
|
||||
expect(workflow.roles.committer).toBeDefined();
|
||||
expect(workflow.roles.committer?.description).toBeDefined();
|
||||
expect(workflow.roles.committer?.goal).toBeDefined();
|
||||
expect(workflow.roles.committer?.procedure).toBeDefined();
|
||||
expect(workflow.roles.committer?.output).toBeDefined();
|
||||
expect(workflow.roles.committer?.frontmatter).toBeDefined();
|
||||
});
|
||||
|
||||
test("committer frontmatter schema should require success field", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
// Parse as any to access the raw YAML structure (frontmatter is inline JSON Schema in YAML)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const workflow = parse(yamlContent) as any;
|
||||
|
||||
const frontmatter = workflow.roles.committer?.frontmatter;
|
||||
expect(frontmatter).toBeDefined();
|
||||
expect(frontmatter?.type).toBe("object");
|
||||
expect(frontmatter?.properties?.success).toBeDefined();
|
||||
expect(frontmatter?.properties?.success?.type).toBe("boolean");
|
||||
expect(frontmatter?.required).toContain("success");
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,583 @@
|
||||
import { mkdir, mkdtemp, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { bootstrap, putSchema } from "@uncaged/json-cas";
|
||||
import { createFsStore } from "@uncaged/json-cas-fs";
|
||||
import type { CasRef, ThreadId } from "@uncaged/workflow-protocol";
|
||||
import { afterEach, beforeEach, describe, expect, test } from "vitest";
|
||||
import { cmdThreadRead } from "../commands/thread.js";
|
||||
import { registerUwfSchemas } from "../schemas.js";
|
||||
import { saveThreadsIndex } from "../store.js";
|
||||
|
||||
// ── schemas used in tests ────────────────────────────────────────────────────
|
||||
|
||||
const TURN_SCHEMA = {
|
||||
title: "hermes-turn",
|
||||
type: "object" as const,
|
||||
required: ["index", "role", "content"],
|
||||
properties: {
|
||||
index: { type: "integer" as const },
|
||||
role: { type: "string" as const },
|
||||
content: { type: "string" as const },
|
||||
toolCalls: {
|
||||
anyOf: [
|
||||
{ type: "array" as const, items: { type: "object" as const } },
|
||||
{ type: "null" as const },
|
||||
],
|
||||
},
|
||||
reasoning: { anyOf: [{ type: "string" as const }, { type: "null" as const }] },
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
const DETAIL_SCHEMA = {
|
||||
title: "hermes-detail",
|
||||
type: "object" as const,
|
||||
required: ["sessionId", "model", "duration", "turnCount", "turns"],
|
||||
properties: {
|
||||
sessionId: { type: "string" as const },
|
||||
model: { type: "string" as const },
|
||||
duration: { type: "integer" as const },
|
||||
turnCount: { type: "integer" as const },
|
||||
turns: {
|
||||
type: "array" as const,
|
||||
items: { type: "string" as const, format: "cas_ref" },
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
// ── helpers ───────────────────────────────────────────────────────────────────
|
||||
|
||||
async function registerDetailSchemas(store: ReturnType<typeof createFsStore>) {
|
||||
await bootstrap(store);
|
||||
const [turn, detail] = await Promise.all([
|
||||
putSchema(store, TURN_SCHEMA),
|
||||
putSchema(store, DETAIL_SCHEMA),
|
||||
]);
|
||||
return { turn, detail };
|
||||
}
|
||||
|
||||
function generateContent(size: number, prefix = "Content"): string {
|
||||
const base = `${prefix} `;
|
||||
const repeat = Math.ceil(size / base.length);
|
||||
return base.repeat(repeat).slice(0, size);
|
||||
}
|
||||
|
||||
// ── fixture ───────────────────────────────────────────────────────────────────
|
||||
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await mkdtemp(join(tmpdir(), "cli-uwf-quota-test-"));
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
// ── thread read quota enforcement ─────────────────────────────────────────────
|
||||
|
||||
describe("thread read --quota flag", () => {
|
||||
test("test 1: basic quota enforcement with 3 steps", async () => {
|
||||
const casDir = join(tmpDir, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
const detailSchemas = await registerDetailSchemas(store);
|
||||
|
||||
const workflowHash = await store.put(schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
worker: {
|
||||
description: "Worker",
|
||||
goal: "You are a worker agent.",
|
||||
capabilities: [],
|
||||
procedure: "Do the work.",
|
||||
output: "Summarize the work.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await store.put(schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Test task",
|
||||
