requesty.yaml 1.4 KB

1234567891011121314151617181920212223242526272829
  1. name: requesty
  2. repo: https://github.com/requestyai/hermes-provider-requesty
  3. sha: "aa4e37d7f09dfc1e98b915d740d09e8b1b44c98d"
  4. subdir: requesty
  5. title: Requesty
  6. description: >-
  7. Requesty LLM gateway as a Hermes model provider (`--provider requesty`, alias `rq`, or Requesty
  8. in `hermes model`). The picker lists Requesty's managed routing policies (curated routes with
  9. failover, `@eu` variants for EU-only hosting); any Requesty model id or org policy also works.
  10. `/reasoning` maps onto Requesty's `reasoning_effort` for reasoning-capable models, the Hermes
  11. session id is sent as `requesty.trace_id`, and context windows and estimated cost come from the
  12. Requesty catalog. Prompt caching is done server-side by Requesty. Disclosure — chat requests
  13. go to https://router.requesty.ai/v1 (or REQUESTY_BASE_URL) through Hermes' own client with
  14. REQUESTY_API_KEY, which Hermes reads; the plugin itself only fetches Requesty's public model
  15. catalogs (/v1/models/managed and /v1/models, no credentials), once per process, sometimes on a
  16. short-lived background thread. No attribution headers, telemetry, file access or processes.
  17. Supersedes #27908.
  18. maintainer: requestyai
  19. tier: community
  20. category: models
  21. requires_hermes: ">=0.21.6"
  22. docs_url: https://github.com/requestyai/hermes-provider-requesty#readme
  23. version: "0.1.0"
  24. capabilities:
  25. provides_tools: []
  26. provides_hooks: []
  27. provides_middleware: []
  28. requires_env:
  29. - REQUESTY_API_KEY