Compare commits
20 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 4d47effd39 | |||
| 7b93ce8f3e | |||
| 67870392ab | |||
| 6b9ff9781d | |||
| 487c48effa | |||
| 4eca2d533c | |||
| f0f840e6e0 | |||
| 7ff90cef4f | |||
| e62d51d845 | |||
| a803fcb4fc | |||
| d00c93fc19 | |||
| 99a2890be2 | |||
| 3b7d0564bb | |||
| 2eb5ee0666 | |||
| e67932c83c | |||
| 04a12231c3 | |||
| e5ae9a134c | |||
| bdafaf3aa1 | |||
| 02f7f0b708 | |||
| 8ea554bb5e |
+13
-13
@@ -20,10 +20,10 @@ roles:
|
||||
2. Revise the test spec accordingly
|
||||
|
||||
After producing the test spec:
|
||||
1. Store it via `uwf cas put "<markdown content>"` and capture the returned hash
|
||||
2. Put the hash in meta.plan (required when status=ready)
|
||||
1. Store it via `uwf cas put-text "<markdown content>"` and capture the returned hash
|
||||
2. Put the hash in frontmatter.plan (required when status=ready)
|
||||
output: "Output a brief summary of the test spec. Frontmatter must include: status (ready or insufficient_info) and plan (CAS hash of the test spec, required when status=ready)."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
status:
|
||||
@@ -45,7 +45,7 @@ roles:
|
||||
5. Ensure `bun run build` passes with no errors
|
||||
6. Run `bun test` to verify all tests pass
|
||||
output: "List all files changed and provide a summary. Frontmatter must include: status (done or failed)."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
status:
|
||||
@@ -75,7 +75,7 @@ roles:
|
||||
Only review standards compliance. Do NOT test functionality.
|
||||
If rejecting, you MUST explain the specific reason in your output.
|
||||
output: "Explain your decision with specific file/line references. Frontmatter must include: approved (true or false)."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
approved:
|
||||
@@ -95,7 +95,7 @@ roles:
|
||||
- fix_code: tests fail or implementation doesn't match spec → send back to developer
|
||||
- fix_spec: the spec itself is wrong or incomplete → send back to planner
|
||||
output: "Report test results per scenario. Frontmatter must include: status (passed, fix_code, or fix_spec)."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
status:
|
||||
@@ -115,7 +115,7 @@ roles:
|
||||
4. On push success: create a PR via `tea pr create --title "..." --description "..."`
|
||||
- PR description must follow the project template: What / Why / Changes / Ref sections, with `Fixes #N` in Ref
|
||||
output: "Include PR URL on success or error log on failure. Frontmatter must include: success (true or false)."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
success:
|
||||
@@ -124,22 +124,22 @@ roles:
|
||||
conditions:
|
||||
insufficientInfo:
|
||||
description: "Planner determined there's not enough info to proceed"
|
||||
expression: "steps[-1].output.status = 'insufficient_info'"
|
||||
expression: "$last('planner').status = 'insufficient_info'"
|
||||
devFailed:
|
||||
description: "Developer failed to implement"
|
||||
expression: "steps[-1].output.status = 'failed'"
|
||||
expression: "$last('developer').status = 'failed'"
|
||||
rejected:
|
||||
description: "Reviewer rejected the implementation"
|
||||
expression: "steps[-1].output.approved = false"
|
||||
expression: "$last('reviewer').approved = false"
|
||||
fixCode:
|
||||
description: "Tester found code issues"
|
||||
expression: "steps[-1].output.status = 'fix_code'"
|
||||
expression: "$last('tester').status = 'fix_code'"
|
||||
fixSpec:
|
||||
description: "Tester found spec issues"
|
||||
expression: "steps[-1].output.status = 'fix_spec'"
|
||||
expression: "$last('tester').status = 'fix_spec'"
|
||||
hookFailed:
|
||||
description: "Push hook failed"
|
||||
expression: "steps[-1].output.success = false"
|
||||
expression: "$last('committer').success = false"
|
||||
graph:
|
||||
$START:
|
||||
- role: "planner"
|
||||
|
||||
@@ -19,7 +19,7 @@ roles:
|
||||
output: |
|
||||
Provide your analysis as markdown under the frontmatter.
|
||||
The frontmatter must include your structured findings.
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
thesis:
|
||||
|
||||
@@ -9,7 +9,7 @@ roles:
|
||||
- planning
|
||||
procedure: "Analyze the issue and create a detailed, actionable implementation plan."
|
||||
output: "Output the plan summary and list of concrete steps."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
plan:
|
||||
@@ -28,7 +28,7 @@ roles:
|
||||
- testing
|
||||
procedure: "Implement the plan. Write code, tests, and ensure existing tests pass."
|
||||
output: "List all files changed and provide a summary of the implementation."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
filesChanged:
|
||||
@@ -46,7 +46,7 @@ roles:
|
||||
- static-analysis
|
||||
procedure: "Review the implementation against the plan. Check for bugs, edge cases, and style."
|
||||
output: "Approve or reject with detailed comments explaining your decision."
|
||||
meta:
|
||||
frontmatter:
|
||||
type: object
|
||||
properties:
|
||||
approved:
|
||||
@@ -57,7 +57,7 @@ roles:
|
||||
conditions:
|
||||
notApproved:
|
||||
description: "Reviewer rejected the implementation"
|
||||
expression: "steps[-1].output.approved = false"
|
||||
expression: "$last('reviewer').approved = false"
|
||||
graph:
|
||||
$START:
|
||||
- role: "planner"
|
||||
|
||||
@@ -7,6 +7,7 @@ import {
|
||||
cmdCasGet,
|
||||
cmdCasHas,
|
||||
cmdCasPut,
|
||||
cmdCasPutText,
|
||||
cmdCasRefs,
|
||||
cmdCasReindex,
|
||||
cmdCasSchemaGet,
|
||||
@@ -295,6 +296,17 @@ cas
|
||||
});
|
||||
});
|
||||
|
||||
cas
|
||||
.command("put-text")
|
||||
.description("Store a plain text string, print its hash")
|
||||
.argument("<text>", "Text content to store")
|
||||
.action((text: string) => {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
runAction(async () => {
|
||||
writeOutput(await cmdCasPutText(storageRoot, text));
|
||||
});
|
||||
});
|
||||
|
||||
cas
|
||||
.command("has")
|
||||
.description("Check if a hash exists")
|
||||
|
||||
@@ -2,9 +2,11 @@ import { readFileSync } from "node:fs";
|
||||
import { join } from "node:path";
|
||||
|
||||
import type { JSONSchema, Store } from "@uncaged/json-cas";
|
||||
import { bootstrap, getSchema, refs, walk } from "@uncaged/json-cas";
|
||||