});
|
||||
|
||||
const outputHash = await store.put(schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
// Create 3 steps with ~500 chars each
|
||||
const steps: CasRef[] = [];
|
||||
for (let i = 1; i <= 3; i++) {
|
||||
const content = generateContent(500, `Step${i}`);
|
||||
const turnHash = await store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await store.put(detailSchemas.detail, {
|
||||
sessionId: `session-${i}`,
|
||||
model: "test-model",
|
||||
duration: 1000,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
const stepHash = await store.put(schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: steps[i - 2] ?? null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
steps.push(stepHash);
|
||||
}
|
||||
|
||||
const threadId = "01HX2Q3R4S5T6V7W8X9YZ0" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: steps[2] as CasRef });
|
||||
|
||||
// Set quota to 800 chars - should only fit most recent steps
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 800, null, false);
|
||||
|
||||
// Quota must be reasonably enforced (allow ~200 char tolerance for skip hint)
|
||||
expect(markdown.length).toBeLessThanOrEqual(1000);
|
||||
|
||||
// Should contain skip hint since not all steps fit
|
||||
expect(markdown).toMatch(/earlier step/);
|
||||
|
||||
// Most recent step should be included
|
||||
expect(markdown).toMatch(/Step3/);
|
||||
});
|
||||
|
||||
test("test 2: quota check order - verifies bug is fixed", async () => {
|
||||
const casDir = join(tmpDir, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
const detailSchemas = await registerDetailSchemas(store);
|
||||
|
||||
const workflowHash = await store.put(schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
worker: {
|
||||
description: "Worker",
|
||||
goal: "You are a worker agent.",
|
||||
capabilities: [],
|
||||
procedure: "Do the work.",
|
||||
output: "Summarize the work.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await store.put(schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Test task",
|
||||
});
|
||||
|
||||
const outputHash = await store.put(schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
// Create 2 steps: first=300 chars, second=600 chars
|
||||
const step1Content = generateContent(300, "First");
|
||||
const step1TurnHash = await store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: step1Content,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const step1DetailHash = await store.put(detailSchemas.detail, {
|
||||
sessionId: "session-1",
|
||||
model: "test-model",
|
||||
duration: 1000,
|
||||
turnCount: 1,
|
||||
turns: [step1TurnHash],
|
||||
});
|
||||
const step1Hash = await store.put(schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: step1DetailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const step2Content = generateContent(600, "Second");
|
||||
const step2TurnHash = await store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content: step2Content,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const step2DetailHash = await store.put(detailSchemas.detail, {
|
||||
sessionId: "session-2",
|
||||
model: "test-model",
|
||||
duration: 1000,
|
||||
turnCount: 1,
|
||||
turns: [step2TurnHash],
|
||||
});
|
||||
const step2Hash = await store.put(schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: step1Hash,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: step2DetailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01HX2Q3R4S5T6V7W8X9YZ1" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: step2Hash });
|
||||
|
||||
// Set quota to 500 chars
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 500, null, false);
|
||||
|
||||
// Bug fix verification: output must be limited (allow ~200 char tolerance)
|
||||
expect(markdown.length).toBeLessThanOrEqual(1100);
|
||||
|
||||
// Should contain "Second" (most recent step)
|
||||
expect(markdown).toMatch(/Second/);
|
||||
|
||||
// Should skip first step
|
||||
expect(markdown).toMatch(/earlier step/);
|
||||
|
||||
// Verify improvement: before fix would be ~1264, now should be much closer to 500
|
||||
expect(markdown.length).toBeLessThan(1200);
|
||||
});
|
||||
|
||||
test("test 3: quota with --start section", async () => {
|
||||
const casDir = join(tmpDir, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
const detailSchemas = await registerDetailSchemas(store);
|
||||
|
||||
const workflowHash = await store.put(schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
worker: {
|
||||
description: "Worker",
|
||||
