mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(compression): add summary_base_url + move compression config to YAML-only

Browse source 
- Add summary_base_url config option to compression block for custom
  OpenAI-compatible endpoints (e.g. zai, DeepSeek, Ollama)
- Remove compression env var bridges from cli.py and gateway/run.py
  (CONTEXT_COMPRESSION_* env vars no longer set from config)
- Switch run_agent.py to read compression config directly from
  config.yaml instead of env vars
- Fix backwards-compat block in _resolve_task_provider_model to also
  fire when auxiliary.compression.provider is 'auto' (DEFAULT_CONFIG
  sets this, which was silently preventing the compression section's
  summary_* keys from being read)
- Add test for summary_base_url config-to-client flow
- Update docs to show compression as config.yaml-only

Closes #1591
Based on PR #1702 by @uzaylisak
This commit is contained in:
Teknium 2026-03-17 04:46:15 -07:00 • committed by GitHub
parent 867a96c051
commit d1d17f4f0a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 194 additions and 98 deletions
Download patch file Download diff file Expand all files Collapse all files

19
website/docs/reference/environment-variables.md
View file

@ -218,13 +218,18 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
| `SESSION_IDLE_MINUTES` | Reset sessions after N minutes of inactivity (default: 1440) |
| `SESSION_RESET_HOUR` | Daily reset hour in 24h format (default: 4 = 4am) |
## Context Compression
## Context Compression (config.yaml only)
| Variable | Description |
|----------|-------------|
| `CONTEXT_COMPRESSION_ENABLED` | Enable auto-compression (default: `true`) |
| `CONTEXT_COMPRESSION_THRESHOLD` | Trigger at this % of limit (default: 0.50) |
| `CONTEXT_COMPRESSION_MODEL` | Model for summaries |
Context compression is configured exclusively through the `compression` section in `config.yaml` — there are no environment variables for it.
```yaml
compression:
enabled: true
threshold: 0.50
summary_model: google/gemini-3-flash-preview
summary_provider: auto
summary_base_url: null # Custom OpenAI-compatible endpoint for summaries
```
## Auxiliary Task Overrides
@ -238,8 +243,6 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
| `AUXILIARY_WEB_EXTRACT_MODEL` | Override model for web extraction/summarization |
| `AUXILIARY_WEB_EXTRACT_BASE_URL` | Direct OpenAI-compatible endpoint for web extraction/summarization |
| `AUXILIARY_WEB_EXTRACT_API_KEY` | API key paired with `AUXILIARY_WEB_EXTRACT_BASE_URL` |
| `CONTEXT_COMPRESSION_PROVIDER` | Override provider for context compression summaries |
| `CONTEXT_COMPRESSION_MODEL` | Override model for context compression summaries |
For task-specific direct endpoints, Hermes uses the task's configured API key or `OPENAI_API_KEY`. It does not reuse `OPENROUTER_API_KEY` for those custom endpoints.