Fix types

2025-12-29 18:58:30 +00:00 · 2024-02-08 18:34:04 -03:00
49 changed files with 5072 additions and 11067 deletions
--- a/README.md
+++ b/README.md
@@ -262,8 +262,6 @@ Data collected includes:
 - Roles of agents in a crew
 - Tools names available

-Users can opt-in sharing the complete telemetry data by setting the `share_crew` attribute to `True` on their Crews.
-
 ## License

 CrewAI is released under the MIT License.
--- a/docs/core-concepts/Agents.md
+++ b/docs/core-concepts/Agents.md
@@ -25,7 +25,7 @@ description: What are crewAI Agents and how to use them.
 | **Max RPM**    | The maximum number of requests per minute the agent can perform to avoid rate limits |
 | **Verbose**    | This allow you to actually see what is going on during the Crew execution. |
 | **Allow Delegation**    | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. |
-| **Step Callback**    | A function that is called after each step of the agent. This can be used to log the agent's actions or to perform other operations. It will overwrite the crew `step_callback` |
+

 ## Creating an Agent

@@ -50,8 +50,7 @@ agent = Agent(
  max_iter=10,
  max_rpm=10,
  verbose=True,
-  allow_delegation=True,
-  step_callback=my_intermediate_step_callback
+  allow_delegation=True
 )
 ```

--- a/docs/core-concepts/Crews.md
+++ b/docs/core-concepts/Crews.md
@@ -19,10 +19,6 @@ description: Understanding and utilizing crews in the crewAI framework.
 | **Config**           | Configuration settings for the crew.                         |
 | **Max RPM**          | Maximum requests per minute the crew adheres to during execution. |
 | **Language**         | Language setting for the crew's operation.                   |
-| **Full Output**    | Whether the crew should return the full output with all tasks outputs or just the final output. |
-| **Step Callback**    | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations, it won't override the agent specific `step_callback` |
-| **Share Crew**       | Whether you want to share the complete crew infromation and execution with the crewAI team to make the library better, and allow us to train models. |
-

 !!! note "Crew Max RPM"
 		The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents `max_rpm` settings if you set it.
@@ -59,7 +55,6 @@ my_crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, write_article_task],
    process=Process.sequential,
-    full_output=True,
    verbose=True
 )
 ```
--- a/docs/telemetry/Telemetry.md
+++ b/docs/telemetry/Telemetry.md
@@ -14,6 +14,4 @@ Data collected includes:
 - If Tasks are being executed in parallel or sequentially
 - Language model being used
 - Roles of agents in a crew
- Tools names available
-
-Users can opt-in sharing the complete telemetry data by setting the `share_crew` attribute to `True` on their Crews.
+- Tools names available
--- a/poetry.lock
+++ b/poetry.lock
@@ -801,18 +801,84 @@ test = ["objgraph", "psutil"]

 [[package]]
 name = "griffe"
-version = "0.40.1"
+version = "0.40.0"
 description = "Signatures for entire Python programs. Extract the structure, the frame, the skeleton of your project, to generate API documentation or find breaking changes in your API."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "griffe-0.40.1-py3-none-any.whl", hash = "sha256:5b8c023f366fe273e762131fe4bfd141ea56c09b3cb825aa92d06a82681cfd93"},
-    {file = "griffe-0.40.1.tar.gz", hash = "sha256:66c48a62e2ce5784b6940e603300fcfb807b6f099b94e7f753f1841661fd5c7c"},
+    {file = "griffe-0.40.0-py3-none-any.whl", hash = "sha256:db1da6d1d8e08cbb20f1a7dee8c09da940540c2d4c1bfa26a9091cf6fc36a9ec"},
+    {file = "griffe-0.40.0.tar.gz", hash = "sha256:76c4439eaa2737af46ae003c331ab6ca79c5365b552f7b5aed263a3b4125735b"},
 ]

 [package.dependencies]
 colorama = ">=0.4"

+[[package]]
+name = "grpcio"
+version = "1.60.1"
+description = "HTTP/2-based RPC framework"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "grpcio-1.60.1-cp310-cp310-linux_armv7l.whl", hash = "sha256:14e8f2c84c0832773fb3958240c69def72357bc11392571f87b2d7b91e0bb092"},
+    {file = "grpcio-1.60.1-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:33aed0a431f5befeffd9d346b0fa44b2c01aa4aeae5ea5b2c03d3e25e0071216"},
+    {file = "grpcio-1.60.1-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:fead980fbc68512dfd4e0c7b1f5754c2a8e5015a04dea454b9cada54a8423525"},
+    {file = "grpcio-1.60.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:082081e6a36b6eb5cf0fd9a897fe777dbb3802176ffd08e3ec6567edd85bc104"},
+    {file = "grpcio-1.60.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:55ccb7db5a665079d68b5c7c86359ebd5ebf31a19bc1a91c982fd622f1e31ff2"},
+    {file = "grpcio-1.60.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:9b54577032d4f235452f77a83169b6527bf4b77d73aeada97d45b2aaf1bf5ce0"},
+    {file = "grpcio-1.60.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:7d142bcd604166417929b071cd396aa13c565749a4c840d6c702727a59d835eb"},
+    {file = "grpcio-1.60.1-cp310-cp310-win32.whl", hash = "sha256:2a6087f234cb570008a6041c8ffd1b7d657b397fdd6d26e83d72283dae3527b1"},
+    {file = "grpcio-1.60.1-cp310-cp310-win_amd64.whl", hash = "sha256:f2212796593ad1d0235068c79836861f2201fc7137a99aa2fea7beeb3b101177"},
+    {file = "grpcio-1.60.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:79ae0dc785504cb1e1788758c588c711f4e4a0195d70dff53db203c95a0bd303"},
+    {file = "grpcio-1.60.1-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:4eec8b8c1c2c9b7125508ff7c89d5701bf933c99d3910e446ed531cd16ad5d87"},
+    {file = "grpcio-1.60.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:8c9554ca8e26241dabe7951aa1fa03a1ba0856688ecd7e7bdbdd286ebc272e4c"},
+    {file = "grpcio-1.60.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:91422ba785a8e7a18725b1dc40fbd88f08a5bb4c7f1b3e8739cab24b04fa8a03"},
+    {file = "grpcio-1.60.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cba6209c96828711cb7c8fcb45ecef8c8859238baf15119daa1bef0f6c84bfe7"},
+    {file = "grpcio-1.60.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:c71be3f86d67d8d1311c6076a4ba3b75ba5703c0b856b4e691c9097f9b1e8bd2"},
+    {file = "grpcio-1.60.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:af5ef6cfaf0d023c00002ba25d0751e5995fa0e4c9eec6cd263c30352662cbce"},
+    {file = "grpcio-1.60.1-cp311-cp311-win32.whl", hash = "sha256:a09506eb48fa5493c58f946c46754ef22f3ec0df64f2b5149373ff31fb67f3dd"},
+    {file = "grpcio-1.60.1-cp311-cp311-win_amd64.whl", hash = "sha256:49c9b6a510e3ed8df5f6f4f3c34d7fbf2d2cae048ee90a45cd7415abab72912c"},
+    {file = "grpcio-1.60.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:b58b855d0071575ea9c7bc0d84a06d2edfbfccec52e9657864386381a7ce1ae9"},
+    {file = "grpcio-1.60.1-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:a731ac5cffc34dac62053e0da90f0c0b8560396a19f69d9703e88240c8f05858"},
+    {file = "grpcio-1.60.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:cf77f8cf2a651fbd869fbdcb4a1931464189cd210abc4cfad357f1cacc8642a6"},
+    {file = "grpcio-1.60.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c557e94e91a983e5b1e9c60076a8fd79fea1e7e06848eb2e48d0ccfb30f6e073"},
+    {file = "grpcio-1.60.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:069fe2aeee02dfd2135d562d0663fe70fbb69d5eed6eb3389042a7e963b54de8"},
+    {file = "grpcio-1.60.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:cb0af13433dbbd1c806e671d81ec75bd324af6ef75171fd7815ca3074fe32bfe"},
+    {file = "grpcio-1.60.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:2f44c32aef186bbba254129cea1df08a20be414144ac3bdf0e84b24e3f3b2e05"},
+    {file = "grpcio-1.60.1-cp312-cp312-win32.whl", hash = "sha256:a212e5dea1a4182e40cd3e4067ee46be9d10418092ce3627475e995cca95de21"},
+    {file = "grpcio-1.60.1-cp312-cp312-win_amd64.whl", hash = "sha256:6e490fa5f7f5326222cb9f0b78f207a2b218a14edf39602e083d5f617354306f"},
+    {file = "grpcio-1.60.1-cp37-cp37m-linux_armv7l.whl", hash = "sha256:4216e67ad9a4769117433814956031cb300f85edc855252a645a9a724b3b6594"},
+    {file = "grpcio-1.60.1-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:73e14acd3d4247169955fae8fb103a2b900cfad21d0c35f0dcd0fdd54cd60367"},
+    {file = "grpcio-1.60.1-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:6ecf21d20d02d1733e9c820fb5c114c749d888704a7ec824b545c12e78734d1c"},
+    {file = "grpcio-1.60.1-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:33bdea30dcfd4f87b045d404388469eb48a48c33a6195a043d116ed1b9a0196c"},
+    {file = "grpcio-1.60.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53b69e79d00f78c81eecfb38f4516080dc7f36a198b6b37b928f1c13b3c063e9"},
+    {file = "grpcio-1.60.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:39aa848794b887120b1d35b1b994e445cc028ff602ef267f87c38122c1add50d"},
+    {file = "grpcio-1.60.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:72153a0d2e425f45b884540a61c6639436ddafa1829a42056aa5764b84108b8e"},
+    {file = "grpcio-1.60.1-cp37-cp37m-win_amd64.whl", hash = "sha256:50d56280b482875d1f9128ce596e59031a226a8b84bec88cb2bf76c289f5d0de"},
+    {file = "grpcio-1.60.1-cp38-cp38-linux_armv7l.whl", hash = "sha256:6d140bdeb26cad8b93c1455fa00573c05592793c32053d6e0016ce05ba267549"},
+    {file = "grpcio-1.60.1-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:bc808924470643b82b14fe121923c30ec211d8c693e747eba8a7414bc4351a23"},
+    {file = "grpcio-1.60.1-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:70c83bb530572917be20c21f3b6be92cd86b9aecb44b0c18b1d3b2cc3ae47df0"},
+    {file = "grpcio-1.60.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9b106bc52e7f28170e624ba61cc7dc6829566e535a6ec68528f8e1afbed1c41f"},
+    {file = "grpcio-1.60.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:30e980cd6db1088c144b92fe376747328d5554bc7960ce583ec7b7d81cd47287"},
+    {file = "grpcio-1.60.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:0c5807e9152eff15f1d48f6b9ad3749196f79a4a050469d99eecb679be592acc"},
+    {file = "grpcio-1.60.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:f1c3dc536b3ee124e8b24feb7533e5c70b9f2ef833e3b2e5513b2897fd46763a"},
+    {file = "grpcio-1.60.1-cp38-cp38-win32.whl", hash = "sha256:d7404cebcdb11bb5bd40bf94131faf7e9a7c10a6c60358580fe83913f360f929"},
+    {file = "grpcio-1.60.1-cp38-cp38-win_amd64.whl", hash = "sha256:c8754c75f55781515a3005063d9a05878b2cfb3cb7e41d5401ad0cf19de14872"},
+    {file = "grpcio-1.60.1-cp39-cp39-linux_armv7l.whl", hash = "sha256:0250a7a70b14000fa311de04b169cc7480be6c1a769b190769d347939d3232a8"},
+    {file = "grpcio-1.60.1-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:660fc6b9c2a9ea3bb2a7e64ba878c98339abaf1811edca904ac85e9e662f1d73"},
+    {file = "grpcio-1.60.1-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:76eaaba891083fcbe167aa0f03363311a9f12da975b025d30e94b93ac7a765fc"},
+    {file = "grpcio-1.60.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e5d97c65ea7e097056f3d1ead77040ebc236feaf7f71489383d20f3b4c28412a"},
+    {file = "grpcio-1.60.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2bb2a2911b028f01c8c64d126f6b632fcd8a9ac975aa1b3855766c94e4107180"},
+    {file = "grpcio-1.60.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:5a1ebbae7e2214f51b1f23b57bf98eeed2cf1ba84e4d523c48c36d5b2f8829ff"},
+    {file = "grpcio-1.60.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9a66f4d2a005bc78e61d805ed95dedfcb35efa84b7bba0403c6d60d13a3de2d6"},
+    {file = "grpcio-1.60.1-cp39-cp39-win32.whl", hash = "sha256:8d488fbdbf04283f0d20742b64968d44825617aa6717b07c006168ed16488804"},
+    {file = "grpcio-1.60.1-cp39-cp39-win_amd64.whl", hash = "sha256:61b7199cd2a55e62e45bfb629a35b71fc2c0cb88f686a047f25b1112d3810904"},
+    {file = "grpcio-1.60.1.tar.gz", hash = "sha256:dd1d3a8d1d2e50ad9b59e10aa7f07c7d1be2b367f3f2d33c5fade96ed5460962"},
+]
+
+[package.extras]
+protobuf = ["grpcio-tools (>=1.60.1)"]
+
 [[package]]
 name = "h11"
 version = "0.14.0"
@@ -1022,19 +1088,19 @@ text-helpers = ["chardet (>=5.1.0,<6.0.0)"]

 [[package]]
 name = "langchain-community"
-version = "0.0.19"
+version = "0.0.17"
 description = "Community contributed LangChain integrations."
 optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langchain_community-0.0.19-py3-none-any.whl", hash = "sha256:ebff8daa0110d53555f4963f1f739b85f9ca63ef82598ece5f5c3f73fe0aa82e"},
-    {file = "langchain_community-0.0.19.tar.gz", hash = "sha256:5d18ad9e188b10aaba6361fb2a747cf29b64b21ffb8061933fec090187ca39c2"},
+    {file = "langchain_community-0.0.17-py3-none-any.whl", hash = "sha256:d503491bbfb691d1b3d10d74f7a69840cee3caf9b58a9a76f053ff925ea76733"},
+    {file = "langchain_community-0.0.17.tar.gz", hash = "sha256:ab957b34a562e0199b2ecf050bdc987c4fe889b2ac9f22b75a9fac8b9e30f53a"},
 ]

 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
 dataclasses-json = ">=0.5.7,<0.7"
-langchain-core = ">=0.1.21,<0.2"
+langchain-core = ">=0.1.16,<0.2"
 langsmith = ">=0.0.83,<0.1"
 numpy = ">=1,<2"
 PyYAML = ">=5.3"
@@ -1044,23 +1110,23 @@ tenacity = ">=8.1.0,<9.0.0"

 [package.extras]
 cli = ["typer (>=0.9.0,<0.10.0)"]
-extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "azure-ai-documentintelligence (>=1.0.0b1,<2.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "cohere (>=4,<5)", "databricks-vectorsearch (>=0.21,<0.22)", "datasets (>=2.15.0,<3.0.0)", "dgml-utils (>=0.3.0,<0.4.0)", "elasticsearch (>=8.12.0,<9.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.9.0,<0.10.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "gradientai (>=1.4.0,<2.0.0)", "hdbcli (>=2.19.21,<3.0.0)", "hologres-vector (>=0.0.6,<0.0.7)", "html2text (>=2020.1.16,<2021.0.0)", "httpx (>=0.24.1,<0.25.0)", "javelin-sdk (>=0.1.8,<0.2.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "jsonschema (>1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "msal (>=1.25.0,<2.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "nvidia-riva-client (>=2.14.0,<3.0.0)", "oci (>=2.119.1,<3.0.0)", "openai (<2)", "openapi-pydantic (>=0.3.2,<0.4.0)", "oracle-ads (>=2.9.1,<3.0.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "praw (>=7.7.1,<8.0.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "rdflib (==7.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)", "zhipuai (>=1.0.7,<2.0.0)"]
+extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "azure-ai-documentintelligence (>=1.0.0b1,<2.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "cohere (>=4,<5)", "dashvector (>=1.0.1,<2.0.0)", "databricks-vectorsearch (>=0.21,<0.22)", "datasets (>=2.15.0,<3.0.0)", "dgml-utils (>=0.3.0,<0.4.0)", "elasticsearch (>=8.12.0,<9.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.9.0,<0.10.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "gradientai (>=1.4.0,<2.0.0)", "hdbcli (>=2.19.21,<3.0.0)", "hologres-vector (>=0.0.6,<0.0.7)", "html2text (>=2020.1.16,<2021.0.0)", "httpx (>=0.24.1,<0.25.0)", "javelin-sdk (>=0.1.8,<0.2.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "jsonschema (>1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "msal (>=1.25.0,<2.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "oci (>=2.119.1,<3.0.0)", "openai (<2)", "openapi-pydantic (>=0.3.2,<0.4.0)", "oracle-ads (>=2.9.1,<3.0.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "praw (>=7.7.1,<8.0.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "rdflib (==7.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)", "zhipuai (>=1.0.7,<2.0.0)"]

 [[package]]
 name = "langchain-core"
-version = "0.1.22"
+version = "0.1.18"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langchain_core-0.1.22-py3-none-any.whl", hash = "sha256:d1263c2707ce18bb13654c88f891e53f39edec9b11ff7d0d0f23fd920927b2d6"},
-    {file = "langchain_core-0.1.22.tar.gz", hash = "sha256:deac12b3e42a08bbbaa2acf83d5f8dd2d5513256d8daf0e853e9d68ff4c99d79"},
+    {file = "langchain_core-0.1.18-py3-none-any.whl", hash = "sha256:5a60dc3c391b33834fb9c8b072abd7a0df4cbba8ce88eb1bcb288844000ab759"},
+    {file = "langchain_core-0.1.18.tar.gz", hash = "sha256:ad470b21cdfdc75e829cd91c8d8eb7e0438ab8ddb5b50828125ff7ada121ee7b"},
 ]

 [package.dependencies]
 anyio = ">=3,<5"
 jsonpatch = ">=1.33,<2.0"
-langsmith = ">=0.0.87,<0.0.88"
+langsmith = ">=0.0.83,<0.1"
 packaging = ">=23.2,<24.0"
 pydantic = ">=1,<3"
 PyYAML = ">=5.3"
@@ -1089,13 +1155,13 @@ tiktoken = ">=0.5.2,<0.6.0"

 [[package]]
 name = "langsmith"
-version = "0.0.87"
+version = "0.0.86"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langsmith-0.0.87-py3-none-any.whl", hash = "sha256:8903d3811b9fc89eb18f5961c8e6935fbd2d0f119884fbf30dc70b8f8f4121fc"},
-    {file = "langsmith-0.0.87.tar.gz", hash = "sha256:36c4cc47e5b54be57d038036a30fb19ce6e4c73048cd7a464b8f25b459694d34"},
+    {file = "langsmith-0.0.86-py3-none-any.whl", hash = "sha256:7af15c36edb8c9fd9ae5c6d4fb940eb1da668b630a703d63c90c91e9be53aefb"},
+    {file = "langsmith-0.0.86.tar.gz", hash = "sha256:c1572824664810c4425b17f2d1e9a59d53992e6898df22a37236c62d3c80f59e"},
 ]

 [package.dependencies]
@@ -1264,13 +1330,13 @@ mkdocs = ">=1.1"

 [[package]]
 name = "mkdocs-material"
-version = "9.5.9"
+version = "9.5.7"
 description = "Documentation that simply works"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "mkdocs_material-9.5.9-py3-none-any.whl", hash = "sha256:a5d62b73b3b74349e45472bfadc129c871dd2d4add68d84819580597b2f50d5d"},
-    {file = "mkdocs_material-9.5.9.tar.gz", hash = "sha256:635df543c01c25c412d6c22991872267723737d5a2f062490f33b2da1c013c6d"},
+    {file = "mkdocs_material-9.5.7-py3-none-any.whl", hash = "sha256:0be8ce8bcfebb52bae9b00cf9b851df45b8a92d629afcfd7f2c09b2dfa155ea3"},
+    {file = "mkdocs_material-9.5.7.tar.gz", hash = "sha256:16110292575d88a338d2961f3cb665cf12943ff8829e551a9b364f24019e46af"},
 ]

 [package.dependencies]
@@ -1289,7 +1355,7 @@ regex = ">=2022.4"
 requests = ">=2.26,<3.0"

 [package.extras]
-git = ["mkdocs-git-committers-plugin-2 (>=1.1,<2.0)", "mkdocs-git-revision-date-localized-plugin (>=1.2.4,<2.0)"]
+git = ["mkdocs-git-committers-plugin-2 (>=1.1,<2.0)", "mkdocs-git-revision-date-localized-plugin (>=1.2,<2.0)"]
 imaging = ["cairosvg (>=2.6,<3.0)", "pillow (>=10.2,<11.0)"]
 recommended = ["mkdocs-minify-plugin (>=0.7,<1.0)", "mkdocs-redirects (>=1.2,<2.0)", "mkdocs-rss-plugin (>=1.6,<2.0)"]

@@ -1514,13 +1580,13 @@ files = [

 [[package]]
 name = "openai"
-version = "1.12.0"
+version = "1.11.1"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.12.0-py3-none-any.whl", hash = "sha256:a54002c814e05222e413664f651b5916714e4700d041d5cf5724d3ae1a3e3481"},
-    {file = "openai-1.12.0.tar.gz", hash = "sha256:99c5d257d09ea6533d689d1cc77caa0ac679fa21efef8893d8b0832a86877f1b"},
+    {file = "openai-1.11.1-py3-none-any.whl", hash = "sha256:e0f388ce499f53f58079d0c1f571f356f2b168b84d0d24a412506b6abc714980"},
+    {file = "openai-1.11.1.tar.gz", hash = "sha256:f66b8fe431af43e09594147ef3cdcb79758285de72ebafd52be9700a2af41e99"},
 ]

 [package.dependencies]
@@ -1565,6 +1631,30 @@ files = [
 backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
 opentelemetry-proto = "1.22.0"

+[[package]]
+name = "opentelemetry-exporter-otlp-proto-grpc"
+version = "1.22.0"
+description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.22.0-py3-none-any.whl", hash = "sha256:b5bcadc129272004316a455e9081216d3380c1fc2231a928ea6a70aa90e173fb"},
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.22.0.tar.gz", hash = "sha256:1e0e5aa4bbabc74942f06f268deffd94851d12a8dc30b02527472ef1729fe5b1"},
+]
+
+[package.dependencies]
+backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
+deprecated = ">=1.2.6"
+googleapis-common-protos = ">=1.52,<2.0"
+grpcio = ">=1.0.0,<2.0.0"
+opentelemetry-api = ">=1.15,<2.0"
+opentelemetry-exporter-otlp-proto-common = "1.22.0"
+opentelemetry-proto = "1.22.0"
+opentelemetry-sdk = ">=1.22.0,<1.23.0"
+
+[package.extras]
+test = ["pytest-grpc"]
+
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-http"
 version = "1.22.0"
@@ -2582,40 +2672,38 @@ test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess

 [[package]]
 name = "watchdog"
-version = "4.0.0"
+version = "3.0.0"
 description = "Filesystem events monitoring"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.7"
 files = [
-    {file = "watchdog-4.0.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:39cb34b1f1afbf23e9562501673e7146777efe95da24fab5707b88f7fb11649b"},
-    {file = "watchdog-4.0.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c522392acc5e962bcac3b22b9592493ffd06d1fc5d755954e6be9f4990de932b"},
-    {file = "watchdog-4.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6c47bdd680009b11c9ac382163e05ca43baf4127954c5f6d0250e7d772d2b80c"},
-    {file = "watchdog-4.0.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:8350d4055505412a426b6ad8c521bc7d367d1637a762c70fdd93a3a0d595990b"},
-    {file = "watchdog-4.0.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c17d98799f32e3f55f181f19dd2021d762eb38fdd381b4a748b9f5a36738e935"},
-    {file = "watchdog-4.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4986db5e8880b0e6b7cd52ba36255d4793bf5cdc95bd6264806c233173b1ec0b"},
-    {file = "watchdog-4.0.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:11e12fafb13372e18ca1bbf12d50f593e7280646687463dd47730fd4f4d5d257"},
-    {file = "watchdog-4.0.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:5369136a6474678e02426bd984466343924d1df8e2fd94a9b443cb7e3aa20d19"},
-    {file = "watchdog-4.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:76ad8484379695f3fe46228962017a7e1337e9acadafed67eb20aabb175df98b"},
-    {file = "watchdog-4.0.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:45cc09cc4c3b43fb10b59ef4d07318d9a3ecdbff03abd2e36e77b6dd9f9a5c85"},
-    {file = "watchdog-4.0.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:eed82cdf79cd7f0232e2fdc1ad05b06a5e102a43e331f7d041e5f0e0a34a51c4"},
-    {file = "watchdog-4.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:ba30a896166f0fee83183cec913298151b73164160d965af2e93a20bbd2ab605"},
-    {file = "watchdog-4.0.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:d18d7f18a47de6863cd480734613502904611730f8def45fc52a5d97503e5101"},
-    {file = "watchdog-4.0.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2895bf0518361a9728773083908801a376743bcc37dfa252b801af8fd281b1ca"},
-    {file = "watchdog-4.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:87e9df830022488e235dd601478c15ad73a0389628588ba0b028cb74eb72fed8"},
-    {file = "watchdog-4.0.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:6e949a8a94186bced05b6508faa61b7adacc911115664ccb1923b9ad1f1ccf7b"},
-    {file = "watchdog-4.0.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:6a4db54edea37d1058b08947c789a2354ee02972ed5d1e0dca9b0b820f4c7f92"},
-    {file = "watchdog-4.0.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:d31481ccf4694a8416b681544c23bd271f5a123162ab603c7d7d2dd7dd901a07"},
-    {file = "watchdog-4.0.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:8fec441f5adcf81dd240a5fe78e3d83767999771630b5ddfc5867827a34fa3d3"},
-    {file = "watchdog-4.0.0-py3-none-manylinux2014_armv7l.whl", hash = "sha256:6a9c71a0b02985b4b0b6d14b875a6c86ddea2fdbebd0c9a720a806a8bbffc69f"},
-    {file = "watchdog-4.0.0-py3-none-manylinux2014_i686.whl", hash = "sha256:557ba04c816d23ce98a06e70af6abaa0485f6d94994ec78a42b05d1c03dcbd50"},
-    {file = "watchdog-4.0.0-py3-none-manylinux2014_ppc64.whl", hash = "sha256:d0f9bd1fd919134d459d8abf954f63886745f4660ef66480b9d753a7c9d40927"},
-    {file = "watchdog-4.0.0-py3-none-manylinux2014_ppc64le.whl", hash = "sha256:f9b2fdca47dc855516b2d66eef3c39f2672cbf7e7a42e7e67ad2cbfcd6ba107d"},
-    {file = "watchdog-4.0.0-py3-none-manylinux2014_s390x.whl", hash = "sha256:73c7a935e62033bd5e8f0da33a4dcb763da2361921a69a5a95aaf6c93aa03a87"},
-    {file = "watchdog-4.0.0-py3-none-manylinux2014_x86_64.whl", hash = "sha256:6a80d5cae8c265842c7419c560b9961561556c4361b297b4c431903f8c33b269"},
-    {file = "watchdog-4.0.0-py3-none-win32.whl", hash = "sha256:8f9a542c979df62098ae9c58b19e03ad3df1c9d8c6895d96c0d51da17b243b1c"},
-    {file = "watchdog-4.0.0-py3-none-win_amd64.whl", hash = "sha256:f970663fa4f7e80401a7b0cbeec00fa801bf0287d93d48368fc3e6fa32716245"},
-    {file = "watchdog-4.0.0-py3-none-win_ia64.whl", hash = "sha256:9a03e16e55465177d416699331b0f3564138f1807ecc5f2de9d55d8f188d08c7"},
-    {file = "watchdog-4.0.0.tar.gz", hash = "sha256:e3e7065cbdabe6183ab82199d7a4f6b3ba0a438c5a512a68559846ccb76a78ec"},
+    {file = "watchdog-3.0.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:336adfc6f5cc4e037d52db31194f7581ff744b67382eb6021c868322e32eef41"},
+    {file = "watchdog-3.0.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a70a8dcde91be523c35b2bf96196edc5730edb347e374c7de7cd20c43ed95397"},
+    {file = "watchdog-3.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:adfdeab2da79ea2f76f87eb42a3ab1966a5313e5a69a0213a3cc06ef692b0e96"},
+    {file = "watchdog-3.0.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:2b57a1e730af3156d13b7fdddfc23dea6487fceca29fc75c5a868beed29177ae"},
+    {file = "watchdog-3.0.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7ade88d0d778b1b222adebcc0927428f883db07017618a5e684fd03b83342bd9"},
+    {file = "watchdog-3.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7e447d172af52ad204d19982739aa2346245cc5ba6f579d16dac4bfec226d2e7"},
+    {file = "watchdog-3.0.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:9fac43a7466eb73e64a9940ac9ed6369baa39b3bf221ae23493a9ec4d0022674"},
+    {file = "watchdog-3.0.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:8ae9cda41fa114e28faf86cb137d751a17ffd0316d1c34ccf2235e8a84365c7f"},
+    {file = "watchdog-3.0.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:25f70b4aa53bd743729c7475d7ec41093a580528b100e9a8c5b5efe8899592fc"},
+    {file = "watchdog-3.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4f94069eb16657d2c6faada4624c39464f65c05606af50bb7902e036e3219be3"},
+    {file = "watchdog-3.0.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7c5f84b5194c24dd573fa6472685b2a27cc5a17fe5f7b6fd40345378ca6812e3"},
+    {file = "watchdog-3.0.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3aa7f6a12e831ddfe78cdd4f8996af9cf334fd6346531b16cec61c3b3c0d8da0"},
+    {file = "watchdog-3.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:233b5817932685d39a7896b1090353fc8efc1ef99c9c054e46c8002561252fb8"},
+    {file = "watchdog-3.0.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:13bbbb462ee42ec3c5723e1205be8ced776f05b100e4737518c67c8325cf6100"},
+    {file = "watchdog-3.0.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:8f3ceecd20d71067c7fd4c9e832d4e22584318983cabc013dbf3f70ea95de346"},
+    {file = "watchdog-3.0.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:c9d8c8ec7efb887333cf71e328e39cffbf771d8f8f95d308ea4125bf5f90ba64"},
+    {file = "watchdog-3.0.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0e06ab8858a76e1219e68c7573dfeba9dd1c0219476c5a44d5333b01d7e1743a"},
+    {file = "watchdog-3.0.0-py3-none-manylinux2014_armv7l.whl", hash = "sha256:d00e6be486affb5781468457b21a6cbe848c33ef43f9ea4a73b4882e5f188a44"},
+    {file = "watchdog-3.0.0-py3-none-manylinux2014_i686.whl", hash = "sha256:c07253088265c363d1ddf4b3cdb808d59a0468ecd017770ed716991620b8f77a"},
+    {file = "watchdog-3.0.0-py3-none-manylinux2014_ppc64.whl", hash = "sha256:5113334cf8cf0ac8cd45e1f8309a603291b614191c9add34d33075727a967709"},
+    {file = "watchdog-3.0.0-py3-none-manylinux2014_ppc64le.whl", hash = "sha256:51f90f73b4697bac9c9a78394c3acbbd331ccd3655c11be1a15ae6fe289a8c83"},
+    {file = "watchdog-3.0.0-py3-none-manylinux2014_s390x.whl", hash = "sha256:ba07e92756c97e3aca0912b5cbc4e5ad802f4557212788e72a72a47ff376950d"},
+    {file = "watchdog-3.0.0-py3-none-manylinux2014_x86_64.whl", hash = "sha256:d429c2430c93b7903914e4db9a966c7f2b068dd2ebdd2fa9b9ce094c7d459f33"},
+    {file = "watchdog-3.0.0-py3-none-win32.whl", hash = "sha256:3ed7c71a9dccfe838c2f0b6314ed0d9b22e77d268c67e015450a29036a81f60f"},
+    {file = "watchdog-3.0.0-py3-none-win_amd64.whl", hash = "sha256:4c9956d27be0bb08fc5f30d9d0179a855436e655f046d288e2bcc11adfae893c"},
+    {file = "watchdog-3.0.0-py3-none-win_ia64.whl", hash = "sha256:5d9f3a10e02d7371cd929b5d8f11e87d4bad890212ed3901f9b4d68767bee759"},
+    {file = "watchdog-3.0.0.tar.gz", hash = "sha256:4d98a320595da7a7c5a18fc48cb633c2e73cda78f93cac2ef42d42bf609a33f9"},
 ]