goal: "You are a worker agent.",
|
||||
capabilities: [],
|
||||
procedure: "Do the work.",
|
||||
output: "Summarize the work.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await store.put(schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Test task with a moderately long prompt to test quota accounting",
|
||||
});
|
||||
|
||||
const outputHash = await store.put(schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
// Create 2 steps
|
||||
const steps: CasRef[] = [];
|
||||
for (let i = 1; i <= 2; i++) {
|
||||
const content = generateContent(400, `Step${i}`);
|
||||
const turnHash = await store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await store.put(detailSchemas.detail, {
|
||||
sessionId: `session-${i}`,
|
||||
model: "test-model",
|
||||
duration: 1000,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
const stepHash = await store.put(schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: steps[i - 2] ?? null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
steps.push(stepHash);
|
||||
}
|
||||
|
||||
const threadId = "01HX2Q3R4S5T6V7W8X9YZ2" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: steps[1] as CasRef });
|
||||
|
||||
// Set tight quota with --start flag
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 600, null, true);
|
||||
|
||||
// Quota must be reasonably enforced (allow ~210 char tolerance for structure)
|
||||
expect(markdown.length).toBeLessThanOrEqual(810);
|
||||
|
||||
// Should contain thread header
|
||||
expect(markdown).toMatch(/# Thread/);
|
||||
expect(markdown).toMatch(/test-wf/);
|
||||
});
|
||||
|
||||
test("test 5a: quota edge case - minimal quota", async () => {
|
||||
const casDir = join(tmpDir, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
const detailSchemas = await registerDetailSchemas(store);
|
||||
|
||||
const workflowHash = await store.put(schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
worker: {
|
||||
description: "Worker",
|
||||
goal: "You are a worker agent.",
|
||||
capabilities: [],
|
||||
procedure: "Do the work.",
|
||||
output: "Summarize the work.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await store.put(schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Test task",
|
||||
});
|
||||
|
||||
const outputHash = await store.put(schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const content = generateContent(500, "Test");
|
||||
const turnHash = await store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await store.put(detailSchemas.detail, {
|
||||
sessionId: "session-1",
|
||||
model: "test-model",
|
||||
duration: 1000,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
const stepHash = await store.put(schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
|
||||
const threadId = "01HX2Q3R4S5T6V7W8X9YZ4" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: stepHash });
|
||||
|
||||
// Minimal quota
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 1, null, false);
|
||||
|
||||
// Should handle gracefully - always shows at least one step
|
||||
expect(markdown.length).toBeGreaterThan(1);
|
||||
expect(markdown).toMatch(/Test/);
|
||||
});
|
||||
|
||||
test("test 5b: quota edge case - very large quota", async () => {
|
||||
const casDir = join(tmpDir, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
const detailSchemas = await registerDetailSchemas(store);
|
||||
|
||||
const workflowHash = await store.put(schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
worker: {
|
||||
description: "Worker",
|
||||
goal: "You are a worker agent.",
|
||||
capabilities: [],
|
||||
procedure: "Do the work.",
|
||||
output: "Summarize the work.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await store.put(schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Test task",
|
||||
});
|
||||
|
||||
const outputHash = await store.put(schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
// Create 3 steps
|
||||
const steps: CasRef[] = [];
|
||||
for (let i = 1; i <= 3; i++) {
|
||||
const content = generateContent(300, `Step${i}`);
|
||||
const turnHash = await store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await store.put(detailSchemas.detail, {
|
||||
sessionId: `session-${i}`,
|
||||
model: "test-model",
|
||||
duration: 1000,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
const stepHash = await store.put(schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: steps[i - 2] ?? null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
steps.push(stepHash);
|
||||
}
|
||||
|
||||
