Teknium f783986f5a fix: increase stream read timeout default to 120s, auto-raise for local LLMs (#6967) ... Raise the default httpx stream read timeout from 60s to 120s for all providers. Additionally, auto-detect local LLM endpoints (Ollama, llama.cpp, vLLM) and raise the read timeout to HERMES_API_TIMEOUT (1800s) since local models can take minutes for prefill on large contexts before producing the first token. The stale stream timeout already had this local auto-detection pattern; the httpx read timeout was missing it — causing a hard 60s wall that users couldn't find (HERMES_STREAM_READ_TIMEOUT was undocumented). Changes: - Default HERMES_STREAM_READ_TIMEOUT: 60s -> 120s - Auto-detect local endpoints -> raise to 1800s (user override respected) - Document HERMES_STREAM_READ_TIMEOUT and HERMES_STREAM_STALE_TIMEOUT - Add 10 parametrized tests Reported-by: Pavan Srinivas (@pavanandums)		2026-04-09 22:35:30 -07:00
..
developer-guide	fix(bluebubbles): add missing integration points and documentation (#6460)	2026-04-09 00:19:05 -07:00
getting-started	fix(termux): improve status and install UX	2026-04-09 16:24:53 -07:00
guides	docs: fix 40+ discrepancies between documentation and codebase (#5818)	2026-04-07 10:17:44 -07:00
integrations	fix(compaction): don't halve context_length on output-cap-too-large errors	2026-04-09 11:27:41 -07:00
reference	fix: increase stream read timeout default to 120s, auto-raise for local LLMs (#6967)	2026-04-09 22:35:30 -07:00
user-guide	feat: API server model name derived from profile name (#6857)	2026-04-09 17:07:29 -07:00
index.md	fix(bluebubbles): add missing integration points and documentation (#6460)	2026-04-09 00:19:05 -07:00