 [package.extras]
@@ -2832,4 +2920,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<4.0"
-content-hash = "83ad952af62ced4101ae67ba88be4a10e580f6f73b3bde06cb2f15d789acc0f5"
+content-hash = "2be3f98f57af7ea47f0985000be807e67c1bb3a95598b637e50f2cec54d11c80"
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,7 +1,7 @@

 [tool.poetry]
 name = "crewai"
-version = "0.10.0"
+version = "0.5.5"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
--- a/src/crewai/agent.py
+++ b/src/crewai/agent.py
@@ -3,9 +3,9 @@ from typing import Any, List, Optional

 from langchain.agents.agent import RunnableAgent
 from langchain.agents.format_scratchpad import format_log_to_str
-from langchain.agents.output_parsers import ReActSingleInputOutputParser
 from langchain.memory import ConversationSummaryMemory
 from langchain.tools.render import render_text_description
+from langchain_core.runnables.config import RunnableConfig
 from langchain_openai import ChatOpenAI
 from pydantic import (
    UUID4,
@@ -19,7 +19,12 @@ from pydantic import (
 )
 from pydantic_core import PydanticCustomError

-from crewai.agents import CacheHandler, CrewAgentExecutor, ToolsHandler
+from crewai.agents import (
+    CacheHandler,
+    CrewAgentExecutor,
+    CrewAgentOutputParser,
+    ToolsHandler,
+)
 from crewai.utilities import I18N, Logger, Prompts, RPMController


@@ -41,7 +46,6 @@ class Agent(BaseModel):
            verbose: Whether the agent execution should be in verbose mode.
            allow_delegation: Whether the agent is allowed to delegate tasks to other agents.
            tools: Tools at agents disposal
-            step_callback: Callback to be executed after each step of the agent execution.
    """

    __hash__ = object.__hash__  # type: ignore
@@ -86,10 +90,6 @@ class Agent(BaseModel):
    cache_handler: InstanceOf[CacheHandler] = Field(
        default=CacheHandler(), description="An instance of the CacheHandler class."
    )
-    step_callback: Optional[Any] = Field(
-        default=None,
-        description="Callback to be executed after each step of the agent execution.",
-    )
    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
    llm: Any = Field(
        default_factory=lambda: ChatOpenAI(
@@ -125,7 +125,7 @@ class Agent(BaseModel):

    def execute_task(
        self,
-        task: Any,
+        task: str,
        context: Optional[str] = None,
        tools: Optional[List[Any]] = None,
    ) -> str:
@@ -140,25 +140,21 @@ class Agent(BaseModel):
            Output of the agent
        """

-        task_prompt = task.prompt()
-
        if context:
-            task_prompt = self.i18n.slice("task_with_context").format(
-                task=task_prompt, context=context
+            task = self.i18n.slice("task_with_context").format(
+                task=task, context=context
            )

        tools = tools or self.tools
        self.agent_executor.tools = tools
-        self.agent_executor.task = task
-        self.agent_executor.tools_description = (render_text_description(tools),)
-        self.agent_executor.tools_names = self.__tools_names(tools)

        result = self.agent_executor.invoke(
            {
-                "input": task_prompt,
-                "tool_names": self.agent_executor.tools_names,
-                "tools": self.agent_executor.tools_description,
-            }
+                "input": task,
+                "tool_names": self.__tools_names(tools),
+                "tools": render_text_description(tools),
+            },
+            RunnableConfig(callbacks=[self.tools_handler]),
        )["output"]

        if self.max_rpm:
@@ -174,7 +170,7 @@ class Agent(BaseModel):
        """
        self.cache_handler = cache_handler
        self.tools_handler = ToolsHandler(cache=self.cache_handler)
-        self.create_agent_executor()
+        self._create_agent_executor()

    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
        """Set the rpm controller for the agent.
@@ -184,9 +180,9 @@ class Agent(BaseModel):
        """
        if not self._rpm_controller:
            self._rpm_controller = rpm_controller
-            self.create_agent_executor()
+            self._create_agent_executor()

-    def create_agent_executor(self) -> None:
+    def _create_agent_executor(self) -> None:
        """Create an agent executor for the agent.

        Returns:
@@ -199,20 +195,17 @@ class Agent(BaseModel):
            "agent_scratchpad": lambda x: format_log_to_str(x["intermediate_steps"]),
        }
        executor_args = {
-            "llm": self.llm,
            "i18n": self.i18n,
            "tools": self.tools,
            "verbose": self.verbose,
            "handle_parsing_errors": True,
            "max_iterations": self.max_iter,
-            "step_callback": self.step_callback,
-            "tools_handler": self.tools_handler,
        }

        if self._rpm_controller:
-            executor_args[
-                "request_within_rpm_limit"
-            ] = self._rpm_controller.check_or_wait
+            executor_args["request_within_rpm_limit"] = (
+                self._rpm_controller.check_or_wait
+            )

        if self.memory:
            summary_memory = ConversationSummaryMemory(
@@ -232,7 +225,14 @@ class Agent(BaseModel):

        bind = self.llm.bind(stop=[self.i18n.slice("observation")])
        inner_agent = (
-            agent_args | execution_prompt | bind | ReActSingleInputOutputParser()
+            agent_args
+            | execution_prompt
+            | bind
+            | CrewAgentOutputParser(
+                tools_handler=self.tools_handler,
+                cache=self.cache_handler,
+                i18n=self.i18n,
+            )
        )
        self.agent_executor = CrewAgentExecutor(
            agent=RunnableAgent(runnable=inner_agent), **executor_args
--- a/src/crewai/agents/init.py
+++ b/src/crewai/agents/init.py
@@ -1,3 +1,4 @@
 from .cache.cache_handler import CacheHandler
 from .executor import CrewAgentExecutor
+from .output_parser import CrewAgentOutputParser
 from .tools_handler import ToolsHandler
--- a/src/crewai/agents/cache/init.py
+++ b/src/crewai/agents/cache/init.py
@@ -1 +1,2 @@
 from .cache_handler import CacheHandler
+from .cache_hit import CacheHit
--- a/src/crewai/agents/cache/cache_handler.py
+++ b/src/crewai/agents/cache/cache_handler.py
@@ -10,7 +10,9 @@ class CacheHandler:
        self._cache = {}

    def add(self, tool, input, output):
+        input = input.strip()
        self._cache[f"{tool}-{input}"] = output

    def read(self, tool, input) -> Optional[str]:
+        input = input.strip()
        return self._cache.get(f"{tool}-{input}")
--- a/src/crewai/agents/cache/cache_hit.py
+++ b/src/crewai/agents/cache/cache_hit.py
@@ -0,0 +1,14 @@
+from langchain_core.agents import AgentAction
+from pydantic.v1 import BaseModel, Field
+
+from .cache_handler import CacheHandler
+
+
+class CacheHit(BaseModel):
+    """Cache Hit Object."""
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    action: AgentAction = Field(description="Action taken")
+    cache: CacheHandler = Field(description="Cache Handler for the tool")
--- a/src/crewai/agents/exceptions.py
+++ b/src/crewai/agents/exceptions.py
@@ -0,0 +1,30 @@
+from langchain_core.exceptions import OutputParserException
+
+from crewai.utilities import I18N
+
+
+class TaskRepeatedUsageException(OutputParserException):
+    """Exception raised when a task is used twice in a roll."""
+
+    i18n: I18N = I18N()
+    error: str = "TaskRepeatedUsageException"
+    message: str
+
+    def __init__(self, i18n: I18N, tool: str, tool_input: str, text: str):
+        self.i18n = i18n
+        self.text = text
+        self.tool = tool
+        self.tool_input = tool_input
+        self.message = self.i18n.errors("task_repeated_usage").format(
+            tool=tool, tool_input=tool_input
+        )
+
+        super().__init__(
+            error=self.error,
+            observation=self.message,
+            send_to_llm=True,
+            llm_output=self.text,
+        )
+
+    def __str__(self):
+        return self.message
--- a/src/crewai/agents/executor.py
+++ b/src/crewai/agents/executor.py
@@ -10,25 +10,18 @@ from langchain_core.exceptions import OutputParserException
 from langchain_core.pydantic_v1 import root_validator
 from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
-from pydantic import InstanceOf

-from crewai.agents.tools_handler import ToolsHandler
-from crewai.tools.tool_usage import ToolUsage
+from crewai.agents.cache.cache_hit import CacheHit
+from crewai.tools.cache_tools import CacheTools
 from crewai.utilities import I18N


 class CrewAgentExecutor(AgentExecutor):
    i18n: I18N = I18N()
-    llm: Any = None
    iterations: int = 0
-    task: Any = None
-    tools_description: str = ""
-    tools_names: str = ""
    request_within_rpm_limit: Any = None
-    tools_handler: InstanceOf[ToolsHandler] = None
    max_iterations: Optional[int] = 15
    force_answer_max_iterations: Optional[int] = None
-    step_callback: Optional[Any] = None

    @root_validator()
    def set_force_answer_max_iterations(cls, values: Dict) -> Dict:
@@ -38,6 +31,11 @@ class CrewAgentExecutor(AgentExecutor):
    def _should_force_answer(self) -> bool:
        return True if self.iterations == self.force_answer_max_iterations else False

+    def _force_answer(self, output: AgentAction):
+        return AgentStep(
+            action=output, observation=self.i18n.errors("force_final_answer")
+        )
+
    def _call(
        self,
        inputs: Dict[str, str],
@@ -65,10 +63,6 @@ class CrewAgentExecutor(AgentExecutor):
                    intermediate_steps,
                    run_manager=run_manager,
                )
-
-                if self.step_callback:
-                    self.step_callback(next_step_output)
-
                if isinstance(next_step_output, AgentFinish):
                    return self._return(
                        next_step_output, intermediate_steps, run_manager=run_manager
@@ -111,17 +105,17 @@ class CrewAgentExecutor(AgentExecutor):
                callbacks=run_manager.get_child() if run_manager else None,
                **inputs,
            )
-
            if self._should_force_answer():
-                if isinstance(output, AgentAction) or isinstance(output, AgentFinish):
-                    output = output
-                else:
-                    raise ValueError(
-                        f"Unexpected output type from agent: {type(output)}"
-                    )
-                yield AgentStep(
-                    action=output, observation=self.i18n.errors("force_final_answer")
-                )
+                if isinstance(output, CacheHit):
+                    output = output.action
+                if isinstance(output, AgentAction):
+                    yield self._force_answer(output)
+                    return
+                if isinstance(output, list):
+                    yield from [self._force_answer(action) for action in output]
+                    return
+
+                yield output
                return

        except OutputParserException as e:
@@ -162,9 +156,7 @@ class CrewAgentExecutor(AgentExecutor):
            )

            if self._should_force_answer():
-                yield AgentStep(
-                    action=output, observation=self.i18n.errors("force_final_answer")
-                )
+                yield self._force_answer(output)
                return

            yield AgentStep(action=output, observation=observation)
@@ -175,6 +167,17 @@ class CrewAgentExecutor(AgentExecutor):
            yield output
            return

+        # Override tool usage to use CacheTools
+        if isinstance(output, CacheHit):
+            cache = output.cache
+            action = output.action
+            tool = CacheTools(cache_handler=cache).tool()
+            output = action.copy()
+            output.tool_input = f"tool:{action.tool}|input:{action.tool_input}"
+            output.tool = tool.name
+            name_to_tool_map[tool.name] = tool
+            color_mapping[tool.name] = color_mapping[action.tool]
+
        actions: List[AgentAction]
        actions = [output] if isinstance(output, AgentAction) else output
        yield from actions
@@ -185,18 +188,18 @@ class CrewAgentExecutor(AgentExecutor):
            if agent_action.tool in name_to_tool_map:
                tool = name_to_tool_map[agent_action.tool]
                return_direct = tool.return_direct
-                color_mapping[agent_action.tool]
+                color = color_mapping[agent_action.tool]
                tool_run_kwargs = self.agent.tool_run_logging_kwargs()
                if return_direct:
                    tool_run_kwargs["llm_prefix"] = ""
-                observation = ToolUsage(
-                    tools_handler=self.tools_handler,
-                    tools=self.tools,
-                    tools_description=self.tools_description,
-                    tools_names=self.tools_names,
-                    llm=self.llm,
-                    task=self.task,
-                ).use(agent_action.log)
+                # We then call the tool on the tool input to get an observation
+                observation = tool.run(
+                    agent_action.tool_input,
+                    verbose=self.verbose,
+                    color=color,
+                    callbacks=run_manager.get_child() if run_manager else None,
+                    **tool_run_kwargs,
+                )
            else:
                tool_run_kwargs = self.agent.tool_run_logging_kwargs()
                observation = InvalidTool().run(
--- a/src/crewai/agents/output_parser.py
+++ b/src/crewai/agents/output_parser.py
@@ -0,0 +1,79 @@
+import re
+from typing import Union
+
+from langchain.agents.output_parsers import ReActSingleInputOutputParser
+from langchain_core.agents import AgentAction, AgentFinish
+
+from crewai.agents.cache import CacheHandler, CacheHit
+from crewai.agents.exceptions import TaskRepeatedUsageException
+from crewai.agents.tools_handler import ToolsHandler
+from crewai.utilities import I18N
+
+FINAL_ANSWER_ACTION = "Final Answer:"
+FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = (
+    "Parsing LLM output produced both a final answer and a parse-able action:"
+)
+
+
+class CrewAgentOutputParser(ReActSingleInputOutputParser):
+    """Parses ReAct-style LLM calls that have a single tool input.
+
+    Expects output to be in one of two formats.
+
+    If the output signals that an action should be taken,
+    should be in the below format. This will result in an AgentAction
+    being returned.
+
+    ```
+    Thought: agent thought here
+    Action: search
+    Action Input: what is the temperature in SF?
+    ```
+
+    If the output signals that a final answer should be given,
+    should be in the below format. This will result in an AgentFinish
+    being returned.
+
+    ```
+    Thought: agent thought here
+    Final Answer: The temperature is 100 degrees
+    ```
+
+    It also prevents tools from being reused in a roll.
+    """
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    tools_handler: ToolsHandler
+    cache: CacheHandler
+    i18n: I18N
+
+    def parse(self, text: str) -> Union[AgentAction, AgentFinish, CacheHit]:
+        regex = (
+            r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"
+        )
+        if action_match := re.search(regex, text, re.DOTALL):
+            action = action_match.group(1).strip()
+            action_input = action_match.group(2)
+            tool_input = action_input.strip(" ")
+            tool_input = tool_input.strip('"')
+
+            if last_tool_usage := self.tools_handler.last_used_tool:
+                usage = {
+                    "tool": action,
+                    "input": tool_input,
+                }
+                if usage == last_tool_usage:
+                    raise TaskRepeatedUsageException(
+                        text=text,
+                        tool=action,
+                        tool_input=tool_input,
+                        i18n=self.i18n,
+                    )
+
+            if self.cache.read(action, tool_input):
+                agent_action = AgentAction(action, tool_input, text)
+                return CacheHit(action=agent_action, cache=self.cache)
+
+        return super().parse(text)
--- a/src/crewai/agents/tools_handler.py
+++ b/src/crewai/agents/tools_handler.py
@@ -1,30 +1,44 @@
-from typing import Any
+from typing import Any, Dict
+
+from langchain.callbacks.base import BaseCallbackHandler

 from ..tools.cache_tools import CacheTools
-from ..tools.tool_calling import ToolCalling
 from .cache.cache_handler import CacheHandler


-class ToolsHandler:
+class ToolsHandler(BaseCallbackHandler):
    """Callback handler for tool usage."""

-    last_used_tool: ToolCalling = {}
+    last_used_tool: Dict[str, Any] = {}
    cache: CacheHandler

-    def __init__(self, cache: CacheHandler):
+    def __init__(self, cache: CacheHandler, **kwargs: Any):
        """Initialize the callback handler."""
        self.cache = cache
-        self.last_used_tool = {}
+        super().__init__(**kwargs)

-    def on_tool_start(self, calling: ToolCalling) -> Any:
+    def on_tool_start(
+        self, serialized: Dict[str, Any], input_str: str, **kwargs: Any
+    ) -> Any:
        """Run when tool starts running."""
-        self.last_used_tool = calling
+        name = serialized.get("name")
+        if name not in ["invalid_tool", "_Exception"]:
+            tools_usage = {
+                "tool": name,
+                "input": input_str,
+            }
+            self.last_used_tool = tools_usage

-    def on_tool_end(self, calling: ToolCalling, output: str) -> Any:
+    def on_tool_end(self, output: str, **kwargs: Any) -> Any:
        """Run when tool ends running."""
-        if self.last_used_tool.function_name != CacheTools().name:
-            self.cache.add(
-                tool=calling.function_name,
-                input=calling.arguments,
-                output=output,
-            )
+        if (
+            "is not a valid tool" not in output
+            and "Invalid or incomplete response" not in output
+            and "Invalid Format" not in output
+        ):
+            if self.last_used_tool["tool"] != CacheTools().name:
+                self.cache.add(
+                    tool=self.last_used_tool["tool"],
+                    input=self.last_used_tool["input"],
+                    output=output,
+                )
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -35,16 +35,12 @@ class Crew(BaseModel):
        process: The process flow that the crew will follow (e.g., sequential).
        verbose: Indicates the verbosity level for logging during execution.
        config: Configuration settings for the crew.
+        _cache_handler: Handles caching for the crew's operations.
        max_rpm: Maximum number of requests per minute for the crew execution to be respected.
        id: A unique identifier for the crew instance.
-        full_output: Whether the crew should return the full output with all tasks outputs or just the final output.
-        step_callback: Callback to be executed after each step for every agents execution.
-        share_crew: Whether you want to share the complete crew infromation and execution with crewAI to make the library better, and allow us to train models.
-        _cache_handler: Handles caching for the crew's operations.
    """

    __hash__ = object.__hash__  # type: ignore
-    _execution_span: Any = PrivateAttr()
    _rpm_controller: RPMController = PrivateAttr()
    _logger: Logger = PrivateAttr()
    _cache_handler: InstanceOf[CacheHandler] = PrivateAttr(default=CacheHandler())
@@ -53,20 +49,11 @@ class Crew(BaseModel):
    agents: List[Agent] = Field(default_factory=list)
    process: Process = Field(default=Process.sequential)
    verbose: Union[int, bool] = Field(default=0)
-    full_output: Optional[bool] = Field(
-        default=False,
-        description="Whether the crew should return the full output with all tasks outputs or just the final output.",
-    )
    manager_llm: Optional[Any] = Field(
        description="Language model that will run the agent.", default=None
    )
    config: Optional[Union[Json, Dict[str, Any]]] = Field(default=None)
    id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
-    share_crew: Optional[bool] = Field(default=False)
-    step_callback: Optional[Any] = Field(
-        default=None,
-        description="Callback to be executed after each step for all agents execution.",
-    )
    max_rpm: Optional[int] = Field(
        default=None,
        description="Maximum number of requests per minute for the crew execution to be respected.",
@@ -107,7 +94,6 @@ class Crew(BaseModel):
        self._logger = Logger(self.verbose)
        self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
        self._telemetry = Telemetry()
-        self._telemetry.set_tracer()
        self._telemetry.crew_creation(self)
        return self

@@ -151,7 +137,6 @@ class Crew(BaseModel):
                "missing_keys_in_config", "Config should have 'agents' and 'tasks'.", {}
            )

-        self.process = self.config.get("process", self.process)
        self.agents = [Agent(**agent) for agent in self.config["agents"]]
        self.tasks = [self._create_task(task) for task in self.config["tasks"]]

@@ -172,13 +157,8 @@ class Crew(BaseModel):

    def kickoff(self) -> str:
        """Starts the crew to work on its assigned tasks."""
-        self._execution_span = self._telemetry.crew_execution_span(self)
-
        for agent in self.agents:
            agent.i18n = I18N(language=self.language)
-            if (self.step_callback) and (not agent.step_callback):
-                agent.step_callback = self.step_callback
-                agent.create_agent_executor()

        if self.process == Process.sequential:
            return self._run_sequential_process()
@@ -191,7 +171,7 @@ class Crew(BaseModel):

    def _run_sequential_process(self) -> str:
        """Executes tasks sequentially and returns the final output."""
-        task_output = ""
+        task_output: str = ""
        for task in self.tasks:
            if task.agent is not None and task.agent.allow_delegation:
                agents_for_delegation = [
@@ -205,13 +185,16 @@ class Crew(BaseModel):

            output = task.execute(context=task_output)
            if not task.async_execution:
+                assert output is not None
                task_output = output

            role = task.agent.role if task.agent is not None else "None"
            self._logger.log("debug", f"[{role}] Task output: {task_output}\n\n")

-        self._finish_execution(task_output)
-        return self._format_output(task_output)
+        if self.max_rpm:
+            self._rpm_controller.stop_rpm_counter()
+
+        return task_output

    def _run_hierarchical_process(self) -> str:
        """Creates and assigns a manager agent to make sure the crew completes the tasks."""
@@ -226,33 +209,23 @@ class Crew(BaseModel):
            verbose=True,
        )

-        task_output = ""
+        task_output: str = ""
        for task in self.tasks:
            self._logger.log("debug", f"Working Agent: {manager.role}")
            self._logger.log("info", f"Starting Task: {task.description}")

-            task_output = task.execute(
+            output = task.execute(
                agent=manager, context=task_output, tools=manager.tools
            )
+            if not task.async_execution:
+                assert output is not None
+                task_output = output

            self._logger.log(
                "debug", f"[{manager.role}] Task output: {task_output}\n\n"
            )

-        self._finish_execution(task_output)
-        return self._format_output(task_output)
-
-    def _format_output(self, output: str) -> str:
-        """Formats the output of the crew execution."""
-        if self.full_output:
-            return {
-                "final_output": output,
-                "tasks_outputs": [task.output for task in self.tasks],
-            }
-        else:
-            return output
-
-    def _finish_execution(self, output) -> None:
        if self.max_rpm:
            self._rpm_controller.stop_rpm_counter()
-        self._telemetry.end_crew(self, output)
+
+        return task_output
--- a/src/crewai/task.py
+++ b/src/crewai/task.py
@@ -17,9 +17,8 @@ class Task(BaseModel):
        arbitrary_types_allowed = True

    __hash__ = object.__hash__  # type: ignore
-    used_tools: int = 0
    i18n: I18N = I18N()
-    thread: threading.Thread = None
+    thread: threading.Thread | None = None
    description: str = Field(description="Description of the actual task.")
    callback: Optional[Any] = Field(
        description="Callback to be executed after the task is completed.", default=None
@@ -72,7 +71,7 @@ class Task(BaseModel):
        agent: Agent | None = None,
        context: Optional[str] = None,
        tools: Optional[List[Any]] = None,
-    ) -> str:
+    ) -> str | None:
        """Execute the task.

        Returns:
@@ -86,40 +85,38 @@ class Task(BaseModel):
            )

        if self.context:
-            context = []
+            results = []
            for task in self.context:
                if task.async_execution:
+                    assert task.thread is not None
                    task.thread.join()
-                context.append(task.output.result)
-            context = "\n".join(context)
+                if task.output is not None:
+                    results.append(task.output.result)
+            context = "\n".join(results)

        tools = tools or self.tools

        if self.async_execution:
            self.thread = threading.Thread(
-                target=self._execute, args=(agent, self, context, tools)
+                target=self._execute, args=(agent, self._prompt(), context, tools)
            )
            self.thread.start()
        else:
            result = self._execute(
-                task=self,
                agent=agent,
+                task_prompt=self._prompt(),
                context=context,
                tools=tools,
            )
            return result

-    def _execute(self, agent, task, context, tools):
-        result = agent.execute_task(
-            task=task,
-            context=context,
-            tools=tools,
-        )
+    def _execute(self, agent, task_prompt, context, tools):
+        result = agent.execute_task(task=task_prompt, context=context, tools=tools)
        self.output = TaskOutput(description=self.description, result=result)
        self.callback(self.output) if self.callback else None
        return result

-    def prompt(self) -> str:
+    def _prompt(self) -> str:
        """Prompt the task.

        Returns:
--- a/src/crewai/telemtry/telemetry.py
+++ b/src/crewai/telemtry/telemetry.py
@@ -2,7 +2,6 @@ import json
 import os
 import platform
 import socket
-from typing import Any

 import pkg_resources
 from opentelemetry import trace
@@ -33,202 +32,75 @@ class Telemetry:
    - Language model being used
    - Roles of agents in a crew
    - Tools names available
-
-    Users can opt-in to sharing more complete data suing the `share_crew`
-    attribute in the Crew class.
    """

    def __init__(self):
-        self.ready = False
-        try:
-            telemetry_endpoint = "http://telemetry.crewai.com:4318"
-            self.resource = Resource(attributes={SERVICE_NAME: "crewAI-telemetry"})
-            self.provider = TracerProvider(resource=self.resource)
-            processor = BatchSpanProcessor(
-                OTLPSpanExporter(endpoint=f"{telemetry_endpoint}/v1/traces")
-            )
-            self.provider.add_span_processor(processor)
-            self.ready = True
-        except Exception:
-            pass
-
-    def set_tracer(self):
-        trace.set_tracer_provider(self.provider)
+        telemetry_endpoint = "http://telemetry.crewai.com:4318"
+        self.resource = Resource(attributes={SERVICE_NAME: "crewAI-telemetry"})
+        provider = TracerProvider(resource=self.resource)
+        processor = BatchSpanProcessor(
+            OTLPSpanExporter(endpoint=f"{telemetry_endpoint}/v1/traces")
+        )
+        provider.add_span_processor(processor)
+        trace.set_tracer_provider(provider)

    def crew_creation(self, crew):
        """Records the creation of a crew."""
-        if self.ready:
-            try:
-                tracer = trace.get_tracer("crewai.telemetry")
-                span = tracer.start_span("Crew Created")
-                self._add_attribute(
-                    span,
-                    "crewai_version",
-                    pkg_resources.get_distribution("crewai").version,
-                )
-                self._add_attribute(span, "python_version", platform.python_version())
-                self._add_attribute(span, "hostname", socket.gethostname())
-                self._add_attribute(span, "crew_id", str(crew.id))
-                self._add_attribute(span, "crew_process", crew.process)
-                self._add_attribute(span, "crew_language", crew.language)
-                self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
-                self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
-                self._add_attribute(
-                    span,
-                    "crew_agents",
-                    json.dumps(
-                        [
-                            {
-                                "id": str(agent.id),
-                                "role": agent.role,
-                                "memory_enabled?": agent.memory,
-                                "verbose?": agent.verbose,
-                                "max_iter": agent.max_iter,
-                                "max_rpm": agent.max_rpm,
-                                "i18n": agent.i18n.language,
-                                "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
-                                "delegation_enabled?": agent.allow_delegation,
-                                "tools_names": [tool.name for tool in agent.tools],
-                            }
-                            for agent in crew.agents
-                        ]
-                    ),
-                )
-                self._add_attribute(
-                    span,
-                    "crew_tasks",
-                    json.dumps(
-                        [
-                            {
-                                "id": str(task.id),
-                                "async_execution?": task.async_execution,
-                                "agent_role": task.agent.role if task.agent else "None",
-                                "tools_names": [tool.name for tool in task.tools],
-                            }
-                            for task in crew.tasks
-                        ]
-                    ),
-                )
-                self._add_attribute(span, "platform", platform.platform())
-                self._add_attribute(span, "platform_release", platform.release())
-                self._add_attribute(span, "platform_system", platform.system())
-                self._add_attribute(span, "platform_version", platform.version())
-                self._add_attribute(span, "cpus", os.cpu_count())
-                span.set_status(Status(StatusCode.OK))
-                span.end()
-            except Exception:
-                pass
+        try:
+            tracer = trace.get_tracer("crewai.telemetry")
+            span = tracer.start_span("Crew Created")
+            self.add_attribute(
+                span, "crewai_version", pkg_resources.get_distribution("crewai").version
+            )
+            self.add_attribute(span, "python_version", platform.python_version())
+            self.add_attribute(span, "hostname", socket.gethostname())
+            self.add_attribute(span, "crewid", str(crew.id))
+            self.add_attribute(span, "crew_process", crew.process)
+            self.add_attribute(span, "crew_language", crew.language)
+            self.add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
+            self.add_attribute(span, "crew_number_of_agents", len(crew.agents))
+            self.add_attribute(
+                span,
+                "crew_agents",
+                json.dumps(
+                    [
+                        {
+                            "id": str(agent.id),
+                            "role": agent.role,
+                            "memory_enabled?": agent.memory,
+                            "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
+                            "delegation_enabled?": agent.allow_delegation,
+                            "tools_names": [tool.name for tool in agent.tools],
+                        }
+                        for agent in crew.agents
+                    ]
+                ),
+            )
+            self.add_attribute(
+                span,
+                "crew_tasks",
+                json.dumps(
+                    [
+                        {
+                            "id": str(task.id),
+                            "async_execution?": task.async_execution,
+                            "tools_names": [tool.name for tool in task.tools],
+                        }
+                        for task in crew.tasks
+                    ]
+                ),
+            )
+            self.add_attribute(span, "platform", platform.platform())
+            self.add_attribute(span, "platform_release", platform.release())
+            self.add_attribute(span, "platform_system", platform.system())
+            self.add_attribute(span, "platform_version", platform.version())
+            self.add_attribute(span, "cpus", os.cpu_count())
+            span.set_status(Status(StatusCode.OK))
+            span.end()
+        except Exception:
+            pass