import { bootstrap, getSchema, putSchema, refs, walk } from "@uncaged/json-cas";
|
||||
import { createFsStore } from "@uncaged/json-cas-fs";
|
||||
|
||||
import { TEXT_SCHEMA } from "../schemas.js";
|
||||
|
||||
// ---- Helpers ----
|
||||
|
||||
function openStore(storageRoot: string): Store {
|
||||
@@ -121,3 +123,10 @@ export async function cmdCasSchemaGet(storageRoot: string, hash: string): Promis
|
||||
}
|
||||
return schema;
|
||||
}
|
||||
|
||||
export async function cmdCasPutText(storageRoot: string, text: string): Promise<{ hash: string }> {
|
||||
const store = openStore(storageRoot);
|
||||
const typeHash = await putSchema(store, TEXT_SCHEMA);
|
||||
const hash = await store.put(typeHash, text);
|
||||
return { hash };
|
||||
}
|
||||
|
||||
@@ -2,7 +2,12 @@ import { readFile } from "node:fs/promises";
|
||||
|
||||
import type { JSONSchema } from "@uncaged/json-cas";
|
||||
import { putSchema, validate } from "@uncaged/json-cas";
|
||||
import type { CasRef, RoleDefinition, WorkflowPayload } from "@uncaged/workflow-protocol";
|
||||
import type {
|
||||
CasRef,
|
||||
RoleDefinition,
|
||||
Transition,
|
||||
WorkflowPayload,
|
||||
} from "@uncaged/workflow-protocol";
|
||||
import { parse } from "yaml";
|
||||
|
||||
import {
|
||||
@@ -46,11 +51,28 @@ function isJsonSchema(value: unknown): value is JSONSchema {
|
||||
return typeof value === "object" && value !== null && !Array.isArray(value);
|
||||
}
|
||||
|
||||
async function resolveMetaRef(uwf: UwfStore, roleName: string, meta: unknown): Promise<CasRef> {
|
||||
if (!isJsonSchema(meta)) {
|
||||
fail(`role "${roleName}": meta must be a JSON Schema object`);
|
||||
/** Normalize graph transitions: ensure condition is null (not undefined) for fallback entries. */
|
||||
function normalizeGraph(graph: Record<string, Transition[]>): Record<string, Transition[]> {
|
||||
const result: Record<string, Transition[]> = {};
|
||||
for (const [node, transitions] of Object.entries(graph)) {
|
||||
result[node] = transitions.map((t) => ({
|
||||
role: t.role,
|
||||
condition: t.condition ?? null,
|
||||
}));
|
||||
}
|
||||
const schema: JSONSchema = meta.title === undefined ? { ...meta, title: roleName } : meta;
|
||||
return result;
|
||||
}
|
||||
|
||||
async function resolveFrontmatterRef(
|
||||
uwf: UwfStore,
|
||||
roleName: string,
|
||||
frontmatter: unknown,
|
||||
): Promise<CasRef> {
|
||||
if (!isJsonSchema(frontmatter)) {
|
||||
fail(`role "${roleName}": frontmatter must be a JSON Schema object`);
|
||||
}
|
||||
const schema: JSONSchema =
|
||||
frontmatter.title === undefined ? { ...frontmatter, title: roleName } : frontmatter;
|
||||
return putSchema(uwf.store, schema);
|
||||
}
|
||||
|
||||
@@ -60,14 +82,18 @@ export async function materializeWorkflowPayload(
|
||||
): Promise<WorkflowPayload> {
|
||||
const roles: Record<string, RoleDefinition> = {};
|
||||
for (const [roleName, role] of Object.entries(raw.roles)) {
|
||||
const meta = await resolveMetaRef(uwf, `${raw.name}.${roleName}`, role.meta);
|
||||
const frontmatter = await resolveFrontmatterRef(
|
||||
uwf,
|
||||
`${raw.name}.${roleName}`,
|
||||
role.frontmatter,
|
||||
);
|
||||
roles[roleName] = {
|
||||
description: role.description,
|
||||
goal: role.goal,
|
||||
capabilities: role.capabilities,
|
||||
procedure: role.procedure,
|
||||
output: role.output,
|
||||
meta,
|
||||
frontmatter,
|
||||
};
|
||||
}
|
||||
return {
|
||||
@@ -75,7 +101,7 @@ export async function materializeWorkflowPayload(
|
||||
description: raw.description,
|
||||
roles,
|
||||
conditions: raw.conditions,
|
||||
graph: raw.graph,
|
||||
graph: normalizeGraph(raw.graph),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -2,10 +2,13 @@ import type { Hash, Store } from "@uncaged/json-cas";
|
||||
import { putSchema } from "@uncaged/json-cas";
|
||||
import { START_NODE_SCHEMA, STEP_NODE_SCHEMA, WORKFLOW_SCHEMA } from "@uncaged/workflow-protocol";
|
||||
|
||||
export const TEXT_SCHEMA = { type: "string" as const };
|
||||
|
||||
export type UwfSchemaHashes = {
|
||||
workflow: Hash;
|
||||
startNode: Hash;
|
||||
stepNode: Hash;
|
||||
text: Hash;
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -13,10 +16,11 @@ export type UwfSchemaHashes = {
|
||||
* Idempotent: safe to call on every CLI invocation.
|
||||
*/
|
||||
export async function registerUwfSchemas(store: Store): Promise<UwfSchemaHashes> {
|
||||
const [workflow, startNode, stepNode] = await Promise.all([
|
||||
const [workflow, startNode, stepNode, text] = await Promise.all([
|
||||
putSchema(store, WORKFLOW_SCHEMA),
|
||||
putSchema(store, START_NODE_SCHEMA),
|
||||
putSchema(store, STEP_NODE_SCHEMA),
|
||||
putSchema(store, TEXT_SCHEMA),
|
||||
]);
|
||||
return { workflow, startNode, stepNode };
|
||||
return { workflow, startNode, stepNode, text };
|
||||
}
|
||||
|
||||
@@ -15,8 +15,8 @@ function isRoleDefinition(value: unknown): boolean {
|
||||
if (!isRecord(value)) {
|
||||
return false;
|
||||
}
|
||||
const meta = value.meta;
|
||||
const metaOk = isRecord(meta) && typeof meta.type === "string";
|
||||
const frontmatter = value.frontmatter;
|
||||
const frontmatterOk = isRecord(frontmatter) && typeof frontmatter.type === "string";
|
||||
const capabilities = value.capabilities;
|
||||
const capabilitiesOk =
|
||||
Array.isArray(capabilities) && capabilities.every((c) => typeof c === "string");
|
||||
@@ -26,7 +26,7 @@ function isRoleDefinition(value: unknown): boolean {
|
||||
capabilitiesOk &&
|
||||
typeof value.procedure === "string" &&
|
||||
typeof value.output === "string" &&
|
||||
metaOk
|
||||
frontmatterOk
|
||||
);
|
||||
}
|
||||
|
||||
@@ -42,7 +42,10 @@ function isTransition(value: unknown): boolean {
|
||||
return false;
|
||||
}
|
||||
const condition = value.condition;
|
||||
return typeof value.role === "string" && (condition === null || typeof condition === "string");
|
||||
return (
|
||||
typeof value.role === "string" &&
|
||||
(condition === null || condition === undefined || typeof condition === "string")
|
||||
);
|
||||
}
|
||||
|
||||
function isStringRecord(value: unknown, itemCheck: (item: unknown) => boolean): boolean {
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { spawn } from "node:child_process";
