feat: Paseo-like orchestrator Phase 1-2 — trace system, session persistence, timeline, run_command, auto-fix loop

Phase 1: Trace System + Observability
- tool_traces DB table + insert/update service
- tool_trace_start/tool_trace_finish WS frames (contracts + FE types)
- Instrumented tool-phase.ts with timing around every tool call
- GET /api/chats/:id/traces paginated endpoint
- Trace viewer frontend (collapsible panel with timing bars + token breakdown)

Phase 2: Session Persistence + Resume
- agent_snapshots table (UPSERT per chat, persisted on turn boundaries)
- save/load/delete service functions
- Agent snapshot sent on WS reconnect
- Session timeline view (vertical timeline with scroll-to + restore)

Tooling:
- run_command tool (execFile, 30s timeout, 32KB cap, path-guarded)
- Auto-fix loop: after write tools, runs pnpm build, injects errors into next turn
This commit is contained in:
2026-06-08 02:26:47 +00:00
parent 8f061c8d43
commit 9ef8f1948a
22 changed files with 2231 additions and 101 deletions

View File

@@ -20,6 +20,7 @@ import { resolveGrantRoot } from '../grant_resolver.js';
import { stripToolMarkup } from './tool-call-parser.js';
import { repairToolInput } from './tool-input-repair.js';
import type { FailureKind } from './mistake-tracker.js';
import { insertToolTrace, updateToolTrace } from '../tool-traces.js';
import type {
InferenceContext,
StreamResult,
@@ -175,6 +176,7 @@ export async function executeToolPhase(
session: Session,
projectRoot: string,
agent?: Agent | null,
turnNumber?: number,
): Promise<ToolPhaseResult> {
const { sessionId, chatId, assistantMessageId } = args;
const content = stripToolMarkup(result.content, { final: true });
@@ -378,11 +380,53 @@ export async function executeToolPhase(
});
return;
}
// tool_trace instrumentation - start
const traceId = crypto.randomUUID();
const traceStartTime = Date.now();
const startedAtIso = new Date().toISOString();
insertToolTrace(ctx.sql, {
session_id: sessionId,
chat_id: chatId,
message_id: assistantMessageId,
turn_number: turnNumber ?? 0,
tool_name: tc.name,
tool_input: tc.args as Record<string, unknown>,
}).catch(() => {});
ctx.publish(sessionId, {
type: 'tool_trace_start',
trace_id: traceId,
message_id: assistantMessageId,
chat_id: chatId,
tool_name: tc.name,
tool_input: tc.args as Record<string, unknown>,
started_at: startedAtIso,
});
const tres = await executeToolCall(
projectRoot, tc, session.allowed_read_paths,
{ sql: ctx.sql, sessionId },
ctx.hooks, sessionId,
);
// tool_trace instrumentation - finish
const finishedAtIso = new Date().toISOString();
const latencyMs = Date.now() - traceStartTime;
updateToolTrace(ctx.sql, traceId, {
finished_at: finishedAtIso,
...(tres.outcome === 'success' && tres.output != null ? { tool_output: JSON.stringify(tres.output) } : {}),
latency_ms: latencyMs,
outcome: tres.outcome,
...(tres.error ? { error: tres.error } : {}),
}).catch(() => {});
ctx.publish(sessionId, {
type: 'tool_trace_finish',
trace_id: traceId,
message_id: assistantMessageId,
chat_id: chatId,
tool_name: tc.name,
finished_at: finishedAtIso,
outcome: tres.outcome,
latency_ms: latencyMs,
...(tres.error ? { error: tres.error } : {}),
});
// vWhale: PostToolUse hook (best-effort, non-blocking).
if (ctx.hooks) {
ctx.hooks.run('PostToolUse', {