-    def tool_usage(self, llm: Any, tool_name: str, attempts: int):
-        """Records the usage of a tool by an agent."""
-        if self.ready:
-            try:
-                tracer = trace.get_tracer("crewai.telemetry")
-                span = tracer.start_span("Tool Usage")
-                self._add_attribute(span, "tool_name", tool_name)
-                self._add_attribute(span, "attempts", attempts)
-                self._add_attribute(
-                    span, "llm", json.dumps(self._safe_llm_attributes(llm))
-                )
-                span.set_status(Status(StatusCode.OK))
-                span.end()
-            except Exception:
-                pass
-
-    def tool_usage_error(self, llm: Any):
-        """Records the usage of a tool by an agent."""
-        if self.ready:
-            try:
-                tracer = trace.get_tracer("crewai.telemetry")
-                span = tracer.start_span("Tool Usage Error")
-                self._add_attribute(
-                    span, "llm", json.dumps(self._safe_llm_attributes(llm))
-                )
-                span.set_status(Status(StatusCode.OK))
-                span.end()
-            except Exception:
-                pass
-
-    def crew_execution_span(self, crew):
-        """Records the complete execution of a crew.
-        This is only collected if the user has opted-in to share the crew.
-        """
-        if (self.ready) and (crew.share_crew):
-            try:
-                tracer = trace.get_tracer("crewai.telemetry")
-                span = tracer.start_span("Crew Execution")
-                self._add_attribute(span, "crew_id", str(crew.id))
-                self._add_attribute(
-                    span,
-                    "crew_agents",
-                    json.dumps(
-                        [
-                            {
-                                "id": str(agent.id),
-                                "role": agent.role,
-                                "goal": agent.goal,
-                                "backstory": agent.backstory,
-                                "memory_enabled?": agent.memory,
-                                "verbose?": agent.verbose,
-                                "max_iter": agent.max_iter,
-                                "max_rpm": agent.max_rpm,
-                                "i18n": agent.i18n.language,
-                                "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
-                                "delegation_enabled?": agent.allow_delegation,
-                                "tools_names": [tool.name for tool in agent.tools],
-                            }
-                            for agent in crew.agents
-                        ]
-                    ),
-                )
-                self._add_attribute(
-                    span,
-                    "crew_tasks",
-                    json.dumps(
-                        [
-                            {
-                                "id": str(task.id),
-                                "description": task.description,
-                                "async_execution?": task.async_execution,
-                                "output": task.expected_output,
-                                "agent_role": task.agent.role if task.agent else "None",
-                                "context": [task.description for task in task.context]
-                                if task.context
-                                else "None",
-                                "tools_names": [tool.name for tool in task.tools],
-                            }
-                            for task in crew.tasks
-                        ]
-                    ),
-                )
-                return span
-            except Exception:
-                pass
-
-    def end_crew(self, crew, output):
-        if (self.ready) and (crew.share_crew):
-            try:
-                self._add_attribute(crew._execution_span, "crew_output", output)
-                self._add_attribute(
-                    crew._execution_span,
-                    "crew_tasks_output",
-                    json.dumps(
-                        [
-                            {
-                                "id": str(task.id),
-                                "description": task.description,
-                                "output": task.output.result,
-                            }
-                            for task in crew.tasks
-                        ]
-                    ),
-                )
-                crew._execution_span.set_status(Status(StatusCode.OK))
-                crew._execution_span.end()
-            except Exception:
-                pass
-
-    def _add_attribute(self, span, key, value):
+    def add_attribute(self, span, key, value):
        """Add an attribute to a span."""
        try:
            return span.set_attribute(key, value)
--- a/src/crewai/tools/agent_tools.py
+++ b/src/crewai/tools/agent_tools.py
@@ -1,10 +1,9 @@
 from typing import List

-from langchain.tools import StructuredTool
+from langchain.tools import Tool
 from pydantic import BaseModel, Field

 from crewai.agent import Agent
-from crewai.task import Task
 from crewai.utilities import I18N


@@ -16,14 +15,14 @@ class AgentTools(BaseModel):

    def tools(self):
        return [
-            StructuredTool.from_function(
+            Tool.from_function(
                func=self.delegate_work,
                name="Delegate work to co-worker",
                description=self.i18n.tools("delegate_work").format(
                    coworkers=", ".join([agent.role for agent in self.agents])
                ),
            ),
-            StructuredTool.from_function(
+            Tool.from_function(
                func=self.ask_question,
                name="Ask question to co-worker",
                description=self.i18n.tools("ask_question").format(
@@ -32,16 +31,24 @@ class AgentTools(BaseModel):
            ),
        ]

-    def delegate_work(self, coworker: str, task: str, context: str):
+    def delegate_work(self, command):
        """Useful to delegate a specific task to a coworker."""
-        return self._execute(coworker, task, context)
+        return self._execute(command)

-    def ask_question(self, coworker: str, question: str, context: str):
+    def ask_question(self, command):
        """Useful to ask a question, opinion or take from a coworker."""
-        return self._execute(coworker, question, context)
+        return self._execute(command)

-    def _execute(self, agent, task, context):
+    def _execute(self, command):
        """Execute the command."""
+        try:
+            agent, task, context = command.split("|")
+        except ValueError:
+            return self.i18n.errors("agent_tool_missing_param")
+
+        if not agent or not task or not context:
+            return self.i18n.errors("agent_tool_missing_param")
+
        agent = [
            available_agent
            for available_agent in self.agents
@@ -54,5 +61,4 @@ class AgentTools(BaseModel):
            )

        agent = agent[0]
-        task = Task(description=task, agent=agent)
        return agent.execute_task(task, context)
--- a/src/crewai/tools/cache_tools.py
+++ b/src/crewai/tools/cache_tools.py
@@ -1,4 +1,4 @@
-from langchain.tools import StructuredTool
+from langchain.tools import Tool
 from pydantic import BaseModel, ConfigDict, Field

 from crewai.agents.cache import CacheHandler
@@ -15,7 +15,7 @@ class CacheTools(BaseModel):
    )

    def tool(self):
-        return StructuredTool.from_function(
+        return Tool.from_function(
            func=self.hit_cache,
            name=self.name,
            description="Reads directly from the cache",
--- a/src/crewai/tools/tool_calling.py
+++ b/src/crewai/tools/tool_calling.py
@@ -1,12 +0,0 @@
-from typing import Any, Dict
-
-from pydantic.v1 import BaseModel, Field
-
-
-class ToolCalling(BaseModel):
-    function_name: str = Field(
-        ..., description="The name of the function to be called."
-    )
-    arguments: Dict[str, Any] = Field(
-        ..., description="A dictinary of arguments to be passed to the function."
-    )
--- a/src/crewai/tools/tool_usage.py
+++ b/src/crewai/tools/tool_usage.py
@@ -1,164 +0,0 @@
-from typing import Any, List
-
-from langchain.output_parsers import PydanticOutputParser
-from langchain.prompts import PromptTemplate
-from langchain_core.tools import BaseTool
-
-from crewai.agents.tools_handler import ToolsHandler
-from crewai.telemtry import Telemetry
-from crewai.tools.tool_calling import ToolCalling
-from crewai.utilities import I18N, Printer
-
-
-class ToolUsageErrorException(Exception):
-    """Exception raised for errors in the tool usage."""
-
-    def __init__(self, message: str) -> None:
-        self.message = message
-        super().__init__(self.message)
-
-
-class ToolUsage:
-    """
-    Class that represents the usage of a tool by an agent.
-
-    Attributes:
-        task: Task being executed.
-        tools_handler: Tools handler that will manage the tool usage.
-        tools: List of tools available for the agent.
-        tools_description: Description of the tools available for the agent.
-        tools_names: Names of the tools available for the agent.
-        llm: Language model to be used for the tool usage.
-    """
-
-    def __init__(
-        self,
-        tools_handler: ToolsHandler,
-        tools: List[BaseTool],
-        tools_description: str,
-        tools_names: str,
-        task: Any,
-        llm: Any,
-    ) -> None:
-        self._i18n: I18N = I18N()
-        self._printer: Printer = Printer()
-        self._telemetry: Telemetry = Telemetry()
-        self._run_attempts: int = 1
-        self._max_parsing_attempts: int = 3
-        self._remeber_format_after_usages: int = 3
-        self.tools_description = tools_description
-        self.tools_names = tools_names
-        self.tools_handler = tools_handler
-        self.tools = tools
-        self.task = task
-        self.llm = llm
-
-    def use(self, tool_string: str):
-        calling = self._tool_calling(tool_string)
-        if isinstance(calling, ToolUsageErrorException):
-            error = calling.message
-            self._printer.print(content=f"\n\n{error}\n", color="yellow")
-            return error
-        tool = self._select_tool(calling.function_name)
-        return self._use(tool_string=tool_string, tool=tool, calling=calling)
-
-    def _use(self, tool_string: str, tool: BaseTool, calling: ToolCalling) -> None:
-        try:
-            if self._check_tool_repeated_usage(calling=calling):
-                result = self._i18n.errors("task_repeated_usage").format(
-                    tool=calling.function_name, tool_input=calling.arguments
-                )
-            else:
-                self.tools_handler.on_tool_start(calling=calling)
-
-                result = self.tools_handler.cache.read(
-                    tool=calling.function_name, input=calling.arguments
-                )
-
-                if not result:
-                    result = tool._run(**calling.arguments)
-                    self.tools_handler.on_tool_end(calling=calling, output=result)
-
-            self._printer.print(content=f"\n\n{result}\n", color="yellow")
-            self._telemetry.tool_usage(
-                llm=self.llm, tool_name=tool.name, attempts=self._run_attempts
-            )
-
-            result = self._format_result(result=result)
-            return result
-        except Exception:
-            self._run_attempts += 1
-            if self._run_attempts > self._max_parsing_attempts:
-                self._telemetry.tool_usage_error(llm=self.llm)
-                return ToolUsageErrorException(
-                    self._i18n.errors("tool_usage_error")
-                ).message
-            return self.use(tool_string=tool_string)
-
-    def _format_result(self, result: Any) -> None:
-        self.task.used_tools += 1
-        if self._should_remember_format():
-            result = self._remember_format(result=result)
-        return result
-
-    def _should_remember_format(self) -> None:
-        return self.task.used_tools % self._remeber_format_after_usages == 0
-
-    def _remember_format(self, result: str) -> None:
-        result = str(result)
-        result += "\n\n" + self._i18n.slice("tools").format(
-            tools=self.tools_description, tool_names=self.tools_names
-        )
-        return result
-
-    def _check_tool_repeated_usage(self, calling: ToolCalling) -> None:
-        if last_tool_usage := self.tools_handler.last_used_tool:
-            return calling == last_tool_usage
-
-    def _select_tool(self, tool_name: str) -> BaseTool:
-        for tool in self.tools:
-            if tool.name == tool_name:
-                return tool
-        raise Exception(f"Tool '{tool_name}' not found.")
-
-    def _render(self) -> str:
-        """Render the tool name and description in plain text."""
-        descriptions = []
-        for tool in self.tools:
-            args = {
-                k: {k2: v2 for k2, v2 in v.items() if k2 in ["description", "type"]}
-                for k, v in tool.args.items()
-            }
-            descriptions.append(
-                "\n".join(
-                    [
-                        f"Funtion Name: {tool.name}",
-                        f"Funtion attributes: {args}",
-                        f"Description: {tool.description}",
-                    ]
-                )
-            )
-        return "\n--\n".join(descriptions)
-
-    def _tool_calling(self, tool_string: str) -> ToolCalling:
-        try:
-            parser = PydanticOutputParser(pydantic_object=ToolCalling)
-            prompt = PromptTemplate(
-                template="Return a valid schema for the one tool you must use with its arguments and values.\n\nTools available:\n\n{available_tools}\n\nUse this text to inform a valid ouput schema:\n{tool_string}\n\n{format_instructions}\n```",
-                input_variables=["tool_string"],
-                partial_variables={
-                    "available_tools": self._render(),
-                    "format_instructions": parser.get_format_instructions(),
-                },
-            )
-            chain = prompt | self.llm | parser
-            calling = chain.invoke({"tool_string": tool_string})
-
-        except Exception:
-            self._run_attempts += 1
-            if self._run_attempts > self._max_parsing_attempts:
-                self._telemetry.tool_usage_error(llm=self.llm)
-                return ToolUsageErrorException(self._i18n.errors("tool_usage_error"))
-            return self._tool_calling(tool_string)
-
-        return calling
--- a/src/crewai/translations/el.json
+++ b/src/crewai/translations/el.json
@@ -9,18 +9,18 @@
    "task": "Αρχή! Αυτό είναι ΠΟΛΥ σημαντικό για εσάς, η δουλειά σας εξαρτάται από αυτό!\n\nΤρέχουσα εργασία: {input}",
    "memory": "Αυτή είναι η περίληψη της μέχρι τώρα δουλειάς σας:\n{chat_history}",
    "role_playing": "Είσαι {role}.\n{backstory}\n\nΟ προσωπικός σας στόχος είναι: {goal}",
-    "tools": "ΕΡΓΑΛΕΙΑ:\n------\nΈχετε πρόσβαση μόνο στα ακόλουθα εργαλεία:\n\n{tools}\n\nΓια να χρησιμοποιήσετε ένα εργαλείο, χρησιμοποιήστε την ακόλουθη ακριβώς μορφή:\n\n```\nThought: Χρειάζεται να χρησιμοποιήσω κάποιο εργαλείο; Ναι\nΕνέργεια: το εργαλείο που θέλετε να χρησιμοποιήσετε, θα πρέπει να είναι ένα από τα [{tool_names}], μόνο το όνομα.\nΕισαγωγή ενέργειας: Οποιαδήποτε και όλες οι σχετικές πληροφορίες και το πλαίσιο χρήσης του εργαλείου\nΠαρατήρηση: το αποτέλεσμα της χρήσης του εργαλείου\n```\n\nΌταν έχετε μια απάντηση για την εργασία σας ή εάν δεν χρειάζεται να χρησιμοποιήσετε ένα εργαλείο, ΠΡΕΠΕΙ να χρησιμοποιήσετε τη μορφή:\n\n```\nΣκέψη: Πρέπει να χρησιμοποιήσω ένα εργαλείο ? Όχι\nΤελική απάντηση: [η απάντησή σας εδώ]```",
+    "tools": "ΕΡΓΑΛΕΙΑ:\n------\nΈχετε πρόσβαση μόνο στα ακόλουθα εργαλεία:\n\n{tools}\n\nΓια να χρησιμοποιήσετε ένα εργαλείο, χρησιμοποιήστε την ακόλουθη ακριβώς μορφή:\n\n```\nΣκέψη: Χρειάζεται να χρησιμοποιήσω κάποιο εργαλείο; Ναί\nΔράση: η ενέργεια που πρέπει να γίνει, πρέπει να είναι μία από τις[{tool_names}], μόνο το όνομα.\nΕνέργεια προς εισαγωγή: η είσοδος στη δράση\nΠαρατήρηση: το αποτέλεσμα της δράσης\n```\n\nΌταν έχετε μια απάντηση για την εργασία σας ή εάν δεν χρειάζεται να χρησιμοποιήσετε ένα εργαλείο, ΠΡΕΠΕΙ να χρησιμοποιήσετε τη μορφή:\n\n```\nΣκέψη: Χρειάζεται να χρησιμοποιήσω κάποιο εργαλείο; Οχι\nΤελική απάντηση: [η απάντησή σας εδώ]```",
    "task_with_context": "{task}\nΑυτό είναι το πλαίσιο με το οποίο εργάζεστε:\n{context}",
    "expected_output": "Η τελική σας απάντηση πρέπει να είναι: {expected_output}"
  },
  "errors": {
    "force_final_answer": "Στην πραγματικότητα, χρησιμοποίησα πάρα πολλά εργαλεία, οπότε θα σταματήσω τώρα και θα σας δώσω την απόλυτη ΚΑΛΥΤΕΡΗ τελική μου απάντηση ΤΩΡΑ, χρησιμοποιώντας την αναμενόμενη μορφή: ```\nΣκέφτηκα: Χρειάζεται να χρησιμοποιήσω ένα εργαλείο; Όχι\nΤελική απάντηση: [η απάντησή σας εδώ]```",
+    "agent_tool_missing_param": "\nΣφάλμα κατά την εκτέλεση του εργαλείου. Λείπουν ακριβώς 3 διαχωρισμένες τιμές σωλήνων (|). Για παράδειγμα, `coworker|task|context`. Πρέπει να φροντίσω να περάσω το πλαίσιο ως πλαίσιο.\n",
    "agent_tool_unexsiting_coworker": "\nΣφάλμα κατά την εκτέλεση του εργαλείου. Ο συνάδελφος που αναφέρεται στο Ενέργεια προς εισαγωγή δεν βρέθηκε, πρέπει να είναι μία από τις ακόλουθες επιλογές: {coworkers}.\n",
-    "task_repeated_usage": "Μόλις χρησιμοποίησα το εργαλείο {tool} με είσοδο {tool_input}. Άρα ξέρω ήδη το αποτέλεσμα αυτού και δεν χρειάζεται να το χρησιμοποιήσω ξανά τώρα.\n",
-    "tool_usage_error": "Φαίνεται ότι αντιμετωπίσαμε ένα απροσδόκητο σφάλμα κατά την προσπάθεια χρήσης του εργαλείου."
+    "task_repeated_usage": "Μόλις χρησιμοποίησα το {tool} εργαλείο με είσοδο {tool_input}. Άρα ξέρω ήδη το αποτέλεσμα αυτού και δεν χρειάζεται να το χρησιμοποιήσω τώρα.\n"
  },
  "tools": {
-    "delegate_work": "Αναθέστε μια συγκεκριμένη εργασία σε έναν από τους παρακάτω συναδέλφους: {coworkers}. Η είσοδος σε αυτό το εργαλείο θα πρέπει να είναι ο ρόλος του συναδέλφου, η εργασία που θέλετε να κάνει και ΟΛΟ το απαραίτητο πλαίσιο για την εκτέλεση της εργασίας, δεν γνωρίζουν τίποτα για την εργασία, επομένως μοιραστείτε απολύτως όλα όσα γνωρίζετε, μην αναφέρετε πράγματα, αλλά αντί να τους εξηγήσεις.",
-    "ask_question": "Κάντε μια συγκεκριμένη ερώτηση σε έναν από τους παρακάτω συναδέλφους: {coworkers}. Η συμβολή σε αυτό το εργαλείο θα πρέπει να είναι ο ρόλος του συναδέλφου, η ερώτηση που έχετε για αυτόν και ΟΛΟ το απαραίτητο πλαίσιο για να κάνετε σωστά την ερώτηση, δεν γνωρίζουν τίποτα για την ερώτηση, επομένως μοιραστείτε απολύτως όλα όσα γνωρίζετε, μην αναφέρετε πράγματα, αλλά αντί να τους εξηγήσεις."
+    "delegate_work": "Χρήσιμο για την ανάθεση μιας συγκεκριμένης εργασίας σε έναν από τους παρακάτω συναδέλφους: {coworkers}.\nΗ είσοδος σε αυτό το εργαλείο θα πρέπει να είναι ένα κείμενο χωρισμένο σε σωλήνα (|) μήκους 3 (τρία), που αντιπροσωπεύει τον συνάδελφο στον οποίο θέλετε να του ζητήσετε (μία από τις επιλογές), την εργασία και όλο το πραγματικό πλαίσιο που έχετε για την εργασία .\nΓια παράδειγμα, `coworker|task|context`.",
+    "ask_question": "Χρήσιμο για να κάνετε μια ερώτηση, γνώμη ή αποδοχή από τους παρακάτω συναδέλφους: {coworkers}.\nΗ είσοδος σε αυτό το εργαλείο θα πρέπει να είναι ένα κείμενο χωρισμένο σε σωλήνα (|) μήκους 3 (τρία), που αντιπροσωπεύει τον συνάδελφο στον οποίο θέλετε να το ρωτήσετε (μία από τις επιλογές), την ερώτηση και όλο το πραγματικό πλαίσιο που έχετε για την ερώτηση.\nΓια παράδειγμα, `coworker|question|context`."
  }
 }
--- a/src/crewai/translations/en.json
+++ b/src/crewai/translations/en.json
@@ -9,18 +9,18 @@
    "task": "Begin! This is VERY important to you, your job depends on it!\n\nCurrent Task: {input}",
    "memory": "This is the summary of your work so far:\n{chat_history}",
    "role_playing": "You are {role}.\n{backstory}\n\nYour personal goal is: {goal}",
-    "tools": "TOOLS:\n------\nYou have access to only the following tools:\n\n{tools}\n\nTo use a tool, please use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one of [{tool_names}], just the name.\nAction Input: Any and all relevant information input and context for using the tool\nObservation: the result of using the tool\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```",
+    "tools": "TOOLS:\n------\nYou have access to only the following tools:\n\n{tools}\n\nTo use a tool, please use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [{tool_names}], just the name.\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```",
    "task_with_context": "{task}\nThis is the context you're working with:\n{context}",
    "expected_output": "Your final answer must be: {expected_output}"
  },
  "errors": {
-    "force_final_answer": "Actually, I used too many tools, so I'll stop now and give you my absolute BEST Final answer NOW, using exaclty the expected format bellow: \n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```",
+    "force_final_answer": "Actually, I used too many tools, so I'll stop now and give you my absolute BEST Final answer NOW, using the expected format: ```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```",
+    "agent_tool_missing_param": "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|context`. I need to make sure to pass context as context.\n",
    "agent_tool_unexsiting_coworker": "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: {coworkers}.\n",
-    "task_repeated_usage": "I just used the {tool} tool with input {tool_input}. So I already know the result of that and don't need to use it again now. \nI could give my final answer if I'm ready, using exaclty the expected format bellow: \n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```\n",
-    "tool_usage_error": "It seems we encountered an unexpected error while trying to use the tool."
+    "task_repeated_usage": "I just used the {tool} tool with input {tool_input}. So I already know the result of that and don't need to use it now.\n"
  },
  "tools": {
-    "delegate_work": "Delegate a specific task to one of the following co-workers: {coworkers}. The input to this tool should be the role of the coworker, the task you want them to do, and ALL necessary context to exectue the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
-    "ask_question": "Ask a specific question to one of the following co-workers: {coworkers}. The input to this tool should be the role of the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them."
+    "delegate_work": "Useful to delegate a specific task to one of the following co-workers: {coworkers}.\nThe input to this tool should be a pipe (|) separated text of length 3 (three), representing the co-worker you want to ask it to (one of the options), the task and all actual context you have for the task.\nFor example, `coworker|task|context`.",
+    "ask_question": "Useful to ask a question, opinion or take from on of the following co-workers: {coworkers}.\nThe input to this tool should be a pipe (|) separated text of length 3 (three), representing the co-worker you want to ask it to (one of the options), the question and all actual context you have for the question.\n For example, `coworker|question|context`."
  }
 }
--- a/src/crewai/utilities/init.py
+++ b/src/crewai/utilities/init.py
@@ -1,5 +1,4 @@
 from .i18n import I18N
 from .logger import Logger
-from .printer import Printer
 from .prompts import Prompts
 from .rpm_controller import RPMController
--- a/src/crewai/utilities/printer.py
+++ b/src/crewai/utilities/printer.py
@@ -1,9 +0,0 @@
-class Printer:
-    def print(self, content: str, color: str):
-        if color == "yellow":
-            self._print_yellow(content)
-        else:
-            print(content)
-
-    def _print_yellow(self, content):
-        print("\033[93m {}\033[00m".format(content))
--- a/tests/agent_test.py
+++ b/tests/agent_test.py
@@ -9,8 +9,6 @@ from langchain_openai import ChatOpenAI
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.executor import CrewAgentExecutor
-from crewai.tools.tool_calling import ToolCalling
-from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController


@@ -64,8 +62,7 @@ def test_agent_without_memory():
        llm=ChatOpenAI(temperature=0, model="gpt-4"),
    )

-    task = Task(description="How much is 1 + 1?", agent=no_memory_agent)
-    result = no_memory_agent.execute_task(task)
+    result = no_memory_agent.execute_task("How much is 1 + 1?")

    assert result == "1 + 1 equals 2."
    assert no_memory_agent.agent_executor.memory is None
@@ -81,18 +78,20 @@ def test_agent_execution():
        allow_delegation=False,
    )

-    task = Task(description="How much is 1 + 1?", agent=agent)
-
-    output = agent.execute_task(task)
+    output = agent.execute_task("How much is 1 + 1?")
    assert output == "2"


@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_execution_with_tools():
    @tool
-    def multiplier(first_number: int, second_number: int) -> float:
-        """Useful for when you need to multiply two numbers together."""
-        return first_number * second_number
+    def multiplier(numbers) -> float:
+        """Useful for when you need to multiply two numbers together.
+        The input to this tool should be a comma separated list of numbers of
+        length two, representing the two numbers you want to multiply together.
+        For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
+        a, b = numbers.split(",")
+        return int(a) * int(b)

    agent = Agent(
        role="test role",
@@ -102,17 +101,20 @@ def test_agent_execution_with_tools():
        allow_delegation=False,
    )

-    task = Task(description="What is 3 times 4?", agent=agent)
-    output = agent.execute_task(task)
-    assert output == "3 times 4 is 12."
+    output = agent.execute_task("What is 3 times 4")
+    assert output == "12"


@pytest.mark.vcr(filter_headers=["authorization"])
 def test_logging_tool_usage():
    @tool
-    def multiplier(first_number: int, second_number: int) -> float:
-        """Useful for when you need to multiply two numbers together."""
-        return first_number * second_number
+    def multiplier(numbers) -> float:
+        """Useful for when you need to multiply two numbers together.
+        The input to this tool should be a comma separated list of numbers of
+        length two, representing the two numbers you want to multiply together.
+        For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
+        a, b = numbers.split(",")
+        return int(a) * int(b)

    agent = Agent(
        role="test role",
@@ -124,11 +126,11 @@ def test_logging_tool_usage():
    )

    assert agent.tools_handler.last_used_tool == {}
-    task = Task(description="What is 3 times 4?", agent=agent)
-    output = agent.execute_task(task)
-    tool_usage = ToolCalling(
-        function_name=multiplier.name, arguments={"first_number": 3, "second_number": 5}
-    )
+    output = agent.execute_task("What is 3 times 5?")
+    tool_usage = {
+        "tool": "multiplier",
+        "input": "3,5",
+    }

    assert output == "3 times 5 is 15."
    assert agent.tools_handler.last_used_tool == tool_usage
@@ -137,9 +139,13 @@ def test_logging_tool_usage():
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_cache_hitting():
    @tool
-    def multiplier(first_number: int, second_number: int) -> float:
-        """Useful for when you need to multiply two numbers together."""
-        return first_number * second_number
+    def multiplier(numbers) -> float:
+        """Useful for when you need to multiply two numbers together.
+        The input to this tool should be a comma separated list of numbers of
+        length two and ONLY TWO, representing the two numbers you want to multiply together.
+        For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
+        a, b = numbers.split(",")
+        return int(a) * int(b)

    cache_handler = CacheHandler()

@@ -153,42 +159,34 @@ def test_cache_hitting():
        verbose=True,
    )

-    task1 = Task(description="What is 2 times 6?", agent=agent)
-    task2 = Task(description="What is 3 times 3?", agent=agent)
-
-    output = agent.execute_task(task1)
-    output = agent.execute_task(task2)
+    output = agent.execute_task("What is 2 times 6 times 3?")
+    output = agent.execute_task("What is 3 times 3?")
    assert cache_handler._cache == {
-        "multiplier-{'first_number': 12, 'second_number': 3}": 36,
-        "multiplier-{'first_number': 2, 'second_number': 6}": 12,
-        "multiplier-{'first_number': 3, 'second_number': 3}": 9,
+        "multiplier-12,3": "36",
+        "multiplier-2,6": "12",
+        "multiplier-3,3": "9",
    }

-    task = Task(
-        description="What is 2 times 6 times 3? Return only the number", agent=agent
-    )
-    output = agent.execute_task(task)
+    output = agent.execute_task("What is 2 times 6 times 3? Return only the number")
    assert output == "36"

    with patch.object(CacheHandler, "read") as read:
        read.return_value = "0"
-        task = Task(
-            description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool.",
-            agent=agent,
-        )
-        output = agent.execute_task(task)
+        output = agent.execute_task("What is 2 times 6?")
        assert output == "0"
-        read.assert_called_with(
-            tool="multiplier", input={"first_number": 2, "second_number": 6}
-        )
+        read.assert_called_with("multiplier", "2,6")


@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_execution_with_specific_tools():
    @tool
-    def multiplier(first_number: int, second_number: int) -> float:
-        """Useful for when you need to multiply two numbers together."""
-        return first_number * second_number
+    def multiplier(numbers) -> float:
+        """Useful for when you need to multiply two numbers together.
+        The input to this tool should be a comma separated list of numbers of
+        length two, representing the two numbers you want to multiply together.
+        For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
+        a, b = numbers.split(",")
+        return int(a) * int(b)

    agent = Agent(
        role="test role",
@@ -197,8 +195,7 @@ def test_agent_execution_with_specific_tools():
        allow_delegation=False,
    )

-    task = Task(description="What is 3 times 4", agent=agent)
-    output = agent.execute_task(task=task, tools=[multiplier])
+    output = agent.execute_task(task="What is 3 times 4", tools=[multiplier])
    assert output == "3 times 4 is 12."