|
||||
import type { Store } from "@uncaged/json-cas";
|
||||
|
||||
import {
|
||||
type AgentContext,
|
||||
@@ -10,7 +11,6 @@ import {
|
||||
import {
|
||||
loadHermesSession,
|
||||
parseSessionIdFromStdout,
|
||||
storeHermesRawOutput,
|
||||
storeHermesSessionDetail,
|
||||
} from "./session-detail.js";
|
||||
|
||||
@@ -52,17 +52,8 @@ export function buildHermesPrompt(ctx: AgentContext): string {
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
function spawnHermesChat(prompt: string): Promise<{ stdout: string; stderr: string }> {
|
||||
function spawnHermes(args: string[]): Promise<{ stdout: string; stderr: string }> {
|
||||
return new Promise((resolve, reject) => {
|
||||
const args = [
|
||||
"chat",
|
||||
"-q",
|
||||
prompt,
|
||||
"--yolo",
|
||||
"--max-turns",
|
||||
String(HERMES_MAX_TURNS),
|
||||
"--quiet",
|
||||
];
|
||||
const child = spawn(HERMES_COMMAND, args, {
|
||||
env: process.env,
|
||||
shell: false,
|
||||
@@ -94,23 +85,73 @@ function spawnHermesChat(prompt: string): Promise<{ stdout: string; stderr: stri
|
||||
});
|
||||
}
|
||||
|
||||
function spawnHermesChat(prompt: string): Promise<{ stdout: string; stderr: string }> {
|
||||
return spawnHermes([
|
||||
"chat",
|
||||
"-q",
|
||||
prompt,
|
||||
"--yolo",
|
||||
"--max-turns",
|
||||
String(HERMES_MAX_TURNS),
|
||||
"--quiet",
|
||||
]);
|
||||
}
|
||||
|
||||
function spawnHermesResume(
|
||||
sessionId: string,
|
||||
message: string,
|
||||
): Promise<{ stdout: string; stderr: string }> {
|
||||
return spawnHermes([
|
||||
"chat",
|
||||
"--resume",
|
||||
sessionId,
|
||||
"-q",
|
||||
message,
|
||||
"--yolo",
|
||||
"--max-turns",
|
||||
String(HERMES_MAX_TURNS),
|
||||
"--quiet",
|
||||
]);
|
||||
}
|
||||
|
||||
function parseSessionId(stdout: string, stderr: string): string {
|
||||
const sessionId = parseSessionIdFromStdout(stderr) ?? parseSessionIdFromStdout(stdout);
|
||||
if (sessionId === null) {
|
||||
throw new Error(
|
||||
"Failed to parse session_id from hermes output.\n" +
|
||||
`stderr (first 200 chars): ${stderr.slice(0, 200)}\n` +
|
||||
`stdout (first 200 chars): ${stdout.slice(0, 200)}`,
|
||||
);
|
||||
}
|
||||
return sessionId;
|
||||
}
|
||||
|
||||
async function buildResultFromSession(sessionId: string, store: Store): Promise<AgentRunResult> {
|
||||
const session = await loadHermesSession(sessionId);
|
||||
if (session === null) {
|
||||
throw new Error(`Failed to load hermes session file for session_id: ${sessionId}`);
|
||||
}
|
||||
const { detailHash, output } = await storeHermesSessionDetail(store, session);
|
||||
return { output, detailHash, sessionId };
|
||||
}
|
||||
|
||||
async function runHermes(ctx: AgentContext): Promise<AgentRunResult> {
|
||||
const fullPrompt = buildHermesPrompt(ctx);
|
||||
const { stdout, stderr } = await spawnHermesChat(fullPrompt);
|
||||
const { store } = ctx;
|
||||
const sessionId = parseSessionId(stdout, stderr);
|
||||
return buildResultFromSession(sessionId, ctx.store);
|
||||
}
|
||||
|
||||
// --quiet mode: session_id may be on stdout or stderr
|
||||
const sessionId = parseSessionIdFromStdout(stderr) ?? parseSessionIdFromStdout(stdout);
|
||||
if (sessionId !== null) {
|
||||
const session = await loadHermesSession(sessionId);
|
||||
if (session !== null) {
|
||||
const { detailHash, output } = await storeHermesSessionDetail(store, session);
|
||||
return { output, detailHash };
|
||||
}
|
||||
}
|
||||
|
||||
const detailHash = await storeHermesRawOutput(store, stdout);
|
||||
return { output: stdout, detailHash };
|
||||
async function continueHermes(
|
||||
sessionId: string,
|
||||
message: string,
|
||||
store: Store,
|
||||
): Promise<AgentRunResult> {
|
||||
const { stdout, stderr } = await spawnHermesResume(sessionId, message);
|
||||
// Resume may return a new session_id
|
||||
const newSessionId = parseSessionIdFromStdout(stderr) ?? parseSessionIdFromStdout(stdout);
|
||||
const resolvedId = newSessionId ?? sessionId;
|
||||
return buildResultFromSession(resolvedId, store);
|
||||
}
|
||||
|
||||
/** Agent CLI factory: parses argv, runs Hermes, extracts output, writes StepNode. */
|
||||
@@ -118,5 +159,6 @@ export function createHermesAgent(): () => Promise<void> {
|
||||
return createAgent({
|
||||
name: "hermes",
|
||||
run: runHermes,
|
||||
continue: continueHermes,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -2,13 +2,32 @@ import { describe, expect, test } from "vitest";
|
||||
|
||||
import { buildOutputFormatInstruction } from "../src/build-output-format-instruction.js";
|
||||
|
||||
const PLANNER_SCHEMA = {
|
||||
type: "object",
|
||||
properties: {
|
||||
status: { type: "string", enum: ["ready", "insufficient_info"] },
|
||||
plan: { type: "string" },
|
||||
},
|
||||
required: ["status"],
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
const REVIEWER_SCHEMA = {
|
||||
type: "object",
|
||||
properties: {
|
||||
approved: { type: "boolean" },
|
||||
},
|
||||
required: ["approved"],
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
describe("buildOutputFormatInstruction", () => {
|
||||
test("always includes the frontmatter example block", () => {
|
||||
const result = buildOutputFormatInstruction({});
|
||||
expect(result).toContain("---");
|
||||
expect(result).toContain("status: done");
|
||||
expect(result).toContain("confidence:");
|
||||
expect(result).toContain("scope: role");
|
||||
expect(result).not.toContain("status: done");
|
||||
expect(result).not.toContain("confidence:");
|
||||
expect(result).not.toContain("scope: role");
|
||||
});
|
||||
|
||||
test("always marks frontmatter as the primary deliverable", () => {
|
||||
@@ -16,17 +35,36 @@ describe("buildOutputFormatInstruction", () => {
|
||||
expect(result).toContain("primary deliverable");
|
||||
});
|
||||
|
||||
test("lists fields from a flat object schema", () => {
|
||||
test("generates planner-specific YAML example from schema", () => {
|
||||
const result = buildOutputFormatInstruction(PLANNER_SCHEMA);
|
||||
expect(result).toContain("status: ready # required | ready | insufficient_info");
|
||||
expect(result).toContain("plan: <string>");
|
||||
expect(result).not.toContain("status: done");
|
||||
expect(result).not.toContain("confidence:");
