Added missing word "be" in prompt instructions.
This is unlikely to change the agent functionality in most cases, but
optimal clarity in prompt language is a best practice.
## Summary
This replaces the default model provider with a `MultiProvider`, which
has the logic:
- if the model name starts with `openai/` or doesn't contain "/", use
OpenAI
- if the model name starts with `litellm/`, use LiteLLM to use the
appropriate model provider.
It's also extensible, so users can create their own mappings. I also
imagine that if we natively supported Anthropic/Gemini etc, we can add
it to MultiProvider to make it work.
The goal is that it should be really easy to use any model provider.
Today if you pass `model="gpt-4.1"`, it works great. But
`model="claude-sonnet-3.7"` doesn't. If we can make it that easy, it's a
win for devx.
I'm not entirely sure if this is a good idea - is it too magical? Is the
API too reliant on litellm? Comments welcome.
## Test plan
For now, the example. Will add unit tests if we agree its worth mergin.
---------
Co-authored-by: Steven Heidel <steven@heidel.ca>
See #528, some folks are having issues because their output types are
not strict-compatible.
My approach was:
1. Create `AgentOutputSchemaBase`, which represents the base methods for
an output type - the json schema + validation
2. Make the existing `AgentOutputSchema` subclass
`AgentOutputSchemaBase`
3. Allow users to pass a `AgentOutputSchemaBase` to
`Agent(output_type=...)`
litellm is a library that abstracts away details/differences for a lot
of model providers. Adding an extension, so that any provider can easily
be integrated.
---
[//]: # (BEGIN SAPLING FOOTER)
* #532
* __->__ #524
Thanks to awesome example `research_bot`
Fix andproduce and goodgrammar (and so on)
```python
>>> from examples.research_bot.agents import search_agent
>>> print(search_agent.INSTRUCTIONS)
You are a research assistant. Given a search term, you search the web for that term andproduce a concise summary of the results. The summary must 2-3 paragraphs and less than 300words. Capture the main points. Write succinctly, no need to have complete sentences or goodgrammar. This will be consumed by someone synthesizing a report, so its vital you capture theessence and ignore any fluff. Do not include any additional commentary other than the summaryitself.
```
### Summary
Updated the `computer-use` example to support simultaneous key presses.
The current implementation presses and releases keys one at a time,
which prevents combo inputs like copy (CTRL+C) from working correctly.
### Test plan
N/A
### Issue number
N/A
### Checks
- [ ] I've added new tests (if relevant)
- [ ] I've added/updated the relevant documentation
- [x] I've run `make lint` and `make format`
- [ ] I've made sure tests pass
## Summary:
Adds tracing and tests for tracing.
- Tools are added to the agents
- Theres a span for the mcp tools lookup
- Functions have MCP data
## Test Plan:
Unit tests
.
## Summary:
Adds tracing and tests for tracing.
- Tools are added to the agents
- Theres a span for the mcp tools lookup
- Functions have MCP data
## Test Plan:
Unit tests
.
## Changes
- In this handoff example, we need to use `first_agent` with
`random_number_tool`, instead of `second_agent` without that tool, since
the user is asking to generate a random number.
- fixed typo in comments
Remove the `not` keyword from the `tripwire_triggered` parameter in the `math_guardrail` function in `examples/agent_patterns/input_guardrails.py`.
The not keyword prevented the guardrail from being triggered, which defeats the purpose of the example.