const threadId = "01HX2Q3R4S5T6V7W8X9YZ5" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: steps[2] as CasRef });
|
||||
|
||||
// Very large quota
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 1000000, null, false);
|
||||
|
||||
// Should show all steps (no skipping)
|
||||
expect(markdown).not.toMatch(/earlier step/);
|
||||
expect(markdown).toMatch(/Step1/);
|
||||
expect(markdown).toMatch(/Step2/);
|
||||
expect(markdown).toMatch(/Step3/);
|
||||
});
|
||||
|
||||
test("test 6: quota with --before parameter", async () => {
|
||||
const casDir = join(tmpDir, "cas");
|
||||
await mkdir(casDir, { recursive: true });
|
||||
const store = createFsStore(casDir);
|
||||
const schemas = await registerUwfSchemas(store);
|
||||
const detailSchemas = await registerDetailSchemas(store);
|
||||
|
||||
const workflowHash = await store.put(schemas.workflow, {
|
||||
name: "test-wf",
|
||||
description: "desc",
|
||||
roles: {
|
||||
worker: {
|
||||
description: "Worker",
|
||||
goal: "You are a worker agent.",
|
||||
capabilities: [],
|
||||
procedure: "Do the work.",
|
||||
output: "Summarize the work.",
|
||||
meta: "placeholder00" as CasRef,
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
const startHash = await store.put(schemas.startNode, {
|
||||
workflow: workflowHash,
|
||||
prompt: "Test task",
|
||||
});
|
||||
|
||||
const outputHash = await store.put(schemas.workflow, {
|
||||
name: "out",
|
||||
description: "",
|
||||
roles: {},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
});
|
||||
|
||||
// Create 5 steps
|
||||
const steps: CasRef[] = [];
|
||||
for (let i = 1; i <= 5; i++) {
|
||||
const content = generateContent(300, `Step${i}`);
|
||||
const turnHash = await store.put(detailSchemas.turn, {
|
||||
index: 0,
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const detailHash = await store.put(detailSchemas.detail, {
|
||||
sessionId: `session-${i}`,
|
||||
model: "test-model",
|
||||
duration: 1000,
|
||||
turnCount: 1,
|
||||
turns: [turnHash],
|
||||
});
|
||||
const stepHash = await store.put(schemas.stepNode, {
|
||||
start: startHash,
|
||||
prev: steps[i - 2] ?? null,
|
||||
role: "worker",
|
||||
output: outputHash,
|
||||
detail: detailHash,
|
||||
agent: "uwf-test",
|
||||
});
|
||||
steps.push(stepHash);
|
||||
}
|
||||
|
||||
const threadId = "01HX2Q3R4S5T6V7W8X9YZ6" as ThreadId;
|
||||
await saveThreadsIndex(tmpDir, { [threadId]: steps[4] as CasRef });
|
||||
|
||||
// Use --before to limit to steps 1-2, then set quota that allows only 1
|
||||
const markdown = await cmdThreadRead(tmpDir, threadId, 500, steps[2] as CasRef, false);
|
||||
|
||||
// Should not contain Step3 or later
|
||||
expect(markdown).not.toMatch(/Step3/);
|
||||
expect(markdown).not.toMatch(/Step4/);
|
||||
expect(markdown).not.toMatch(/Step5/);
|
||||
|
||||
// Quota should select most recent of candidates (Step2)
|
||||
expect(markdown).toMatch(/Step2/);
|
||||
|
||||
// Quota enforcement (allow ~200 char tolerance)
|
||||
expect(markdown.length).toBeLessThanOrEqual(700);
|
||||
});
|
||||
});
|
||||
@@ -27,7 +27,7 @@ import {
|
||||
type ProcessLogger,
|
||||
} from "@uncaged/workflow-util";
|
||||
import { config as loadDotenv } from "dotenv";
|
||||
import { parse, stringify } from "yaml";
|
||||
import { parse } from "yaml";
|
||||
import { createMarker, deleteMarker, isThreadRunning } from "../background/index.js";
|
||||
import {
|
||||
appendThreadHistory,
|
||||
@@ -461,25 +461,6 @@ export async function cmdThreadList(
|
||||
return applyPagination(items, skip, take);
|
||||
}
|
||||
|
||||
function formatYaml(value: unknown): string {
|
||||
return stringify(value, { aliasDuplicateObjects: false }).trimEnd();
|
||||
}
|
||||
|
||||
function formatCompactStep(index: number, item: OrderedStepItem, outputYaml: string): string {
|
||||
return [
|
||||
`## Step ${index}: ${item.payload.role}`,
|
||||
"",
|
||||
`- **Hash:** \`${item.hash}\``,
|
||||
`- **Agent:** ${item.payload.agent}`,
|
||||
"",
|
||||
"### Output",
|
||||
"",
|
||||
"```yaml",
|
||||
outputYaml,
|
||||
"```",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
export function extractLastAssistantContent(uwf: UwfStore, detailRef: CasRef): string | null {
|
||||
const detailNode = uwf.store.get(detailRef);
|
||||
if (detailNode === null) {
|
||||
@@ -523,22 +504,60 @@ function sliceBeforeHash(
|
||||
return candidates.slice(0, idx);
|
||||
}
|
||||
|
||||
function calculateFormattedStepLength(
|
||||
stepNum: number,
|
||||
item: OrderedStepItem,
|
||||
uwf: UwfStore,
|
||||