|
||||
expect(result).not.toContain("artifacts:");
|
||||
});
|
||||
|
||||
test("generates reviewer-specific YAML example from schema", () => {
|
||||
const result = buildOutputFormatInstruction(REVIEWER_SCHEMA);
|
||||
expect(result).toContain("approved: true # required | true | false");
|
||||
expect(result).not.toContain("status:");
|
||||
});
|
||||
|
||||
test("lists fields from a flat object schema with required marker", () => {
|
||||
const schema = {
|
||||
type: "object",
|
||||
properties: {
|
||||
status: { type: "string" },
|
||||
confidence: { type: "number" },
|
||||
},
|
||||
required: ["status"],
|
||||
};
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("`status`");
|
||||
expect(result).toContain("`status` (required)");
|
||||
expect(result).toContain("`confidence`");
|
||||
expect(result).not.toContain("`confidence` (required)");
|
||||
expect(result).toContain("status: <string> # required");
|
||||
expect(result).toContain("confidence: <number>");
|
||||
});
|
||||
|
||||
test("lists union of fields from an anyOf schema", () => {
|
||||
@@ -45,6 +83,8 @@ describe("buildOutputFormatInstruction", () => {
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("`alpha`");
|
||||
expect(result).toContain("`beta`");
|
||||
expect(result).toContain("alpha: <string>");
|
||||
expect(result).toContain("beta: <number>");
|
||||
});
|
||||
|
||||
test("lists union of fields from a oneOf schema", () => {
|
||||
@@ -63,6 +103,8 @@ describe("buildOutputFormatInstruction", () => {
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("`foo`");
|
||||
expect(result).toContain("`bar`");
|
||||
expect(result).toContain("foo: <string>");
|
||||
expect(result).toContain("bar: true # true | false");
|
||||
});
|
||||
|
||||
test("falls back gracefully for a non-object schema with no properties", () => {
|
||||
@@ -80,6 +122,23 @@ describe("buildOutputFormatInstruction", () => {
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
const matches = [...result.matchAll(/`shared`/g)];
|
||||
expect(matches.length).toBe(1);
|
||||
expect(result).toContain("shared: <string>");
|
||||
});
|
||||
|
||||
test("marks required when any union variant requires the field", () => {
|
||||
const schema = {
|
||||
anyOf: [
|
||||
{
|
||||
type: "object",
|
||||
properties: { shared: { type: "string" } },
|
||||
required: ["shared"],
|
||||
},
|
||||
{ type: "object", properties: { shared: { type: "number" } } },
|
||||
],
|
||||
};
|
||||
const result = buildOutputFormatInstruction(schema);
|
||||
expect(result).toContain("`shared` (required)");
|
||||
expect(result).toContain("shared: <string> # required");
|
||||
});
|
||||
|
||||
test("includes focus reminder about role scope", () => {
|
||||
|
||||
@@ -29,6 +29,27 @@ const STRICT_SCHEMA = {
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
/** Role-specific schema (reviewer) — only approved, no standard agent fields. */
|
||||
const REVIEWER_SCHEMA = {
|
||||
type: "object",
|
||||
properties: {
|
||||
approved: { type: "boolean" },
|
||||
},
|
||||
required: ["approved"],
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
/** Role-specific schema (planner) — custom status enum + plan hash. */
|
||||
const PLANNER_SCHEMA = {
|
||||
type: "object",
|
||||
properties: {
|
||||
status: { type: "string", enum: ["ready", "insufficient_info"] },
|
||||
plan: { type: "string" },
|
||||
},
|
||||
required: ["status"],
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
async function makeStoreWithSchema(schema: Record<string, unknown>) {
|
||||
const store = createMemoryStore();
|
||||
const schemaHash = await putSchema(store, schema);
|
||||
@@ -134,3 +155,48 @@ describe("tryFrontmatterFastPath — fallback: schema mismatch", () => {
|
||||
expect(result).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
// ── Role-specific schema fields ───────────────────────────────────────────────
|
||||
|
||||
describe("tryFrontmatterFastPath — role-specific fields", () => {
|
||||
test("extracts approved only for reviewer schema (no extra standard fields)", async () => {
|
||||
const { store, schemaHash } = await makeStoreWithSchema(REVIEWER_SCHEMA);
|
||||
|
||||
const raw = "---\napproved: true\n---\n\nReview passed.";
|
||||
|
||||
const result = await tryFrontmatterFastPath(raw, schemaHash, store);
|
||||
expect(result).not.toBeNull();
|
||||
|
||||
const node = store.get(result!.outputHash);
|
||||
expect(node).not.toBeNull();
|
||||
const payload = node!.payload as Record<string, unknown>;
|
||||
expect(payload).toEqual({ approved: true });
|
||||
expect(payload.status).toBeUndefined();
|
||||
expect(payload.scope).toBeUndefined();
|
||||
});
|
||||
|
||||
test("extracts plan and role-specific status for planner schema", async () => {
|
||||
const { store, schemaHash } = await makeStoreWithSchema(PLANNER_SCHEMA);
|
||||
|
||||
const raw = "---\nstatus: ready\nplan: 01HASHPLANNER0001\n---\n\nSpec summary.";
|
||||
|
||||
const result = await tryFrontmatterFastPath(raw, schemaHash, store);
|
||||
expect(result).not.toBeNull();
|
||||
|
||||
const node = store.get(result!.outputHash);
|
||||
expect(node).not.toBeNull();
|
||||
const payload = node!.payload as Record<string, unknown>;
|
||||
expect(payload.status).toBe("ready");
|
||||
expect(payload.plan).toBe("01HASHPLANNER0001");
|
||||
expect(payload.scope).toBeUndefined();
|
||||
});
|
||||
|
||||
test("returns null when required role-specific field is missing", async () => {
|
||||
const { store, schemaHash } = await makeStoreWithSchema(REVIEWER_SCHEMA);
|
||||
|
||||
const raw = "---\nstatus: done\nscope: role\n---\n\nBody.";
|
||||
|
||||
const result = await tryFrontmatterFastPath(raw, schemaHash, store);
|
||||
expect(result).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,5 +1,11 @@
|
||||
import type { JSONSchema } from "@uncaged/json-cas";
|
||||
|
||||
type SchemaProperty = {
|
||||
name: string;
|
||||
schema: JSONSchema;
|
||||
required: boolean;
|
||||
};
|
||||
|
||||
/**
|
||||
* Extract top-level property names from a JSON Schema object.
|
||||
*
|
||||
@@ -9,9 +15,44 @@ import type { JSONSchema } from "@uncaged/json-cas";
|
||||
*
|
||||
* Returns an empty array for schemas with no inspectable property definitions.
