Production incident: #rss get lublin failed with "summary failed: The operation was aborted due to timeout" — the LlmService call hit its 60 s cap while the local OpenAI-compatible server (qwen3.8-27b, uncontrollable reasoning tokens) was in a slow/busy period. Same endpoint answers trivial prompts in ~1 s when idle, so this is latency variance on the server side.
LLM_TIMEOUT_MS default 60000 → 180000 (3 min headroom); still env-overridable
AGENTS.md + code comment synced
No test changes needed (spec pins its own timeout). Build clean, oxlint clean. Lockfile untouched.
Production incident: `#rss get lublin` failed with "summary failed: The operation was aborted due to timeout" — the LlmService call hit its 60 s cap while the local OpenAI-compatible server (qwen3.8-27b, uncontrollable reasoning tokens) was in a slow/busy period. Same endpoint answers trivial prompts in ~1 s when idle, so this is latency variance on the server side.
- LLM_TIMEOUT_MS default 60000 → **180000** (3 min headroom); still env-overridable
- AGENTS.md + code comment synced
No test changes needed (spec pins its own timeout). Build clean, oxlint clean. Lockfile untouched.
Production incident: '#rss get lublin' at 9:41 AM failed with 'The operation
was aborted due to timeout' — the LlmService call hit its 60 s cap while the
local OpenAI-compatible server (qwen3.8-27b, uncontrollable reasoning tokens)
was slow/busy. The same endpoint answers a trivial prompt in ~1 s when idle,
so this is latency variance on the server side, not a dead endpoint.
Bump the LLM_TIMEOUT_MS fallback from 60000 to 180000 (3 min headroom for
slow reasoning periods); still env-overridable, only the default changed.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Production incident:
#rss get lublinfailed with "summary failed: The operation was aborted due to timeout" — the LlmService call hit its 60 s cap while the local OpenAI-compatible server (qwen3.8-27b, uncontrollable reasoning tokens) was in a slow/busy period. Same endpoint answers trivial prompts in ~1 s when idle, so this is latency variance on the server side.No test changes needed (spec pins its own timeout). Build clean, oxlint clean. Lockfile untouched.