| 12345678910111213141516171819202122232425 |
- name: tool-call-salvage
- repo: https://github.com/Julientalbot/hermes-tool-call-salvage
- sha: 2d0ad4fba66499659179ac9932ec0c6d2c70b744
- version: "0.1.0"
- title: Tool Call Salvage
- description: >-
- Removes tool-call markup that a model wrote into its final reply as text instead of calling
- the tool (Qwen <function=...>, <invoke>, DeepSeek DSML and tool tokens, Harmony, Kimi, Mistral
- and Llama formats). Only complete markup that ends the reply is touched; code blocks and
- markup followed by more text are left as they are. An optional salvage mode, off by default
- and limited to the models you list, turns the markup into a real call to a tool offered in
- that request. Disclosure: no network, files, shell, subprocesses, telemetry or stored state;
- logs name the format and tools, never arguments; in salvage mode text the model wrote can
- become a real tool call (tools offered in the request, or Hermes's tool_call bridge when
- deferred_tools is on), run through Hermes's normal approvals.
- maintainer: Julientalbot
- tier: community
- category: models
- requires_hermes: ">=0.21.0"
- docs_url: https://github.com/Julientalbot/hermes-tool-call-salvage/blob/2d0ad4fba66499659179ac9932ec0c6d2c70b744/README.md
- capabilities:
- provides_tools: []
- provides_hooks: [transform_llm_output]
- provides_middleware: [llm_execution]
- requires_env: []
|