mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-23 16:36:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7
hermes-agent/website
History
DanielMaly e5078e3152 feat(compression): add absolute token threshold via compression.threshold_tokens 
Add compression.threshold_tokens config option that sets an absolute
token cap for auto-compaction. When configured alongside the existing
ratio-based threshold, the effective trigger point is the lower of the
two, so compression never fires later than the user's preferred token
count regardless of which model is active.

This solves the problem where switching between models with different
context windows (e.g. 1M → 400K) shifts the absolute trigger point,
causing premature or delayed compression.

Rework from PR #24279 addressing sweeper feedback:
- The cap is now a first-class compressor configuration value
  (threshold_tokens_cap parameter on ContextCompressor.__init__),
  not a post-construction patch on the live instance.
- Applied in both __init__ and update_model() so it survives model
  switches and fallback activations (the old approach was undone by
  update_model() restoring _configured_threshold_percent).
- Clamped to the model's context length so a cap above the window is
  a no-op (ratio-based threshold wins).
- Works with max_tokens output-token reservations.
- Added 9 tests covering cap-vs-ratio selection, model switch survival,
  context-length clamping, max_tokens interaction, and invalid values.
- Updated user-facing configuration docs.
- Removed unrelated background-review/curator/Honcho changes (main
  already contains background-review memory isolation in 973f27e95).

Config example:
  compression:
    threshold: 0.50
    threshold_tokens: 200000   # never compress later than 200K tokens
2026-07-22 08:12:14 -07:00
..
docs feat(compression): add absolute token threshold via compression.threshold_tokens 2026-07-22 08:12:14 -07:00
i18n/zh-Hans/docusaurus-plugin-content-docs/current fix(secrets): validate bitwarden status token 2026-07-22 03:20:09 -07:00
scripts refactor(cron): rebrand Cron Recipes -> Automation Blueprints 2026-06-11 10:49:47 -07:00
src refactor(cron): rebrand Cron Recipes -> Automation Blueprints 2026-06-11 10:49:47 -07:00
static fix: regenerate model-catalog.json to dedupe sonnet-5 entries 2026-07-20 02:25:44 -07:00
.gitignore feat(skills-hub): health checks, freshness badge, and a watchdog cron (#32345) 2026-05-25 23:10:45 -07:00
docusaurus.config.ts fix(docs): disable fuzzy matching in docs search (exact word or prefix only) (#65103) 2026-07-15 09:57:46 -07:00
package-lock.json docs(website): redirect old automation-templates URL to automation-blueprints 2026-06-12 09:46:27 -07:00
package.json docs(website): redirect old automation-templates URL to automation-blueprints 2026-06-12 09:46:27 -07:00
README.md docs: replace ASCII diagrams with Mermaid/lists, add linting note 2026-03-21 17:58:30 -07:00
sidebars.ts feat(skills): bundle docx, xlsx, and pdf office skills; refresh powerpoint (#68595) 2026-07-21 05:39:23 -07:00
tsconfig.json change(tooling): typecheck in CI, update ts to 6 2026-06-10 11:59:34 -04:00

README.md

Website

This website is built using Docusaurus, a modern static website generator.

Installation

yarn

Local Development

yarn start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.

Build

yarn build

This command generates static content into the build directory and can be served using any static contents hosting service.

Deployment

Using SSH:

USE_SSH=true yarn deploy

Not using SSH:

GIT_USER=<Your GitHub username> yarn deploy

If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.

Diagram Linting

CI runs ascii-guard to lint docs for ASCII box diagrams. Use Mermaid (````mermaid`) or plain lists/tables instead of ASCII boxes to avoid CI failures.