claude-bot/EJClaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(paired): cap consecutive reviewer silent-failure retries

Browse Source 
The reviewer (codex) sometimes emits a final result with no visible text.
The runtime marks the run failed → handleFailedReviewerExecution
preserves status as review_ready → the follow-up scheduler re-queues
another reviewer-turn → loop. The existing round_trip / arbiter caps
never fire because round_trip_count only advances on owner-side
submissions; bot-side reviewer flakes never increment it.

Mirror the owner_failure_count pattern: add reviewer_failure_count to
paired_tasks, increment on each silent failure, and escalate via
requestArbiterOrEscalate once it reaches 2. Reset to 0 on every
successful reviewer completion path (PROCEED/REVISE/arbiter/wait-for-user)
and when the owner re-submits a fresh review cycle.

Repro chat: 1507762222724546560 (stock-adiviser). Task
33968d31-0da2-480c-85d3-7a3999822ab4 logged 11 consecutive
reviewer-turn entries with no work_items and round_trip_count stuck
at 1.
This commit is contained in:
Codex
2026-05-29 23:40:35 +09:00
parent cdb59ce9fe
commit 32fbb00dd2
11 changed files with 147 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/paired-execution-context-shared.ts
View File

@@ -270,6 +270,7 @@ export function transitionPairedTaskStatus(args: {
review_requested_at?: string | null;
round_trip_count?: number;
owner_failure_count?: number;
reviewer_failure_count?: number;
owner_step_done_streak?: number;
finalize_step_done_count?: number;
task_done_then_user_reopen_count?: number;
@@ -318,6 +319,7 @@ export function applyPairedTaskPatch(args: {
review_requested_at?: string | null;
round_trip_count?: number;
owner_failure_count?: number;
reviewer_failure_count?: number;
owner_step_done_streak?: number;
finalize_step_done_count?: number;
task_done_then_user_reopen_count?: number;
@@ -363,6 +365,7 @@ export function requestArbiterOrEscalate(args: {
review_requested_at?: string | null;
round_trip_count?: number;
owner_failure_count?: number;
reviewer_failure_count?: number;
owner_step_done_streak?: number;
finalize_step_done_count?: number;
task_done_then_user_reopen_count?: number;