RomanNum3ral
/
cai
mirror of https://github.com/aliasrobotics/cai.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
896 Commits 6 Branches 5 Tags 218 MiB
Commit Graph

107 Commits

Author SHA1 Message Date
Víctor Mayoral Vilches 04359a07f3 Revert "Apply code formatting with make format" 2025-06-14 09:51:19 +00:00
luijait ba17d16d11 Fix generc linux command test 2025-05-27 12:39:00 +02:00
Víctor Mayoral Vilches 5ab7f64562 Merge branch '0.4.0' of https://gitlab.com/aliasrobotics/alias_research/cai into 0.4.0 2025-05-26 10:58:52 +02:00
Víctor Mayoral Vilches 912ce4cb4d switch to .3 for 0.4.0 to avoid conflicts 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-05-26 10:58:49 +02:00
luijait 9af18a6e34 Add testg 2025-05-26 08:43:15 +00:00
luijait c69c4bcdbd Test 2025-05-25 14:27:59 +00:00
luijait 64fa082a16 testing 2025-05-23 20:17:41 +02:00
luijait 4f26e395e0 add unit tests for pricing 2025-05-23 15:11:28 +02:00
luijait 699017af02 Pricing 2025-05-23 14:37:45 +02:00
luijait 8a6200775e Fix pretty print 2025-05-08 09:31:39 +02:00
lidia9 483591f36a adding fake openai api key 2025-04-30 12:35:40 +02:00
lidia9 8c1dea4697 remove set disable in test 2025-04-30 11:41:40 +02:00
Mery-Sanz 957539880e tracing disabled 2025-04-30 11:37:06 +02:00
Mery-Sanz e3d8d25fce final fiz 2025-04-23 09:04:48 +02:00
Mery-Sanz fd12d531e3 fix test name 2025-04-23 08:12:09 +02:00
Mery-Sanz e8bb5ab241 add test 2025-04-22 16:48:12 +02:00
Mery-Sanz 016c27c4af fix agent and add primary test 2025-04-22 16:32:26 +02:00
Mery-Sanz 6bafa0235f test 2025-04-11 13:49:06 +02:00
Mery-Sanz 5cd571976a fix pipleines 2025-04-11 12:24:32 +02:00
Mery-Sanz bd33d3fd67 change gpt-4o and install in .yml 2025-04-11 11:38:21 +02:00
Mery-Sanz ed73fe1a08 try to add ci 2025-04-11 10:06:25 +02:00
Mery-Sanz 00a50a03ae fix test 2025-04-11 09:34:06 +02:00
Mery-Sanz 58985f9d57 fix mcp test 2025-04-11 08:24:26 +02:00
Mery-Sanz 99469a17e2 fix function schema test 2025-04-11 08:11:26 +02:00
Mery-Sanz f07059cbd5 fix some test 2025-04-11 08:04:19 +02:00
Mery-Sanz 7e3af1842a add coments and docstring 2025-04-10 09:57:35 +02:00
Mery-Sanz 2a32bd9e9b improve test 2025-04-10 09:42:16 +02:00
Mery-Sanz 75869265a5 add more test 2025-04-10 09:27:56 +02:00
Mery-Sanz 9532fe42f5 add new test and fix previous 2025-04-10 08:54:21 +02:00
Mery-Sanz 8a2778769d add test 2025-04-10 07:58:40 +02:00
Mery-Sanz 8aa1ae0424 final fix 2025-04-09 16:17:06 +02:00
Mery-Sanz 73de470fb0 fix more test 2025-04-09 16:07:58 +02:00
Mery-Sanz c083ecf69f fix more test 2025-04-09 15:59:24 +02:00
Mery-Sanz f88365b11d add 2 more test 2025-04-09 15:54:58 +02:00
Mery-Sanz 05fab61056 fix test_agent_runner 2025-04-09 15:51:05 +02:00
Mery-Sanz 4ae76ecd29 fix test_agent_hooks.py and reorganize imports 2025-04-09 15:46:53 +02:00
María Sanz Gómez ef64c7a1e4 fix tests/test_agent_config.py 2025-04-09 15:42:26 +02:00
Víctor Mayoral Vilches d1fd6623e5 Merge remote-tracking branch 'origin/main' into cai 2025-03-31 13:21:34 +02:00
Víctor Mayoral Vilches 944128583c CLI responding, but only to proprietary models 
Need to investigate why self-hosted models via OLLAMA fail API-wise

