Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 67870392ab | |||
| 6b9ff9781d | |||
| 487c48effa | |||
| 4eca2d533c | |||
| f0f840e6e0 | |||
| 7ff90cef4f | |||
| e62d51d845 | |||
| a803fcb4fc | |||
| d00c93fc19 | |||
| 99a2890be2 |
@@ -21,7 +21,7 @@ roles:
|
||||
|
||||
After producing the test spec:
|
||||
1. Store it via `uwf cas put-text "<markdown content>"` and capture the returned hash
|
||||
2. Put the hash in meta.plan (required when status=ready)
|
||||
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)."
|
||||
frontmatter:
|
||||
type: object
|
||||
|
||||
@@ -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,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -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();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -9,7 +9,7 @@ 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[] {
|
||||
if (typeof schema.properties === "object" && schema.properties !== null) {
|
||||
return Object.keys(schema.properties as Record<string, unknown>);
|
||||
}
|
||||
|
||||
@@ -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);
|
||||
@@ -135,13 +116,31 @@ export function createAgent(options: AgentOptions): () => Promise<void> {
|
||||
ctx.outputFormatInstruction = buildOutputFormatInstruction(frontmatterSchema);
|
||||
}
|
||||
|
||||
const agentResult = await runAgent(options, ctx);
|
||||
const outputHash = await extractOutput(
|
||||
agentResult.output,
|
||||
roleDef.frontmatter,
|
||||
storageRoot,
|
||||
ctx,
|
||||
);
|
||||
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 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;
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user