Commit Graph

3 Commits

Author SHA1 Message Date
gsxdsm
2b8df56cb8 fix: escalate reviewer provider errors instead of looping on them
A rate-limited reviewer filled a task's Chat tab with 14 identical
"Reviewer using model: ..." markers and no review text, hammering an
already-limited provider.

Root cause: the reviewer was the only AI lane that never classified
provider errors, so a 429 became an UNAVAILABLE verdict. With no
validator fallback configured the fallback ladder re-ran the SAME model
instantly, and fn_review_step answered with "code review remains
blocking; retry once" — bounding the loop with prompt text rather than
code. The tool's catch-all also swallowed the error into tool output, so
withRateLimitRetry, UsageLimitPauser and RetryStormError never fired.

- reviewer: throw ReviewerProviderError for usage-limit/transient errors
  instead of laundering them into UNAVAILABLE, and never spend the
  fallback budget (which bounds bad reviews) on an outage.
- reviewer: absorb flaky-network blips in-lane via withRetry with
  jittered backoff; rate limits still escalate immediately.
- executor: re-raise the fatal after the prompt via
  throwDeferredReviewerFatal — pi-agent-core converts tool throws into
  tool_error results, so a tool cannot throw out of session.prompt().
- executor: give code review a real MAX_CODE_REVIEW_UNAVAILABLE_RETRIES
  counter, mirroring the plan/spec limiter.
- reviewer: dedupe the model marker on text, so same-model retries stay
  silent while a genuine model switch still emits.

Also fixes the run-on rendering: AgentLogType gains `status` for complete
engine messages. `text` means "streamed delta" and is re-glued with
join(""), which is why N standalone markers rendered as one string. The
split is at the type, not a separator — a separator would reintroduce the
FN-5787/5789/5803 streamed-spacing regression.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-15 12:54:16 -07:00
gsxdsm
278ede9dfa fix(FN-7952): recover provider failures without retry loops
Preserve authenticated CLI usage after migration, surface OAuth remediation, and use a single distinct model fallback before parking permanent failures. Keep transient credential errors retryable and confirm each OAuth expiry notification independently.

Fusion-Task-Id: FN-7952
2026-07-14 15:54:44 -07:00
gsxdsm
a3ce8e1f8e fix(FN-XXX): unify codex auth and chat fallback 2026-05-03 23:08:05 -07:00