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

224 Commits

Author SHA1 Message Date
Han Hwang Lim b2e04bef06 fix annotation numbering in context management 
Fix inconsistent numbering between code and explanatory annotations in
the context management documentation.
 2025-03-21 21:10:30 +00:00
Dmitry Pimenov 3d97f0980d fix line in guardrails doc (#290) 2025-03-21 13:00:18 -07:00
James Hills 860eddd749 fix line in guardrails 2025-03-21 15:58:34 -04:00
Rohan Mehta de407c688c Replace remaining uses of `fetch_ordered_spans` and `fetch_traces` for stronger tests (#288) 
Following https://github.com/openai/openai-agents-python/pull/261
 2025-03-21 13:25:43 -04:00
Alex Hall e16c38a6e3 More fetch_normalized_spans 2025-03-21 18:31:06 +02:00
Alex Hall b7df4e470e empty assertions 2025-03-21 18:26:04 +02:00
Rohan Mehta 17868e38a8 Create py.typed (#285) 
- Ensure library is properly typehinted
 2025-03-21 12:19:48 -04:00
Alex Hall 99d6bc5199 More fetch_normalized_spans 2025-03-21 18:15:52 +02:00
Alex Hall 0d0f35787f More fetch_normalized_spans 2025-03-21 18:14:59 +02:00
Alex Hall b1cfcfd18b More fetch_normalized_spans 2025-03-21 18:13:04 +02:00
Alex Hall 5cea0dffc6 More fetch_normalized_spans 2025-03-21 18:09:19 +02:00
Richie Caputo 353d5eab77 Create py.typed 
- Ensure library is properly typehinted
 2025-03-21 11:16:24 -04:00
Rohan Mehta ecd06140ff Remove redundant weaker tracing assertions (#261) 
Following up on https://github.com/openai/openai-agents-python/pull/25,
this removes uses of `fetch_traces` and `fetch_ordered_spans` where
there's already a stronger assertion using `fetch_normalized_spans`.
This is to help move towards the stronger style as much as possible,
since people are still adding weaker assertions such as
[this](7a0ca7930e/tests/test_concurrency.py (L59-L61))
in https://github.com/openai/openai-agents-python/pull/91. The next step
will be to find remaining uses of `fetch_ordered_spans` that can be
replaced.
 2025-03-21 10:31:41 -04:00
Rohan Mehta caa3c6c856 docs: add Langfuse to tracing documentation (#284) 2025-03-21 10:31:05 -04:00
Rohan Mehta b52fea05fe fixed from agents.voice import SingleAgentVoiceWorkflow, VoicePipelin… (#275) 
…e in  quickstart.md

from agents.voice import SingleAgentVoiceWorkflow, VoicePipeline,

remove extra "," from the first line
 2025-03-21 10:29:13 -04:00
Jannik Maierhöfer d0e25ad1e3 docs: add Langfuse to tracing documentation 2025-03-21 13:39:17 +01:00
Alex Hall e9611e22ca Merge branch 'main' of github.com:openai/openai-agents-python into alex/cleanup-tests 2025-03-21 10:13:33 +02:00
Sir Qasim 56f53caa36 fixed from agents.voice import SingleAgentVoiceWorkflow, VoicePipeline in quickstart.md 
from agents.voice import SingleAgentVoiceWorkflow, VoicePipeline,

remove extra "," from the first line
 2025-03-21 06:58:47 +05:00
Rohan Mehta d65f05e1b6 Make the optional dependency installation compatible with zsh (#274) 2025-03-20 21:33:23 -04:00
Kazuhiro Sera 4bc92307d8 Make the optional dependency installation compatible with zsh 2025-03-21 10:01:24 +09:00
Rohan Mehta bba8ba5406 Updating tracing doc for new spans (#272) 2025-03-20 20:05:42 -04:00
Dmitry Pimenov 9dabf96fe8 fixing object path 2025-03-20 17:03:52 -07:00
Rohan Mehta a5f0646b9c [doc] fix invalid imports (#273) 2025-03-20 20:03:00 -04:00
Yoshinori Sano d212b0d0e7 [doc] fix invalid imports 2025-03-21 08:37:45 +09:00
Dmitry Pimenov 8ad5c6f245 fixing whitespace 2025-03-20 16:05:54 -07:00
Dmitry Pimenov 3e8103ad72 removing erroneous changes 2025-03-20 15:53:41 -07:00
Dmitry Pimenov 54cda1cc37 include reference to new audio span related concepts 2025-03-20 15:51:02 -07:00
Rohan Mehta 281144ecf1 v0.0.6 (voice support) (#267) 
Release a new version with voice support
 2025-03-20 13:13:00 -04:00
Rohan Mehta 1ed6e67080 v0.0.6 (voice support) 2025-03-20 13:10:54 -04:00
Rohan Mehta 6b34df037e update tests (#266) 2025-03-20 13:10:47 -04:00
Rohan Mehta ec66b71419 update tests 2025-03-20 13:08:38 -04:00
Rohan Mehta 57b0b5f628 feat: add voice pipeline support (#265) 
> Co-authored-by: rm@openai.com
 2025-03-20 12:54:42 -04:00
Dominik Kundel f476521c53 fix tests 2025-03-20 09:52:15 -07:00
Dominik Kundel 20f0793862 feat: add voice pipeline support 
> Co-authored-by: rm@openai.com
 2025-03-20 09:43:13 -07:00
Rohan Mehta b62379306f Indentation for mkdocs.yml (#264) 2025-03-20 11:21:27 -04:00
Rohan Mehta 9d27b33cde Indentation for mkdocs.yml 2025-03-20 11:18:08 -04:00
Rohan Mehta 8f56664dff 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
Alex Hall da4122975c lint 2025-03-20 13:56:11 +02:00
Alex Hall 8ff2f3a72c Remove redundant weaker tracing assertions 2025-03-20 13:49:38 +02:00
Shyamal H Anadkat ec5211c38f Adds example for financial agent 2025-03-19 22:33:13 -07:00
Rohan Mehta d300729e4f formatting updates to examples doc (#249) 2025-03-19 17:26:24 -04:00
James Hills 3de6c69f25 formatting updates to examples doc 2025-03-19 14:23:28 -07:00
Rohan Mehta b0604f6d8c 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 266359977d add examples section to docs 2025-03-19 11:43:09 -07:00
Rohan Mehta b2a7d1f376 v0.0.5 (#241) 2025-03-19 12:35:15 -04:00
Rohan Mehta a4cfa67160 v0.0.5 2025-03-19 12:32:36 -04:00
Rohan Mehta 66e6cd16e2 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 4d6edb9eb9 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 e7caa14c30 Fix breaking changes from openai 1.66.2 2025-03-19 12:30:45 -04:00
Rohan Mehta de5710f229 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