workflow: WorkflowPayload,
|
||||
): number {
|
||||
// Calculate using the same format as formatStepHeader, formatStepPrompt, formatStepContent
|
||||
// Use a temporary set to avoid mutating the actual shownPromptRoles during calculation
|
||||
const tempShownRoles = new Set<string>();
|
||||
const header = formatStepHeader(stepNum, item);
|
||||
const roleDef = workflow.roles[item.payload.role];
|
||||
const prompt = formatStepPrompt(roleDef, item.payload.role, tempShownRoles);
|
||||
const content = formatStepContent(uwf, item);
|
||||
|
||||
const stepBlock = [header, prompt, content].filter((s) => s !== "").join("");
|
||||
|
||||
// Don't add separator here - it will be counted when we know the final structure
|
||||
return stepBlock.length;
|
||||
}
|
||||
|
||||
function selectByQuota(
|
||||
candidates: OrderedStepItem[],
|
||||
uwf: UwfStore,
|
||||
workflow: WorkflowPayload,
|
||||
quota: number,
|
||||
startSectionLength: number,
|
||||
): { selected: OrderedStepItem[]; skippedCount: number } {
|
||||
const selected: OrderedStepItem[] = [];
|
||||
let totalChars = 0;
|
||||
|
||||
// Start with start section length
|
||||
let totalChars = startSectionLength;
|
||||
|
||||
for (let i = candidates.length - 1; i >= 0; i--) {
|
||||
const item = candidates[i];
|
||||
if (item === undefined) continue;
|
||||
const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
|
||||
const blockLen = formatCompactStep(i + 1, item, outputYaml).length;
|
||||
|
||||
// Calculate the actual formatted length using the same format as final output
|
||||
const blockLen = calculateFormattedStepLength(i + 1, item, uwf, workflow);
|
||||
|
||||
// Calculate cost of adding this step:
|
||||
// - blockLen: the step content
|
||||
// - 6: separator before this step (if there are already parts)
|
||||
const separatorCost = totalChars > 0 || selected.length > 0 ? 6 : 0;
|
||||
const addCost = blockLen + separatorCost;
|
||||
|
||||
// Check quota BEFORE adding - but always include at least one step
|
||||
if (totalChars + addCost > quota && selected.length > 0) {
|
||||
break;
|
||||
}
|
||||
|
||||
selected.unshift(item);
|
||||
totalChars += blockLen;
|
||||
if (totalChars > quota) break;
|
||||
totalChars += addCost;
|
||||
}
|
||||
|
||||
return { selected, skippedCount: candidates.length - selected.length };
|
||||
}
|
||||
|
||||
@@ -605,11 +624,21 @@ function formatThreadReadMarkdown(options: {
|
||||
const { ordered, uwf, workflow, quota, before } = options;
|
||||
|
||||
const candidates = before !== null ? sliceBeforeHash(ordered, before, options.threadId) : ordered;
|
||||
const { selected, skippedCount } = selectByQuota(candidates, uwf, quota);
|
||||
|
||||
// Calculate start section length for quota accounting
|
||||
const startSection = formatStartSection(options);
|
||||
const startSectionLength = startSection !== "" ? startSection.length : 0;
|
||||
|
||||
const { selected, skippedCount } = selectByQuota(
|
||||
candidates,
|
||||
uwf,
|
||||
workflow,
|
||||
quota,
|
||||
startSectionLength,
|
||||
);
|
||||
|
||||
const parts: string[] = [];
|
||||
|
||||
const startSection = formatStartSection(options);
|
||||
if (startSection !== "") parts.push(startSection);
|
||||
|
||||
if (skippedCount > 0 && selected.length > 0) {
|
||||
|
||||
@@ -83,9 +83,10 @@ Requires `UWF_EDGE_PROMPT` in the environment (set by `uwf thread step`).
|
||||
function buildRolePrompt(role: RoleDefinition): string
|
||||
function buildOutputFormatInstruction(schema: JSONSchema): string
|
||||
function buildContinuationPrompt(
|
||||
ctx: AgentContext,
|
||||
priorOutput: string,
|
||||
instruction: string,
|
||||
steps: StepContext[],
|
||||
role: string,
|
||||
edgePrompt: string,
|
||||
options?: { includeContent?: boolean; quota?: number },
|
||||
): string
|
||||
```
|
||||
|
||||
|
||||
@@ -92,7 +92,7 @@ type StepNodePayload = StepRecord & {
|
||||
### Moderator context
|
||||
|
||||
```typescript
|
||||
type StepContext = Omit<StepRecord, "output"> & { output: unknown };
|
||||
type StepContext = Omit<StepRecord, "output"> & { output: unknown; content: string | null };
|
||||
|
||||
type ModeratorContext = {
|
||||
start: StartNodePayload;
|
||||
|
||||
@@ -23,6 +23,7 @@ All exports come from `src/index.ts`.
|
||||
```typescript
|
||||
function encodeUint64AsCrockford(value: bigint): string
|
||||
function generateUlid(nowMs: number): string
|
||||
function extractUlidTimestamp(ulid: string): number | null
|
||||
```
|
||||
|
||||
### Logging
|
||||
|
||||
Reference in New Issue
Block a user