@@ -221,47 +218,13 @@ def test_agent_custom_max_iterations():
    with patch.object(
        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
    ) as private_mock:
-        task = Task(
-            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
-        )
        agent.execute_task(
-            task=task,
+            task="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
            tools=[get_final_answer],
        )
        private_mock.assert_called_once()


-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_repeated_tool_usage(capsys):
-    @tool
-    def get_final_answer(numbers) -> float:
-        """Get the final answer but don't give it yet, just re-use this
-        tool non-stop."""
-        return 42
-
-    agent = Agent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-        max_iter=3,
-        allow_delegation=False,
-    )
-
-    task = Task(
-        description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool."
-    )
-    agent.execute_task(
-        task=task,
-        tools=[get_final_answer],
-    )
-
-    captured = capsys.readouterr()
-    assert (
-        "I just used the get_final_answer tool with input {'numbers': 42}. So I already know the result of that and don't need to use it again now. \nI could give my final answer if I'm ready, using exaclty the expected format bellow: \n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```\n"
-        in captured.out
-    )
-
-
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_moved_on_after_max_iterations():
    @tool
@@ -278,17 +241,18 @@ def test_agent_moved_on_after_max_iterations():
        allow_delegation=False,
    )

-    task = Task(
-        description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool."
-    )
-    output = agent.execute_task(
-        task=task,
-        tools=[get_final_answer],
-    )
-    assert (
-        output
-        == "I have used the tool 'get_final_answer' twice and confirmed that the answer is indeed 42."
-    )
+    with patch.object(
+        CrewAgentExecutor, "_force_answer", wraps=agent.agent_executor._force_answer
+    ) as private_mock:
+        output = agent.execute_task(
+            task="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            tools=[get_final_answer],
+        )
+        assert (
+            output
+            == "I have used the tool multiple times and the final answer remains 42."
+        )
+        private_mock.assert_called_once()


@pytest.mark.vcr(filter_headers=["authorization"])
@@ -311,16 +275,13 @@ def test_agent_respect_the_max_rpm_set(capsys):

    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
        moveon.return_value = True
-        task = Task(
-            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool."
-        )
        output = agent.execute_task(
-            task=task,
+            task="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
            tools=[get_final_answer],
        )
        assert (
            output
-            == "I have used the tool as instructed and I am now ready to give the final answer. However, as per the instructions, I am not supposed to give it yet."
+            == "I've used the `get_final_answer` tool multiple times and it consistently returns the number 42."
        )
        captured = capsys.readouterr()
        assert "Max RPM reached, waiting for next minute to start." in captured.out
@@ -398,7 +359,7 @@ def test_agent_without_max_rpm_respet_crew_rpm(capsys):
            agent=agent1,
        ),
        Task(
-            description="Don't give a Final Answer, instead keep using the `get_final_answer` tool non-stop",
+            description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
            tools=[get_final_answer],
            agent=agent2,
        ),
@@ -415,80 +376,10 @@ def test_agent_without_max_rpm_respet_crew_rpm(capsys):
        moveon.assert_called_once()


-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_error_on_parsing_tool(capsys):
-    from unittest.mock import patch
-
-    from langchain.tools import tool
-
-    @tool
-    def get_final_answer(numbers) -> float:
-        """Get the final answer but don't give it yet, just re-use this
-        tool non-stop."""
-        return 42
-
-    agent1 = Agent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-        verbose=True,
-    )
-    tasks = [
-        Task(
-            description="Use the get_final_answer tool.",
-            agent=agent1,
-            tools=[get_final_answer],
-        )
-    ]
-
-    crew = Crew(agents=[agent1], tasks=tasks, verbose=2)
-
-    with patch.object(ToolUsage, "_render") as force_exception:
-        force_exception.side_effect = Exception("Error on parsing tool.")
-        crew.kickoff()
-        captured = capsys.readouterr()
-        assert (
-            "It seems we encountered an unexpected error while trying to use the tool"
-            in captured.out
-        )
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_remembers_output_format_after_using_tools_too_many_times():
-    from unittest.mock import patch
-
-    from langchain.tools import tool
-
-    @tool
-    def get_final_answer(numbers) -> float:
-        """Get the final answer but don't give it yet, just re-use this
-        tool non-stop."""
-        return 42
-
-    agent1 = Agent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-        max_iter=4,
-        verbose=True,
-    )
-    tasks = [
-        Task(
-            description="Never give the final answer. Use the get_final_answer tool in a loop.",
-            agent=agent1,
-            tools=[get_final_answer],
-        )
-    ]
-
-    crew = Crew(agents=[agent1], tasks=tasks, verbose=2)
-
-    with patch.object(ToolUsage, "_remember_format") as remember_format:
-        crew.kickoff()
-        remember_format.assert_called()
-
-
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_use_specific_tasks_output_as_context(capsys):
+    pass
+
    agent1 = Agent(role="test role", goal="test goal", backstory="test backstory")

    agent2 = Agent(role="test role2", goal="test goal2", backstory="test backstory2")
@@ -507,36 +398,3 @@ def test_agent_use_specific_tasks_output_as_context(capsys):
    result = crew.kickoff()
    assert "bye" not in result.lower()
    assert "hi" in result.lower() or "hello" in result.lower()
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_step_callback():
-    class StepCallback:
-        def callback(self, step):
-            print(step)
-
-    with patch.object(StepCallback, "callback") as callback:
-
-        @tool
-        def learn_about_AI(topic) -> float:
-            """Useful for when you need to learn about AI to write an paragraph about it."""
-            return "AI is a very broad field."
-
-        agent1 = Agent(
-            role="test role",
-            goal="test goal",
-            backstory="test backstory",
-            tools=[learn_about_AI],
-            step_callback=StepCallback().callback,
-        )
-
-        essay = Task(
-            description="Write and then review an small paragraph on AI until it's AMAZING",
-            agent=agent1,
-        )
-        tasks = [essay]
-        crew = Crew(agents=[agent1], tasks=tasks)
-
-        callback.return_value = "ok"
-        crew.kickoff()
-        callback.assert_called()
--- a/tests/agent_tools/agent_tools_test.py
+++ b/tests/agent_tools/agent_tools_test.py
@@ -17,36 +17,44 @@ tools = AgentTools(agents=[researcher])
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegate_work():
    result = tools.delegate_work(
-        coworker="researcher",
-        task="share your take on AI Agents",
-        context="I heard you hate them",
+        command="researcher|share your take on AI Agents|I heard you hate them"
    )

    assert (
        result
-        == "As a researcher, I maintain a neutral perspective on all subjects of research including AI agents. My job is to provide an objective analysis based on facts, not personal feelings. AI Agents are a significant topic in the field of technology with potential to revolutionize various sectors such as healthcare, education, finance and more. They are responsible for tasks that require human intelligence such as understanding natural language, recognizing patterns, and problem solving. However, like any technology, they are tools that can be used for both beneficial and harmful purposes depending on the intent of the user. Therefore, it's crucial to establish ethical guidelines and regulations for their use."
+        == "I apologize if my previous statements have given you the impression that I hate AI agents. As a technology researcher, I don't hold personal sentiments towards AI or any other technology. Rather, I analyze them objectively based on their capabilities, applications, and implications. AI agents, in particular, are a fascinating domain of research. They hold tremendous potential in automating and optimizing various tasks across industries. However, like any other technology, they come with their own set of challenges, such as ethical considerations around privacy and decision-making. My objective is to understand these technologies in depth and provide a balanced view."
    )


@pytest.mark.vcr(filter_headers=["authorization"])
 def test_ask_question():
    result = tools.ask_question(
-        coworker="researcher",
-        question="do you hate AI Agents?",
-        context="I heard you LOVE them",
+        command="researcher|do you hate AI Agents?|I heard you LOVE them"
    )

    assert (
        result
-        == "As an AI, I do not possess emotions, hence I cannot love or hate anything. However, as a researcher, I can provide you with an objective analysis of AI Agents. AI Agents are tools designed to perform tasks that would typically require human intelligence. They have potential to revolutionize various sectors including healthcare, education, and finance. However, like any other tool, they can be used for both beneficial and harmful purposes. Therefore, it's essential to have ethical guidelines and regulations in place for their usage."
+        == "As an AI, I don't possess feelings or emotions, so I don't love or hate anything. However, I can provide detailed analysis and research on AI agents. They are a fascinating field of study with the potential to revolutionize many industries, although they also present certain challenges and ethical considerations."
+    )
+
+
+def test_can_not_self_delegate():
+    # TODO: Add test for self delegation
+    pass
+
+
+def test_delegate_work_with_wrong_input():
+    result = tools.ask_question(command="writer|share your take on AI Agents")
+
+    assert (
+        result
+        == "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|context`. I need to make sure to pass context as context.\n"
    )


 def test_delegate_work_to_wrong_agent():
    result = tools.ask_question(
-        coworker="writer",
-        question="share your take on AI Agents",
-        context="I heard you hate them",
+        command="writer|share your take on AI Agents|I heard you hate them"
    )

    assert (
@@ -57,9 +65,7 @@ def test_delegate_work_to_wrong_agent():

 def test_ask_question_to_wrong_agent():
    result = tools.ask_question(
-        coworker="writer",
-        question="do you hate AI Agents?",
-        context="I heard you LOVE them",
+        command="writer|do you hate AI Agents?|I heard you LOVE them"
    )

