4 people acecb7dd60 fix(pi): keep turn error when process exits 1 [MUL-6585] (#7451) ...

* fix(pi): keep turn error when process exits 1

Pi (and pi-print-clean-exit) exits 1 after stopReason=error. The backend
then overwrote lastTurnError with "pi exited with error: exit status 1",
so Classify filed a LiteLLM Connection error / Request timed out as
non-retryable process_failure.

Preserve the provider message and classify those strings as
provider_network so auto-retry can resume the session.

* fix(taskfailure): scope Pi network error matching

Co-authored-by: multica-agent <[email protected]>

---------

Co-authored-by: buihongduc132 <[email protected]>
Co-authored-by: Sol-Boy <[email protected]>
Co-authored-by: multica-agent <[email protected]>

2026-08-24 14:02:33 +08:00

..

classify_test.go

fix(pi): keep turn error when process exits 1 [MUL-6585] (#7451)

2026-08-24 14:02:33 +08:00

classify.go

fix(pi): keep turn error when process exits 1 [MUL-6585] (#7451)

2026-08-24 14:02:33 +08:00

context_exhausted_test.go

fix(agent): fail a run whose provider session ran out of context (MUL-5739) (#6422)

2026-08-05 15:41:15 +08:00

context_exhausted.go

fix(agent): fail a run whose provider session ran out of context (MUL-5739) (#6422)

2026-08-05 15:41:15 +08:00

failure_test.go

MUL-6343: Enforce recently created issue windows (#7305)

2026-08-21 12:55:57 +08:00

failure.go

MUL-6343: Enforce recently created issue windows (#7305)

2026-08-21 12:55:57 +08:00

resume_test.go

fix(daemon): recover in-turn when a resumed session cannot resolve provider auth (#6798)

2026-08-12 12:48:03 +08:00

resume.go

fix(daemon): recover in-turn when a resumed session cannot resolve provider auth (#6798)

2026-08-12 12:48:03 +08:00