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

519 Commits

Author SHA1 Message Date
Rohan Mehta 1771c1e856 update tests 2025-03-20 13:08:38 -04:00
Rohan Mehta 6f13d50a6e
feat: add voice pipeline support (#265) 
> Co-authored-by: rm@openai.com
 2025-03-20 12:54:42 -04:00
Dominik Kundel aec066649c fix tests 2025-03-20 09:52:15 -07:00
Dominik Kundel c7ce154637 feat: add voice pipeline support 
> Co-authored-by: rm@openai.com
 2025-03-20 09:43:13 -07:00
Rohan Mehta 1e02b9894d
Indentation for mkdocs.yml (#264) 2025-03-20 11:21:27 -04:00
Rohan Mehta 5c77298a47 Indentation for mkdocs.yml 2025-03-20 11:18:08 -04:00
Rohan Mehta 03dc8f7f82
Adds example for financial agent (#255) 
This example shows how you might compose a richer financial research
agent using the Agents SDK. The pattern is similar to the `research_bot`
example, but with more specialized sub‑agents and a verification step.

The flow is:

1. **Planning**: A planner agent turns the end user’s request into a
list of search terms relevant to financial analysis – recent news,
earnings calls, corporate filings, industry commentary, etc.
2. **Search**: A search agent uses the built‑in `WebSearchTool` to
retrieve terse summaries for each search term. (You could also add
`FileSearchTool` if you have indexed PDFs or 10‑Ks.)
3. **Sub‑analysts**: Additional agents (e.g. a fundamentals analyst and
a risk analyst) are exposed as tools so the writer can call them inline
and incorporate their outputs.
4. **Writing**: A writer agent brings together the search snippets and
any sub‑analyst summaries into a long‑form markdown report plus a short
executive summary.
5. **Verification**: A final verifier agent audits the report for
obvious inconsistencies or missing sourcing.
 2025-03-20 10:55:31 -04:00
xianghuijin d169d79288 Update documentation for tool_choice auto-reset feature 2025-03-20 21:49:38 +08:00
xianghuijin 9384a0fb3f Revert test file name to match project naming style 2025-03-20 21:28:24 +08:00
xianghuijin cde67f2b71 Rename test file for better clarity 2025-03-20 21:26:59 +08:00
xianghuijin fb77c74fa1 Fix potential infinite tool call loop by resetting tool_choice after tool execution 2025-03-20 21:22:27 +08:00
Alex Hall ea3e8ce230 lint 2025-03-20 13:56:11 +02:00
Alex Hall 7031d4ab87 Remove redundant weaker tracing assertions 2025-03-20 13:49:38 +02:00
Raduan77 96d1e8af8e fix typos in tests 2025-03-20 11:24:15 +01:00
Raduan77 e9f6d08260 fix typos in src/ 2025-03-20 11:24:08 +01:00
Raduan77 65264b6b8a fix typos in /examples 2025-03-20 11:23:57 +01:00
Shyamal H Anadkat 0dec5712db Adds example for financial agent 2025-03-19 22:33:13 -07:00
Rohan Mehta cef3d5357c
formatting updates to examples doc (#249) 2025-03-19 17:26:24 -04:00
James Hills d295a53e53
formatting updates to examples doc 2025-03-19 14:23:28 -07:00
Rohan Mehta 249bb56c23
add examples section to docs (#242) 
Have gotten feedback that Examples are somewhat buried in the Github
docs. Adding new page after quickstart.
 2025-03-19 15:42:41 -04:00
jhills20 4dd3e210ac add examples section to docs 2025-03-19 11:43:09 -07:00
Rohan Mehta 82754c7a85
v0.0.5 (#241) 2025-03-19 12:35:15 -04:00
Rohan Mehta 1ed181c641 v0.0.5 2025-03-19 12:32:36 -04:00
Rohan Mehta 54cf54c6f5
Fix breaking changes from openai 1.66.2 (#232) 
Breaking change in 1.66.2
 2025-03-19 12:31:59 -04:00
Rohan Mehta 545c20342a
chore(docs): Added comet opik to tracing AND formatted into a list (#73) 
Comet Opik added support for Agent SDK tracing and should be included.
 2025-03-19 12:31:02 -04:00
Rohan Mehta 8c9974bc90 Fix breaking changes from openai 1.66.2 2025-03-19 12:30:45 -04:00
Rohan Mehta 6d35c33592
Introduce tool_use_behavior on agents (#203) 
## Context
By default, the outputs of tools are sent to the LLM again. The LLM gets
to read the outputs, and produce a new response. There are cases where
this is not desired:
1. Every tool results in another round trip, and sometimes the output of
the tool is enough.
2. If you force tool use (via model settings `tool_choice=required`),
then the agent will just infinite loop.