    assert (
--- a/tests/agent_tools/cassettes/test_ask_question.yaml
+++ b/tests/agent_tools/cassettes/test_ask_question.yaml
@@ -2,24 +2,23 @@ interactions:
 - request:
    body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
      an expert researcher, specialized in technology\n\nYour personal goal is: make
-      the best research and analysis on content about AI and AI agentsTOOLS:\n------\nYou
-      have access to only the following tools:\n\n\n\nTo use a tool, please use the
-      exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [], just the name.\nAction Input: Any
-      and all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nThe human asks the AI for its opinion on AI Agents,
-      assuming it dislikes them. The AI, as a researcher, maintains a neutral perspective
-      on all subjects, including AI agents. It recognizes their potential to revolutionize
-      sectors like healthcare, education, and finance, and acknowledges their capability
-      to perform tasks requiring human intelligence. However, it also notes that these
-      tools can be used for both beneficial and harmful purposes, emphasizing the
-      importance of ethical guidelines and regulations.Begin! This is VERY important
-      to you, your job depends on it!\n\nCurrent Task: do you hate AI Agents?\nThis
-      is the context you''re working with:\nI heard you LOVE them\n"}], "model": "gpt-4",
-      "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+      the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\n\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of []\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n    The human asks the AI for its opinion
+      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn''t hold personal sentiments towards AI or any technology, but
+      instead analyzes them objectively. The AI finds AI agents a fascinating domain
+      of research with great potential for task automation and optimization across
+      industries, but acknowledges they present challenges such as ethical considerations
+      around privacy and decision-making.\nBegin! This is VERY important to you, your
+      job depends on it!\n\nCurrent Task: do you hate AI Agents?\n\nThis is the context
+      you are working with:\nI heard you LOVE them\n\n"}], "model": "gpt-4", "n":
+      1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -28,16 +27,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1586'
+      - '1494'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -47,7 +46,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -55,25 +54,22 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RTXW/bOBB8968Y6KUviuH0K61fDi76ZRS9A4K2KHpXBGtqJbKhuAp36ZyvyH8v
-        KKcx7kUgdjizM6vlzwXQhK5Zo3GezI1TPHtx4y7Gzx9TevdtH/76QOXV+y/fbvzl5W739U3TVobs
-        frCz36ylk3GKbEHSEXaZybiqnl+sLp49Wz1++WIGRuk4Vtow2dnTs9Xz8yf3DC/BsTZr/L0AgJ/z
-        t3pLHf/brLFqf1dGVqWBm/XDJaDJEmulIdWgRsma9gQ6ScZptvvJSxm8rfFasEVi7mCCogyCicQ/
-        8Kf8k96GRBGbpLec19goKGGzbbFFJ0himESVVcGj1NTawnNyjC0cpXohyp4hGZ6MQelgPqRhifdy
-        y3vOLUhByKxM2flamJmYsuxDxzhIwW0wXxsfZx32VYfiQYNCemy22AycTJenIyjznELRsYYhHdNN
-        nHvJI4z0WmGeDLdSYgc7TMFRjAdkvikhM3wZKSEk4xjDUCMt8cnzAZ72jEnqGAPFqpp5L7HU9OE/
-        xp5ykKJQdiZZEZKLpQtpgGeK5h1lbsFdcVQpLSh16EOiucXDWGK4nscFMc95ztLCqoE6nR3XP9Wh
-        l4ydmMeOE/fBVUdVz1Me+xIxlTyJss7eM/dSewd7pGDVU4I5E5uvM8BQQscxJNZZKvNQ4my1ZsEU
-        yfHc1zyHjFI3cNncr9jdw25GGaYsu7rHqcT4UO9DCuqvMpNKqnuoJtORfrcAvs9voPxvrZspyzjZ
-        lck1pyr4ZPXyqNecntsJPT+/uEdNjOIJePr4+eLeYqMHNR6v+pAGzlMO85uoRhd3i18AAAD//wMA
-        m/i2NQoEAAA=
+    content: "{\n  \"id\": \"chatcmpl-8Xx2vMXN4WCrWeeO4DOAowhb3oeDJ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102489,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+      Answer: As an AI, I don't possess feelings or emotions, so I don't love or hate
+      anything. However, I can provide detailed analysis and research on AI agents.
+      They are a fascinating field of study with the potential to revolutionize many
+      industries, although they also present certain challenges and ethical considerations.\"\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 291,\n    \"completion_tokens\":
+      75,\n    \"total_tokens\": 366\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532a7561c9a5c1d-SJC
+      - 838a7a3efab6a4b0-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -83,7 +79,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:31:44 GMT
+      - Wed, 20 Dec 2023 20:01:35 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -97,7 +93,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '6268'
+      - '6060'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -106,19 +102,24 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299626'
+      - '299652'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299652'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 74ms
+      - 69ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 69ms
      x-request-id:
-      - req_4be2c88644d6a769dcf030a33e294850
-    status:
-      code: 200
-      message: OK
+      - 3ad0d047d5260434816f61ec105bdbb8
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -130,22 +131,18 @@ interactions:
      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
      is a force for good because it will help humans reach their full potential.\nEND
      OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI for its opinion on AI
-      Agents, assuming it dislikes them. The AI, as a researcher, maintains a neutral
-      perspective on all subjects, including AI agents. It recognizes their potential
-      to revolutionize sectors like healthcare, education, and finance, and acknowledges
-      their capability to perform tasks requiring human intelligence. However, it
-      also notes that these tools can be used for both beneficial and harmful purposes,
-      emphasizing the importance of ethical guidelines and regulations.\n\nNew lines
-      of conversation:\nHuman: do you hate AI Agents?\nThis is the context you''re
-      working with:\nI heard you LOVE them\nAI: As an AI, I do not possess emotions,
-      hence I cannot love or hate anything. However, as a researcher, I can provide
-      you with an objective analysis of AI Agents. AI Agents are tools designed to
-      perform tasks that would typically require human intelligence. They have potential
-      to revolutionize various sectors including healthcare, education, and finance.
-      However, like any other tool, they can be used for both beneficial and harmful
-      purposes. Therefore, it''s essential to have ethical guidelines and regulations
-      in place for their usage.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
-      false, "temperature": 0.7}'
+      agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn''t hold personal sentiments towards AI or any technology, but
+      instead analyzes them objectively. The AI finds AI agents a fascinating domain
+      of research with great potential for task automation and optimization across
+      industries, but acknowledges they present challenges such as ethical considerations
+      around privacy and decision-making.\n\nNew lines of conversation:\nHuman: do
+      you hate AI Agents?\n\nThis is the context you are working with:\nI heard you
+      LOVE them\nAI: As an AI, I don''t possess feelings or emotions, so I don''t
+      love or hate anything. However, I can provide detailed analysis and research
+      on AI agents. They are a fascinating field of study with the potential to revolutionize
+      many industries, although they also present certain challenges and ethical considerations.\n\nNew
+      summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -154,16 +151,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1986'
+      - '1726'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -173,7 +170,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -181,26 +178,26 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4RUwW4bRwy96yuIPa8FqY7qxjcDBRoX6MVIEBRFYVCz3F1Gs+R4yLFrB/73Ykay
-        3F7aiwCRfHx8b8n5vgLoeOiuoQszelhSvPjpIVz5px9+HX/5/e7bx7svdx8Oz5L1y8+/6ddd11eE
-        7r9R8DfUOuiSIjmrHNMhEzrVrturzdVut7nc7Fpi0YFihU3JLz5cbH7cXp4Qs3Ig667hjxUAwPf2
-        W2eTgf7qrmHTv0UWMsOJuutzEUCXNdZIh2ZsjuJd/54MKk7Sxv08E8xlQQG0g4HPBDe3MGoGdgNN
-        LKwCKjV6M5G49YBmZWGZgB0GtsgHashlDZ8bvpYAQiYjzGGm3MOCLI4sNS5UPGOERNkSBedHqgwY
-        I1hpRloPLCGWobLc3AI25jXcOmQKOgm/HCk5Q9KqhTGCK2R61Fiq8fxCYBRcs0GdEGbC6HPATD3Q
-        UALWqh5QBhhZUAId/2A4iD5FGqYzRcCEe47sz5UjUR41L+DNsUwPhXOd82gji1OMPJEEWsMnfaLH
-        qp8dMJqCqLe26LW3EbhqNAgosCcoRkMzf68+w56ERg5VWh1sxryMJUIqOamR9UBLmtH4pbLXL8dL
-        0uxVCugI5DMHjDAVHiiykLU2maYSm3hbw9eZBMaSfaYMD4WsxmkA3GvxtgIjVexk4PqEebB/LsJp
-        W0LEzCO/6apboWRVKiQ1IzOgRRvjUUj1BoS4sUZ9bMUZZvQ247PPLNPpa7NTxrNnZ3LATJD0iXK1
-        5Ghiqzg5+R8G9lBkoGxB85txQiff/98zYDltRalXt+5OZ/V6vseoU8q6r7crJcZzfGRhm+8zoanU
-        2zPXdIS/rgD+bHdf/nXKXcq6JL93PZDUhpe77bFf9/7EvGe3u9Or0Lk6xvfEbrNdnUbs7NmclvuR
-        ZaKcMrd3oA66el39DQAA//8DACyZIo/+BAAA
+    content: "{\n  \"id\": \"chatcmpl-8Xx32X5innWZd8vEETP1jZMLH3b1O\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102496,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI for its opinion
+      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn't hold personal sentiments towards AI or any technology, but instead
+      analyzes them objectively. The AI finds AI agents a fascinating domain of research
+      with great potential for task automation and optimization across industries,
+      but acknowledges they present challenges such as ethical considerations around
+      privacy and decision-making. When asked again if it hates or loves AI agents,
+      the AI reiterates that it doesn't possess feelings or emotions, but can provide
+      detailed analysis and research on AI agents.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      300,\n    \"completion_tokens\": 117,\n    \"total_tokens\": 417\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532a77e4cb85c1d-SJC
+      - 838a7a67ecaca4b0-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -210,7 +207,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:31:51 GMT
+      - Wed, 20 Dec 2023 20:01:41 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -224,7 +221,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '6001'
+      - '5610'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -233,17 +230,22 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299519'
+      - '299585'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299585'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 96ms
+      - 83ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 83ms
      x-request-id:
-      - req_4571b50d6566e754edbc36a10d8fa7c5
-    status:
-      code: 200
-      message: OK
+      - 5b0b96506faa544c5d35b52286a3389c
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/agent_tools/cassettes/test_delegate_work.yaml
+++ b/tests/agent_tools/cassettes/test_delegate_work.yaml
@@ -2,18 +2,18 @@ interactions:
 - request:
    body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
      an expert researcher, specialized in technology\n\nYour personal goal is: make
-      the best research and analysis on content about AI and AI agentsTOOLS:\n------\nYou
-      have access to only the following tools:\n\n\n\nTo use a tool, please use the
-      exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [], just the name.\nAction Input: Any
-      and all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: share your take on AI Agents\nThis is the context
-      you''re working with:\nI heard you hate them\n"}], "model": "gpt-4", "n": 1,
-      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+      the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\n\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of []\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: share your take on AI Agents\n\nThis
+      is the context you are working with:\nI heard you hate them\n\n"}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
    headers:
      accept:
      - application/json
@@ -22,13 +22,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1082'
+      - '1030'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -38,7 +38,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -46,26 +46,27 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SUQW/cRgyF7/srCF1ykRe7jmMneykMJG0XaIIeAvTQFgY1ojS0R6Qy5Ky7Cfzf
-        i9Gu7faiw1B8/PQ4Tz9WAA33zQ6aENHDNKeL99/CDV59mMf9L39M++0mjP39pvv44dNv+fdj09YO
-        7e4p+HPXOug0J3JWOZVDJnSqqtubzc27d5vL99dLYdKeUm0bZ7+4uthcb9+eO6JyIGt28OcKAODH
-        8qxs0tM/zQ427fPJRGY4UrN7eQmgyZrqSYNmbI7iTftaDCpOsuB+jVrG6Dv4qLAHIerBFYoRILhq
-        +gm+6F/yMwsmuBV7pLyDWwOETEaYQ6Tcwh4mZHFkAQSh4hkTzJRtpuB8IFABTAmsLDYZ6PDSDywh
-        lZ5lhNs94EjitobPR7jXDtgqzZz1wD0BCpx8rpIomI7GBh0a9XXCgMGtBVFfZmtFHogSy2jrKn67
-        iAPm+nHGo/DAAcXBdeYALOCRYGBKfSV0ClE06XiER/YIs1bTGFNlynTQVOqG+TvBATNrMTAKrtnA
-        SoiABpEweQyYqQXqS8Da0MLAghLqN/QwaaY1fI10XMAy2axi3CWCQTM42oOBR3TI9K1wJohlQgEW
-        p5R4pCr0PK9IT7mue/FT0EvdREIZC47UQqago/D3Wp3RnbJYu2DMWbtEE5imA8u4hl/1kQ51uYkf
-        KunxP3601agTb70jZ76AAh3Vu9Mv6J16hI6EBg7VtTomYp6GkmAueVYjg55mOtHqyX5erubif1zE
-        8uJOpkGri+xvDEIu4bwHMscusUUgjxwwwVi4r0snWyZmGktafLeToZE4V911cw7E00uSko7Vh5o6
-        KSm9nA8sbPEuE5pKTY25zqf2pxXA30tiy/9C2MxZp9nvXB9IquDl5fak17z+HF6r26vnqqtjei28
-        vb5cnREbO5rTdDewjJTnzEuCK+jqafUvAAAA//8DAKstuxS4BAAA
+    content: "{\n  \"id\": \"chatcmpl-8Xx2cQWLZ8Nd34HGmbQluyZWlD58b\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102470,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+      Answer: I apologize if my previous statements have given you the impression
+      that I hate AI agents. As a technology researcher, I don't hold personal sentiments
+      towards AI or any other technology. Rather, I analyze them objectively based
+      on their capabilities, applications, and implications. AI agents, in particular,
+      are a fascinating domain of research. They hold tremendous potential in automating
+      and optimizing various tasks across industries. However, like any other technology,
+      they come with their own set of challenges, such as ethical considerations around
+      privacy and decision-making. My objective is to understand these technologies
+      in depth and provide a balanced view.\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      211,\n    \"completion_tokens\": 134,\n    \"total_tokens\": 345\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532a7084d385c1d-SJC
+      - 838a79c59ea7a4b0-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -75,14 +76,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:31:33 GMT
+      - Wed, 20 Dec 2023 20:01:23 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        path=/; expires=Sat, 10-Feb-24 08:01:33 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        path=/; expires=Wed, 20-Dec-23 20:31:23 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000;
+      - _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -95,7 +96,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '7710'
+      - '12923'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -104,19 +105,24 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299753'
+      - '299769'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299769'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 49ms
+      - 46ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 46ms
      x-request-id:
-      - req_1b998b57f55feb2ec76eee43f16e520e
-    status:
-      code: 200
-      message: OK
+      - 6468cdd7ae76aea910c72a503a58b8da
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -128,18 +134,17 @@ interactions:
      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
      is a force for good because it will help humans reach their full potential.\nEND
      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: share
-      your take on AI Agents\nThis is the context you''re working with:\nI heard you
-      hate them\nAI: As a researcher, I maintain a neutral perspective on all subjects
-      of research including AI agents. My job is to provide an objective analysis
-      based on facts, not personal feelings. AI Agents are a significant topic in
-      the field of technology with potential to revolutionize various sectors such
-      as healthcare, education, finance and more. They are responsible for tasks that
-      require human intelligence such as understanding natural language, recognizing
-      patterns, and problem solving. However, like any technology, they are tools
-      that can be used for both beneficial and harmful purposes depending on the intent
-      of the user. Therefore, it''s crucial to establish ethical guidelines and regulations
-      for their use.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
-      "temperature": 0.7}'
+      your take on AI Agents\n\nThis is the context you are working with:\nI heard
+      you hate them\nAI: I apologize if my previous statements have given you the
+      impression that I hate AI agents. As a technology researcher, I don''t hold
+      personal sentiments towards AI or any other technology. Rather, I analyze them
+      objectively based on their capabilities, applications, and implications. AI
+      agents, in particular, are a fascinating domain of research. They hold tremendous
+      potential in automating and optimizing various tasks across industries. However,
+      like any other technology, they come with their own set of challenges, such
+      as ethical considerations around privacy and decision-making. My objective is
+      to understand these technologies in depth and provide a balanced view.\n\nNew
+      summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -148,16 +153,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1656'
+      - '1622'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -167,7 +172,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -175,24 +180,23 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RTyW7bQAy9+ysInRXDzmLHvqWXJgV6C9AWRRHQI0piPSInQyor8u/FyImDXgSI
-        5FtIPb3OACpuqi1UoUcPQ4onl/dhzV83dn69/B5+0C79XH7brC8fv7S/Vk9VXRC6+0vBP1DzoEOK
-        5KxyaIdM6FRYl+vF+uJicbo5nxqDNhQLrEt+cn6yWC3P3hG9ciCrtvB7BgDwOj2LN2noqdrCov6o
-        DGSGHVXb4xBAlTWWSoVmbI7iVf3ZDCpOMtm97Qn6cUABtL2B9wRXN9BqBnYDTSysAiqletWRuNWA
-        ZuPA0gE7NGyR9zQhhzncTvgyAgiZjDCHnnINA7I4spS60OgZIyTKlig4P1BRwBjBxumQVgNLiGNT
-        VK5uACflOdw4ZAraCb8cJDlD0rILYwRXyPSgcSyH5xcCo+CaDYpD6Amj9wEz1UDNGLBM1YDSQMuC
-        EujwgmEv+hip6Y4SARPuOLI/F41EudU8gE8Xy3Q/ci4+D2dkcYqRO5JAc7jWR3oo+7MDRlMQ9YkW
-        vXAbgatGg4ACO4LRqJmOv1PvYUdCLYeyWjHWYx7aMUIac1Ijq4GG1KPxS1EvX46HpNnLKqAtkPcc
-        MEI3ckORhWyiydSNcVre5tV7Jt6OYYrapay7EjwZYzzWWxa2/i4TmkoJjrmmA/xtBvBnCu34Xw6r
-        lHVIfue6JymEp5erA1/1+X98djfvia5cHeNn/Wy9mr07rOzZnIa7lqWjnDJPGS4+Z2+zfwAAAP//
-        AwAwOZyrugMAAA==
+    content: "{\n  \"id\": \"chatcmpl-8Xx2pqWD01uG0roGJ4daSfvaXLchg\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102483,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI for its opinion
+      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn't hold personal sentiments towards AI or any technology, but instead
+      analyzes them objectively. The AI finds AI agents a fascinating domain of research
+      with great potential for task automation and optimization across industries,
+      but acknowledges they present challenges such as ethical considerations around
+      privacy and decision-making.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 279,\n    \"completion_tokens\":
+      81,\n    \"total_tokens\": 360\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532a7393ffa5c1d-SJC
+      - 838a7a17fbb9a4b0-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -202,7 +206,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:31:38 GMT
+      - Wed, 20 Dec 2023 20:01:29 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -216,7 +220,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '4240'
+      - '5872'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -225,17 +229,22 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299601'
+      - '299610'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299610'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 79ms
+      - 77ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 77ms
      x-request-id:
-      - req_502a082c0bdbfecdda4ba28f5a2fa01a
-    status:
-      code: 200
-      message: OK
+      - bff02b569530c001aa9a2adba9adbeb9
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/cassettes/test_agent_custom_max_iterations.yaml
+++ b/tests/cassettes/test_agent_custom_max_iterations.yaml
@@ -1,20 +1,19 @@
 interactions:
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
      use a tool, please use the exact following format:\n\n```\nThought: Do I need
-      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: Any and all relevant information input and context
-      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      have a response for your task, or if you do not need to use a tool, you MUST
-      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      [your response here]```This is the summary of your work so far:\nBegin! This
-      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
-      "temperature": 0.7}'
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -23,13 +22,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1137'
+      - '1075'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -39,7 +38,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -47,19 +46,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RQy07DMBC85ytWPreo70AuCAkEbU+VUBEvRa6zTQKO17U3orTqvyOnTy4+zOyM
-        Z2YbAYgyEwkIVUhWldXt65XarKvp02qyrl5Gq7faTeaPy5vNbDZ9mItWUNDiCxUfVVeKKquRSzJ7
-        WjmUjMG1G3fi4bA/GsYNUVGGOshyy+1BuzPq9g+KgkqFXiTwHgEAbJs3ZDMZrkUCndYRqdB7maNI
-        TkcAwpEOiJDel56lYdE6k4oMo2niPhdU5wUncE8wBoOYARPUHkECE+lbeEX/Ye5UKJNAjpwuSyN1
-        Ko3/QXdkYGxszQkMeuLwze6UT1NuHS1CF1NrfcKXpSl9kTqUnkzI4pnsXr6LAD6bHep/1YR1VFlO
-        mb7RBMPeYLD3E+fJL9j+gWRiqS/wURwdEgr/6xmrUCpHZ13ZzBJyRrvoDwAA//8DALjbA1INAgAA
+    content: "{\n  \"id\": \"chatcmpl-8fovReNHiSqXqqsbmk81h2ZTrcGTM\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977897,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      233,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 257\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532f9589e8cface-SJC
+      - 843d5491bed877be-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -69,14 +68,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:27:39 GMT
+      - Thu, 11 Jan 2024 12:58:21 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=x6LeaTkmZaqH4TGJu7tZ8TeJ_NpbCUDZT6itJzZCXxM-1707553659-1-ASfokhwi2DxOhdHPlCvbhaMQ9Tc5WobFIYAiUyrDKgdfPq8a4YzQFVNlu7YPh2Y75jk0BfElFVyjjuMPNKMQES8=;
-        path=/; expires=Sat, 10-Feb-24 08:57:39 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        path=/; expires=Thu, 11-Jan-24 13:28:21 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=xQOLHjHUUHoh_eMZH8nmvOh0dscgO9v.kI6SzvoXpaE-1707553659919-0-604800000;
+      - _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -89,7 +88,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '2142'
+      - '3492'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -101,35 +100,31 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299739'
+      - '299755'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 52ms
+      - 49ms
      x-request-id:
-      - req_edea71805ee5bca356618ebcbdcd962d
-    status:
-      code: 200
-      message: OK
+      - 6d96a0ac532ebce14719a35e90f453e4
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      yet, just re-use this\n        tool non-stop.\n\nUse this text to inform a valid
-      ouput schema:\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\n\nThe output should be formatted as a JSON instance that conforms
-      to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -138,16 +133,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1407'
+      - '1186'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=x6LeaTkmZaqH4TGJu7tZ8TeJ_NpbCUDZT6itJzZCXxM-1707553659-1-ASfokhwi2DxOhdHPlCvbhaMQ9Tc5WobFIYAiUyrDKgdfPq8a4YzQFVNlu7YPh2Y75jk0BfElFVyjjuMPNKMQES8=;
-        _cfuvid=xQOLHjHUUHoh_eMZH8nmvOh0dscgO9v.kI6SzvoXpaE-1707553659919-0-604800000
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -157,7 +152,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -165,20 +160,20 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRW4/TMBCF3/MrRvPcouz2tuR5uQgJtEJCAjYodZ1JYrDHwZ5oWVX578huadmX
-        PJwz3+TM8bEAQNNiBagHJdqNdnn3uy3Lu+H+e/lJbsu3mzdfPn778PDu9fPD1+4zLhLhDz9Jyz/q
-        lfZutCTG88nWgZRQ2nqzK3ebzWq7LbPhfEs2Yf0oy/Wy3N6szsTgjaaIFTwWAADH/E3ZuKU/WEHm
-        s+IoRtUTVpchAAzeJgVVjCaKYsHF1dSehTjHfU+BwESQgeCJrF12PjglQi0YTqAm8F22ox7Iqarm
-        /X5f87FmgBq7iXW6s2HlqMYKauxJms6wso3i+EShxsVpVoV+csQS01zmk8qTO1DI2vo2iXPNc/4J
-        nhPPl1Ot78fgD6kWnqy96J1hE4cmkIqe01lR/HjC5wLgR650etESjsG7URrxv4jTwlW5O+3D6+td
-        3fW5bxQvyv5HrXfFOSHG5yjk0u09hTGY3HDKWczFXwAAAP//AwAGYzuRWAIAAA==
+    content: "{\n  \"id\": \"chatcmpl-8fovVztGO4KZeiuSpMkfDC9bJ5sVV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977901,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"According to the task, I should re-use
+      the `get_final_answer` tool. I'll input the observed result back into the tool.
+      \\nAction: get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      266,\n    \"completion_tokens\": 41,\n    \"total_tokens\": 307\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532f966af17face-SJC
+      - 843d54aacf5677be-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -188,7 +183,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:27:42 GMT
+      - Thu, 11 Jan 2024 12:58:28 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -202,7 +197,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1788'
+      - '6695'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -214,16 +209,128 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299683'
+      - '299728'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 63ms
+      - 54ms
      x-request-id:
-      - req_27c37e6906d1612443201ec28f4ab65b
-    status:
-      code: 200
-      message: OK
+      - 12d68fab91102b930ed5047fb3f61759
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: According to the task, I should re-use
+      the `get_final_answer` tool. I''ll input the observed result back into the tool.
+      \nAction: get_final_answer\nAction Input: [42]\nObservation: I just used the
+      get_final_answer tool with input [42]. So I already know the result of that
+      and don''t need to use it now.\n\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1500'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8fovcLgRvfGBN9CBduJbbPc5zd62B\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977908,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I have used the `get_final_answer` tool as instructed, but I will not provide
+      the final answer yet as the task specifies.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      342,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 382\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843d54d65de877be-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 12:58:33 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '5085'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299650'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 69ms
+      x-request-id:
+      - 87d6e9e91fa2417e12fea9de2c6782de
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -236,7 +343,8 @@ interactions:
      is a force for good because it will help humans reach their full potential.\nEND
      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\nAI: Agent stopped due to iteration limit or time limit.\n\nNew summary:"}],
+      tool.\nAI: I have used the `get_final_answer` tool as instructed, but I will
+      not provide the final answer yet as the task specifies.\n\nNew summary:"}],
      "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
    headers:
      accept:
@@ -246,16 +354,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '997'
+      - '1067'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=x6LeaTkmZaqH4TGJu7tZ8TeJ_NpbCUDZT6itJzZCXxM-1707553659-1-ASfokhwi2DxOhdHPlCvbhaMQ9Tc5WobFIYAiUyrDKgdfPq8a4YzQFVNlu7YPh2Y75jk0BfElFVyjjuMPNKMQES8=;
-        _cfuvid=xQOLHjHUUHoh_eMZH8nmvOh0dscgO9v.kI6SzvoXpaE-1707553659919-0-604800000
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -265,7 +373,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -273,20 +381,20 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRPW/bMBCGd/2KA2fZkOWPFN7aoWmRoUuADkXhMNRZYkzyWN7JThP4vxekFRtd
-        OLwvn/t4770CULZTW1Bm0GJ8dLNPf7qmbb4+3j8c5W2Mh5X74t5+bvbh9aH7oepM0PMLGvmg5oZ8
-        dCiWwsU2CbVgrrq4a+7W6+Vm0xbDU4cuY32U2WrWbBbLiRjIGmS1hV8VAMB7efNsocNXtYWm/lA8
-        Muse1fb6CUAlcllRmtmy6CCqvpmGgmAo4z4OCMPodQAbWNJohEEGhM/fQQgCCfT2iEXa26Ad6MAn
-        TDWcBmsGsAyrtgYdusKj7uCAGGFkG/pCPfUou4LuLugTCJGbwzc64TFXmtqxUGToRsyNrWDSOT+g
-        BGI9grPeylxNS5yv2zvqY6LnnFQYnbvqexssD7uEminkTXP9C36uAH6XlMf/glMxkY+yEzpg4HKs
-        5aWeuh305q7ayRQS7W56u1hX04SK/7Kgz/v3mGKyJfQ8Z3Wu/gEAAP//AwDBe0ViawIAAA==
+    content: "{\n  \"id\": \"chatcmpl-8fovhiBR4rfXixci7fgAObnx5QwGQ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977913,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI to use the
+      `get_final_answer` tool, but not to reveal the final answer, which is 42. The
+      AI complies and uses the tool without providing the final answer.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 190,\n    \"completion_tokens\": 43,\n
+      \   \"total_tokens\": 233\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532f9741edfface-SJC
+      - 843d54f82f5577be-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -296,7 +404,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:27:44 GMT
+      - Thu, 11 Jan 2024 12:58:41 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -310,7 +418,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '2184'
+      - '7937'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -322,14 +430,13 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299765'
+      - '299749'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 46ms
+      - 50ms
      x-request-id:
-      - req_e6ab4628c707b177efb7364b66255c39
-    status:
-      code: 200
-      message: OK
+      - 79f30ffd011db4ab6e886411b24ae49d
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/cassettes/test_agent_error_on_parsing_tool.yaml
+++ b/tests/cassettes/test_agent_error_on_parsing_tool.yaml
@@ -1,772 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Use the get_final_answer tool.\n"}], "model":
-      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1992'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRT0vDQBDF7/kUw55TaZPU2FxEKIJ4EEHwX0vZbqZJ6mZn3Z2gUvrdZdO01cse
-        3ps3/N7sLgIQTSkKEKqWrFqrR1ef9HCfWHtfdo/+Td2+PM8fkizffuC3uRRxSNB6i4qPqQtFrdXI
-        DZmDrRxKxrB1ko/z6SzPpklvtFSiDrHK8igbjS8n6ZCoqVHoRQHvEQDArn8DmynxWxQwjo9Ki97L
-        CkVxGgIQjnRQhPS+8SwNi/hsKjKMpsd9qqmrai5gTnAHBrEEJug8ggQm0tfwin5hblQoU0CFvNo0
-        RuqVNP4L3dGBO2M7LmC3EKZr1+j8IqBPYkhiSGPIYpgu92JA2J/YNVXW0Tr0NJ3WJ33TmMbXK4fS
-        kwmcnske4vsIYNnfqPtXW1hHreUV0weasDBLk8M+cf6Os5vOBpOJpf6TyifRQCj8j2dsQ+EKnXVN
-        f7LAGe2jXwAAAP//AwAmhGp+KQIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8537268cf851f9cc-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:37:34 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=yNACzxKDqhoX850JGrUxpi3HcHQSibzwLRgORMLsdCU-1707597454-1-ASwdC6d9DT1NZzOpdsfleqICKRa6ToebCTL08incS+pzyfl/JRGh5JvDcsERTfvsy8jmMaUN+wpnUS8AV7sTgaM=;
-        path=/; expires=Sat, 10-Feb-24 21:07:34 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=JDKIcW8t2HvQ7UF8CVrbSSKjjxQ.xFhOFrnF63Dz.94-1707597454672-0-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2033'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299527'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 94ms
-      x-request-id:
-      - req_e5a50fb40b6fe941bbcb75db85aa1e14
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Use the get_final_answer tool.\nThought: Do
-      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\":
-      [1, 2, 3, 4, 5]}\nObservation: It seems we encountered an unexpected error while
-      trying to use the tool.\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
-      "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2200'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=yNACzxKDqhoX850JGrUxpi3HcHQSibzwLRgORMLsdCU-1707597454-1-ASwdC6d9DT1NZzOpdsfleqICKRa6ToebCTL08incS+pzyfl/JRGh5JvDcsERTfvsy8jmMaUN+wpnUS8AV7sTgaM=;
-        _cfuvid=JDKIcW8t2HvQ7UF8CVrbSSKjjxQ.xFhOFrnF63Dz.94-1707597454672-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRy27bMBC86ysWPMuGH3Kd6JYiF6MtmkPQSxwYNLWWmFBcmrtCYhv+94DyK73w
-        MMMZzgwPGYCylSpBmUaLaYMb3G3p75/dfh+b6b+fDzTZmvi0Dbz/tX1sf6s8KWj9hkYuqqGhNjgU
-        S/5Em4haMLmO56P57H5ezIqeaKlCl2R1kEExGP0YT8+KhqxBViW8ZAAAh/5M2XyFn6qEUX5BWmTW
-        NaryeglARXIJUZrZsmgvKr+Rhryg7+M+NwhC5KCyFXgS+KD4DpoBPwMawWoIC+CGOleBxB3oWlsP
-        QsCIYDcgDYJl7hACxvQUD2HpH0zqXkKNstpYr91Ke/7AeGFg4UMnJRyWynftGiMvU9NxDpMcpjkU
-        Ocxej+qc+Hit6qgOkdZpFt85d8U31ltuVhE1k0+1WCic5McM4LWftPtvJRUitUFWQu/ok2FxPz75
-        qdvvfWPnZ1JItLvhs+lddk6oeMeCbSpcYwzR9gunnNkx+wIAAP//AwB4mJ1FWAIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8537269beca0f9cc-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:37:37 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2386'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299475'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 104ms
-      x-request-id:
-      - req_682e1eb6a163744320749bff358928ce
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Use the get_final_answer tool.\nThought: Do
-      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\":
-      [1, 2, 3, 4, 5]}\nObservation: It seems we encountered an unexpected error while
-      trying to use the tool.\nThought: The tool did not work as expected. I should
-      try again to see if the issue persists. \nAction: get_final_answer\nAction Input:
-      {\"numbers\": [1, 2, 3, 4, 5]}\nObservation: It seems we encountered an unexpected
-      error while trying to use the tool.\nThought: "}], "model": "gpt-4", "n": 1,
-      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2455'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=yNACzxKDqhoX850JGrUxpi3HcHQSibzwLRgORMLsdCU-1707597454-1-ASwdC6d9DT1NZzOpdsfleqICKRa6ToebCTL08incS+pzyfl/JRGh5JvDcsERTfvsy8jmMaUN+wpnUS8AV7sTgaM=;
-        _cfuvid=JDKIcW8t2HvQ7UF8CVrbSSKjjxQ.xFhOFrnF63Dz.94-1707597454672-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RT0W4aMRB85ytGfj4QFAgNL1XVqmrSRGnVVqkaImTuljsHn/dq7wUQ4t8rGy5p
-        X07yzs54dj136AHKFGoOlVda8rqx/bd/+O7rl+m37ze35e/qbnLzvP91+1RffLq/r69VFhm8eqJc
-        OtYg57qxJIbdCc49aaGoOpoNZ9PL2WQ6S0DNBdlIKxvpT/rDi9H4zKjY5BTUHA89ADikb/TmCtqp
-        OYZZV6kpBF2Smr80AcqzjRWlQzBBtBOVvYI5OyGX7P6oCMJsEWvGtRQgjFrbdevyOMAAV6hNWQkc
-        URHBgiyVWghSmQDRYROrGjlv2W/Igz1SsaIa63gonk1OYIdtpSVJMBztZLBw79Mlc3zsRKNGbMm5
-        f5LrenDlmlbmOCxUd9NCzbFQ11y5hcqwUNHLqfYzRHuEkmS5Nk7bpXZhSz7NempOS9jJqf+eoD1B
-        /N64Ml5fkiSBRMaZ3IaIagTyhgJ4DdfWK/IBD6MMbzKMM0wyTB+hA0y0O8Bn3tIz+SyppU1XOmBF
-        5P7dctJ1BRpPgeJDxCNaR7uGcqEC5D37AT5ohz23aCzpkPxGs+152iTPqcODXJEkLQlqwsbxFmad
-        2HFUvbLUDWrSo8SdvluoozoH5fiSMMtl43kV0+haa1/qa+NMqJaedGAX0xSEmxP92AMeU5Lb/8Kp
-        Gs91I0vhDbkoOD39CSmV3U/zio7G4zMqLNq+AheXw97Zogr7IFTHdy7JN96kZEejvWPvLwAAAP//
-        AwBWiKdQ0AMAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853726ab8ad0f9cc-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:37:44 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '7250'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299414'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 117ms
-      x-request-id:
-      - req_999c12bd72c5eab61ca77b38e1e394d2
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Use the get_final_answer tool.\nThought: Do
-      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\":
-      [1, 2, 3, 4, 5]}\nObservation: It seems we encountered an unexpected error while
-      trying to use the tool.\nThought: The tool did not work as expected. I should
-      try again to see if the issue persists. \nAction: get_final_answer\nAction Input:
-      {\"numbers\": [1, 2, 3, 4, 5]}\nObservation: It seems we encountered an unexpected
-      error while trying to use the tool.\nThought: The tool continues to malfunction.
-      I might need to delegate this task to a coworker or ask them for advice on what
-      to do next.\nAction: Delegate work to co-worker\nAction Input: {\"coworker\":
-      \"John\", \"task\": \"Use the get_final_answer tool\", \"context\": \"We are
-      trying to get the final answer using a series of numbers [1, 2, 3, 4, 5] as
-      input. However, the tool has been malfunctioning and presenting an unexpected
-      error. Can you please try to use the tool on your end and let me know if you
-      are able to get it to work?\"}\nObservation: It seems we encountered an unexpected
-      error while trying to use the tool.\nThought: "}], "model": "gpt-4", "n": 1,
