diff options
| author | Agando <roduccomm@gmail.com> | 2026-10-26 14:50:54 +0100 |
|---|---|---|
| committer | Agando <roduccomm@gmail.com> | 2026-10-26 14:50:54 +0100 |
| commit | b79d70926ae88a3b10a13e2e029bbb7f487b8cf4 (patch) | |
| tree | b568c61110ad1c12dc7e7061d2676d20e507ced7 /scripts/newos4-feedback-collect.py | |
| parent | 02ffef703a1b8d85915f344e182a1a4e67dac9df (diff) | |
feat(feedback): autonomous first-pass reviewer — decide what is provable, leave the rest
The operator asked: "when I don't do anything, an agent can do it for me and I can just follow up
or steer it." This is that agent, deterministic (no LLM): same input, same decision, and every
reason is a grep or a commit hash that can be checked.
spaces/newos4/scripts/newos4-feedback-autoreview.py — rules, first match wins:
R1 duplicate same fingerprint already decided -> resolve
R2 already-fixed identifiers absent from modules/**/*.js AND
`git log -S<token>` proves a commit removed them -> resolve
R3 noise fetch/abort/probe patterns -> reject
R4 still-present auto report + stack + identifiers still in code -> approve (max 2/day)
R5 plan / R6 user report -> never decided
Writes to the same append-only decisions.jsonl with actor=auto-reviewer, note + evidence; the
applier's last-wins rule means any operator click overrides an agent decision. Kill switch:
data/feedback/autonomy.json {"mode":"off"} (safe default, aggressive = cap 5).
Cron job e31ac58a559e, 07:40 and 19:40, no_agent, silent unless it decided something.
Fixture proof (6 cases, /tmp corpus, git repo with a real removal commit):
RPT-A duplicate -> resolve (duplicate of already-decided RPT-B)
RPT-C already-fixed -> resolve (goneFromCode removed from modules/ in fc4eaf3)
RPT-D noise -> reject
RPT-E still-present -> approve
RPT-F user report -> SKIP
RPT-G never existed -> SKIP <- caught the first draft, which called it "already fixed"
Live dry-run on the real corpus: "nothing provable (0 left for the operator, mode=safe)" and
`git log -S emptyTrash -- spaces/newos4/modules` resolves to 563a9be, i.e. the report I wrongly
approved by hand tonight would have been auto-resolved correctly.
Dashboard: agent-decided cards carry a 🤖 badge + the reason + "Any button below overrides it",
and the tab shows "🤖 feedback agent: N decided on its own in its last run (safe mode, M left for
you)".
Diffstat (limited to 'scripts/newos4-feedback-collect.py')
| -rwxr-xr-x | scripts/newos4-feedback-collect.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/scripts/newos4-feedback-collect.py b/scripts/newos4-feedback-collect.py index 226a74c..c0711d9 100755 --- a/scripts/newos4-feedback-collect.py +++ b/scripts/newos4-feedback-collect.py @@ -17,6 +17,7 @@ STEER = os.path.join(ROOT, 'spaces/newos4/data/maintenance/steering.json') DECISIONS = os.path.join(ROOT, 'spaces/newos4/data/feedback/decisions.jsonl') APPLIED = os.path.join(ROOT, 'spaces/newos4/data/feedback/applied.json') # ledger written by the applier NETFAIL = os.path.join(ROOT, 'spaces/newos4/data/debug/network_failures.json') # ingest-filter counter +AUTOREVIEW = os.path.join(ROOT, 'spaces/newos4/data/feedback/autoreview-latest.json') def load(path, default): @@ -80,7 +81,7 @@ def plans_needing_decision(dec): os.path.getmtime(p), timezone.utc).isoformat(timespec='seconds'), 'excerpt': excerpt, 'tasks': tasks, 'status': status, 'decision': d.get('decision'), 'decided_at': d.get('decided_at') or d.get('ts'), - 'note': d.get('note', ''), + 'note': d.get('note', ''), 'actor': d.get('actor', ''), }) return items @@ -103,6 +104,7 @@ def reports_needing_decision(dec): 'created_at': r.get('created_at'), 'auto': bool(diag.get('auto')), 'new': rid in new_ids, 'decision': d.get('decision'), 'decided_at': d.get('decided_at') or d.get('ts'), 'note': d.get('note', ''), + 'actor': d.get('actor', ''), 'message': (r.get('body') or '')[:1500], 'page': diag.get('url') or '', 'version': diag.get('version') or '', 'ua': (diag.get('ua') or '')[:120], 'errors': [str(e)[:300] for e in errs[:3]], @@ -147,6 +149,7 @@ def main(): }, 'plans': plans, 'reports': reports, 'steering': steer[:20], 'recent_apply': recent_apply(8), + 'autoreview': {k: (load(AUTOREVIEW, {}) or {}).get(k) for k in ('generated_at', 'mode', 'decided', 'skipped')}, 'triage_checks': (triage.get('checks') or {}), 'triage_generated_at': triage.get('generated_at'), } |