Adil Hafeez 421bff03ac fix: prevent index-out-of-bounds panic in signal analyzer follow-up ... The signals analyzer preprocesses messages by filtering out any message without extractable text (tool calls, tool results, empty content), but it stores each surviving entry's ORIGINAL conversation index in the tuple. `analyze_follow_up` then used that stored index to look up previous user messages inside `normalized_messages`, which panicked ("index out of bounds: the len is N but the index is M") whenever any message was filtered out before the current turn — a common pattern for Anthropic conversations containing <tool_use_error> blocks. The panic is caught at the tokio task boundary so requests still complete with the default model, but every affected request logs a noisy stack trace and silently skips signal analysis, which can degrade routing decisions. Fix by walking the normalized list with `iter().enumerate()` and using the inner position for index lookups. The stored original index is kept only for display ("Turn N") strings. Includes a regression test that reproduces the exact panic shape via the public `analyze` entry point.		2026-04-17 18:21:57 -07:00
..
src	fix: prevent index-out-of-bounds panic in signal analyzer follow-up	2026-04-17 18:21:57 -07:00
Cargo.toml	Redis-backed session cache for cross-replica model affinity (#879)	2026-04-13 19:30:47 -07:00