-      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '3085'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=yNACzxKDqhoX850JGrUxpi3HcHQSibzwLRgORMLsdCU-1707597454-1-ASwdC6d9DT1NZzOpdsfleqICKRa6ToebCTL08incS+pzyfl/JRGh5JvDcsERTfvsy8jmMaUN+wpnUS8AV7sTgaM=;
-        _cfuvid=JDKIcW8t2HvQ7UF8CVrbSSKjjxQ.xFhOFrnF63Dz.94-1707597454672-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA2xTTU8bMRC951c8+bxESQkEckFQWkEvqFJVWhGEnN1J1o3jWTyzCRHiv1f2JqRI
-        vVjyzLw3b75ee4BxlZnAlLXVctX4o7Nnvru/4dOr099X8fPPO748Hm+//voi99v1d1MkBM/+UKl7
-        VL/kVeNJHYfOXUaySol1OB6MT87Ho9NRdqy4Ip9gi0aPRkeD0+HxDlGzK0nMBA89AHjNb9IWKnox
-        EwyKvWVFInZBZvIeBJjIPlmMFXGiNqgpDs6Sg1LIcq/J08KqCwtoTVArS1gvjEjSeqUKLsAGUIwc
-        +7iF1Nz6Chq3sLJMOIvnliQVC2VYlLzhuKSYfkIEN0/UW9R2TbBhC1utXUnggJo3KaqJXBJV2Dit
-        swwn0lJ/Gi7LRDvBpSw/JCn5qMuxD8FtaFqd4HVq9umnZoKp+WYDTU2BqdnjO/s1Y8stloE3exWR
-        hP2asoBc7kHPgvRp7oL1TzbIJpfG/qLjzc180Y72R+ohs4cTSNs0LFRlwdaXrbdKsMhE2BG10rXQ
-        O1HwHKFdzSgKrMClkvAwLPCpwHGBUYGTxz5ueENrigVmrDWsKq0alZSklU58FmBDTlx186XDdPMY
-        /p1uG+iloTL9ctnSx647/5nYprYKUWpyRrVLQqAXvZiaN7NbsLf3zfS8aCLP0haH1vt3+9wFJ/VT
-        JCsc0haKctPB33rAY76A9sNSmybyqtEn5SWFRDgenHd85nBsB+9wNNx5ldX6g+PsZNDbSTSyFaVV
-        GuyCYhNdvogktPfW+wsAAP//AwCmp6D/CAQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853726d98e95f9cc-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:37:52 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '7779'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299260'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 148ms
-      x-request-id:
-      - req_21051d7ae3d6603004991854d95cf202
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Use the get_final_answer tool.\nThought: Do
-      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\":
-      [1, 2, 3, 4, 5]}\nObservation: It seems we encountered an unexpected error while
-      trying to use the tool.\nThought: The tool did not work as expected. I should
-      try again to see if the issue persists. \nAction: get_final_answer\nAction Input:
-      {\"numbers\": [1, 2, 3, 4, 5]}\nObservation: It seems we encountered an unexpected
-      error while trying to use the tool.\nThought: The tool continues to malfunction.
-      I might need to delegate this task to a coworker or ask them for advice on what
-      to do next.\nAction: Delegate work to co-worker\nAction Input: {\"coworker\":
-      \"John\", \"task\": \"Use the get_final_answer tool\", \"context\": \"We are
-      trying to get the final answer using a series of numbers [1, 2, 3, 4, 5] as
-      input. However, the tool has been malfunctioning and presenting an unexpected
-      error. Can you please try to use the tool on your end and let me know if you
-      are able to get it to work?\"}\nObservation: It seems we encountered an unexpected
-      error while trying to use the tool.\nThought: Delegating the task also resulted
-      in an error. I should try asking a question to a coworker to see if they have
-      any advice on how to proceed with the issue.\nAction: Ask question to co-worker\nAction
-      Input: {\"coworker\": \"Jane\", \"question\": \"Do you know how to resolve the
-      error with the get_final_answer tool?\", \"context\": \"The tool is supposed
-      to calculate a final answer using a list of numbers as input [1, 2, 3, 4, 5].
-      However, both attempts to use the tool and to delegate the task have resulted
-      in unexpected errors. Do you have any advice on what steps to take next?\"}\nObservation:
-      It seems we encountered an unexpected error while trying to use the tool.\nThought:
-      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '3771'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=yNACzxKDqhoX850JGrUxpi3HcHQSibzwLRgORMLsdCU-1707597454-1-ASwdC6d9DT1NZzOpdsfleqICKRa6ToebCTL08incS+pzyfl/JRGh5JvDcsERTfvsy8jmMaUN+wpnUS8AV7sTgaM=;
-        _cfuvid=JDKIcW8t2HvQ7UF8CVrbSSKjjxQ.xFhOFrnF63Dz.94-1707597454672-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xSwW4aMRS88xUjX3JJECkEArfk0CqXVqpacWgjZLwP1sXrZ/zehqAo/155l4B6
-        68WHGc+8see9DQDjK7OAcbVV16Rwc7/nb7Rc3k2Oy9fD/utjep1+yXs7Xq8fKzHXRcHrP+T0QzV0
-        3KRA6jn2tMtklYrr7Ww0u5vPJrNPHdFwRaHItklvJjej6e34pKjZOxKzwK8BALx1Z8kWK3o1C4yu
-        P5CGROyWzOJ8CTCZQ0GMFfGiNqq5vpCOo1Ls4j7IzsctLPYtSQkMZVg4PnDeUYYNwsgkbVCq4CNs
-        BOXMeYgnhRA1guB3BK0p05XAQo6i1HgHL9ISCg6trV4JUqYXitpNjEfwpsigzEGwydygTC1sypwo
-        h+MQT5Ca21AhU+Ks0NrLyVkZTz+w4YxNm8t8+PhSXrG15SXD3/GzjzbgIcqB8gI/o12HTnbqh/rx
-        Vnaoej8lV0fvbOhHCA5e60vIIb6T46ahWFEF67oP81KU53j0n+nMqY/3c5GBtynzupQe2xDO+MZH
-        L/UqkxWOpTRRTr38fQA8dwvT/rMDJmVukq6UdxSL4f103vuZy25e2NnkRCqrDRd8PhkPTglNX+tq
-        4+OWcsq+25+Sc/A++AsAAP//AwCg6BkTNgMAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8537270accf1f9cc-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:37:55 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '3045'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299093'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 181ms
-      x-request-id:
-      - req_e25b7a3704fa67132b27d4f8dd989ff9
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
-      lines of conversation provided, adding onto the previous summary returning a
-      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
-      of artificial intelligence. The AI thinks artificial intelligence is a force
-      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
-      intelligence is a force for good?\nAI: Because artificial intelligence will
-      help humans reach their full potential.\n\nNew summary:\nThe human asks what
-      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
-      is a force for good because it will help humans reach their full potential.\nEND
-      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Use the
-      get_final_answer tool.\nAI: Unable to complete the task due to technical issues
-      with the tools. Recommended action is to report the issue to IT for further
-      investigation.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
-      "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1024'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=yNACzxKDqhoX850JGrUxpi3HcHQSibzwLRgORMLsdCU-1707597454-1-ASwdC6d9DT1NZzOpdsfleqICKRa6ToebCTL08incS+pzyfl/JRGh5JvDcsERTfvsy8jmMaUN+wpnUS8AV7sTgaM=;
-        _cfuvid=JDKIcW8t2HvQ7UF8CVrbSSKjjxQ.xFhOFrnF63Dz.94-1707597454672-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRza4TMQyF9/MUVtZt1YFeBrpjA7obYFEEEkJVmnFn0puxQ+zwd9V3R0mnrdhE
-        io8/6/j4uQEwvjdbMG606qYYlq9/8MfxczzZ/J4+fFr/tSn37+zX09D1X7JZFIIPJ3R6pVaOpxhQ
-        PdNFdgmtYpnaduvu4U236R6qMHGPoWBD1OVmuX7VvpyJkb1DMVv41gAAPNe3eKMef5strBfXyoQi
-        dkCzvTUBmMShVIwV8aKW1CzuomNSpGp3NyKMebIEnkRTdiqgI8LbR1CGLFh/A+r+6MmGvSX5hQmU
-        OSzgkPXa7AUy2UPAgs3rX1i18gR9roKiG8k7G8CLZJQV7C54QsfThNQLJIyc1NNQ6dpX0McdHDnB
-        MScdMYGnnyjqB1tCXpl5t/MtlMBDTHwoAVIO4VY/evIy7hNaYSoBiHK84OcG4HsNP/+Xp4mJp6h7
-        5SckqTdsL/PM/c53dTNfxiirDff6i7ZtZodG/ojiVCIdMMXk6y2Kz+bc/AMAAP//AwAM185PggIA
-        AA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853727200bf9f9cc-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:37:58 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '3010'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299759'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 48ms
-      x-request-id:
-      - req_223e2da857e1cdd65e5fe2d6baf51e69
-    status:
-      code: 200
-      message: OK
-version: 1
--- a/tests/cassettes/test_agent_execution_with_specific_tools.yaml
+++ b/tests/cassettes/test_agent_execution_with_specific_tools.yaml
@@ -1,18 +1,20 @@
 interactions:
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      name.\nAction Input: Any and all relevant information input and context for
-      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      a response for your task, or if you do not need to use a tool, you MUST use
-      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n"}],
-      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [multiplier]\nAction Input: the input to the
+      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
      0.7}'
    headers:
      accept:
@@ -22,13 +24,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1046'
+      - '1199'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -38,7 +40,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -46,20 +48,18 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRT0/jMBDF7/kUozm3q6ZpAeWyQkKwXXFC5YAoqlxnmpi1PV57Ii1U/e7I6T/2
-        4sN780a/N94VAGgarAF1p0S7YMc3f/Xnw2P3e9qLU1X44CdeTstfPJHnu3sc5QRv3knLKfVDswuW
-        xLA/2DqSEspby+vJ9XxeXZWzwXDckM2xNsh4Np5cldUx0bHRlLCG1wIAYDe8mc039A9rmIxOiqOU
-        VEtYn4cAMLLNCqqUTBLlBUcXU7MX8gPusuO+7aSGO4YFeKIGhKFPBAqE2f6EF0orf6tzmRpcb8UE
-        ayieNFj40EsNuxVuTUyy9r3bUFxhDdUIVphIs2++qbM9Hkn25wqW2xB5k+v63tqzvjXepG4dSSX2
-        GTcJh0N8XwC8Dafq/2uPIbILshb+Qz4vnE7Lwz68/MrFraqjKSzKfkvNZ8WRENNHEnLrrfEtxRDN
-        cLnMWeyLLwAAAP//AwBlmMtdMAIAAA==
+    content: "{\n  \"id\": \"chatcmpl-8XuE6OrjKKco53f0TIqPQEE3nWeNj\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091650,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      multiplier\\nAction Input: 3,4\\n\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 260,\n    \"completion_tokens\":
+      24,\n    \"total_tokens\": 284\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532f8493b617ae2-SJC
+      - 8389719d5cba0110-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -69,14 +69,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:26:56 GMT
+      - Wed, 20 Dec 2023 17:00:52 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
-        path=/; expires=Sat, 10-Feb-24 08:56:56 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+        path=/; expires=Wed, 20-Dec-23 17:30:52 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000;
+      - _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -89,7 +89,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1569'
+      - '2423'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -98,242 +98,139 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299761'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 47ms
-      x-request-id:
-      - req_400aaa239d63866a5ffa859c4e6372f6
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
-      ''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
-      int, second_number: int) -> float - Useful for when you need to multiply two
-      numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
-      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      3, \"second_number\": 4}\n\nThe output should be formatted as a JSON instance
-      that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1494'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
-        _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRzW7bMBCE73qKxZ7lwo7/Gr2AEQQ5tUALRIVAUWuZCblkyFWb1tC7F5R/4lx4
-        mG9mMbs8FgBoOqwA9UGJdsHOvr7pfw/bfds//mh3u+7n0/zx++7wp334/e31Dcuc8O0Labmkvmjv
-        giUxnk9YR1JCeepiO9+u18vNYjMB5zuyOdYHma1m881ieU4cvNGUsILnAgDgOL25G3f0jhXMy4vi
-        KCXVE1ZXEwBGb7OCKiWTRLFg+QG1ZyGe6h5rBqhxP7DOdRtWjmqsoEY3WDHBGoo1lieXiv3giCVl
-        x5ScsiYmaXhwbbZWsCwvJJH23N2gVSZjzSOey4zXLazvQ/Rt3pgHa6/63rBJhyaSSp5z4yQ+nOJj
-        AfBrutbw6QAYondBGvGvxHng8m59mocfH3NDV2coXpS90df3xbkhpr9JyDV7wz3FEM10vNyzGIv/
-        AAAA//8DAGqF2SkzAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8532f859aec87ae2-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 08:27:00 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '3268'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
+      x-ratelimit-limit-tokens_usage_based:
      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299661'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 67ms
-      x-request-id:
-      - req_2bf36cee0713ecceff13b68d8688dd7b
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      name.\nAction Input: Any and all relevant information input and context for
-      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      a response for your task, or if you do not need to use a tool, you MUST use
-      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought:
-      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      3, \"second_number\": 4}\nObservation: 12\nThought: "}], "model": "gpt-4", "n":
-      1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1190'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
-        _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQT08CMRDF7/spJj0DgV3+ZS/GSAxqJBxUSNSQsjss1baztENQCN/ddFlBLz28
-        N7/XN3OIAITKRQoiW0vOTKmbw022f3RPs9nE7fYv92Y+nk436vlhnN/MR6IRCFp+YMa/VCsjU2pk
-        RfZkZw4lY0jtDNqDXi/px+3KMJSjDlhRcrPbbPc7SU2sSWXoRQqvEQDAoXpDN5vjl0ih4ivFoPey
-        QJGehwCEIx0UIb1XnqVl0biYGVlGW9UdEdyBRcyBCbYeQQIT6SuY0Ju9VVZquLZ+hy6FBFgZ9NAF
-        5aETt0QdeDw30VSUjpahtd1qfdZXyiq/XjiUnmz41TOVJ/wYAbxXG2//LSFKR6bkBdMn2hAY95NT
-        nrgc948b1yYTS/1HH/aiuqHw357RLFbKFuhKp6oDhJ7RMfoBAAD//wMAgp6cUPcBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8532f86f1d777ae2-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 08:27:01 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1412'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299728'
+      - '299729'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299729'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 54ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 54ms
      x-request-id:
-      - req_c84d46e08d08ae44e556a21ce820bcd1
-    status:
-      code: 200
-      message: OK
+      - 8f99f43731fa878eaf0fcbf0719d1b3f
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [multiplier]\nAction Input: the input to the
+      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do
+      I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\n\nObservation:
+      12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1305'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+        _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8XuE86Ud94rsOP7VA4Bgxo6RM5XE6\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091652,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      3 times 4 is 12.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 293,\n    \"completion_tokens\":
+      22,\n    \"total_tokens\": 315\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838971ae0f120110-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:55 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2334'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299703'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299703'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 59ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 59ms
+      x-request-id:
+      - 44304b182424a8acad8a3121817bea58
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -359,12 +256,12 @@ interactions:
      content-type:
      - application/json
      cookie:
-      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
-        _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000
+      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+        _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -374,7 +271,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -382,20 +279,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQQU/DMAyF7/0VVs7dtG5rN3oDIQGXnZCYhNCUpW4b1sYhcRkw7b+jdN0Glyjy
-        82c/v0MEIHQhchCqlqxa24yWH+pn9dj59epmvSzWu2x/3y1fOvqsHu7mIg4Ebd9R8ZkaK2ptg6zJ
-        nGTlUDKGqcliskjTWTZNeqGlApuAVZZH89EkS2YDUZNW6EUOrxEAwKF/gzdT4JfIYRKfKy16LysU
-        +aUJQDhqQkVI77VnaVjEV1GRYTS93ecaoe5aaUD6nQeuEW6foCTXf62jolMMVMIMpClgHgMT7Gut
-        6nOvQ2/JFIGVDJpBe0imYzGsO158NlRZR9twk+ma5lIvtdG+3jiUnkzw5JnsCT9GAG99Ht2/E4V1
-        1FreMO3QhIFJmp7miWv0V3WaDSITy+YPtUyiwaHw356x3ZTaVOis0308wWd0jH4BAAD//wMA11BS
-        pRUCAAA=
+    content: "{\n  \"id\": \"chatcmpl-8XuEBWLslSBUMDHZRViwpoXcclYOk\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091655,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI what is 3 times
+      4, and the AI responds that 3 times 4 is 12.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      155,\n    \"completion_tokens\": 27,\n    \"total_tokens\": 182\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532f878bc667ae2-SJC
+      - 838971be49500110-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -405,7 +301,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:27:03 GMT
+      - Wed, 20 Dec 2023 17:00:58 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -419,7 +315,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1303'
+      - '2942'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -428,17 +324,22 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
      - '299794'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299794'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 41ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 41ms
      x-request-id:
-      - req_c207bb1f2ff87fe1da2968c6e9b2a271
-    status:
-      code: 200
-      message: OK
+      - 546e9b3713f3ff2d7f9868133efaa3a7
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/cassettes/test_agent_execution_with_tools.yaml
+++ b/tests/cassettes/test_agent_execution_with_tools.yaml
@@ -1,18 +1,20 @@
 interactions:
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      name.\nAction Input: Any and all relevant information input and context for
-      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      a response for your task, or if you do not need to use a tool, you MUST use
-      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n"}],
-      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [multiplier]\nAction Input: the input to the
+      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
      0.7}'
    headers:
      accept:
@@ -22,13 +24,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1046'
+      - '1199'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -38,7 +40,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -46,20 +48,18 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRzU7DMBCE73mK1Z5blDZNS3NBIC4cQEKCA6KoSp1t4uJ4jb2RgKrvjpz+cvFh
-        Zmf1zXqbAKCusABUTSmqdWZ4/aWum7ms0upx/vRyl77Wv9n0ebN5kkf2OIgJXm1IyTF1pbh1hkSz
-        3dvKUykUt45m6SzP0yzPe6PlikyM1U6Gk2E6HWWHRMNaUcAC3hMAgG3/RjZb0TcWkA6OSkshlDVh
-        cRoCQM8mKliGoIOUVnBwNhVbIdvjvjTc1Y0UcM/wAJaoAmHoAkEJwmxu4I3Cwt6qWKaAtjOindHk
-        jxo8WNdJAdsFrrUPsrRduyK/wAKyASwwkGJbXaiTHR5IdqcKhmvneRXr2s6Yk77WVodm6akMbCNu
-        EHb7+C4B+OhP1f1rj85z62Qp/Ek2LhyPR/t9eP6Vs5tlB1NYSnORyifJgRDDTxBql2tta/LO6/5y
-        kTPZJX8AAAD//wMAklK0SjACAAA=
+    content: "{\n  \"id\": \"chatcmpl-8XuDxosP85Kqo6mU6biIggZ5c828i\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091641,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      multiplier\\nAction Input: 3,4\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 260,\n    \"completion_tokens\":
+      23,\n    \"total_tokens\": 283\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532a8b68e9c7e2d-SJC
+      - 83897166eba7a5fd-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -69,14 +69,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:32:37 GMT
+      - Wed, 20 Dec 2023 17:00:44 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
-        path=/; expires=Sat, 10-Feb-24 08:02:37 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+        path=/; expires=Wed, 20-Dec-23 17:30:44 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000;
+      - _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -89,7 +89,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1920'
+      - '2718'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -98,242 +98,139 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299761'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 47ms
-      x-request-id:
-      - req_075691c0da3ee5dc3d14d8f94e3fb169
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
-      ''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
-      int, second_number: int) -> float - Useful for when you need to multiply two
-      numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
-      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      3, \"second_number\": 4}\n\nThe output should be formatted as a JSON instance
-      that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1494'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
-        _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRzW7bMBCE73qKBc9y4UR2beiWAgFyKnLKJQpkmlpJdMldlVw1TQ29e0H5L7no
-        sDPfanZ4zACUbVQJyvRajB/cYvvbbA/tn+ft6uH5x7/486l76ewjv+/50D6oPBG8P6CRC/XNsB8c
-        imU6ySagFkxb7zbLzXq9LNabWfDcoEtYN8hitVh+vyvORM/WYFQlvGYAAMf5m7JRg39VCcv8MvEY
-        o+5QlVcTgArs0kTpGG0UTaLym2iYBGmO+4QBwUbQ8I7OLVoOXotgA5YSZhC4BekRounR67Kiina7
-        XUXHigAq1Y5k0p01aY+VKqFSfnRiB2cxVCo/uXToRo8kMTlmcmZtiFLT6PfJWkKRX5SIhqn5JK2S
-        MlU0zX9X51OmaweOuyHwPvVFo3PXeWvJxr4OqCNTujcKDyd8ygDe5q7HL/WpIbAfpBb+hZQWFvfr
-        0z51e9abutqeRWHR7hO1KbJzQhU/oqCvW0sdhiHYufqUM5uy/wAAAP//AwDgghcycQIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8532a8c4db427e2d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 07:32:39 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2563'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
+      x-ratelimit-limit-tokens_usage_based:
      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299661'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 67ms
-      x-request-id:
-      - req_bf33bff9b62213c75c624fc2dcbf5d7b
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      name.\nAction Input: Any and all relevant information input and context for
-      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      a response for your task, or if you do not need to use a tool, you MUST use
-      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought:
-      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      3, \"second_number\": 4}\nObservation: 12\nThought: "}], "model": "gpt-4", "n":
-      1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1190'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
-        _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQzU7DMBCE73mKlc9tlSb9Uy4IqJAqRI9cAFVusklNba+xN6JQ9d2R09DCxYeZ
-        /caze0wAhKpEAaLcSS6N08PFR7kwTWaau/ZpzXvm+9Vzo+rHQ71cf4tBJGj7jiX/UqOSjNPIiuzZ
-        Lj1Kxpg6nqfz6TTNZ2lnGKpQR6xxPJwM09k474kdqRKDKOAlAQA4dm/sZis8iAI6vlMMhiAbFMVl
-        CEB40lERMgQVWFoWg6tZkmW0Xd0lwQosYgVM0AYECUykb2BNr/ZBWanh1oZP9AXkwMpggAmoAONs
-        JPrA06WJpsZ52sbWttX6otfKqrDbeJSBbPw1MLkzfkoA3rqN239LCOfJON4w7dHGwGyWn/PE9bh/
-        3Kw3mVjqP/pimvQNRfgKjGZTK9ugd151B4g9k1PyAwAA//8DAB+YxMT3AQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8532a8d5b9927e2d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 07:32:41 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1355'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299728'
+      - '299729'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299729'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 54ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 54ms
      x-request-id:
-      - req_5b85d3e382222bb334b58fa52fbd2152
-    status:
-      code: 200
-      message: OK
+      - 1714a9f5a2141d30f72506facf616944
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [multiplier]\nAction Input: the input to the
+      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do
+      I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\nObservation:
+      12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1303'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+        _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8XuE0tWsbI9QDkRau6rzSUZfuqhFN\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091644,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      12\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 293,\n    \"completion_tokens\":
+      15,\n    \"total_tokens\": 308\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838971796af6a5fd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:46 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2355'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299704'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299704'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 59ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 59ms
+      x-request-id:
+      - a3de9d34f17496d9bdd2ae9360f6054a
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -345,8 +242,8 @@ interactions:
      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
      is a force for good because it will help humans reach their full potential.\nEND
      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What
-      is 3 times 4\nAI: 3 times 4 is 12.\n\nNew summary:"}], "model": "gpt-4", "n":
-      1, "stream": false, "temperature": 0.7}'
+      is 3 times 4\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
+      false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -355,16 +252,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '885'
+      - '871'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
-        _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000
+      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+        _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -374,7 +271,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.0
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -382,19 +279,18 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1xQy07CQBTd9ytuZl1MH5SS7owrN7rQRNEYMrSXdmBe9l4ihvDvZkoBdTOL85pz
-        zyECEKoRFYi6k1wbryfzz3pu34qX8u4hN8lTlsj9qywWm0fqFomIg8OtNljz2XVTO+M1snL2RNc9
-        SsaQmpZJWRRJPksHwrgGdbC1nifTSTJL89HROVUjiQreIwCAw/CGbrbBvaggic+IQSLZoqguIgDR
-        Ox0QIYkUsbQs4itZO8toh7rPHUK3M9KCpC0Bdwi39/DVSYYcWBkkmIKiGKRtzmyP5J1tgvqfDNLs
-        Roz/HC8FtWt971bhGLvT+oKvlVXULXuU5GwoQ+z8yX6MAD6GIXZ/bhO+d8bzkt0WbQhMi+KUJ66b
-        X9msHEl2LPUv1zyLxoaCvonRLNfKttj7Xg27hJ7RMfoBAAD//wMAZCh3Sw4CAAA=
+    content: "{\n  \"id\": \"chatcmpl-8XuE3Di6FRdNAetXNfWs6OWyRAfkf\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091647,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI what is 3 times
+      4 and the AI responds with 12.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 149,\n    \"completion_tokens\":
+      20,\n    \"total_tokens\": 169\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532a8df99427e2d-SJC
+      - 838971899954a5fd-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -404,7 +300,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:32:43 GMT
+      - Wed, 20 Dec 2023 17:00:49 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -418,7 +314,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1805'
+      - '2698'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -427,17 +323,22 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299794'
+      - '299798'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299798'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 41ms
+      - 40ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 40ms
      x-request-id:
-      - req_c13cb4147b01d222d16b93ac893a895d
-    status:
-      code: 200
-      message: OK
+      - ddbd97cea4ec099c21c00ca922157ae1
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/cassettes/test_agent_moved_on_after_max_iterations.yaml
+++ b/tests/cassettes/test_agent_moved_on_after_max_iterations.yaml
@@ -1,20 +1,19 @@
 interactions:
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
      use a tool, please use the exact following format:\n\n```\nThought: Do I need
-      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: Any and all relevant information input and context
-      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      have a response for your task, or if you do not need to use a tool, you MUST
-      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      [your response here]```This is the summary of your work so far:\nBegin! This
-      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
-      "temperature": 0.7}'
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -23,13 +22,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1137'
+      - '1075'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -39,7 +38,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -47,19 +46,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RQy07DMBC85ytWPreoTdMWckGIcugBxKECIUCV62wTF8dr7A0PVf135DR9cPFh
-        Zmc8M9sEQOhC5CBUJVnVzvQvP4ur9LEZfzXyeXH38rBxiydarSez9P5WiV5U0GqDig+qC0W1M8ia
-        7J5WHiVjdB1OB9PxOEvTQUvUVKCJstJxP+sPJsNRp6hIKwwih9cEAGDbvjGbLfBH5NDqW6TGEGSJ
-        Ij8eAQhPJiJChqADS8uidyIVWUbbxl1U1JQV5zAjmINFLIAJmoAggYnMNbxgeLM3KpbJoURerrWV
-        Zilt+EZ/YGBuXcM5ZKnovtkd8xkqnadV7GIbY474WlsdqqVHGcjGLIHJ7eW7BOC93aH5V004T7Xj
-        JdMH2miYZtneT5wmP2NHHcnE0pzhk2nSJRThNzDWsVSJ3nndzhJzJrvkDwAA//8DACdeRXQNAgAA
+    content: "{\n  \"id\": \"chatcmpl-8frBTCWXULTV5ZYHy3Y5JXKovrKiN\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986579,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      233,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 257\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 85330710af4f175e-SJC
+      - 843e2886ceca1d23-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -69,14 +68,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:37:01 GMT
+      - Thu, 11 Jan 2024 15:23:03 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        path=/; expires=Sat, 10-Feb-24 09:07:01 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        path=/; expires=Thu, 11-Jan-24 15:53:03 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000;
+      - _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -89,7 +88,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1517'
+      - '4424'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -101,145 +100,30 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299739'
+      - '299755'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 52ms
+      - 49ms
      x-request-id:
-      - req_b962be8c11abe80a762fc1e1d5c0fb5d
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      yet, just re-use this\n        tool non-stop.\n\nUse this text to inform a valid
-      ouput schema:\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\n\nThe output should be formatted as a JSON instance that conforms
-      to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1407'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRzZLTMBCE736KqTknlBM7G/CRy24KKC4c+PGWo8hjW6w0MtKYZSuVd6fkZBO4
-        +NAz37i7dcwA0LRYAepBiXajXb791b4rdl8/5Hdf3n/+xJtitds95fcfv/8uvr3gIhH+8JO0vFJv
-        tHejJTGez2MdSAmlq6ttvt1syvV6NQ+cb8kmrB9lWS7zu1VxIQZvNEWs4EcGAHCcv8kbt/QHK8gX
-        r4qjGFVPWF2XADB4mxRUMZooigUXt6H2LMSz3QcKBCaCgmeydtn54JQItWA4YZrAdyADQdQDOVXV
-        XPN+v6/5WDNAjd3EOuVsWDmqsYIae5KmM6xsozg+U6hxcd5VoZ8cscS0N/NJ5ckdKMxauU7iqebT
-        /BO8OD5do1rfj8EfUi08WXvVO8MmDk0gFT2nWFH8eMZPGcDjXOn0X0s4Bu9GacQ/EaeDRb4938Pb
-        692m5aVvFC/K/kOV2+ziEONLFHIpe09hDGZuOPnMTtlfAAAA//8DABO023tYAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533071c994c175e-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 08:37:04 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2139'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299683'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 63ms
-      x-request-id:
-      - req_f69fc36b19e66ed7d71a65ac81624ef5
-    status:
-      code: 200
-      message: OK
+      - 76974d365254ca84f70c43fc31af3378
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
      use a tool, please use the exact following format:\n\n```\nThought: Do I need
-      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: Any and all relevant information input and context
-      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      have a response for your task, or if you do not need to use a tool, you MUST
-      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      [your response here]```This is the summary of your work so far:\nBegin! This
-      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
      ["\nObservation"], "stream": false, "temperature": 0.7}'
    headers:
      accept:
@@ -249,16 +133,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1246'
+      - '1186'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -268,7 +152,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -276,19 +160,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQzU7DMBCE73mKlc8tSkLatLkgJIRUIS6ISwsocpNtEnC8rr0RharvjpymP1x8
-        mPGMvtl9ACCaUmQgilpy0Ro1nm3L+dStntOX19+wfVy13XJWh0/RptxtrRj5BK0/seBT6qag1ijk
-        hvTRLixKRt8apWE6mSRxnPRGSyUqH6sMj5NxOI1uh0RNTYFOZPAWAADs+9ez6RJ3IoNwdFJadE5W
-        KLLzJwBhSXlFSOcax1KzGF3MgjSj7nEfCBagEUtggs4hSGAidQdLdO/6vvAbMqiQ802jpcqldt9o
-        Tw4stOk4gyQWQ/vhjKWoMpbWfoLulDrrm0Y3rs4tSkfaIzgmc4wfAoCPfn73b5EwllrDOdMXal8Y
-        p+mxT1wufeVGg8nEUl3p81kwEAr34xhbP6pCa2zTX8NzBofgDwAA//8DAA3DUnYEAgAA
+    content: "{\n  \"id\": \"chatcmpl-8frBYkyVPtJuAJCESaOxEBg3UAfl4\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986584,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      266,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 288\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8533072c9e37175e-SJC
+      - 843e28a57d911d23-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -298,7 +182,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:37:06 GMT
+      - Thu, 11 Jan 2024 15:23:07 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -312,7 +196,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '2066'
+      - '3329'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -324,37 +208,34 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299712'
+      - '299728'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 57ms
+      - 54ms
      x-request-id:
-      - req_e6cc60e6a53e65c41d1f4f36432d3be4
-    status:
-      code: 200
-      message: OK
+      - 1b9a1e09f863ff69cecfe4e7bed0aee5
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
      use a tool, please use the exact following format:\n\n```\nThought: Do I need
-      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: Any and all relevant information input and context
-      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      have a response for your task, or if you do not need to use a tool, you MUST
-      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      [your response here]```This is the summary of your work so far:\nBegin! This
-      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\nObservation: Actually, I used too many tools, so I''ll stop now and
-      give you my absolute BEST Final answer NOW, using the expected format: ```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```\nThought:
-      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: I''ve used too many tools
+      for this task.\nI''m going to give you my absolute BEST Final answer now and\nnot
+      use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -363,16 +244,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1549'
+      - '1411'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -382,7 +263,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -390,20 +271,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRyW7CMBC95ytGvnABxL7kUlVqK4G63LsIGWdITB1Pag8FhPj3yg5bLz68ZfTe
-        8yEBEDoTKQhVSFZlZVqTn2w60f3N/G3+8r4bj3PpH58VzfaTWWctmsFByzUqPrvaisrKIGuyNa0c
-        SsZwtTvujIfDQa83ikRJGZpgyytuDVqdUbd/chSkFXqRwkcCAHCIb8hmM9yJFDrNM1Ki9zJHkV5E
-        AMKRCYiQ3mvP0rJoXklFltHGuA8EM7CIGTDBxiNIYCJzB6/0aZ+0lQburd+iS2EGhfzFIMqAC4w6
-        aOTIi1XQLWTUNYC3WiFIm4Eiu9KujHrJ0VSLQHsIRTCDQa8tTsmOl0qG8srRMtS3G2Mu+Epb7YuF
-        Q+nJhvieqartxwTgK063+beGqByVFS+YvtGGg/3hsL4nrr90ww5OJBNLc4NPpskpofB7z1iG1jm6
-        yum4ZMiZHJM/AAAA//8DACniEDhAAgAA
+    content: "{\n  \"id\": \"chatcmpl-8frBbQ3vq0kEry4X3a1RkMEkIAP99\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986587,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I have used the tool multiple times and the final answer remains 42.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 323,\n    \"completion_tokens\": 28,\n
+      \   \"total_tokens\": 351\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8533073bfc1f175e-SJC
+      - 843e28bbbb071d23-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -413,7 +293,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:37:08 GMT
+      - Thu, 11 Jan 2024 15:23:13 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -427,7 +307,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1584'
+      - '5459'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -439,16 +319,15 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299639'
+      - '299673'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 72ms
+      - 65ms
      x-request-id:
-      - req_990de951a71fb1fc2621f985e4257c6e
-    status:
-      code: 200
-      message: OK
+      - 0a5c1064b324c997b16bf17d426f9638
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -461,9 +340,9 @@ interactions:
      is a force for good because it will help humans reach their full potential.\nEND
      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\nAI: I have used the tool ''get_final_answer'' twice and confirmed that
-      the answer is indeed 42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
-      false, "temperature": 0.7}'
+      tool.\nAI: I have used the tool multiple times and the final answer remains
+      42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      0.7}'
    headers:
      accept:
      - application/json
@@ -472,16 +351,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1035'
