feat(runtime): stuck-incident detector + skill metrics + edit scope (Phase 6) (#17)

Phase 6 of plans/autonomous-survival-bot-prd.md. Expand the
self-improvement loop so the bot can spot and report no-progress
stagnation, not just exception-class failures.

New:
- runtime/stuck-incident.js: detector fires a structured proposal when
  the same noProgressReason persists past 5 min (cooldown 30 min).
  Body includes runtimeState, milestone, suggested skill, slim
  snapshot, last action result, per-skill success/failure metrics
  and a forbidden-paths list. Pure module — caller (bot.js) writes
  the proposal.
- runtime/skill-metrics.js: in-memory per-skill ok/fail counters
  surfaced on snapshot.skillMetrics for the TUI and the incident
  body.
- runtime/stuck-incident.test.js: 6 tests covering null reason,
  threshold gating, cooldown, reason change resetting the timer,
  body composition and metrics snapshot.

Wiring:
- runtime/state-store.js: writeProposal accepts {editScope: string[]}
  and persists it in the frontmatter; readProposalEditScope() reads
  it back so future auto-patch.js can refuse cherry-picks that touch
  other areas.
- runtime/bot.js: tick() invokes the stuck detector each tick,
  records skill ok/fail via skillMetrics, stamps snapshot.skillMetrics
  and writes the stuck proposal via writeProposal({editScope}).
  dispatchAction now records into skillMetrics for both the
  resolved-result and the exception path.

npm test now 46/46.

Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit was merged in pull request #17.
This commit is contained in:
Yuriy Mayatnikov
2026-05-25 22:35:01 +03:00
committed by GitHub
co-authored by mayatnikov Claude Opus 4.7
parent fc62160524
commit c7eab06f22
7 changed files with 325 additions and 8 deletions
+28
View File
@@ -0,0 +1,28 @@
// Per-skill ok/fail counters. Aggregated for the lifetime of the bot
// process (best-effort persistence is left for a future iteration —
// today's counters reset on restart, which keeps the data store
// simple while still being useful for incident bodies and the TUI).
export function createSkillMetrics() {
const counts = new Map(); // id → { ok, fail, lastTs }
function record(id, ok) {
const cur = counts.get(id) ?? { ok: 0, fail: 0, lastTs: 0 };
if (ok) cur.ok++;
else cur.fail++;
cur.lastTs = Date.now();
counts.set(id, cur);
}
function snapshot() {
const out = {};
for (const [id, m] of counts) out[id] = { ...m };
return out;
}
function reset() {
counts.clear();
}
return { record, snapshot, reset };
}