This enables you to have different behavior, e.g. use the first tool
output as the final output, or write a custom function to process tool
results and potentially produce an output.

## Test plan
Added new tests and ran existing tests
Also added examples.


Closes #117
 2025-03-19 12:27:02 -04:00
Vincent Koc e7c2c19564
Merge branch 'main' into patch-1 2025-03-20 02:57:34 +11:00
Rohan Mehta 48ff99bb73
fix reasoning order in guardrails.md (#234) 2025-03-18 23:27:33 -04:00
CCM bc8369c76a
fix reasoning order in guardrails.md 2025-03-19 11:10:58 +08:00
Rohan Mehta 10aa5555af Introduce tool_use_behavior on agents 2025-03-18 21:55:12 -04:00
Rohan Mehta 6f7e801da0
Update tests and docs for strict mode decorator (#205) 
As titled. Test plan: unit tests/docs.
 2025-03-18 21:35:00 -04:00
Rohan Mehta ff65fb48dd
Add min 95% code coverage (#229) 
Run the tests with `coverage`, and make sure the min coverage is 95%.
 2025-03-18 16:50:00 -04:00
Rohan Mehta 74b197bc2c Add min 95% code coverage 2025-03-18 16:48:43 -04:00
Dmitry Pimenov 3b2afe118d
chore: adds Maxim AI to tracing processors (#210) 2025-03-18 09:10:52 -07:00
Rohan Mehta 97508557b9
[doc] add mlflow tracing integration (#171) 
Hi team! Congrats on the new Agents SDK launch!

This PR adds MLflow to the tracing documentation, as it supports
automatic tracing for OpenAI Agents SDK. It has also been supporting
tracing for
[Swarm](https://mlflow.org/docs/latest/tracing/integrations/swarm) as
well, so it is fantastic that the new SDK offers built-in mechanism for
3P trace providers🙂


![image](https://github.com/user-attachments/assets/d36382da-dca1-4335-a915-ca94a994e26a)
 2025-03-18 10:21:54 -04:00
Martín Bravo f4edc1f372 style: improve string formatting in visualization functions 2025-03-18 10:15:41 +01:00
Martín Bravo b7627cb642 style: improve string formatting 2025-03-18 10:14:52 +01:00
Martín Bravo 0079bca717 style: improve code formatting and readability in visualization functions 2025-03-18 10:09:44 +01:00
Martín Bravo 39ff00dd9d rename: test_visualization.py 2025-03-18 09:59:47 +01:00
Martín Bravo 53367be893 feat: add visualization module for agent graphs using Graphviz 2025-03-18 09:55:30 +01:00
Martín Bravo c745fe156a feat: add documentation for agent visualization using Graphviz 2025-03-18 09:55:23 +01:00
Martín Bravo 6f2f7293a0 refactor: move graphviz dependency to visualization section 2025-03-18 09:53:53 +01:00
Martín Bravo f7c594da08 feat: add visualization functions for agent graphs 2025-03-18 09:53:48 +01:00
B-Step62 e0eb4be145 [doc] add mlflow tracing integration 
Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
 2025-03-18 11:29:21 +09:00
Akshay Deo e5befd0cba
chore: adds Maxim AI to tracing processors 2025-03-18 07:49:33 +05:30
Martín Bravo aff1d60ea1 Merge branch 'main' of https://github.com/openai/openai-agents-python into feat/draw_graph 2025-03-17 23:50:52 +01:00
Dmitry Pimenov fe6bb8c8ab
Docs: update readme text to clarify handoffs (#208) 
Clarifying that the handoff abstraction is implemented via Responses
tool calling
 2025-03-17 15:15:13 -07:00
Dmitry Pimenov a43cf1542b clarifying that handoffs are a type of tool call under the hood 2025-03-17 15:05:15 -07:00
Rohan Mehta 3a97b15b89
Stronger tracing tests with `inline-snapshot` (#25) 
`assert len(spans) == 12` is a very weak assertion. This PR asserts the
exported traces and spans more precisely in a readable tree format. And
when the format of an exported trace/span changes (e.g. a new key is
added to every span), you can use `pytest --inline-snapshot=fix` to
update all relevant tests automatically. See
https://15r10nk.github.io/inline-snapshot/latest/ for more info.
 2025-03-17 17:59:04 -04:00