Add Experience V1 schema migration and agent-run completion extractor.

Extend h5_experience with structured fields, wire mindspace-agent-runner and agent-run-gateway to persist task_outcome records with provenance, and add local migration and verification scripts.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
john
2026-09-02 10:26:46 +08:00
parent 908db04b67
commit b923e54eff
19 changed files with 1340 additions and 131 deletions
+91 -47
View File
@@ -1,5 +1,12 @@
import crypto from 'node:crypto';
import {
experienceSearchHaystack,
mapExperienceRow,
normalizeExperienceRecordInput,
serializeExperienceJson,
} from './experience-schema.mjs';
/**
* PostgreSQL + pgvector backed experience store (etat C, polyglot mode).
*
@@ -51,10 +58,35 @@ export async function createPgExperienceService(options = {}) {
source_user_id TEXT,
use_count BIGINT NOT NULL DEFAULT 0,
embedding vector(${embeddingDim}),
problem TEXT,
environment_json JSONB,
hypothesis TEXT,
action_json JSONB,
result TEXT,
confidence DOUBLE PRECISION,
evidence_json JSONB,
parent_experience_id UUID,
supersedes_id UUID,
status TEXT NOT NULL DEFAULT 'active',
created_at BIGINT NOT NULL,
updated_at BIGINT NOT NULL
)
`);
const pgExperienceColumns = [
['problem', 'TEXT'],
['environment_json', 'JSONB'],
['hypothesis', 'TEXT'],
['action_json', 'JSONB'],
['result', 'TEXT'],
['confidence', 'DOUBLE PRECISION'],
['evidence_json', 'JSONB'],
['parent_experience_id', 'UUID'],
['supersedes_id', 'UUID'],
["status", "TEXT NOT NULL DEFAULT 'active'"],
];
for (const [column, definition] of pgExperienceColumns) {
await pool.query(`ALTER TABLE h5_experience ADD COLUMN IF NOT EXISTS ${column} ${definition}`);
}
await pool.query(
'CREATE INDEX IF NOT EXISTS idx_h5_experience_scope_updated ON h5_experience (scope, updated_at DESC)',
);
@@ -66,80 +98,88 @@ export async function createPgExperienceService(options = {}) {
// ivfflat needs the extension + may warn on empty table; non-fatal.
});
function normalizeTags(tags) {
if (!Array.isArray(tags)) return [];
return [...new Set(tags.map((t) => String(t).trim()).filter(Boolean))];
}
function toVectorLiteral(vec) {
// pgvector accepts a string like '[0.1,0.2,...]'
return `[${vec.map((n) => Number(n)).join(',')}]`;
}
function rowToExperience(row) {
return {
id: row.id,
scope: row.scope,
kind: row.kind,
title: row.title,
body: row.body,
tags: Array.isArray(row.tags) ? row.tags : [],
sourceSessionId: row.source_session_id ?? null,
sourceUserId: row.source_user_id ?? null,
useCount: Number(row.use_count ?? 0),
createdAt: Number(row.created_at),
updatedAt: Number(row.updated_at),
};
return mapExperienceRow({
...row,
tags_json: row.tags,
});
}
async function record(input) {
const title = String(input?.title ?? '').trim();
const body = String(input?.body ?? '').trim();
if (!title) throw experienceError('经验标题不能为空', 'invalid_experience_input');
if (!body) throw experienceError('经验内容不能为空', 'invalid_experience_input');
const normalized = normalizeExperienceRecordInput(input);
if (!normalized.title) throw experienceError('经验标题不能为空', 'invalid_experience_input');
if (!normalized.body) throw experienceError('经验内容不能为空', 'invalid_experience_input');
const id = crypto.randomUUID();
const ts = now();
const scope = String(input?.scope ?? 'global').trim() || 'global';
const kind = String(input?.kind ?? 'lesson').trim() || 'lesson';
const tags = normalizeTags(input?.tags);
const environmentJson = normalized.environment;
const actionJson = normalized.action;
const evidenceJson = normalized.evidence;
let embedding = null;
if (embed) {
try {