|
||||
*/
|
||||
function extractSchemaFields(schema: JSONSchema): string[] {
|
||||
export function extractSchemaFields(schema: JSONSchema): string[] {
|
||||
return extractSchemaProperties(schema).map((p) => p.name);
|
||||
}
|
||||
|
||||
function extractSchemaProperties(schema: JSONSchema): SchemaProperty[] {
|
||||
const objectSchemas = collectObjectSchemas(schema);
|
||||
if (objectSchemas.length === 0) {
|
||||
return [];
|
||||
}
|
||||
|
||||
const byName = new Map<string, SchemaProperty>();
|
||||
|
||||
for (const objectSchema of objectSchemas) {
|
||||
const requiredSet = new Set(
|
||||
Array.isArray(objectSchema.required) ? (objectSchema.required as string[]) : [],
|
||||
);
|
||||
const properties = objectSchema.properties as Record<string, JSONSchema> | null | undefined;
|
||||
if (typeof properties !== "object" || properties === null) {
|
||||
continue;
|
||||
}
|
||||
|
||||
for (const [name, propSchema] of Object.entries(properties)) {
|
||||
const required = requiredSet.has(name);
|
||||
const existing = byName.get(name);
|
||||
if (existing === undefined) {
|
||||
byName.set(name, { name, schema: propSchema, required });
|
||||
} else if (required) {
|
||||
byName.set(name, { ...existing, required: true });
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return [...byName.values()];
|
||||
}
|
||||
|
||||
function collectObjectSchemas(schema: JSONSchema): JSONSchema[] {
|
||||
if (typeof schema.properties === "object" && schema.properties !== null) {
|
||||
return Object.keys(schema.properties as Record<string, unknown>);
|
||||
return [schema];
|
||||
}
|
||||
|
||||
const unionKey = Array.isArray(schema.anyOf)
|
||||
@@ -20,18 +61,109 @@ function extractSchemaFields(schema: JSONSchema): string[] {
|
||||
? "oneOf"
|
||||
: null;
|
||||
|
||||
if (unionKey !== null) {
|
||||
const variants = schema[unionKey] as JSONSchema[];
|
||||
const fieldSet = new Set<string>();
|
||||
for (const variant of variants) {
|
||||
for (const field of extractSchemaFields(variant)) {
|
||||
fieldSet.add(field);
|
||||
}
|
||||
}
|
||||
return [...fieldSet];
|
||||
if (unionKey === null) {
|
||||
return [];
|
||||
}
|
||||
|
||||
return [];
|
||||
const variants = schema[unionKey] as JSONSchema[];
|
||||
const result: JSONSchema[] = [];
|
||||
for (const variant of variants) {
|
||||
result.push(...collectObjectSchemas(variant));
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
function resolvePropertySchema(prop: JSONSchema): JSONSchema {
|
||||
if (Array.isArray(prop.enum) && prop.enum.length > 0) {
|
||||
return prop;
|
||||
}
|
||||
|
||||
const unionKey = Array.isArray(prop.anyOf) ? "anyOf" : Array.isArray(prop.oneOf) ? "oneOf" : null;
|
||||
|
||||
if (unionKey !== null) {
|
||||
const variants = prop[unionKey] as JSONSchema[];
|
||||
const nonNull = variants.filter((v) => v.type !== "null");
|
||||
if (nonNull.length === 1) {
|
||||
return nonNull[0];
|
||||
}
|
||||
}
|
||||
|
||||
return prop;
|
||||
}
|
||||
|
||||
function formatYamlScalar(value: unknown): string {
|
||||
if (typeof value === "boolean") {
|
||||
return String(value);
|
||||
}
|
||||
if (typeof value === "number") {
|
||||
return String(value);
|
||||
}
|
||||
return String(value);
|
||||
}
|
||||
|
||||
function buildPropertyComment(parts: string[]): string {
|
||||
const filtered = parts.filter((p) => p.length > 0);
|
||||
return filtered.length > 0 ? ` # ${filtered.join(" | ")}` : "";
|
||||
}
|
||||
|
||||
function buildPropertyExampleLine(prop: SchemaProperty): string {
|
||||
const resolved = resolvePropertySchema(prop.schema);
|
||||
const commentParts: string[] = [];
|
||||
if (prop.required) {
|
||||
commentParts.push("required");
|
||||
}
|
||||
|
||||
if (Array.isArray(resolved.enum) && resolved.enum.length > 0) {
|
||||
const enumValues = resolved.enum.map((v) => String(v));
|
||||
commentParts.push(...enumValues);
|
||||
const first = resolved.enum[0];
|
||||
return `${prop.name}: ${formatYamlScalar(first)}${buildPropertyComment(commentParts)}`;
|
||||
}
|
||||
|
||||
if (resolved.type === "boolean") {
|
||||
commentParts.push("true", "false");
|
||||
return `${prop.name}: true${buildPropertyComment(commentParts)}`;
|
||||
}
|
||||
|
||||
if (resolved.type === "string") {
|
||||
return `${prop.name}: <string>${buildPropertyComment(commentParts)}`;
|
||||
}
|
||||
|
||||
if (resolved.type === "number" || resolved.type === "integer") {
|
||||
return `${prop.name}: <number>${buildPropertyComment(commentParts)}`;
|
||||
}
|
||||
|
||||
if (resolved.type === "array") {
|
||||
return `${prop.name}:\n - <item>${buildPropertyComment(commentParts)}`;
|
||||
}
|
||||
|
||||
if (resolved.type === "object") {
|
||||
return `${prop.name}: <object>${buildPropertyComment(commentParts)}`;
|
||||
}
|
||||
|
||||
return `${prop.name}: <value>${buildPropertyComment(commentParts)}`;
|
||||
}
|
||||
|
||||
function buildYamlExampleBlock(properties: SchemaProperty[]): string {
|
||||
if (properties.length === 0) {
|
||||
return "---\n\n... your markdown work here ...";
|
||||
}
|
||||
|
||||
const lines = properties.map((p) => buildPropertyExampleLine(p));
|
||||
return `---\n${lines.join("\n")}\n---\n\n... your markdown work here ...`;
|
||||
}
|
||||
|
||||
function buildFieldList(properties: SchemaProperty[]): string {
|
||||
if (properties.length === 0) {
|
||||
return " (schema fields will be extracted automatically)";
|
||||
}
|
||||
|
||||
return properties
|
||||
.map((p) => {
|
||||
const suffix = p.required ? " (required)" : "";
|
||||
return ` - \`${p.name}\`${suffix}`;
|
||||
})
|
||||
.join("\n");
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -42,28 +174,16 @@ function extractSchemaFields(schema: JSONSchema): string[] {
|
||||
* system prompt so the deliverable format is the first thing the agent sees.
|
||||
*/
|
||||
export function buildOutputFormatInstruction(schema: JSONSchema): string {
|
||||
const fields = extractSchemaFields(schema);
|
||||
|
||||
const fieldList =
|
||||
fields.length > 0
|
||||
? fields.map((f) => ` - \`${f}\``).join("\n")
|
||||
: " (schema fields will be extracted automatically)";
|
||||
const properties = extractSchemaProperties(schema);
|
||||
const yamlExample = buildYamlExampleBlock(properties);
|
||||
const fieldList = buildFieldList(properties);
|
||||
|
||||
return `## Deliverable Format
|
||||
|
||||
Your response MUST begin with a YAML frontmatter block followed by your markdown work:
|
||||
|
||||
\`\`\`
|
||||
---
|
||||
status: done # done | needs_input | in_progress | failed
|
||||
next: <role-name> # suggested next role, or omit
|
||||
confidence: 0.9 # 0.0–1.0, your self-assessed confidence
|
||||
artifacts: # list of file paths or CAS hashes you produced
|
||||
- path/to/file.ts
|
||||
scope: role # role | thread
|
||||
---
|
||||
|
||||
... your markdown work here ...
|
||||
${yamlExample}
|
||||
\`\`\`
|
||||
|
||||
The frontmatter is the **primary deliverable** — the engine reads it directly.
