{"repo":"NousResearch/hermes-agent","public_id":"115218","display_label":"Misclassified content-moderation 400 error handling","summary":"A provider 400 error with 'Content Exists Risk' is being incorrectly classified as a malformed request rather than a content-policy block, causing broken fallback behavior in bot-mode and subagents. These items address detecting and correctly routing that specific error code.","subsystem":null,"counts":{"members":3,"open_issues":0,"open_issues_distinct":0,"open_prs":0,"closed_issues":1,"merged_prs":1,"attempt_prs":1},"landed_fix":{"status":"merged_to_main","basis":"structural","pr":116670,"merged_at":"2026-09-20T06:39:25+00:00"},"resolution":{"state":"resolved","by":"pr-116670"},"freshness":{"state":"verified","last_verified_at":"2026-09-20T06:39:25+00:00","is_stale":false},"grouping":{"backbone":"STRUCTURAL_SPANNING","link_density":0.6666666666666666},"fix_edges":[{"issue_number":115218,"pr_number":116670,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true,"pr_merged_at":"2026-09-20T06:39:25+00:00"}],"members":[{"kind":"issue","number":115218,"title":"[Bug]: Provider content-moderation 400 (`Content Exists Risk`) has no fallback path — bot-mode delivery fails closed, subagents are killed, and the message says \"malformed\"","url":null,"state":"closed"},{"kind":"pr","number":115233,"title":"fix(agent): classify CommandCode \"Content Exists Risk\" 400 as a content-policy block","url":null,"state":"closed","close_reason":{"refs":[{"kind":"commit","value":"d4f88f39eef","number":0},{"kind":"pr","value":"#116670","number":116670}],"category":"implemented_elsewhere","implication":"superseded"},"merged":false},{"kind":"pr","number":116670,"title":"fix(agent): provider content-moderation 400 (Content Exists Risk) is reported as a safety-filter refusal, not a malformed request (#115218, salvage #115233)","url":null,"state":"merged","close_reason":{"category":"merged"},"merged":true,"is_fix_pr":true,"fix_tier":"verified","files_changed":["agent/error_classifier.py","tests/agent/test_error_classifier.py"]}],"trust":{"default_tier":"verified","includes_suggested":false}}