diff options
| author | Florian <2320560+florianbuetow@users.noreply.github.com> | 2026-01-31 23:48:38 +0100 |
|---|---|---|
| committer | Florian <2320560+florianbuetow@users.noreply.github.com> | 2026-01-31 23:48:38 +0100 |
| commit | 22009e90a4576764687328ed3cf81efbd2813d77 (patch) | |
| tree | e69b810f813955e24b79409bc27ff6b86adf11e3 /config.toml.example | |
| parent | 7194696eb8c4c5bd50f69df96e9a6b87cec1f049 (diff) | |
feat: add configurable request timeout for LLM calls
Local LLMs (LM Studio, Ollama, etc.) often need more than the default
30-second timeout. Added request_timeout config option (in seconds)
to [general] section and HEXAI_REQUEST_TIMEOUT env var.
Original constructor signatures preserved via *WithTimeout variants,
so no test changes required.
Diffstat (limited to 'config.toml.example')
| -rw-r--r-- | config.toml.example | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/config.toml.example b/config.toml.example index ae8110a..cc34e04 100644 --- a/config.toml.example +++ b/config.toml.example @@ -3,6 +3,7 @@ [general] max_tokens = 4000 max_context_tokens = 4000 +request_timeout = 30 # LLM request timeout in seconds # context_mode controls how much of the current document is sent as extra context: # - minimal: no additional context beyond the request payload. # - window: include a sliding window of ~context_window_lines around the cursor. |