const vec = await embed(`${title}\n${body}`);
const vec = await embed(`${normalized.title}\n${normalized.body}`);
if (Array.isArray(vec) && vec.length === embeddingDim) embedding = toVectorLiteral(vec);
} catch {
embedding = null; // embedding failure must not block recording
embedding = null;
}
}
await pool.query(
`INSERT INTO h5_experience
(id, scope, kind, title, body, tags, source_session_id, source_user_id,
use_count, embedding, created_at, updated_at)
VALUES ($1,$2,$3,$4,$5,$6::jsonb,$7,$8,0,$9::vector,$10,$11)`,
use_count, embedding, problem, environment_json, hypothesis, action_json,
result, confidence, evidence_json, parent_experience_id, supersedes_id,
status, created_at, updated_at)
VALUES ($1,$2,$3,$4,$5,$6::jsonb,$7,$8,0,$9::vector,$10,$11::jsonb,$12,$13::jsonb,
$14,$15,$16::jsonb,$17::uuid,$18::uuid,$19,$20,$21)`,
[
id,
scope,
kind,
title,
body,
JSON.stringify(tags),
input?.sourceSessionId ?? null,
input?.sourceUserId ?? null,
normalized.scope,
normalized.kind,
normalized.title,
normalized.body,
JSON.stringify(normalized.tags),
normalized.sourceSessionId,
normalized.sourceUserId,
embedding,
normalized.problem,
environmentJson == null ? null : JSON.stringify(environmentJson),
normalized.hypothesis,
actionJson == null ? null : JSON.stringify(actionJson),
normalized.result,
normalized.confidence,
evidenceJson == null ? null : JSON.stringify(evidenceJson),
normalized.parentExperienceId,
normalized.supersedesId,
normalized.status,
ts,
ts,
],
);
return rowToExperience({
id,
scope,
kind,
title,
body,
tags,
source_session_id: input?.sourceSessionId ?? null,
source_user_id: input?.sourceUserId ?? null,
scope: normalized.scope,
kind: normalized.kind,
title: normalized.title,
body: normalized.body,
tags: normalized.tags,
source_session_id: normalized.sourceSessionId,
source_user_id: normalized.sourceUserId,
use_count: 0,
problem: normalized.problem,
environment_json: environmentJson,
hypothesis: normalized.hypothesis,
action_json: actionJson,
result: normalized.result,
confidence: normalized.confidence,
evidence_json: evidenceJson,
parent_experience_id: normalized.parentExperienceId,
supersedes_id: normalized.supersedesId,
status: normalized.status,
created_at: ts,
updated_at: ts,
});
@@ -157,9 +197,11 @@ export async function createPgExperienceService(options = {}) {
if (Array.isArray(vec) && vec.length === embeddingDim) {
const { rows } = await pool.query(
`SELECT id, scope, kind, title, body, tags, source_session_id,
source_user_id, use_count, created_at, updated_at
source_user_id, use_count, problem, environment_json, hypothesis,
action_json, result, confidence, evidence_json, parent_experience_id,
supersedes_id, status, created_at, updated_at
FROM h5_experience
WHERE scope = $1 AND embedding IS NOT NULL
WHERE scope = $1 AND status = 'active' AND embedding IS NOT NULL
ORDER BY embedding <=> $2::vector, updated_at DESC
LIMIT $3`,
[scope, toVectorLiteral(vec), max],
@@ -181,9 +223,11 @@ export async function createPgExperienceService(options = {}) {
const params = [scope, ...terms.map((t) => `%${t}%`), max];
const { rows } = await pool.query(
`SELECT id, scope, kind, title, body, tags, source_session_id,
source_user_id, use_count, created_at, updated_at
source_user_id, use_count, problem, environment_json, hypothesis,
action_json, result, confidence, evidence_json, parent_experience_id,
supersedes_id, status, created_at, updated_at
FROM h5_experience
WHERE scope = $1 AND (${likeClauses.join(' OR ')})
WHERE scope = $1 AND status = 'active' AND (${likeClauses.join(' OR ')})
ORDER BY updated_at DESC
LIMIT $${terms.length + 2}`,
params,