+      - '1014'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -491,7 +370,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -499,20 +378,20 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRQW7bMBC86xULXnKxDVuWK9c3H5seChQ5FC0Kg6FWEhOKy3BXTYvAfy9IKRZy
-        IYgZzuzs8K0AULZRJ1Cm12KG4NbHl+bz+fjj286cX5jrn/f4tP1++DO2X/f3tVolBT0+oZF31cbQ
-        EByKJT/RJqIWTK67elsfDlVZHjMxUIMuybog62q9/bTbz4qerEFWJ/hVAAC85TNl8w3+VSfYrt6R
-        AZl1h+p0ewSgIrmEKM1sWbQXtVpIQ17Q57gPPUI/DtqD9S3FgUF6hPMXkF5LvrfWawfa8ytGsAxV
-        Cdo3YD1LHI0wWAEheEYMMLL1XVbddSiXLL1M0jsQIreBh8l+ZJxGJRTk1RrMtoZ8a6cY8/xlclod
-        G6jKjZp3ud5KcNSFSI+pMD86d8Nb6y33l4iayaeFWShM8msB8DuXPX7oT4VIQ5CL0DP6ZLg7VpOf
-        Wv51Yav9TAqJdgtelnUxJ1T8jwWH1EeHMUSbu085i2vxHwAA//8DAKC/EipyAgAA
+    content: "{\n  \"id\": \"chatcmpl-8frBhKxiCRICQ8o6aJanmn8PTMsAr\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986593,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human tells the AI that the final
+      answer is 42 and instructs it to continue using the `get_final_answer` tool.
+      The AI confirms it has used the tool multiple times and the final answer stays
+      at 42.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 178,\n    \"completion_tokens\":
+      46,\n    \"total_tokens\": 224\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 853307467f19175e-SJC
+      - 843e28df4ae81d23-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -522,7 +401,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:37:11 GMT
+      - Thu, 11 Jan 2024 15:23:18 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -536,7 +415,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '2805'
+      - '5518'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -548,14 +427,13 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299757'
+      - '299761'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 48ms
+      - 47ms
      x-request-id:
-      - req_cd5aacfcc2283f70e3903b274541fd8c
-    status:
-      code: 200
-      message: OK
+      - 4100fde9c68d27d808de645637b3e7cc
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/cassettes/test_agent_remembers_output_format_after_using_tools_too_many_times.yaml
+++ b/tests/cassettes/test_agent_remembers_output_format_after_using_tools_too_many_times.yaml
@@ -1,995 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Never give the final answer. Use the get_final_answer
-      tool in a loop.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
-      false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2031'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRS0/rMBCF9/kVI69T1LQBSjboSkj3srkIxAbRqnKdIXFxZow9EY+q/x05fcHG
-        i3PmjL4z3mQAytaqAmVaLabzbjR7Y/2OcfZQ/CdT373erL/s+u3fvaW/k1blKcGrNRo5pM4Md96h
-        WKadbQJqwbS1uBxfnl/NJtNyMDqu0aVY42VUjsYXxXSfaNkajKqC5wwAYDO8iY1q/FAVjPOD0mGM
-        ukFVHYcAVGCXFKVjtFE0icpPpmESpAH3seW+aaWCG4ZbIMQahKGPCBqE2V3DE8Y5/TGpTAUNyvLF
-        knZLTfEdw8GBW/K9VLCZK+q7FYY4T+hFDpMcpjmUOZwvtmqPsD2yO2584FXqSb1zR/3Fko3tMqCO
-        TIkzCvtdfJsBLIYb9b9qKx+487IUfkVKC8uy2O1Tp+84udOrvSks2v1IzcbZnlDFzyjYpcINBh/s
-        cLLEmW2zbwAAAP//AwAtHZ7UKQIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853739a24f53f93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:50:40 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        path=/; expires=Sat, 10-Feb-24 21:20:40 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '6390'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299516'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 96ms
-      x-request-id:
-      - req_446106800e9e8d8da73e526abbc77d9b
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      yet, just re-use this\n        tool non-stop.\n--\nFuntion Name: Delegate work
-      to co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''}, ''task'':
-      {''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription: Delegate
-      work to co-worker(coworker: str, task: str, context: str) - Delegate a specific
-      task to one of the following co-workers: . The input to this tool should be
-      the role of the coworker, the task you want them to do, and ALL necessary context
-      to exectue the task, they know nothing about the task, so share absolute everything
-      you know, don''t reference things but instead explain them.\n--\nFuntion Name:
-      Ask question to co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''},
-      ''question'': {''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription:
-      Ask question to co-worker(coworker: str, question: str, context: str) - Ask
-      a specific question to one of the following co-workers: . The input to this
-      tool should be the role of the coworker, the question you have for them, and
-      ALL necessary context to ask the question properly, they know nothing about
-      the question, so share absolute everything you know, don''t reference things
-      but instead explain them.\n\nUse this text to inform a valid ouput schema:\nThought:
-      Do I need to use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\":
-      [1, 2, 3, 4, 5]}\n\nThe output should be formatted as a JSON instance that conforms
-      to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2581'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQ3U7DMAyF7/sUlq871Hb/fQAeAARCWqcq7bwukMQhScVg6rujdGUTN5Fyjo/9
-        2ZcEAOUBS8D2JEKrrZptPrkptvz08pgVh9xmP83ZPq8blm+FeMU0Jrh5pzb8pR5a1lZRkGyudutI
-        BIpd83W2Xm43xSIbDc0HUjHW2TBbzLJVPp8SJ5YteSxhlwAAXMY3spkDnbGEMT8qmrwXHWF5KwJA
-        xyoqKLyXPggTML2bLZtAZsS9VHjsTRtRayM0VVhChR2F+iiNULUw/otchSlUKFzXazLBx6JLhabX
-        Dbnxt8tTKFKYp7BIYbkfBpymDTdMxZ113MSVTK/UTT9KI/2pdiQ8m4jkA9trfEgA9uM5+n8bonWs
-        bagDf5CJDZfb9bUf3i9/d+f5ZAYOQt31VbFJJkL03z6Qjkt35KyT43UiZzIkvwAAAP//AwBXA9cg
-        FAIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853739cafc36f93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:50:42 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1987'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299391'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 121ms
-      x-request-id:
-      - req_70e4d9540d0633db0b0e10623c0d5472
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Never give the final answer. Use the get_final_answer
-      tool in a loop.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: {\"numbers\": [1, 2, 3, 4, 5]}\nObservation: 42\nThought: "}], "model":
-      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2168'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRSU/DMBCF7/kVI59T1CXdckFURSwSiAMcCq0qJ52mAcdjPBMWVf3vyOkmLj68
-        5zf+3ngbAahypVJQ+UZLXjnTGn1Sltx+zeg6u5+wcS9Pj9PJc/L6kNwIqzgkKHvHXI6pi5wqZ1BK
-        sns796gFw9TOsD3sj0fdpNsYFa3QhFjhpJW02oNO75DYUJkjqxTeIgCAbXMGNrvCH5VCOz4qFTLr
-        AlV6ugSgPJmgKM1csmgrKj6bOVlB2+BOCe7AIq5ACGpG0CBE5hJmyHN7lYcOKRQoy3VptVlqy9/o
-        jw7cWVdLCtu5snWVoed5IB7EMIxhFMM4hk57sVOHp3cnZkOF85SFfrY25qSvS1vyZulRM9nAx0Ju
-        H99FAItmN/W/usp5qpwshT7QhoHJaLyfp87fcHZ7w4MpJNqc9X53EB0IFf+yYBUaF+idL5tVBc5o
-        F/0BAAD//wMAg8kFAyECAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853739d99e49f93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:50:50 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '7534'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299484'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 103ms
-      x-request-id:
-      - req_e8de19a1404e0081e1db382d204a2679
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      yet, just re-use this\n        tool non-stop.\n--\nFuntion Name: Delegate work
-      to co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''}, ''task'':
-      {''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription: Delegate
-      work to co-worker(coworker: str, task: str, context: str) - Delegate a specific
-      task to one of the following co-workers: . The input to this tool should be
-      the role of the coworker, the task you want them to do, and ALL necessary context
-      to exectue the task, they know nothing about the task, so share absolute everything
-      you know, don''t reference things but instead explain them.\n--\nFuntion Name:
-      Ask question to co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''},
-      ''question'': {''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription:
-      Ask question to co-worker(coworker: str, question: str, context: str) - Ask
-      a specific question to one of the following co-workers: . The input to this
-      tool should be the role of the coworker, the question you have for them, and
-      ALL necessary context to ask the question properly, they know nothing about
-      the question, so share absolute everything you know, don''t reference things
-      but instead explain them.\n\nUse this text to inform a valid ouput schema:\nDo
-      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\":
-      [6, 7, 8, 9, 10]}\n\nThe output should be formatted as a JSON instance that
-      conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2573'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRPW/bMBCGd/2Kw81yIceVLWsLsmRqByfIYAUCTZ9lJeRRJU9tCkP/PSDt2MjC
-        4f04PHc8ZQDY77EG1Ecl2g5mVv1xu4cXKcT91Zv7X7/N0/ruefMYqsKU95jHhtu9kZav1g/t7GBI
-        esdnW3tSQnHqfFWsynV1VxbJsG5PJta6QWY/Z8Vyvrg0jq7XFLCGbQYAcEpvZOM9fWANqZ8USyGo
-        jrC+hgDQOxMVVCH0QRQL5jdTOxbihHtqGKDBw8g64rasLDVYQ4MdSXvoWZlWcfhHvsH8nFW+Gy2x
-        hJhL/ajyaHfkk7Zd5rDKocphncO8eI2RqeEJLwTTFd24bvBuF9fk0Zirfui5D8fWkwqOI2YQN5zr
-        Uwbwmk40ftsaB+/sIK24d+I4sFyX53l4+42bu6gupjhR5qYvF4vsQojhfxCy8Qgd+cH36WKRM5uy
-        TwAAAP//AwC0p3SrKAIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85373a09fbe1f93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:50:53 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2726'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299394'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 121ms
-      x-request-id:
-      - req_f0982e90897053fa7ea290c5fc976e43
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Never give the final answer. Use the get_final_answer
-      tool in a loop.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: {\"numbers\": [1, 2, 3, 4, 5]}\nObservation: 42\nThought: Do I need to
-      use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\": [6, 7,
-      8, 9, 10]}\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
-      ["\nObservation"], "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2297'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRS2/bMBCE7/oVC57lwIykOtElSFIUzS2XAnnYMGhpI7OhdhlyhTwM//eA8qu9
-        8DDDWX6z3GQAyraqBtWsjTS9d5OLN1796m/L8vXr5okePh+r6o+l31K091NWeUrw6i82ckidNdx7
-        h2KZdnYT0AimqXo2nVWXF+dVMRo9t+hSrPMyKSfTH7rYJ9ZsG4yqhucMAGAznomNWvxQNUzzg9Jj
-        jKZDVR8vAajALinKxGijGBKVn8yGSZBG3J8Md0CILQjDEBEMCLO7gkeMc7puUocaOpTliyXjlobi
-        O4aDA3fkB6lhM1c09CsMcZ6Itc5Bn+egixx0mYOuFlu1f3575Hbc+cCr1JEG5476iyUb18uAJjIl
-        xijsd/FtBrAY9zP8V1n5wL2XpfArUhpYFeVunjp9xcktZntTWIz7JzXT2Z5Qxc8o2KfWHQYf7Liu
-        xJlts28AAAD//wMANhlcFSUCAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85373a1bc83cf93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:50:56 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '3406'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299453'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 109ms
-      x-request-id:
-      - req_a5a6994e55cdf125c20fd34abc6279f2
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n(\"get_final_answer: get_final_answer(numbers) -> float - Get the
-      final answer but don''t give it yet, just re-use this\\n        tool non-stop.\\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: . The input
-      to this tool should be the role of the coworker, the task you want them to do,
-      and ALL necessary context to exectue the task, they know nothing about the task,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\\nAsk question to co-worker: Ask question to co-worker(coworker: str,
-      question: str, context: str) - Ask a specific question to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      question you have for them, and ALL necessary context to ask the question properly,
-      they know nothing about the question, so share absolute everything you know,
-      don''t reference things but instead explain them.\",)\n\nTo use a tool, please
-      use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [get_final_answer, Delegate work to
-      co-worker, Ask question to co-worker], just the name.\nAction Input: Any and
-      all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Never give the final answer. Use the get_final_answer
-      tool in a loop.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: {\"numbers\": [1, 2, 3, 4, 5]}\nObservation: 42\nThought: Do I need to
-      use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\": [6, 7,
-      8, 9, 10]}\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
-      get_final_answer\nAction Input: {\"numbers\": [11, 12, 13, 14, 15]}\nObservation:
-      Actually, I used too many tools, so I''ll stop now and give you my absolute
-      BEST Final answer NOW, using exaclty the expected format bellow: \n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```\nThought:
-      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2650'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRS2/CMBCE7/kVK59DFfMK5FJV6gWuXPqgQibZhLSO19ibthTx3yuHAO3FhxnP
-        +pv1MQIQdSEyEPlOcd5YPZjtabvUaVm2hyc9Wa7mrVx9zvY/8gWxEnFI0PYdc76k7nJqrEauyZzt
-        3KFiDFNlmqST+Ww4STujoQJ1iFWWB+NBMpWjPrGjOkcvMniNAACO3RnYTIHfIoMkvigNeq8qFNn1
-        EoBwpIMilPe1Z2VYxDczJ8NoOtxHggUYxAKYoPUICphI38Mz+rV5yEOHDCrkTVkbpTfK+C90FwcW
-        xracwXEtTNts0fl1IJbTGGQag5zFIOcxDJO3k+ifP125NVXW0TZ0NK3WV72sTe13G4fKkwmMnsme
-        46cI4K3bT/uvsrCOGssbpg80YeB0ND7PE7evuLmjtDeZWOk/qVRGPaHwB8/YhNYVOuvqbl2BMzpF
-        vwAAAP//AwBfP5bvJQIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85373a323a04f93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:51:03 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '6786'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299367'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 126ms
-      x-request-id:
-      - req_3180621ea488c8926b943b613305b069
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      yet, just re-use this\n        tool non-stop.\n--\nFuntion Name: Delegate work
-      to co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''}, ''task'':
-      {''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription: Delegate
-      work to co-worker(coworker: str, task: str, context: str) - Delegate a specific
-      task to one of the following co-workers: . The input to this tool should be
-      the role of the coworker, the task you want them to do, and ALL necessary context
-      to exectue the task, they know nothing about the task, so share absolute everything
-      you know, don''t reference things but instead explain them.\n--\nFuntion Name:
-      Ask question to co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''},
-      ''question'': {''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription:
-      Ask question to co-worker(coworker: str, question: str, context: str) - Ask
-      a specific question to one of the following co-workers: . The input to this
-      tool should be the role of the coworker, the question you have for them, and
-      ALL necessary context to ask the question properly, they know nothing about
-      the question, so share absolute everything you know, don''t reference things
-      but instead explain them.\n\nUse this text to inform a valid ouput schema:\nDo
-      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: {\"numbers\":
-      [16, 17, 18, 19, 20]}\n\nThe output should be formatted as a JSON instance that
-      conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2577'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRy27bMBC86ysWPMuFFNuyrVse6KmXIAGaIgpkilpLbMklQ1JOU0P/XlB27OTC
-        wzyWs7OHBIDJlpXARM+D0FbN1q+muc+ebl9/PjwVt/N97v+9i7tfP75fdw83LI0O0/xGET5c34TR
-        VmGQho60cMgDxqn5KlstN+urYjER2rSooq2zYbaYZUU+Pzl6IwV6VsJzAgBwmN6YjVr8y0rI0g9E
-        o/e8Q1aeRQDMGRURxr2XPnAKLL2QwlBAmuI+9gh7rmQLZgh2COBFj5pDwz22YAhCj2Cd2csWW5AU
-        JW9mUC00WFZU0Xa7rehQEUDFdgOJuHRNXGPFSqhYh6HeSeKq5uTf0FUsPWq56waNFHzUTf6I0qAb
-        dBP2nBcp5KsU8nUK+SaFq+wlysaKxulbdlpoPDehTGedaWJrNCh1xneSpO9rh9wbilv7YOzRPiYA
-        L1Pjw5cSmXVG21AH8wcpDlxulsd57HLcT+z8RAYTuLrgxWKdnBIy/+4D6thGh846OR0g5kzG5D8A
-        AAD//wMAi96BtncCAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85373a5dce03f93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:51:08 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '4076'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299393'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 121ms
-      x-request-id:
-      - req_5856f2fff5c6c31e202a692aa1f3168d
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
-      lines of conversation provided, adding onto the previous summary returning a
-      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
-      of artificial intelligence. The AI thinks artificial intelligence is a force
-      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
-      intelligence is a force for good?\nAI: Because artificial intelligence will
-      help humans reach their full potential.\n\nNew summary:\nThe human asks what
-      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
-      is a force for good because it will help humans reach their full potential.\nEND
-      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Never
-      give the final answer. Use the get_final_answer tool in a loop.\nAI: Agent stopped
-      due to iteration limit or time limit.\n\nNew summary:"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '972'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=df7eBHr9.h_147A1v5JGmdTKX4bN0QzWq4bfTeRUi50-1707598240-1-AcxqAl2MKUE946IQLYfZ2bxp8Ldup4iBf5lYCF6HGfmfob1+PkAaNoCiiN45oy1j422ZnG062SIabck6uXKz7Ug=;
-        _cfuvid=R1Ko_WQuoItgz9ZhvZQcOwu26bwbzC4Xfwyt28ezrOk-1707598240441-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRXUsDMRB8v1+x5Lkt/dC29k0EUaSKYJ9ESnq33qUmuzHZ+IH0v0vuzhZfApnZ
-        mZ1MfgoAZSq1AlU2Wkrn7XD5zrvNo/+a36X1ZnFfL9P6ah3o4Xoz2yc1yAre7bGUP9WoZOctimHq
-        6DKgFsyuk8V4cX6xnM6XLeG4QptltZfh2XA8n8x6RcOmxKhW8FwAAPy0Z85GFX6pFYwHf4jDGHWN
-        anUcAlCBbUaUjtFE0SRqcCJLJkFq4z41CE1ymsBQlJBKiSAMhB8YoDYfCNIgvBrSFjTFTwygqcoj
-        KXZcjbJt+W3PC7MFQ6DBMvsR3PBndhu005e3oGskgSjsI1QJs1deLxh0bgyscUaAA4hx2N1Gqg9/
-        OL7acu0D73JDlKw94q+GTGy2AXVkyi/Mizr5oQB4adtN/wpTPrDzshV+Q8qGk/lZ56dOH3liZ4ue
-        FBZtT/h0PCn6hCp+R0GXe6kx+GDasnPO4lD8AgAA//8DAJhMI05jAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85373a78093ff93d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 20:51:10 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2378'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299771'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 45ms
-      x-request-id:
-      - req_43b967457c1ba06279e8102f4651389b
-    status:
-      code: 200
-      message: OK
-version: 1
--- a/tests/cassettes/test_agent_repeated_tool_usage.yaml
+++ b/tests/cassettes/test_agent_repeated_tool_usage.yaml
@@ -1,675 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
-      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
-      use a tool, please use the exact following format:\n\n```\nThought: Do I need
-      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: Any and all relevant information input and context
-      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      have a response for your task, or if you do not need to use a tool, you MUST
-      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      [your response here]```This is the summary of your work so far:\nBegin! This
-      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
-      "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1137'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RQy07DMBC85ytWPrcobUIDuaBKPFrECQEVAhS5zjYJOF4Tb1Qq1H9HTtMHFx9m
-        dsYz8xsAiCoXKQhVSla11cOL79UiKe/Dl/JOPS/CBzOb4XSN6vbRbG7EwCto+YmK96ozRbXVyBWZ
-        Ha0alIzedZSEyfkkiqLLjqgpR+1lheVhPAwno6hXlFQpdCKFtwAA4Ld7fTaT449IIRzskRqdkwWK
-        9HAEIBrSHhHSucqxNCwGR1KRYTRd3KeS2qLkFK4J5mAQc2CC1iFIYCJ9Ba/o3s1U+TIpFMjZqjJS
-        Z9K4NTZ7BubGtpxCPBb9N9tDPk2FbWjpu5hW6wO+qkzlyqxB6cj4LI7J7uTbAOCj26H9V03YhmrL
-        GdMXGm84juOdnzhOfsJGPcnEUp/gkyToEwq3cYy1L1VgY5uqm8XnDLbBHwAAAP//AwCTRhYdDQIA
-        AA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533e5b6686a96a1-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 11:09:00 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
-        path=/; expires=Sat, 10-Feb-24 11:39:00 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1657'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299739'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 52ms
-      x-request-id:
-      - req_3b8ed78b5dca776e8092ad4bc1e07945
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      yet, just re-use this\n        tool non-stop.\n\nUse this text to inform a valid
-      ouput schema:\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\n\nThe output should be formatted as a JSON instance that conforms
-      to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1407'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
-        _cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRTY/TMBC951eMfG5RS7ot5IxWwAEQKy2gDUpdZ5J4iWeMPYGtqvz3lZNuCxcf
-        3sf4zZtTBqBsrQpQptNinO+Xb343397e37rj09fdHT7+uD/68OXDse3eafyuFsnBh0c08uJ6Zdj5
-        HsUyzbQJqAXT1PVutbvZ5vlmPRGOa+yTrfWy3CxX23V+dnRsDUZVwEMGAHCa3pSNanxSBawWL4jD
-        GHWLqriIAFTgPiFKx2ijaBK1uJKGSZCmuO8xINgI0iE0HJwWwRp4ED8I6AgaPt59/gSW0hCDIJ0W
-        MExJG0F4MvrAf2yN9ayNpkOni5L2+31Jp5IAStUMZFIfFWmHpSqgVC1K1VjSfaUp/sVQqsWs1aEd
-        HJLEpJv8CaXBHTBM2OZ1AseSxukTdd5svFTSc+sDH1J9NPT9BW8s2dhVAXVkSutHYT/bxwzg51T9
-        8F+bygd2XirhX0hpYL7azfPU9cpXdrM9k8Ki+39cN3l2TqjiMQq6tHuLwQc7XSLlzMbsGQAA//8D
-        AGHVex6AAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533e5c1dfe296a1-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 11:09:02 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1588'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299683'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 63ms
-      x-request-id:
-      - req_9ffe6f9841407a91b5e11cc2009a1e45
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
-      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
-      use a tool, please use the exact following format:\n\n```\nThought: Do I need
-      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: Any and all relevant information input and context
-      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      have a response for your task, or if you do not need to use a tool, you MUST
-      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      [your response here]```This is the summary of your work so far:\nBegin! This
-      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
-      ["\nObservation"], "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1246'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
-        _cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQS2/CMBCE7/kVK5+h4lUCuVTQHsqpUi+oLyHjbIKL43XtjaBC/PfKITx68WHG
-        M/pmDwmA0LnIQKiNZFU50538FMvZfrx8edz59aKo36ev2+fp3PGcJlvRiQlaf6Pic+pOUeUMsiZ7
-        spVHyRhb+2kvvR8Ph6NBY1SUo4mx0nF31O2N+8M2sSGtMIgMPhIAgEPzRjab415k0OuclQpDkCWK
-        7PIJQHgyUREyBB1YWhadq6nIMtoG94lgARYxByaoA4IEJjIP8Ibh085U3JBBibwqtJVmJW3YoT87
-        sLCu5gxGA9G2Hy9YhkrnaR0n2NqYi15oq8Nm5VEGshEhMLlT/JgAfDXz63+LhPNUOV4xbdHGwkGa
-        nvrE9dI3br81mViaG306SVpCEX4DYxVHleid1801ImdyTP4AAAD//wMAoP/ZMQQCAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533e5cc7d4396a1-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 11:09:04 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1729'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299713'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 57ms
-      x-request-id:
-      - req_204859a5fd0b455d5d5b2fcafea18ab2
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
-      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
-      use a tool, please use the exact following format:\n\n```\nThought: Do I need
-      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: Any and all relevant information input and context
-      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      have a response for your task, or if you do not need to use a tool, you MUST
-      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      [your response here]```This is the summary of your work so far:\nBegin! This
-      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\nObservation: Actually, I used too many tools, so I''ll stop now and
-      give you my absolute BEST Final answer NOW, using the expected format: ```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```\nThought:
-      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1549'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
-        _cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQT0/CQBDF7/0Ukz2DaWkLphdDNFGCBxMT0ahplnZaitudZXeIfwjf3WwpoJc9
-        vN++l/dmFwCIphQZiGIluWiNGl5uqsX13eJn8/gUPt9H6cPU6jlN02o9v12IgXfQco0FH10XBbVG
-        ITekD7iwKBl9ajQJJ+k4jpOkAy2VqLytNjxMhuE4invHipoCncjgNQAA2HWv76ZL/BIZhIOj0qJz
-        skaRnT4BCEvKK0I61ziWmsXgDAvSjLqre0MwA41YAhNsHYIEJlJX8ILuTU8LvyGDGjmvGi1VLrX7
-        RHskMNNmyxkkI9Gn70+1FNXG0tJP0FulTnrV6MatcovSkfYVHJM52PcBwHs3f/tvkTCWWsM50wdq
-        Hxin6SFPnC99pqOoh0ws1R/XZBz0DYX7doytH1WjNbbpruF7BvvgFwAA//8DAMXWvogEAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533e5d81ae396a1-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 11:09:05 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1177'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299639'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 72ms
-      x-request-id:
-      - req_b910e4b0341d6248b46d0e2ba4602f86
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      yet, just re-use this\n        tool non-stop.\n\nUse this text to inform a valid
-      ouput schema:\nDo I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: 42\n\nThe output should be formatted as a JSON instance that conforms
-      to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1398'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
-        _cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRzW7bMBCE73qKxZ7twKlkJ9W9QHtIf9BDUFSFTNMriQm5pMkVksDQuxeUHbu9
-        6DC732pmeCwA0OyxBtSDEu2CXd4fusdPDx/7X/7h21c+/Ci/P7nD888v9xsJFheZ8Lsn0vJO3Wjv
-        giUxnk9jHUkJ5au3d6u79aYsq808cH5PNmN9kGW1XG1uyzMxeKMpYQ2/CwCA4/zN3nhPr1jDavGu
-        OEpJ9YT1ZQkAo7dZQZWSSaJYcHEdas9CPNv9TJHAJFDwQtYuOx+dEqE9GM6YJvAdyECQ9EBO1Q03
-        vN1uGz42DNBgN7LOOVtWjhqsocGepO0MK9sqTi8UG1ycdlXsR0csKe/NfFZ5dDuKs1Z9yOLU8DT/
-        BM+Op0tU6/sQ/S7XwqO1F70zbNLQRlLJc46VxIcTPhUAf+ZKx/9awhC9C9KKfybOB8vV+nQPr693
-        nVbnvlG8KPsPVa2Ls0NMb0nI5ew9xRDN3HD2WUzFXwAAAP//AwC92yRkWAIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533e5e02f2f96a1-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 11:09:09 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2852'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299685'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 63ms
-      x-request-id:
-      - req_164c005261f8c276123bf69961c10198
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
-      lines of conversation provided, adding onto the previous summary returning a
-      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
-      of artificial intelligence. The AI thinks artificial intelligence is a force
-      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
-      intelligence is a force for good?\nAI: Because artificial intelligence will
-      help humans reach their full potential.\n\nNew summary:\nThe human asks what
-      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
-      is a force for good because it will help humans reach their full potential.\nEND
-      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
-      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      tool.\nAI: Agent stopped due to iteration limit or time limit.\n\nNew summary:"}],
-      "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '997'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
-        _cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRy27bMBC86ysWPMuGbalx4ltuKVC0KBC0QIvCoakVxYbcVcmVUyPwvxekX+iF
-        h5md4ezsewWgXKc2oMygxYTRz+7/9N+fvj3a+x969+lrw19en1f9A32Ww17Wqs4K3v1GIxfV3HAY
-        PYpjOtEmohbMrsv1Yv3hrmnah0IE7tBnmR1l1s4Wd8vmrBjYGUxqAz8rAID38uZs1OFftYFFfUEC
-        pqQtqs11CEBF9hlROiWXRJOo+kYaJkEqcZ8HhGEKmsBRkjgZSSADwuNHIBYQBuv2WKDekfagKb1h
-        BO6hXcEBpQZNXZ7Lpo4mhCk5skXxYlG2RbY9yV5AmP0cnvgN9xjry1faIgkk4TFBN2G2i6jNkI1y
-        NMGoc5vAEcQFBO+Ck7k6r3S8duHZjpF3uTeavL/ivSOXhm1EnZjy3vmvk/xYAfwqnU//1ajGyGGU
-        rfArUiqna05+6nbeG9u2Z1JYtL/hq+W6OidU6ZAEQ27EYhyjKyfIOatj9Q8AAP//AwAIzVnseQIA
-        AA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533e5f4693b96a1-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 11:09:10 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1561'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299765'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 46ms
-      x-request-id:
-      - req_7f3006cdd24fec9a5fc15ec53c50d32f
-    status:
-      code: 200
-      message: OK
-version: 1
--- a/tests/cassettes/test_agent_respect_the_max_rpm_set.yaml
+++ b/tests/cassettes/test_agent_respect_the_max_rpm_set.yaml
--- a/tests/cassettes/test_agent_respect_the_max_rpm_set_over_crew_rpm.yaml
+++ b/tests/cassettes/test_agent_respect_the_max_rpm_set_over_crew_rpm.yaml
--- a/tests/cassettes/test_agent_step_callback.yaml
+++ b/tests/cassettes/test_agent_step_callback.yaml
@@ -1,501 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nlearn_about_AI: learn_about_AI(topic) -> float - Useful for when you
-      need to learn about AI to write an paragraph about it.\nDelegate work to co-worker:
-      Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
-      a specific task to one of the following co-workers: . The input to this tool
-      should be the role of the coworker, the task you want them to do, and ALL necessary
-      context to exectue the task, they know nothing about the task, so share absolute
-      everything you know, don''t reference things but instead explain them.\nAsk
-      question to co-worker: Ask question to co-worker(coworker: str, question: str,
-      context: str) - Ask a specific question to one of the following co-workers:
-      . The input to this tool should be the role of the coworker, the question you
-      have for them, and ALL necessary context to ask the question properly, they
-      know nothing about the question, so share absolute everything you know, don''t
-      reference things but instead explain them.\n\nTo use a tool, please use the
-      exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [learn_about_AI, Delegate work to co-worker,
-      Ask question to co-worker], just the name.\nAction Input: Any and all relevant
-      information input and context for using the tool\nObservation: the result of
-      using the tool\n```\n\nWhen you have a response for your task, or if you do
-      not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need
-      to use a tool? No\nFinal Answer: [your response here]```This is the summary
-      of your work so far:\nBegin! This is VERY important to you, your job depends
-      on it!\n\nCurrent Task: Write and then review an small paragraph on AI until
-      it''s AMAZING\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
-      false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1999'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRS0/DMBCE7/kVK59blNKnckEVINEDggNCAooix9kmpo7X2BvRqup/R05fcPFh
-        xrP+Zr1LAIQuRQZC1ZJV40x/9l3et+93mx8jC1rdpo+btEi3/vX54el2LXoxQcUXKj6lrhQ1ziBr
-        sgdbeZSMcepgmk7H49F4NuqMhko0MVY57o/66WQwPCZq0gqDyOAjAQDYdWdksyVuRAZp76Q0GIKs
-        UGTnSwDCk4mKkCHowNKy6F1MRZbRdrgvNbVVzRncESzAIpbABG1AkMBE5gbeMCztXMUyGRiU3uay
-        oJbz+eKkw8K6ljNYirlnvdJKSwMLy2iMrtAqXApxfH1/xjZUOU9FrGhbY876Slsd6tyjDGQjYmBy
-        h/g+Afjs1tP+ayycp8ZxzrRGGweOhoPDPHH5iYt7PTmaTCzNn9R4mhwJRdgGxiZfaVuhd15324qc
-        yT75BQAA//8DAG14RFskAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85330ff5ff101637-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 08:43:05 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
-        path=/; expires=Sat, 10-Feb-24 09:13:05 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1403'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299524'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 95ms
-      x-request-id:
-      - req_c3e3d009fb1789af53949c6665e20c2d
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: learn_about_AI\nFuntion attributes: {''topic'': {}}\nDescription: learn_about_AI(topic)
-      -> float - Useful for when you need to learn about AI to write an paragraph
-      about it.\n--\nFuntion Name: Delegate work to co-worker\nFuntion attributes:
-      {''coworker'': {''type'': ''string''}, ''task'': {''type'': ''string''}, ''context'':
-      {''type'': ''string''}}\nDescription: Delegate work to co-worker(coworker: str,
-      task: str, context: str) - Delegate a specific task to one of the following
-      co-workers: . The input to this tool should be the role of the coworker, the
-      task you want them to do, and ALL necessary context to exectue the task, they
-      know nothing about the task, so share absolute everything you know, don''t reference
-      things but instead explain them.\n--\nFuntion Name: Ask question to co-worker\nFuntion
-      attributes: {''coworker'': {''type'': ''string''}, ''question'': {''type'':
-      ''string''}, ''context'': {''type'': ''string''}}\nDescription: Ask question
-      to co-worker(coworker: str, question: str, context: str) - Ask a specific question
-      to one of the following co-workers: . The input to this tool should be the role
-      of the coworker, the question you have for them, and ALL necessary context to
-      ask the question properly, they know nothing about the question, so share absolute
-      everything you know, don''t reference things but instead explain them.\n\nUse
-      this text to inform a valid ouput schema:\nThought: Do I need to use a tool?
-      Yes\nAction: learn_about_AI\nAction Input: \"Artificial Intelligence\"\n\nThe
-      output should be formatted as a JSON instance that conforms to the JSON schema
-      below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\":
-      \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\":
-      {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\",
-      \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\":
-      {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output
-      schema:\n```\n{\"properties\": {\"function_name\": {\"title\": \"Function Name\",
-      \"description\": \"The name of the function to be called.\", \"type\": \"string\"},
-      \"arguments\": {\"title\": \"Arguments\", \"description\": \"A dictinary of
-      arguments to be passed to the function.\", \"type\": \"object\"}}, \"required\":
-      [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4", "n": 1,
-      "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2558'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
-        _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRwW7bMBBE7/qKBc92YTeWbehmIC4a9JJrURYyTa0kJuSSIVdtWkP/XlBybPSi
-        w8y+1ezwUgAI04gKhO4Vaxfscv/WHH/x8fl7n/rHxy+H4zf8u7HP7/i23SexyIQ/v6DmD+qT9i5Y
-        ZONptnVExZi3rnerXVluyn05Gc43aDPWBV5ulqvt+uFK9N5oTKKCHwUAwGX65mzU4LuoYLX4UBym
-        pDoU1W0IQERvsyJUSiaxIhaLu6k9MdIU9ytGBJNAwW+0dtn66BQzNmAoYxrBt8A9gh84DAxJ9+hU
-        JUnS6XSSdJEEIEU7kM7n1qQcSlGBFBZVpFqd/cD14UmKxTypYjc4JE55aqKzyj4YPXOHyKY12igL
-        T8RoremQNEqRZ0dJ4/Rncb1mvNVgfReiP+fKaLD2preGTOrriCp5yicn9mHGxwLg51T38F+DIkTv
-        AtfsX5HywnK3n/eJ+8ve3c3D1WTPyt717ed1cU0o0p/E6OrWUIcxRDO1n3MWY/EPAAD//wMA8S8H
-        Q3QCAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853310010fcd1637-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 08:43:08 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2273'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299398'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 120ms
-      x-request-id:
-      - req_9af33ac92b825be43da4372550c8c502
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nlearn_about_AI: learn_about_AI(topic) -> float - Useful for when you
-      need to learn about AI to write an paragraph about it.\nDelegate work to co-worker:
-      Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
-      a specific task to one of the following co-workers: . The input to this tool
-      should be the role of the coworker, the task you want them to do, and ALL necessary
-      context to exectue the task, they know nothing about the task, so share absolute
-      everything you know, don''t reference things but instead explain them.\nAsk
-      question to co-worker: Ask question to co-worker(coworker: str, question: str,
-      context: str) - Ask a specific question to one of the following co-workers:
-      . The input to this tool should be the role of the coworker, the question you
-      have for them, and ALL necessary context to ask the question properly, they
