apunkt/ktx
1
0
Fork 0
mirror of https://github.com/Kaelio/ktx.git synced 2026-06-10 08:05:14 +02:00
Code Issues Projects Releases Packages Wiki Activity

docs: clarify claude-code host discovery metadata

Browse source
This commit is contained in:
Andrey Avtomonov 2026-05-15 17:00:23 +02:00
parent a5b364415a
commit abc7795744
2 changed files with 8 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

5
docs-site/content/docs/guides/building-context.mdx
View file

@ -59,8 +59,9 @@ Deep ingest needs LLM and embedding readiness. If those providers are not
configured, run `ktx setup` or use `--fast`.
When you use `claude-code`, KTX still controls the tool surface for ingest and
memory capture. Claude Code built-in tools, discovered MCP servers, hooks,
skills, plugins, agents, and slash commands are not exposed to KTX agent loops.
memory capture. Claude Code built-in tools, discovered MCP servers, plugins,
skills, agents, and slash commands are not invokable by KTX agent loops unless
they are exact KTX MCP tools for the current run.
## Query history

7
docs-site/content/docs/guides/llm-configuration.mdx
View file

@ -37,8 +37,11 @@ llm:
```
`claude-code` keeps KTX tool boundaries intact. KTX exposes only the MCP tools
needed for the current KTX agent loop and disables Claude Code built-in tools,
filesystem settings, skills, plugins, agents, hooks, and slash commands.
needed for the current KTX agent loop, disables Claude Code built-in tools,
keeps plugins empty, and denies every non-KTX tool request through
`canUseTool`. The Claude Agent SDK may still report host-discovered slash
commands, skills, and subagent names in init metadata; that metadata is not an
execution grant for KTX agent loops.
## Prompt caching