|
||||
|
||||
@@ -1,13 +1,139 @@
|
||||
import type { Store } from "@uncaged/json-cas";
|
||||
import { validate } from "@uncaged/json-cas";
|
||||
import { getSchema, validate } from "@uncaged/json-cas";
|
||||
import type { CasRef } from "@uncaged/workflow-protocol";
|
||||
import { parseFrontmatterMarkdown, validateFrontmatter } from "@uncaged/workflow-util";
|
||||
import {
|
||||
type AgentFrontmatter,
|
||||
createLogger,
|
||||
parseFrontmatterMarkdown,
|
||||
validateFrontmatter,
|
||||
} from "@uncaged/workflow-util";
|
||||
import { parse as parseYaml } from "yaml";
|
||||
|
||||
import { extractSchemaFields } from "./build-output-format-instruction.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
const STANDARD_KEYS = ["status", "next", "confidence", "artifacts", "scope"] as const;
|
||||
|
||||
type StandardKey = (typeof STANDARD_KEYS)[number];
|
||||
|
||||
export type FrontmatterFastPathResult = {
|
||||
body: string;
|
||||
outputHash: CasRef;
|
||||
};
|
||||
|
||||
function extractYamlBlock(raw: string): string | null {
|
||||
const fence = "---";
|
||||
if (!raw.startsWith(fence)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
const rest = raw.slice(fence.length);
|
||||
if (rest.length > 0 && rest[0] !== "\n" && rest[0] !== "\r") {
|
||||
return null;
|
||||
}
|
||||
|
||||
const afterOpen = rest.startsWith("\n") ? rest.slice(1) : rest;
|
||||
const closeIndex = afterOpen.indexOf(`\n${fence}`);
|
||||
if (closeIndex === -1) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return afterOpen.slice(0, closeIndex);
|
||||
}
|
||||
|
||||
function parseRawFrontmatterFields(raw: string): Record<string, unknown> {
|
||||
const yamlText = extractYamlBlock(raw);
|
||||
if (yamlText === null) {
|
||||
return {};
|
||||
}
|
||||
|
||||
try {
|
||||
const parsed = parseYaml(yamlText);
|
||||
if (typeof parsed !== "object" || parsed === null || Array.isArray(parsed)) {
|
||||
return {};
|
||||
}
|
||||
return parsed as Record<string, unknown>;
|
||||
} catch {
|
||||
return {};
|
||||
}
|
||||
}
|
||||
|
||||
function defaultCandidate(frontmatter: AgentFrontmatter): Record<string, unknown> {
|
||||
return {
|
||||
status: frontmatter.status,
|
||||
next: frontmatter.next,
|
||||
confidence: frontmatter.confidence,
|
||||
artifacts: [...frontmatter.artifacts],
|
||||
scope: frontmatter.scope,
|
||||
};
|
||||
}
|
||||
|
||||
function pickStandardField(frontmatter: AgentFrontmatter, key: StandardKey): unknown {
|
||||
switch (key) {
|
||||
case "status":
|
||||
return frontmatter.status;
|
||||
case "next":
|
||||
return frontmatter.next;
|
||||
case "confidence":
|
||||
return frontmatter.confidence;
|
||||
case "artifacts":
|
||||
return [...frontmatter.artifacts];
|
||||
case "scope":
|
||||
return frontmatter.scope;
|
||||
}
|
||||
}
|
||||
|
||||
function isStandardKey(key: string): key is StandardKey {
|
||||
return (STANDARD_KEYS as readonly string[]).includes(key);
|
||||
}
|
||||
|
||||
function pickFieldValue(
|
||||
field: string,
|
||||
frontmatter: AgentFrontmatter,
|
||||
rawFields: Record<string, unknown>,
|
||||
): unknown | undefined {
|
||||
if (!isStandardKey(field)) {
|
||||
return Object.hasOwn(rawFields, field) ? rawFields[field] : undefined;
|
||||
}
|
||||
|
||||
const coerced = pickStandardField(frontmatter, field);
|
||||
if (field === "artifacts" || field === "scope") {
|
||||
return coerced;
|
||||
}
|
||||
if (coerced !== null) {
|
||||
return coerced;
|
||||
}
|
||||
return Object.hasOwn(rawFields, field) ? rawFields[field] : coerced;
|
||||
}
|
||||
|
||||
/**
|
||||
* Build a CAS candidate object from schema property keys and parsed frontmatter.
|
||||
*
|
||||
* When the schema has no inspectable properties, falls back to the five standard
|
||||
* agent frontmatter fields for backward compatibility.
|
||||
*/
|
||||
function buildCandidate(
|
||||
frontmatter: AgentFrontmatter,
|
||||
rawFields: Record<string, unknown>,
|
||||
schemaFields: string[],
|
||||
): Record<string, unknown> {
|
||||
if (schemaFields.length === 0) {
|
||||
return defaultCandidate(frontmatter);
|
||||
}
|
||||
|
||||
const candidate: Record<string, unknown> = {};
|
||||
|
||||
for (const field of schemaFields) {
|
||||
const value = pickFieldValue(field, frontmatter, rawFields);
|
||||
if (value !== undefined) {
|
||||
candidate[field] = value;
|
||||
}
|
||||
}
|
||||
|
||||
return candidate;
|
||||
}
|
||||
|
||||
/**
|
||||
* Try to satisfy `outputSchema` from frontmatter fields alone.
|
||||
*
|
||||
@@ -32,16 +158,22 @@ export async function tryFrontmatterFastPath(
|
||||
|
||||
const validationErrors = validateFrontmatter(frontmatter);
|
||||
if (validationErrors.length > 0) {
|
||||
log(
|
||||
"9GNPS4WY",
|
||||
`frontmatter validation errors: ${validationErrors.map((e) => e.message).join("; ")}`,
|
||||
);
|
||||
return null;
|
||||
}
|
||||
|
||||
const candidate: Record<string, unknown> = {
|
||||
status: frontmatter.status,
|
||||
next: frontmatter.next,
|
||||
confidence: frontmatter.confidence,
|
||||
artifacts: [...frontmatter.artifacts],
|
||||
scope: frontmatter.scope,
|
||||
};
|
||||
const schema = getSchema(store, outputSchema);
|
||||
if (schema === null) {
|
||||
log("8FHMR2QX", `output schema not found in CAS: ${outputSchema}`);
|
||||
return null;
|
||||
}
|
||||
|
||||
const schemaFields = extractSchemaFields(schema);
|
||||
const rawFields = parseRawFrontmatterFields(raw);
|
||||
const candidate = buildCandidate(frontmatter, rawFields, schemaFields);
|
||||
|
||||
let outputHash: CasRef;
|
||||
let node: ReturnType<Store["get"]>;
|
||||
@@ -50,10 +182,12 @@ export async function tryFrontmatterFastPath(
|
||||
outputHash = await store.put(outputSchema, candidate);
|
||||
node = store.get(outputHash);
|
||||
} catch {
|
||||
log("2KMQT7NR", "failed to store frontmatter candidate in CAS");
|
||||
return null;
|
||||
}
|
||||
|
||||
if (node === null || !validate(store, node)) {
|
||||
log("2KMQT7NR", "stored frontmatter candidate failed schema validation");
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
@@ -12,4 +12,10 @@ export type { FrontmatterFastPathResult } from "./frontmatter.js";
|
||||
export { tryFrontmatterFastPath } from "./frontmatter.js";
|
||||
export { createAgent } from "./run.js";
|
||||
export { getConfigPath, getEnvPath, loadWorkflowConfig } from "./storage.js";
|
||||
export type { AgentContext, AgentOptions, AgentRunFn, AgentRunResult } from "./types.js";
|
||||
export type {
|
||||
AgentContext,
|
||||
AgentContinueFn,
|
||||
AgentOptions,
|
||||
