mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
docs: comprehensive update for recent merged PRs (#9019)
Audit and update documentation across 12 files to match changes from
~50 recently merged PRs. Key updates:
Slash commands (slash-commands.md):
- Add 5 missing commands: /snapshot, /fast, /image, /debug, /restart
- Fix /status incorrectly labeled as messaging-only (available in both)
- Add --global flag to /model docs
- Add [focus topic] arg to /compress docs
CLI commands (cli-commands.md):
- Add hermes debug share section with options and examples
- Add hermes backup section with --quick and --label flags
- Add hermes import section
Feature docs:
- TTS: document global tts.speed and per-provider speed for Edge/OpenAI
- Web dashboard: add docs for 5 missing pages (Sessions, Logs,
Analytics, Cron, Skills) and 15+ API endpoints
- WhatsApp: add streaming, 4K chunking, and markdown formatting docs
- Skills: add GitHub rate-limit/GITHUB_TOKEN troubleshooting tip
- Budget: document CLI notification on iteration budget exhaustion
Config migration (compression.summary_* → auxiliary.compression.*):
- Update configuration.md, environment-variables.md,
fallback-providers.md, cli.md, and context-compression-and-caching.md
- Replace legacy compression.summary_model/provider/base_url references
with auxiliary.compression.model/provider/base_url
- Add legacy migration info boxes explaining auto-migration
Minor fixes:
- wecom-callback.md: clarify 'text only' limitation (input only)
- Escape {session_id}/{job_id} in web-dashboard.md headings for MDX
This commit is contained in:
parent
c449cd1af5
commit
4ca6668daf
12 changed files with 299 additions and 40 deletions
|
|
@ -322,7 +322,11 @@ Long conversations are automatically summarized when approaching context limits:
|
|||
compression:
|
||||
enabled: true
|
||||
threshold: 0.50 # Compress at 50% of context limit by default
|
||||
summary_model: "google/gemini-3-flash-preview" # Model used for summarization
|
||||
|
||||
# Summarization model configured under auxiliary:
|
||||
auxiliary:
|
||||
compression:
|
||||
model: "google/gemini-3-flash-preview" # Model used for summarization
|
||||
```
|
||||
|
||||
When compression triggers, middle turns are summarized while the first 3 and last 4 turns are always preserved.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue