| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
| |
The MCP server exports all aflow tools (and actions as tools) we have.
Fixes #6763
|
| |
|
|
|
|
| |
Add a tool that executes git grep with the given expression.
It can handle long tail of cases that codesearcher can't handle,
while still providing less output than reading whole files.
|
| |
|
|
| |
Add simple codeeditor tests to test testing.
|
| | |
|
| |
|
|
|
|
|
|
|
|
| |
Currently we handle several errors in LLMAgent (wrong tool name,
wrong tool arguments), and return the error to LLM,
but nothing is injected into the trajectory wrt what happened.
This makes trajectory incomplete and confusing,
one just sees repeated LLM calls w/o understanding what caused them.
Inject these tool failures into the trace, so that it's clear
what happened.
|
| |
|
|
|
|
|
|
|
|
| |
The error allows tools to communicate that an error is not an infrastructure error
that must fail the whole workflow, but rather a bad tool invocation by an LLM
(e.g. asking for a non-existent file contents).
Previously in the codesearcher tool we used a separate Missing bool
to communicate that. With the error everything just becomes cleaner and nicer.
The errors also allows all other tools to communicate any errors to the LLM
when the normal results cannot be provided and don't make sense.
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Gracefully handle (reply to LLM with error):
- incorrect tool name
- incorrect tool arg type
- missing tool arg
Silently handle:
- more than one call to set-results
- excessive tool args
Fixes #6604
|
| |
|