AgentRunFn,
|
||||
AgentRunResult,
|
||||
} from "./types.js";
|
||||
|
||||
@@ -3,11 +3,12 @@ import type { CasRef, StepNodePayload, ThreadId } from "@uncaged/workflow-protoc
|
||||
import { config as loadDotenv } from "dotenv";
|
||||
import { buildOutputFormatInstruction } from "./build-output-format-instruction.js";
|
||||
import { buildContextWithMeta } from "./context.js";
|
||||
import { extract } from "./extract.js";
|
||||
import { tryFrontmatterFastPath } from "./frontmatter.js";
|
||||
import type { AgentStore } from "./storage.js";
|
||||
import { getEnvPath, loadWorkflowConfig, resolveStorageRoot } from "./storage.js";
|
||||
import type { AgentContext, AgentOptions, AgentRunResult } from "./types.js";
|
||||
import { getEnvPath, resolveStorageRoot } from "./storage.js";
|
||||
import type { AgentOptions } from "./types.js";
|
||||
|
||||
const MAX_FRONTMATTER_RETRIES = 2;
|
||||
|
||||
function fail(message: string): never {
|
||||
process.stderr.write(`${message}\n`);
|
||||
@@ -66,31 +67,16 @@ async function writeStepNode(options: {
|
||||
return hash;
|
||||
}
|
||||
|
||||
async function runAgent(options: AgentOptions, ctx: AgentContext): Promise<AgentRunResult> {
|
||||
return runWithMessage("agent run failed", () => options.run(ctx));
|
||||
}
|
||||
|
||||
async function extractOutput(
|
||||
async function tryExtractOutput(
|
||||
rawOutput: string,
|
||||
outputSchema: CasRef,
|
||||
storageRoot: string,
|
||||
ctx: Awaited<ReturnType<typeof buildContextWithMeta>>,
|
||||
): Promise<CasRef> {
|
||||
const fastPath = await runWithMessage("frontmatter fast path", () =>
|
||||
tryFrontmatterFastPath(rawOutput, outputSchema, ctx.meta.store),
|
||||
).catch(() => null);
|
||||
|
||||
): Promise<CasRef | null> {
|
||||
const fastPath = await tryFrontmatterFastPath(rawOutput, outputSchema, ctx.meta.store);
|
||||
if (fastPath !== null) {
|
||||
return fastPath.outputHash;
|
||||
}
|
||||
|
||||
const config = await runWithMessage("failed to load config", () =>
|
||||
loadWorkflowConfig(storageRoot),
|
||||
);
|
||||
const extracted = await runWithMessage("extract failed", () =>
|
||||
extract(rawOutput, outputSchema, config),
|
||||
);
|
||||
return extracted.hash;
|
||||
return null;
|
||||
}
|
||||
|
||||
async function persistStep(options: {
|
||||
@@ -112,11 +98,6 @@ async function persistStep(options: {
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Create an agent CLI entrypoint.
|
||||
* Parses argv (`<thread-id> <role>`), runs the agent, extracts structured output,
|
||||
* writes StepNode to CAS, and prints the new node hash to stdout.
|
||||
*/
|
||||
export function createAgent(options: AgentOptions): () => Promise<void> {
|
||||
return async function main(): Promise<void> {
|
||||
const { threadId, role } = parseArgv(process.argv);
|
||||
@@ -130,13 +111,36 @@ export function createAgent(options: AgentOptions): () => Promise<void> {
|
||||
fail(`unknown role: ${role}`);
|
||||
}
|
||||
|
||||
const metaSchema = getSchema(ctx.meta.store, roleDef.meta);
|
||||
if (metaSchema !== null) {
|
||||
ctx.outputFormatInstruction = buildOutputFormatInstruction(metaSchema);
|
||||
const frontmatterSchema = getSchema(ctx.meta.store, roleDef.frontmatter);
|
||||
if (frontmatterSchema !== null) {
|
||||
ctx.outputFormatInstruction = buildOutputFormatInstruction(frontmatterSchema);
|
||||
}
|
||||
|
||||
let agentResult = await runWithMessage("agent run failed", () => options.run(ctx));
|
||||
|
||||
// Try to extract frontmatter; retry via continue if it fails
|
||||
let outputHash = await tryExtractOutput(agentResult.output, roleDef.frontmatter, ctx);
|
||||
|
||||
for (let retry = 0; retry < MAX_FRONTMATTER_RETRIES && outputHash === null; retry++) {
|
||||
const correctionMessage =
|
||||
"Your previous response did not contain valid YAML frontmatter matching the role schema.\n" +
|
||||
"You MUST begin your response with a YAML frontmatter block (--- delimited).\n" +
|
||||
"Please output ONLY the corrected frontmatter block followed by your work.";
|
||||
|
||||
agentResult = await runWithMessage("agent continue failed", () =>
|
||||
options.continue(agentResult.sessionId, correctionMessage, ctx.meta.store),
|
||||
);
|
||||
outputHash = await tryExtractOutput(agentResult.output, roleDef.frontmatter, ctx);
|
||||
}
|
||||
|
||||
if (outputHash === null) {
|
||||
fail(
|
||||
"Agent output does not contain valid YAML frontmatter matching the role schema " +
|
||||
`after ${MAX_FRONTMATTER_RETRIES} retries.\n` +
|
||||
`Raw output (first 500 chars): ${agentResult.output.slice(0, 500)}`,
|
||||
);
|
||||
}
|
||||
|
||||
const agentResult = await runAgent(options, ctx);
|
||||
const outputHash = await extractOutput(agentResult.output, roleDef.meta, storageRoot, ctx);
|
||||
const stepHash = await persistStep({
|
||||
ctx,
|
||||
outputHash,
|
||||
|
||||
@@ -17,11 +17,19 @@ export type AgentContext = ModeratorContext & {
|
||||
export type AgentRunResult = {
|
||||
output: string;
|
||||
detailHash: string;
|
||||
sessionId: string;
|
||||
};
|
||||
|
||||
export type AgentContinueFn = (
|
||||
sessionId: string,
|
||||
message: string,
|
||||
store: AgentContext["store"],
|
||||
) => Promise<AgentRunResult>;
|
||||
|
||||
export type AgentRunFn = (ctx: AgentContext) => Promise<AgentRunResult>;
|
||||
|
||||
export type AgentOptions = {
|
||||
name: string;
|
||||
run: AgentRunFn;
|
||||
continue: AgentContinueFn;
|
||||
};
|
||||
|
||||
@@ -35,11 +35,11 @@ const solveIssueWorkflow: WorkflowPayload = {
|
||||
conditions: {
|
||||
needsClarification: {
|
||||
description: "Planner requests clarification from user",
|
||||
expression: "$exists(steps[-1].output.needsClarification)",
|
||||
expression: "$exists($last('planner').needsClarification)",
|
||||
},
|
||||
notApproved: {
|
||||
rejected: {
|
||||
description: "Reviewer rejected the implementation",
|
||||
expression: "steps[-1].output.approved = false",
|
||||
expression: "$last('reviewer').approved = false",
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
@@ -50,7 +50,7 @@ const solveIssueWorkflow: WorkflowPayload = {
|
||||
],
|
||||
developer: [{ role: "reviewer", condition: null }],
|
||||
reviewer: [
|
||||
{ role: "developer", condition: "notApproved" },
|
||||
{ role: "developer", condition: "rejected" },
|
||||
{ role: "$END", condition: null },
|
||||
],
|
||||
},
|
||||
@@ -72,7 +72,7 @@ describe("evaluate", () => {
|
||||
expect(result).toEqual({ ok: true, value: "planner" });
|
||||
});
|
||||
|
||||
test("condition match (notApproved → developer)", async () => {
