eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Added a configurable LLM timeout

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-29 18:08:39 -05:00
parent d8bc84934e
commit f841f7eb71
7 changed files with 143 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -87,6 +87,7 @@ Useful configuration can be supplied by CLI flag or environment variable. CLI fl
| `AUDITA_LLM_API_KEY` | `--llm-api-key` | unset | Preferred provider-neutral LLM API credential; CLI overrides both environment-key variants |
| `AUDITA_MODEL` | `--model` | `openrouter/google/gemma-4-31b-it` | LLM model name sent to the configured OpenAI-compatible endpoint |
| `AUDITA_BASE_URL` | `--base-url` | `https://openrouter.ai/api/v1` | OpenAI-compatible API base URL |
| `AUDITA_LLM_TIMEOUT_SECONDS` | `--llm-timeout-seconds` | `600` | Per-request timeout in seconds for LLM calls to the configured OpenAI-compatible endpoint |
| `AUDITA_MAX_RETRIES` | `--max-retries` | `3` | Maximum Instructor retries for structured responses |
| `AUDITA_MAX_SECTION_TOKENS` | `--max-section-tokens` | `16384` | Maximum estimated tokens per proposal-stage transcript section |
| `AUDITA_MIN_SECTION_TOKENS` | `--min-section-tokens` | `4096` | Minimum estimated tokens per proposal-stage transcript section when balancing for concurrency |