[serge] integration failure triage - 2026-09-11

[github-actions]

Automated integration-failure triage for the daily CI window 2026-09-05 → 2026-09-11.

This issue was generated by AI-assisted automation. The grouping, summaries, and recommended follow-up can be incomplete or misleading; verify the failures before acting.

Serge dispatched one task per failure group below — each opens or updates its own PR on a serge/fix/itf-<fingerprint> branch. This table is refreshed in place as Serge runs: a group links its #<pr> when opened, shows 🚫 no fix when Serge found no safe change, ⚠️ task failed on error, or (pending) while still running (a late PR links on the next nightly run).

Dispatched failure groups

Model	Error	Occurrences	PR
inkling (regressed by PR #47827)	mixed — tensor values differ (4)	4	#48667
generation	cuda_runtime — other (12)	12	🚫 no fix
blt	import_or_config — other (4)	4	⚠️ task failed
depth_anything	output_mismatch — tensor values differ (2)	2	#48725
kimi_k25	other — other (2)	2	🚫 no fix

Not dispatched — environment / dependency

These groups were triaged but NOT handed to Serge: their failure mode is a property of the runner or the environment, so no minimal source patch can fix them. They need a human (runner capacity, a dependency pin).

2 models ran out of device memory (7 failures) — needs runner capacity, not a patch, so none of these were dispatched: bamba (4), llama4 (3).

18 group(s) skipped — stopped failing before this run (4 integration tests regressed by commit ce5c8f5e4352 (PR #47988), musicgen_melody, glm_ocr, hunyuan_vl +14 more). Not dispatched and not awaiting a human.

Outcome recap

Why each group that opened no PR ended without one, and what it cost — surfaced here from the Serge dashboard. Failing tests links straight to each test's dashboard view, since these are the groups a human has to pick up.

Group	Reason	LLM	Tokens (in / out)	Failing tests
generation	[not_reproduced] GPU reproduce: the targeted tests did NOT fail at the base commit (not_reproduced) — the failure is stale, already fixed, flaky, or environment-specific. Skipping this group; no investigation, no PR.	moonshotai/Kimi-K2.7-Code	— / —	test_validate_assistant · test_matches_immediate_check_at_max_length · test_matches_immediate_check_on_a_batch · +3 more
blt	LLM returned unparseable output (finish_reason=stop, 49 LLM turns · 49 tool calls · 74.8s · 2150112 in / 11702 out tokens, 1 salvage re-ask(s) did not recover it)	moonshotai/Kimi-K2.7-Code	2,150,112 / 11,702	test_model_logits · test_model_logits_bf16
kimi_k25	[not_fixed] GPU verification did not confirm the fix (not_fixed): the patch did not turn the targeted tests green.	moonshotai/Kimi-K2.7-Code	2,083,714 / 19,205	test_model_logits · test_model_logits_batched

Generated 2026-09-12T00:16:31+00:00.