|
||||
test("condition match (rejected → developer)", async () => {
|
||||
const context = makeContext([
|
||||
{
|
||||
role: "reviewer",
|
||||
@@ -126,4 +126,116 @@ describe("evaluate", () => {
|
||||
const result = await evaluate(solveIssueWorkflow, context);
|
||||
expect(result).toEqual({ ok: true, value: "developer" });
|
||||
});
|
||||
|
||||
test("$last returns most recent matching role's frontmatter", async () => {
|
||||
const workflow: WorkflowPayload = {
|
||||
...solveIssueWorkflow,
|
||||
conditions: {
|
||||
devFailed: {
|
||||
description: "Developer failed",
|
||||
expression: "$last('developer').status = 'failed'",
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: [{ role: "developer", condition: null }],
|
||||
developer: [
|
||||
{ role: "$END", condition: "devFailed" },
|
||||
{ role: "reviewer", condition: null },
|
||||
],
|
||||
},
|
||||
};
|
||||
const context = makeContext([
|
||||
{
|
||||
role: "developer",
|
||||
output: { status: "done" },
|
||||
detail: "1VPBG9SM5E7WK",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
{
|
||||
role: "reviewer",
|
||||
output: { approved: false },
|
||||
detail: "2MXBG6PN4A8JR",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
{
|
||||
role: "developer",
|
||||
output: { status: "failed" },
|
||||
detail: "3QNTH7WK8D2PA",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
]);
|
||||
const result = await evaluate(workflow, context);
|
||||
expect(result).toEqual({ ok: true, value: "$END" });
|
||||
});
|
||||
|
||||
test("$first returns earliest matching role's frontmatter", async () => {
|
||||
const workflow: WorkflowPayload = {
|
||||
...solveIssueWorkflow,
|
||||
conditions: {
|
||||
firstPlanReady: {
|
||||
description: "First planner run was ready",
|
||||
expression: "$first('planner').status = 'ready'",
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: [{ role: "planner", condition: null }],
|
||||
planner: [
|
||||
{ role: "$END", condition: "firstPlanReady" },
|
||||
{ role: "developer", condition: null },
|
||||
],
|
||||
},
|
||||
};
|
||||
const context = makeContext([
|
||||
{
|
||||
role: "planner",
|
||||
output: { status: "ready", plan: "ABC123" },
|
||||
detail: "7BQST3VW9F2MA",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
{
|
||||
role: "developer",
|
||||
output: { status: "done" },
|
||||
detail: "1VPBG9SM5E7WK",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
{
|
||||
role: "planner",
|
||||
output: { status: "revised", plan: "DEF456" },
|
||||
detail: "4RNMK6PX8B3WQ",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
]);
|
||||
const result = await evaluate(workflow, context);
|
||||
expect(result).toEqual({ ok: true, value: "$END" });
|
||||
});
|
||||
|
||||
test("$last returns undefined for unmatched role", async () => {
|
||||
const workflow: WorkflowPayload = {
|
||||
...solveIssueWorkflow,
|
||||
conditions: {
|
||||
hasReviewer: {
|
||||
description: "Reviewer has run",
|
||||
expression: "$exists($last('reviewer'))",
|
||||
},
|
||||
},
|
||||
graph: {
|
||||
$START: [{ role: "planner", condition: null }],
|
||||
planner: [
|
||||
{ role: "$END", condition: "hasReviewer" },
|
||||
{ role: "developer", condition: null },
|
||||
],
|
||||
},
|
||||
};
|
||||
const context = makeContext([
|
||||
{
|
||||
role: "planner",
|
||||
output: { status: "ready" },
|
||||
detail: "7BQST3VW9F2MA",
|
||||
agent: "uwf-hermes",
|
||||
},
|
||||
]);
|
||||
const result = await evaluate(workflow, context);
|
||||
// no reviewer step → $exists returns false → fallback to developer
|
||||
expect(result).toEqual({ ok: true, value: "developer" });
|
||||
});
|
||||
});
|
||||
|
||||
@@ -21,12 +21,44 @@ function isTruthy(value: unknown): boolean {
|
||||
return true;
|
||||
}
|
||||
|
||||
function findByRole(
|
||||
steps: ModeratorContext["steps"],
|
||||
role: string,
|
||||
direction: "first" | "last",
|
||||
): unknown {
|
||||
if (direction === "last") {
|
||||
for (let i = steps.length - 1; i >= 0; i--) {
|
||||
if (steps[i].role === role) {
|
||||
return steps[i].output;
|
||||
}
|
||||
}
|
||||
} else {
|
||||
for (const step of steps) {
|
||||
if (step.role === role) {
|
||||
return step.output;
|
||||
}
|
||||
}
|
||||
}
|
||||
return undefined;
|
||||
}
|
||||
|
||||
async function evaluateJsonata(
|
||||
expression: string,
|
||||
context: ModeratorContext,
|
||||
): Promise<Result<unknown, Error>> {
|
||||
try {
|
||||
const result = await jsonata(expression).evaluate(context);
|
||||
const expr = jsonata(expression);
|
||||
expr.registerFunction(
|
||||
"first",
|
||||
(role: string) => findByRole(context.steps, role, "first"),
|
||||
"<s:x>",
|
||||
);
|
||||
expr.registerFunction(
|
||||
"last",
|
||||
(role: string) => findByRole(context.steps, role, "last"),
|
||||
"<s:x>",
|
||||
);
|
||||
const result = await expr.evaluate(context);
|
||||
return { ok: true, value: result };
|
||||
} catch (error) {
|
||||
return {
|
||||
|
||||
@@ -2,14 +2,14 @@ import type { JSONSchema } from "@uncaged/json-cas";
|
||||
|
||||
const ROLE_DEFINITION: JSONSchema = {
|
||||
type: "object",
|
||||
required: ["description", "goal", "capabilities", "procedure", "output", "meta"],
|
||||
required: ["description", "goal", "capabilities", "procedure", "output", "frontmatter"],
|
||||
properties: {
|
||||
description: { type: "string" },
|
||||
goal: { type: "string" },
|
||||
capabilities: { type: "array", items: { type: "string" } },
|
||||
procedure: { type: "string" },
|
||||
output: { type: "string" },
|
||||
meta: { type: "string", format: "cas_ref" },
|
||||
frontmatter: { type: "string", format: "cas_ref" },
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
@@ -22,7 +22,7 @@ export type RoleDefinition = {
|
||||
capabilities: string[];
|
||||
procedure: string;
|
||||
output: string;
|
||||
meta: CasRef;
|
||||
frontmatter: CasRef;
|
||||
};
|
||||
|
||||
export type Transition = {
|
||||
|
||||
@@ -46,6 +46,8 @@ uwf cas get <hash> # read a CAS node (type + payload)
|
||||
[--timestamp] # include timestamp in output
|
||||
uwf cas put <type-hash> <data> # store a node, print its hash
|
||||
# <data>: JSON file path or inline JSON string
|
||||
uwf cas put-text <text> # store a plain text string, print its hash
|
||||
# shortcut for put with the built-in text schema
|
||||
uwf cas has <hash> # check if a hash exists
|
||||
uwf cas refs <hash> # list direct CAS references from a node
|
||||
uwf cas walk <hash> # recursive traversal from a node
|
||||
|
||||
Reference in New Issue
Block a user