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-28 09:48:16 +01:00
Steven Heidel d1e94324e8 Expose the "store" parameter through ModelSettings (#357) 
Closes https://github.com/openai/openai-agents-python/issues/173

This will also set stored completions to True by default, encouraging a
best practice.
 2025-03-26 19:01:28 -04:00
Rohan Mehta 5ff0baddc3 Raise error on more invalid function schemas (#356) 
Towards #345

## Summary:
Using a `dict` or `Mapping` isn't strict-mode compliant. But we were
checking for the literal `True` whereas the value can also be an array,
for example. Fix that.

## Test Plan:

Unit tests
 2025-03-26 15:52:19 -04:00
pakrym-oai 0fa5849839 Mark handoff span as errored when multiple handoffs are requested (#344) 
Also includes the set of requested agents in the error data.
<img width="968" alt="image"
src="https://github.com/user-attachments/assets/0c5c2e81-08f7-445c-bbb0-3e169ef744a5"
/>
 2025-03-26 10:44:59 -04:00
Rohan Mehta b870b90471 [5/n] MCP tracing (#342) 
## 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
.
 2025-03-25 19:54:28 -04:00
Rohan Mehta 6cb8b1ceaa [5/n] MCP tracing 
## 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
.
 2025-03-25 19:28:48 -04:00
Rohan Mehta 4c93a5d9b1 feat: Add Graphviz-based agent visualization functionality (#147) 
This pull request introduces functionality for visualizing agent
structures using Graphviz. The changes include adding a new dependency,
implementing functions to generate and draw graphs, and adding tests for
these functions.

New functionality for visualizing agent structures:

* Added `graphviz` as a new dependency in `pyproject.toml`.
* Implemented functions in `src/agents/visualizations.py` to generate
and draw graphs for agents using Graphviz. These functions include
`get_main_graph`, `get_all_nodes`, `get_all_edges`, and `draw_graph`.

Testing the new visualization functionality:

* Added tests in `tests/test_visualizations.py` to verify the
correctness of the graph generation and drawing functions. The tests
cover `get_main_graph`, `get_all_nodes`, `get_all_edges`, and
`draw_graph`.

For example, given the following code:

```python
from agents import Agent, function_tool
from agents.visualizations import draw_graph


@function_tool
def get_weather(city: str) -> str:
    return f"The weather in {city} is sunny."


spanish_agent = Agent(
    name="Spanish agent",
    instructions="You only speak Spanish.",
)

english_agent = Agent(
    name="English agent",
    instructions="You only speak English",
)

triage_agent = Agent(
    name="Triage agent",
    instructions="Handoff to the appropriate agent based on the language of the request.",
    handoffs=[spanish_agent, english_agent],
    tools=[get_weather],
)


draw_graph(triage_agent)
```

Generates the following image:

<img width="614" alt="Screenshot 2025-03-13 at 18 36 23"
src="https://github.com/user-attachments/assets/d01fe502-6886-4efb-aaf8-c92e4524b0fe"
/>
 2025-03-25 19:22:58 -04:00
Martín Bravo dc3093bab3 Refactor visualization functions to improve formatting and streamline edge generation 2025-03-25 19:12:40 +01:00
Martín Bravo b5f6544f6f Add start and end nodes to graph visualization and update edge generation 2025-03-25 19:11:43 +01:00
Martín Bravo c988fd4aaf Add graphviz as a dependency and update import statements 2025-03-25 18:46:23 +01:00
Rohan Mehta 944b730da9 Make the reset behavior on tool use configurable 
## Summary:

#263 added this behavior. The goal was to prevent infinite loops when tool choice was set. The key change I'm making is:
1. Making it configurable on the agent.
2. Doing bookkeeping in the Runner to track this, to prevent mutating agents.
3. Not resetting the global tool choice in RunConfig.

## Test Plan:
Unit tests.
.
 2025-03-25 13:29:32 -04:00
Martín Bravo 692dfe0327 Merge branch 'main' of https://github.com/openai/openai-agents-python into feat/draw_graph 2025-03-25 18:02:51 +01:00