mirror of
https://github.com/multica-ai/multica.git
synced 2026-06-17 03:38:32 +02:00
6d9ebb0fdd
* fix(daemon): treat upstream API 400 invalid_request_error as poisoned session A markdown-linked image in an issue description that the agent downloads as a tiny CDN auth-error file and Read's as a PNG poisons the conversation: the LLM API rejects the bad image with 400 invalid_request_error, the session_id is pinned mid-flight, and every follow-up task on the issue (comment-trigger, auto-retry) resumes the same poisoned conversation and hits the same 400 — the issue can no longer be executed even after the description is cleaned up. Mirror the existing fallback-output classifier on the error side: detect "API Error: ... 400 ... invalid_request_error" in the agent error string, persist failure_reason='api_invalid_request', and add it to the GetLastTaskSession exclusion list so the next task starts a fresh session that re-reads the (now-clean) description. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): unblock issues already poisoned by API 400 invalid_request_error The forward-only classifier from the previous commit only tags new failures. Issues like MUL-1918 already have multiple failed-task rows whose failure_reason is the pre-fix default 'agent_error', and GetLastTaskSession falls back to those legacy rows on the next claim — so deploying the classifier alone leaves existing poisoned issues stuck (GPT-Boy review on PR #2314). Two complementary changes: - Migration 079 backfills failure_reason='api_invalid_request' on every pre-existing 'agent_error' row whose error text matches the canonical Anthropic 400 invalid_request_error shape. Keeps observability consistent (multica issue runs / UI now report the right reason). - GetLastTaskSession adds a defensive ILIKE clause on error text. Closes the deploy-window gap where the old binary could write a new 'agent_error' row between the migration running and the new code taking over, and protects against future error-format variants the daemon classifier might miss. Plus regression tests covering the legacy + new coexistence case GPT-Boy flagged, and a guard rail asserting benign 'agent_error' failures (timeouts, tool errors) still resume their session. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: multica-agent <github@multica.ai>
19 lines
951 B
SQL
19 lines
951 B
SQL
-- Backfill the api_invalid_request poisoned-session classifier introduced
|
|
-- in MUL-1921. The daemon now tags failed tasks whose error matches an
|
|
-- Anthropic 400 invalid_request_error so GetLastTaskSession excludes them
|
|
-- from the (agent_id, issue_id) resume lookup, but that change is
|
|
-- forward-only: existing failed rows still carry the default
|
|
-- failure_reason='agent_error' and the resume query falls back to them
|
|
-- on the next claim, re-poisoning every retry.
|
|
--
|
|
-- Re-classify any historical row whose error text matches the same
|
|
-- canonical shape (case-insensitive substrings "400" and
|
|
-- "invalid_request_error") so deploying this PR actually unblocks issues
|
|
-- like MUL-1918 instead of just preventing future regressions.
|
|
UPDATE agent_task_queue
|
|
SET failure_reason = 'api_invalid_request'
|
|
WHERE status = 'failed'
|
|
AND COALESCE(failure_reason, '') = 'agent_error'
|
|
AND error ILIKE '%400%'
|
|
AND error ILIKE '%invalid_request_error%';
|