Dark-Alex-17/coyote
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

docs: Updated docs for .tool enable in agent contexts

Dark-Alex-17
2026-07-17 15:46:51 -06:00
parent cdc2faf8e8
commit d616565858
1 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
REPL.md
+12 -6
@@ -300,7 +300,7 @@ Setting `enabled_tools` or `enabled_mcp_servers` via `.set` requires retyping th
| `.mcp enable <server>` | Add a single MCP server to the enabled list and start it |
| `.mcp disable <server>` | Remove a single MCP server from the enabled list and stop it |
These write through the same layer cascade as `.set` (session > role, else the global in-memory config), and the
These write through the same layer cascade as `.set` (session > agent > role, else the global in-memory config), and the
confirmation message tells you which layer was written. Tab completion is state-aware: `enable` offers only entries
not currently enabled, `disable` offers only the current list.
@@ -309,9 +309,15 @@ Notes on edge cases:
* Entries enabled indirectly through a `mapping_tools`/`mapping_mcp_servers` alias cannot be disabled individually;
disable the alias or set the full list via `.set` instead.
* Disabling an MCP server that a loaded [skill](Skills) granted keeps it running until the skill is unloaded.
* `.tool enable/disable` is unavailable in an agent context outside a session, and `.mcp enable/disable` is
unavailable in agent contexts entirely; agent MCP servers are defined by the agent's own config
(`.edit agent-config`).
* In an agent context, `.tool enable/disable` adjusts a runtime-only filter over the agent's tool pool. It is not part
of the agent's configuration file, meaning agents always start with their full pool (own functions plus
`global_tools`) and it can never enable a tool the agent didn't declare; names outside the agent's pool are rejected.
While no filter is set the full pool is active, so enabling is a no-op and the first disable materializes the pool
into a concrete list minus that tool. The filter is in-memory only and resets when the agent is reloaded. Graph
agents are the exception: they define tools per-node via `tools:` in `graph.yaml`, so `.tool` and
`.set enabled_tools` are rejected there.
* `.mcp enable/disable` is unavailable in agent contexts entirely; agent MCP servers are defined by the agent's own
config (`.edit agent-config`).
## `.edit` - Modify configuration files
The `.edit` command lets you modify configuration files for the current mode of the REPL. It will open the selected
@@ -347,7 +353,7 @@ The `.list` command lists the assets of a given kind, making them discoverable w
| `.list rags` | List all RAGs |
| `.list macros` | List all macros |
| `.list skills` | List skills available in this context, with descriptions and a `(loaded)` marker for active skills |
| `.list tools` | List the tools that can be enabled/disabled via `.tool [enable\|disable] <name>` (excludes internal `user__`/`todo__`/`agent__`/`mcp_` tools) |
| `.list tools` | List the tools that can be enabled/disabled via `.tool [enable\|disable] <name>` (excludes internal tools; in an agent context, lists the agent's tool pool) |
| `.list mcp-servers` | List the MCP servers that can be enabled/disabled via `.mcp [enable\|disable] <name>` (configured servers plus mapping aliases) |
`.list skills` honors the same visibility and policy filters as the model-facing `skill__list` tool, so it shows exactly what the model can load in the current role/agent/session context.
@@ -507,4 +513,4 @@ or anything else you'd normally run in a terminal, without leaving the REPL.
- `!cd /tmp` does _not_ persist. Each `!cmd` runs in a fresh child shell, so subsequent `!pwd` will show the REPL's
original working directory, not `/tmp`.
- The command is _not_ written to your shell's history file (`~/.bash_history`, `~/.zsh_history`). It is, however, saved
in the REPL's reedline history (use up-arrow to recall).
in the REPL's reedline history (use up-arrow to recall).