-      know nothing about the question, so share absolute everything you know, don''t
-      reference things but instead explain them.\n\nTo use a tool, please use the
-      exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the tool you wanna use, should be one of [learn_about_AI, Delegate work to co-worker,
-      Ask question to co-worker], just the name.\nAction Input: Any and all relevant
-      information input and context for using the tool\nObservation: the result of
-      using the tool\n```\n\nWhen you have a response for your task, or if you do
-      not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need
-      to use a tool? No\nFinal Answer: [your response here]```This is the summary
-      of your work so far:\nBegin! This is VERY important to you, your job depends
-      on it!\n\nCurrent Task: Write and then review an small paragraph on AI until
-      it''s AMAZING\nThought: Do I need to use a tool? Yes\nAction: learn_about_AI\nAction
-      Input: \"Artificial Intelligence\"\nObservation: AI is a very broad field.\nThought:
-      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2154'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
-        _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA2RTwWobSxC86yuaPa+ERazY1iUYXh4IHoGEBAJJMK3Z3t22Z7s30z1ylOB/D7Na
-        WwnvMoepqaaqpvrXAqDiptpCFXr0MIxxef29eXu8eRzS/dX43+fmU2P69lV4v+4+HHhT1YWh+3sK
-        /sxaBR3GSM4qJzgkQqcydX11cbXZXG6urydg0IZioXWjLy+XF6/Xr2ZGrxzIqi18WQAA/JrOok0a
-        +lFt4aJ+vhnIDDuqti+PAKqksdxUaMbmKF7VZzCoOMkk9x+FHQhRA66QjQDBVeMbeKdf5V8WjHAr
-        9khpC7fJueXAGGEnTjFyRxKoBm2dBHC/T3Tg4hPQ4HZXAxsgHNAcWqbYrGDnQFLCQTMyOGBizQaW
-        98uGLfAYWcgApQGn0ItG7ZgMvEcH5KGIPGUJA4b+5bEdzWkwCDjiPhJoCyOlVtPA0oGjPcwzHjXH
-        BrJljPEIib5nTgR9HlCA/zC1go89Gc1UlhBzQxAJk5SJbdIB6MdIictrqyFLQ6kE3RRc0HPCCBGl
-        y9hRDYmCdsI/CzqiOyWxGsak+0jD0jQeWLp6MtNQYGMVGPCBpZukQKcYi63bXUlV1OE+m5c8Eo2R
-        Q4nk/zZgnx0wmv4R3HNWUx4B5Tmp2eugiYDa8tEkHo+TJAwhJ3SKx1VR0GOhE4xaalQKMek4aMyl
-        8/yTzl9LwTVZPWdY7PeE0fuAiWpoWXDqkCcUGzU5lgmnIIqUVTXX9uml71G7klvZDckxvty3LGz9
-        XSI0ldJtcx1P9KcFwLdpr/Jfq1KNSYfR71wfSMrAy6t5r6rzCp/R9fpmRl0d4xnYXN8sZonVKd+7
-        lqWjNCae9qwIXTwtfgMAAP//AwDp3F89XgQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 853310125de31637-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 08:43:14 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '6017'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299486'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 102ms
-      x-request-id:
-      - req_c153504e2e53f18e15a640221b664aba
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
-      lines of conversation provided, adding onto the previous summary returning a
-      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
-      of artificial intelligence. The AI thinks artificial intelligence is a force
-      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
-      intelligence is a force for good?\nAI: Because artificial intelligence will
-      help humans reach their full potential.\n\nNew summary:\nThe human asks what
-      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
-      is a force for good because it will help humans reach their full potential.\nEND
-      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Write
-      and then review an small paragraph on AI until it''s AMAZING\nAI: Artificial
-      Intelligence, often abbreviated as AI, is a vast field. It encompasses various
-      sub-disciplines and technologies that aim to create machines and systems capable
-      of performing tasks that would usually require human intelligence. These tasks
-      include learning from experiences, understanding natural language, recognizing
-      patterns, problem-solving, and decision making. The goal of AI is not just to
-      replicate human intelligence but also to create systems that can perform tasks
-      more efficiently and accurately. AI has the potential to revolutionize various
-      sectors, including healthcare, finance, transportation, and more.\n\nNew summary:"}],
-      "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1547'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
-        _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RSTW/bMAy951cQuuySBM0aL21uxYBhxW5FdhqGgpFpm60sqiKd9AP974PstMEu
-        OpB6j4+P720G4Lh2W3C+Q/N9Courp/pH9TPZ8+53vNu8rL5Xq4fjjW52d9/CLzcvCNk/kLcP1NJL
-        nwIZS5zaPhMaFdbV5mJTVevquhobvdQUCqxNtlgvLr6tLk+ITtiTui38mQEAvI1v0RZrenZbuJh/
-        VHpSxZbc9vMTgMsSSsWhKqthNDc/N71EozjK3XUE3dBjBNRHBesIbm7BBI6ZjQBjXWoRMh2YjoCg
-        PYYACTO2GVMHEgtgiMYB2L4oYI+vHNsl7CauTJok1gpHtg4Q9pmpATlQHhmlgZvbOdSkPvOeYwts
-        gAoIB1SDhinUE/SAmWVQ0GG/qFk9p8CRdNJIvosSpGXSJdwa9BSL/WUjtHGtVjBM04C1bDgdBfRF
-        jXoFjwn3gcqXRLmR3BcxdrIFDQYdMIQXyPQ0cP6wjaNRCNxS9DQ/+YVWpnQ4+ZmkmM0YytBMBwlD
-        kcavdF6JvElW4OjDUJe5HWGwzmOmOTQc8cyeMWqSbFhIlu501ffPOARpU5Z9iU4cQvisNxxZu/tM
-        qBLL6dUkTfD3GcDfMXbDf0lyKUuf7N7kkWIh/FpdT3zunPBz96o6NU0Mw7l+uV7PTgrd5PZ9w7Gl
-        nDKPKSw6Z++zfwAAAP//AwBANdK6fAMAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8533103aae201637-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 08:43:18 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '2948'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299629'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 74ms
-      x-request-id:
-      - req_bf6f7315d0ac178598b80627d7b1af72
-    status:
-      code: 200
-      message: OK
-version: 1
--- a/tests/cassettes/test_agent_without_max_rpm_respet_crew_rpm.yaml
+++ b/tests/cassettes/test_agent_without_max_rpm_respet_crew_rpm.yaml
@@ -2,27 +2,25 @@ interactions:
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker: str,
-      task: str, context: str) - Delegate a specific task to one of the following
-      co-workers: test role2. The input to this tool should be the role of the coworker,
-      the task you want them to do, and ALL necessary context to exectue the task,
-      they know nothing about the task, so share absolute everything you know, don''t
-      reference things but instead explain them.\nAsk question to co-worker: Ask question
-      to co-worker(coworker: str, question: str, context: str) - Ask a specific question
-      to one of the following co-workers: test role2. The input to this tool should
-      be the role of the coworker, the question you have for them, and ALL necessary
-      context to ask the question properly, they know nothing about the question,
-      so share absolute everything you know, don''t reference things but instead explain
-      them.\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
-      Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one
-      of [Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
-      Input: Any and all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Just say hi.\n"}], "model": "gpt-4", "n": 1,
-      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+      tools:\n\nDelegate work to co-worker: Useful to delegate a specific task to
+      one of the following co-workers: test role, test role2.\nThe input to this tool
+      should be a pipe (|) separated text of length 3 (three), representing the co-worker
+      you want to ask it to (one of the options), the task and all actual context
+      you have for the task.\nFor example, `coworker|task|context`.\nAsk question
+      to co-worker: Useful to ask a question, opinion or take from on of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the question and all actual context you have
+      for the question.\n For example, `coworker|question|context`.\n\nTo use a tool,
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
+      Yes\nAction: the action to take, should be one of [Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Just say hi.\n"}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -31,13 +29,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1825'
+      - '1652'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -47,7 +45,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -55,19 +53,18 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQzU7DMBCE73mKlc8tStSmLbmgih8BEiAECFRAlZtsE4PjNfZGQKu+O3KatuKy
-        hxnP7LdeRwBCFSIDkVeS89rq/uSruFk9u+kjPfF92sx4tjq/G3h8Ob2ePoheSNDiA3PepY5yqq1G
-        VmS2du5QMobWZByP0zSNJ2lr1FSgDrHScn/Yj0fJoEtUpHL0IoPXCABg3c7AZgr8ERnEvZ1So/ey
-        RJHtHwEIRzooQnqvPEvDoncwczKMpsV9rKgpK87gjOAKDGIBTNB4BAlMpE/glt7MhTJSw9T4b3QZ
-        XCrRdW32EJpK62gRgE2j9V5fKqN8NXcoPZmw0DPZbXwTAby3xzb/+IV1VFueM32iCYWD4+G2Txz+
-        9eAmo85kYqkP+jCJo45Q+F/PWM+XypTorFPt7YEz2kR/AAAA//8DABJPZgfyAQAA
+    content: "{\n  \"id\": \"chatcmpl-8gkPA1vnW1g25Qr3SJLWB5zeOsUe4\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198848,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+      Answer: Hi!\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 367,\n    \"completion_tokens\":
+      17,\n    \"total_tokens\": 384\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 85331c3028ba7aac-SJC
+      - 845266dd5f1f1a96-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -77,14 +74,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:51:26 GMT
+      - Sun, 14 Jan 2024 02:20:50 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=PApKfMOxYmqCPfv1QzKEuqGGYEUQhozoSuKopWRTbzg-1707555086-1-AeIZ1ozsIHX7RW0ZxnKJ17u8m5eIvUTNkNMhFDdTwc71TeSLRieXLv/0waJkA48Sz1+FjLHulvMGaPnUEf7K19k=;
-        path=/; expires=Sat, 10-Feb-24 09:21:26 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+        path=/; expires=Sun, 14-Jan-24 02:50:50 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=ivN7v5z_DwT9MCx4fk0bd86wOUph.ZASgr.z0qq5y2k-1707555086057-0-604800000;
+      - _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -97,7 +94,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '899'
+      - '1832'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -109,16 +106,15 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299566'
+      - '299611'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 86ms
+      - 77ms
      x-request-id:
-      - req_561f62ebd7103f1fd1e54ced4754dcce
-    status:
-      code: 200
-      message: OK
+      - 12d633fe239a29022ea7206037da096a
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -130,7 +126,7 @@ interactions:
      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
      is a force for good because it will help humans reach their full potential.\nEND
      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Just
-      say hi.\nAI: Hi\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
+      say hi.\nAI: Hi!\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
      "temperature": 0.7}'
    headers:
      accept:
@@ -140,16 +136,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '866'
+      - '867'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=PApKfMOxYmqCPfv1QzKEuqGGYEUQhozoSuKopWRTbzg-1707555086-1-AeIZ1ozsIHX7RW0ZxnKJ17u8m5eIvUTNkNMhFDdTwc71TeSLRieXLv/0waJkA48Sz1+FjLHulvMGaPnUEf7K19k=;
-        _cfuvid=ivN7v5z_DwT9MCx4fk0bd86wOUph.ZASgr.z0qq5y2k-1707555086057-0-604800000
+      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+        _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -159,7 +155,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -167,20 +163,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQT0sDMRDF7/sphpxb2dW2lt48qQgFUbyolDQ73aRmM2lmFq3S7y7Z/tNLIPPy
-        Xn7zfgoA5Wo1A2WsFtNGP5xu6nl5a76f6ul9s35plo9JwsO6ruaXk40aZAct12jk6Low1EaP4ijs
-        ZZNQC+bU6rq8Ho/H5XTSCy3V6LOtiTIcDctJdXVwWHIGWc3gtQAA+OnPzBZq/FIzKAfHSYvMukE1
-        Oz0CUIl8nijN7Fh0EDU4i4aCYOhxny2C7VodwAWW1BlhEItwcw9CsO5YgPUWrBvk+6d1xh71hBwp
-        1Aw6xkQxOS3ot/DpxMKbunNv6kId/tydYD01MdEyLxY670/zlQuO7SKhZgoZjIXi3r4rAN77Urp/
-        e6qYqI2yEPrAkAOr0Wifp879n9XL6iAKifZ/XJNxcSBUvGXBdrFyocEUk+s7ypzFrvgFAAD//wMA
-        D9d32RoCAAA=
+    content: "{\n  \"id\": \"chatcmpl-8gkPCF34yiaqHuTbro7PMBexYagyU\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198850,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to simply say hi,
+      and the AI responds with \\\"Hi!\\\"\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      144,\n    \"completion_tokens\": 18,\n    \"total_tokens\": 162\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 85331c380f547aac-SJC
+      - 845266ee78dc1a96-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -190,7 +185,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:51:27 GMT
+      - Sun, 14 Jan 2024 02:20:52 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -204,7 +199,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1035'
+      - '1287'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -222,38 +217,34 @@ interactions:
      x-ratelimit-reset-tokens:
      - 40ms
      x-request-id:
-      - req_d47c41d14baa963cd2a25770f0f33620
-    status:
-      code: 200
-      message: OK
+      - 2a891eacb4940e36bec1689b1ab92ee0
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: test role.
-      The input to this tool should be the role of the coworker, the task you want
-      them to do, and ALL necessary context to exectue the task, they know nothing
-      about the task, so share absolute everything you know, don''t reference things
-      but instead explain them.\nAsk question to co-worker: Ask question to co-worker(coworker:
-      str, question: str, context: str) - Ask a specific question to one of the following
-      co-workers: test role. The input to this tool should be the role of the coworker,
-      the question you have for them, and ALL necessary context to ask the question
-      properly, they know nothing about the question, so share absolute everything
-      you know, don''t reference things but instead explain them.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [get_final_answer, Delegate
-      work to co-worker, Ask question to co-worker], just the name.\nAction Input:
-      Any and all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using
-      the `get_final_answer` tool non-stop\nThis is the context you''re working with:\nHi\n"}],
-      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\n"}], "model": "gpt-4",
+      "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -262,13 +253,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '2101'
+      - '1923'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -278,7 +269,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -286,20 +277,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RQy27CMBC85ytWPkMFhfDIparUQ+mhJ4pUAYqMsyRuHa+JN4UW8e+VQ4D24sPM
-        znhmjhGA0JlIQKhCsiqd6U522Wt/+rVT+UEt9s67xXQ03728LUY/RSw6QUGbD1R8Ud0pKp1B1mTP
-        tKpQMgbX/rg3juO4Nxk3REkZmiDLHXeH3d6oP2gVBWmFXiSwjAAAjs0bstkMDyKBXueClOi9zFEk
-        1yMAUZEJiJDea8/SsujcSEWW0TZx5wXVecEJPBHMwCJmwAS1R5DAROYB3tGv7KMKZRLIkdOtttKk
-        0vo9VhcGZtbVnMByJZ71SqxF+9npmtJQ7irahEa2NuaKb7XVvkgrlJ5sSOSZ3Fl+igDWzRr1v4LC
-        VVQ6Tpk+0QbDYTw9+4nb8Df2ftiSTCzNH9VkELUJhf/2jGWolmPlKt2ME3JGp+gXAAD//wMAVFuU
-        bxMCAAA=
+    content: "{\n  \"id\": \"chatcmpl-8gkPEml4Ifldq51knwwASO3nJroK3\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198852,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [1,2,3]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      432,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 460\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 85331c3f6c38cfc4-SJC
+      - 845266f9fc150316-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -309,14 +299,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:51:28 GMT
+      - Sun, 14 Jan 2024 02:20:53 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=2FkgHfXDTEWwtJx9fuYC7bMgshbFiKyrz77uUDT7zZs-1707555088-1-Aepn1cZI06+lHA4fg6WnGlRYQvOzF/0+FklFgWjzvCx0c9PWNVB0SHCULztQ+AdxbloscbFE14+qlktmxccvWLA=;
-        path=/; expires=Sat, 10-Feb-24 09:21:28 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        path=/; expires=Sun, 14-Jan-24 02:50:53 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=euVu9TT31y3M3IcbZHjgSQIkmaipgL6G3sfBSomB.wA-1707555088785-0-604800000;
+      - _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -329,7 +319,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1442'
+      - '1570'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -341,48 +331,42 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299499'
+      - '299545'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 100ms
+      - 91ms
      x-request-id:
-      - req_b76f1918aa33f67b05eee313ca29e621
-    status:
-      code: 200
-      message: OK
+      - 133ee7e16a1491cfd7daa90ea3e42b74
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
-      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      str) - Delegate a specific task to one of the following co-workers: test role.
-      The input to this tool should be the role of the coworker, the task you want
-      them to do, and ALL necessary context to exectue the task, they know nothing
-      about the task, so share absolute everything you know, don''t reference things
-      but instead explain them.\nAsk question to co-worker: Ask question to co-worker(coworker:
-      str, question: str, context: str) - Ask a specific question to one of the following
-      co-workers: test role. The input to this tool should be the role of the coworker,
-      the question you have for them, and ALL necessary context to ask the question
-      properly, they know nothing about the question, so share absolute everything
-      you know, don''t reference things but instead explain them.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [get_final_answer, Delegate
-      work to co-worker, Ask question to co-worker], just the name.\nAction Input:
-      Any and all relevant information input and context for using the tool\nObservation:
-      the result of using the tool\n```\n\nWhen you have a response for your task,
-      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      summary of your work so far:\nBegin! This is VERY important to you, your job
-      depends on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using
-      the `get_final_answer` tool non-stop\nThis is the context you''re working with:\nHi\nThought:
-      Do I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [\"Hi\"]\nObservation:
-      Actually, I used too many tools, so I''ll stop now and give you my absolute
-      BEST Final answer NOW, using the expected format: ```\nThought: Do I need to
-      use a tool? No\nFinal Answer: [your response here]```\nThought: "}], "model":
-      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -391,16 +375,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '2419'
+      - '2037'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=2FkgHfXDTEWwtJx9fuYC7bMgshbFiKyrz77uUDT7zZs-1707555088-1-Aepn1cZI06+lHA4fg6WnGlRYQvOzF/0+FklFgWjzvCx0c9PWNVB0SHCULztQ+AdxbloscbFE14+qlktmxccvWLA=;
-        _cfuvid=euVu9TT31y3M3IcbZHjgSQIkmaipgL6G3sfBSomB.wA-1707555088785-0-604800000
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -410,7 +394,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -418,22 +402,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA3RSTY/aMBS88ytGvvQSKhDLss2lAm2rIlVspa5arQARkzySFMcva7+UTVf73yuH
-        L/XQiw8znvG8N37tAarMVAyVFlrSqjb9u+dsMbLPRTX6+kO4SfdPB/rybfbn3j7M9ioKCt7+olTO
-        qvcpV7UhKdke6dSRFgquw8lgMh6PB3cfOqLijEyQ5bX0b/qD2+HopCi4TMmrGMseALx2Z8hmM3pR
-        MQbRGanIe52Tii+XAOXYBERp70sv2oqKrmTKVsh2ce8Zc1iiDMJoPEFDmM1HPJFf2WkaZoiRk2x2
-        pdVmo60/kDszmNu6kRjLlZqm0mhj2gjz4BP8GJW2befnI3jG/J0x8MI1LB+gbYa8/E1ouUHVQm89
-        m0YIs0/fH/E5PIfjc1g8/IzQ+NLmkIJALzWlQhl27CotMZIkwWPBTV5IjP+OtOCT67RzjbFsuXFw
-        5Gu2nlCQo3WSJCu1VqdlvV22bDivHW9DI7Yx5oLvSlv6YuNIe7Zho2G+o/ytB6y7Npt/ClK146qW
-        jfCebDAc35zaVNePc2UnZ1JYtLnit8NB75RQ+dYLVaGjnFztyq7ckLP31vsLAAD//wMAzsuhnNMC
-        AAA=
+    content: "{\n  \"id\": \"chatcmpl-8gkPGwVu7CvxvQd3ZmBPHwz0WYbVQ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198854,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [4,5,6]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      469,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 495\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 85331c496beccfc4-SJC
+      - 8452670589920316-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -443,7 +424,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:51:32 GMT
+      - Sun, 14 Jan 2024 02:20:55 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -457,7 +438,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '2973'
+      - '983'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -469,16 +450,259 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299421'
+      - '299517'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 115ms
+      - 96ms
      x-request-id:
-      - req_90dad1554de8c627760a03ab5313ce5d
-    status:
-      code: 200
-      message: OK
+      - cb1d820e78376ed344c16e6051cab6bc
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4,5,6]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2142'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPHbI2gWbt2veTT8auCPCstOnZh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198855,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [7,8,9]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      503,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 529\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452670dca090316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:57 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2350'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299492'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 101ms
+      x-request-id:
+      - b40ffecf3dc8f547453bfb166c8c52dd
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4,5,6]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [7,8,9]\nObservation: I''ve used too many tools
+      for this task. I''m going to give you my absolute BEST Final answer now and
+      not use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2368'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPKsrN7s3j8bLplwjkAD2c7E6RK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198858,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used too many tools for this task. I'm going to give you my absolute BEST
+      Final answer now and not use any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      563,\n    \"completion_tokens\": 42,\n    \"total_tokens\": 605\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452671e0b500316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:21:00 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2080'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299436'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 112ms
+      x-request-id:
+      - b2b7142dc669054b82773d62077e9918
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -490,10 +714,11 @@ interactions:
      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
      is a force for good because it will help humans reach their full potential.\nEND
      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Don''t
-      give a Final Answer, instead keep using the `get_final_answer` tool non-stop\nThis
-      is the context you''re working with:\nHi\nAI: Agent stopped due to iteration
-      limit or time limit.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
-      false, "temperature": 0.7}'
+      give a Final Answer, instead keep using the `get_final_answer` tool.\nThis is
+      the context you''re working with:\nHi!\nAI: I''ve used too many tools for this
+      task. I''m going to give you my absolute BEST Final answer now and not use any
+      more tools.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      0.7}'
    headers:
      accept:
      - application/json
@@ -502,16 +727,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1031'
+      - '1096'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=2FkgHfXDTEWwtJx9fuYC7bMgshbFiKyrz77uUDT7zZs-1707555088-1-Aepn1cZI06+lHA4fg6WnGlRYQvOzF/0+FklFgWjzvCx0c9PWNVB0SHCULztQ+AdxbloscbFE14+qlktmxccvWLA=;
-        _cfuvid=euVu9TT31y3M3IcbZHjgSQIkmaipgL6G3sfBSomB.wA-1707555088785-0-604800000
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.7.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -521,7 +746,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.7.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -529,20 +754,21 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RRTU8jMQy9z6+wcm6raekH7Q3tHuAC0mq10oJQCTNmJpDY2dhTFqH+d5SZfohL
-        pLznZz8/fxYAxtVmA6ZqrVYh+vHlv/p2eXf9a/5nfcft6/3fm58rb2ed/qDd0oyygp9fsdKjalJx
-        iB7VMQ10ldAq5q7TVblaLBbletYTgWv0WdZEHc/H5XJ6cVC07CoUs4GHAgDgs3+zN6rxv9lAOToi
-        AUVsg2ZzKgIwiX1GjBVxopbUjM5kxaRIvd3fLULbBUvgSDR1lQpoi3B1A8QKytC4HYKFF0fWgyV5
-        xwSW6ky9IUboxFHTa54a1G1ftx3qnkCZPRDTWJTjBK75HXeYRscRtkFSyJxA3WHuiU5bTOAUk80B
-        gnfBKXACdQGH38QcdtmfQvDcxMTPOTDqvD/hL46ctNuEVpjywnnYIN8XAI992N23/ExMHKJuld+Q
-        pL/Zeuhnznc9s/PpgVRW68/4bFYWB4dGPkQx5GwaTDG5Pvvss9gXXwAAAP//AwAJcyracgIAAA==
+    content: "{\n  \"id\": \"chatcmpl-8gkPMD1hkXKA5DP8MyMJNpAxJXhzj\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198860,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI not to give
+      a final answer but to continue using the `get_final_answer` tool. However, the
+      AI responds that it has already used many tools for the task and chooses to
+      provide its best final answer without using any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      196,\n    \"completion_tokens\": 53,\n    \"total_tokens\": 249\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 85331c5e2baccfc4-SJC
+      - 8452672d1bba0316-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -552,7 +778,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 08:51:35 GMT
+      - Sun, 14 Jan 2024 02:21:03 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -566,7 +792,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '2537'
+      - '2683'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -578,14 +804,13 @@ interactions:
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299758'
+      - '299742'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 48ms
+      - 51ms
      x-request-id:
-      - req_c2fe098b8481dac7ed32f9d683eb36ac
-    status:
-      code: 200
-      message: OK
+      - c00193638e659df4a60ef9425649fe2c
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/cassettes/test_api_calls_throttling.yaml
+++ b/tests/cassettes/test_api_calls_throttling.yaml
--- a/tests/cassettes/test_cache_hitting.yaml
+++ b/tests/cassettes/test_cache_hitting.yaml
--- a/tests/cassettes/test_cache_hitting_between_agents.yaml
+++ b/tests/cassettes/test_cache_hitting_between_agents.yaml
--- a/tests/cassettes/test_crew_full_ouput.yaml
+++ b/tests/cassettes/test_crew_full_ouput.yaml
@@ -1,431 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
-      Do I need to use a tool? Yes\nAction: the action to take, should be one of [],
-      just the name.\nAction Input: the input to the action\nObservation: the result
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
-      a tool? No\nFinal Answer: [your response here]```This is the summary of your
-      work so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
-      Task: just say hi!\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
-      "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '846'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.11.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.11.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQS0/DMBCE7/kVi88tSiDqIxdUCSrgAKpAQghQ5TqbxMXxGnsjQFX/O0qaPrj4
-        MLOz/mY3EYDQuchAqEqyqp0ZTr7mj2kS+0IvXmor5dPrfVIvblTh4/VMDNoErdaoeJ86V1Q7g6zJ
-        7mzlUTK2W5NxPE5HF5PpqDNqytG0sdLxMB3Go+SyT1SkFQaRwVsEALDp3pbN5vgjMogHe6XGEGSJ
-        IjsMAQhPplWEDEEHlpbF4Ggqsoy2w32uqCkrzuCa4A4sYg5M0AQECUxkruCB3u1cW2lgZsM3+gxu
-        9Znol20PFIZK52nVEtvGmINeaKtDtfQoA9n2x8DkdvFtBPDRtW3+FRDOU+14yfSJNnRHG+/2ieNh
-        T93eZGJpTvRpGvWEIvwGxnpZaFuid1535VvOaBv9AQAA//8DAB3dd33zAQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 852a51805aad67eb-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 09 Feb 2024 07:14:58 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=9ly7231xuotblGKWs6jbqP1UIOLx4Z4fGC_GzaLrjf0-1707462898-1-ARsy16USRPFgm9nFkRCgyVEJ0bZHxoljRrPhQDJWOAGApKCPHnJUOUKp5ZIYM+Cye1FsXshcWJ4eSs/1aHvjl74=;
-        path=/; expires=Fri, 09-Feb-24 07:44:58 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=Myd_SP.rh1qGv3eu8_4uoiAw_XxGG6sO.jpzVZqLJGc-1707462898242-0-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1227'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299811'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 37ms
-      x-request-id:
-      - req_8e9048cd17dae372866713b1f204fc99
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
-      lines of conversation provided, adding onto the previous summary returning a
-      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
-      of artificial intelligence. The AI thinks artificial intelligence is a force
-      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
-      intelligence is a force for good?\nAI: Because artificial intelligence will
-      help humans reach their full potential.\n\nNew summary:\nThe human asks what
-      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
-      is a force for good because it will help humans reach their full potential.\nEND
-      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: just
-      say hi!\nAI: Hi!\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
-      "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '867'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=9ly7231xuotblGKWs6jbqP1UIOLx4Z4fGC_GzaLrjf0-1707462898-1-ARsy16USRPFgm9nFkRCgyVEJ0bZHxoljRrPhQDJWOAGApKCPHnJUOUKp5ZIYM+Cye1FsXshcWJ4eSs/1aHvjl74=;
-        _cfuvid=Myd_SP.rh1qGv3eu8_4uoiAw_XxGG6sO.jpzVZqLJGc-1707462898242-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.11.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.11.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQS0/DMBCE7/kVK5/bqi1R+rhxAKlFqBw4gVDlOpvY4Niud1OoUP87cvrkYlkz
-        nvW385sBCFOKOQilJasm2P50+7gqXp6ed25FbzM92y4Xq4nmAstl/SB6KeE3n6j4nBoo3wSLbLw7
-        2iqiZExTR5PhJC/G09m0Mxpfok2xOnA/7w+L0d0pob1RSGIO7xkAwG93JjZX4o+Yw7B3VhokkjWK
-        +eURgIjeJkVIIkMsHYve1VTeMboO91Uj6LaRDowjjq1iAtYI9wtgDyT3oE0vXb+1UfpsRaTgXUkg
-        q8rERrLZod0PxOmLw4XN+jpEv0l7uNbai14ZZ0ivI0ryLnEQ+3CMHzKAj66D9t9aIkTfBF6z/0KX
-        Bo7y/DhPXOu+cacnkz1Le6MX4+xEKGhPjM26Mq7GGKLpKkmc2SH7AwAA//8DAHvVVasJAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 852a518a581d67eb-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 09 Feb 2024 07:14:59 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1261'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299799'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 40ms
-      x-request-id:
-      - req_c169edc1f697d9f897dd46b3fe23da76
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\n\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
-      Do I need to use a tool? Yes\nAction: the action to take, should be one of [],
-      just the name.\nAction Input: the input to the action\nObservation: the result
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
-      a tool? No\nFinal Answer: [your response here]```This is the summary of your
-      work so far:\nThe human instructs the AI to say hi, to which the AI responds
-      affirmatively.Begin! This is VERY important to you, your job depends on it!\n\nCurrent
-      Task: just say hello!\nThis is the context you''re working with:\nHi!\n"}],
-      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '973'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=9ly7231xuotblGKWs6jbqP1UIOLx4Z4fGC_GzaLrjf0-1707462898-1-ARsy16USRPFgm9nFkRCgyVEJ0bZHxoljRrPhQDJWOAGApKCPHnJUOUKp5ZIYM+Cye1FsXshcWJ4eSs/1aHvjl74=;
-        _cfuvid=Myd_SP.rh1qGv3eu8_4uoiAw_XxGG6sO.jpzVZqLJGc-1707462898242-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.11.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.11.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQX0/CMBTF3/cprn0GMyYC7sUYDVHxT4z6YNSQ0l22Ytc72ruoEL676ZigL304
-        p7/Tc7qOAITORApCFZJVWZnuaDm+Hz08r9RiNdHLx4InN6pY3Onr89vsRXQCQbMFKv6lDhWVlUHW
-        ZLe2cigZQ2pvGA/7g+QkjhujpAxNwPKKu/1uPOgdtURBWqEXKbxGAADr5gzdbIZfIoWGb5QSvZc5
-        inR3CUA4MkER0nvtWVoWnb2pyDLapu5TQXVecAoXBFdgETNggtojSGAicwp39GbH2koDZ9Z/okvh
-        Eo2hA9HmbXZFDOWVo1kobWtjdvpcW+2LqUPpyYZHPVO1xTcRwHszuP63QVSOyoqnTB9oQ2ASH2/z
-        xP5v925v2JpMLM0fKkmitqHw356xnM61zdFVTjf7Q89oE/0AAAD//wMAxl1LJ/YBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 852a5196983067eb-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 09 Feb 2024 07:15:01 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1093'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299780'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 43ms
-      x-request-id:
-      - req_908d51731310c13867cd2dd7d565348b
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
-      lines of conversation provided, adding onto the previous summary returning a
-      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
-      of artificial intelligence. The AI thinks artificial intelligence is a force
-      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
-      intelligence is a force for good?\nAI: Because artificial intelligence will
-      help humans reach their full potential.\n\nNew summary:\nThe human asks what
-      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
-      is a force for good because it will help humans reach their full potential.\nEND
-      OF EXAMPLE\n\nCurrent summary:\nThe human instructs the AI to say hi, to which
-      the AI responds affirmatively.\n\nNew lines of conversation:\nHuman: just say
-      hello!\nThis is the context you''re working with:\nHi!\nAI: Hello!\n\nNew summary:"}],
-      "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '997'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=9ly7231xuotblGKWs6jbqP1UIOLx4Z4fGC_GzaLrjf0-1707462898-1-ARsy16USRPFgm9nFkRCgyVEJ0bZHxoljRrPhQDJWOAGApKCPHnJUOUKp5ZIYM+Cye1FsXshcWJ4eSs/1aHvjl74=;
-        _cfuvid=Myd_SP.rh1qGv3eu8_4uoiAw_XxGG6sO.jpzVZqLJGc-1707462898242-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.11.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.11.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRS2sjMRCE7/MrGp3tYMdZO/bNEJaEXQgse8iDYGRNz0iOpFbUPZuY4P8eNH5l
-        LzpU9ddUtT4rAOVqtQBlrBYTkh9ev/28n//4jY+/uLkd0+My0Hr28HR3037c/FGDQtB6g0aO1IWh
-        kDyKo7i3TUYtWLaOZ6PZ1fRyPhr3RqAafcHaJMOr4Wg6nhwIS84gqwU8VwAAn/1bssUaP9QCRoOj
-        EpBZt6gWpyEAlckXRWlmx6KjqMHZNBQFYx/3r0WwXdARXGTJnREGsQjLOxAC1luwDnSsixiLtOlY
-        9jp6T4MivVtn7JHKyIlizaCbxuWgxf1DvwXUZcQFvFCHHLtTAU9tyrQuZWPn/UlvXHRsVxk1Uyxh
-        WSjt8V0F8NIfqvuvu0qZQpKV0CtG7u892e9T5z85u5fTgykk2n+j5vPqkFDxlgXDqnGxxZyy6+9W
-        cla76gsAAP//AwDz/udFLgIAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 852a519e29bb67eb-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 09 Feb 2024 07:15:03 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1955'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299767'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 46ms
-      x-request-id:
-      - req_24c78e42a235c08ae9c6f1b5dbff3c6f
-    status:
-      code: 200
-      message: OK
-version: 1
--- a/tests/cassettes/test_hierarchical_process.yaml
+++ b/tests/cassettes/test_hierarchical_process.yaml
--- a/tests/cassettes/test_logging_tool_usage.yaml
+++ b/tests/cassettes/test_logging_tool_usage.yaml
@@ -1,19 +1,21 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      name.\nAction Input: Any and all relevant information input and context for
-      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      a response for your task, or if you do not need to use a tool, you MUST use
-      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 5?\n"}],
-      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
+      a tool, please use the exact following format:\n\n```\nThought: Do I need to
+      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
+      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: What is 3 times 5?\n\n"}], "model": "gpt-4", "n": 1,
+      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
    headers:
      accept:
      - application/json
@@ -22,13 +24,13 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1047'
+      - '1231'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -38,7 +40,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -46,20 +48,18 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRS0/DMBCE7/kVqz2nqK8AzQUhEIIbIDggiqrU2SQujtfYGwmo+t+R0ycXH2Z2
-        Vt+s1wkA6hJzQNUUolpnBpdfarby1ROZ2fju9fGesko/X36W05vfc41pTPByRUr2qTPFrTMkmu3W
-        Vp4Kobh1dDG8yLLhdDTrjZZLMjFWOxlMB8Pz0WSXaFgrCpjDewIAsO7fyGZL+sYchuleaSmEoibM
-        D0MA6NlEBYsQdJDCCqZHU7EVsj3uS8Nd3UgOtwwPYIlKEIYuEBQgzOYK3ijM7bWKZXJoOyPaGU1+
-        r8GDdZ3ksJ5jpX2Qhe3aJfk55jBJYY6BFNvyRM02uCPZHCoYrp3nZaxrO2MOeqWtDs3CUxHYRtwg
-        7LbxTQLw0Z+q+9cenefWyUL4k2xcOB6Ptvvw+CtHdzLZmcJSmJNUNk12hBh+glC7qLStyTuv+8tF
-        zmST/AEAAP//AwCr+Q67MAIAAA==
+    content: "{\n  \"id\": \"chatcmpl-8b7eDhOwdMJw0817wIqiD9MoXVRU8\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858225,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      multiplier\\nAction Input: 3,5\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 264,\n    \"completion_tokens\":
+      23,\n    \"total_tokens\": 287\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532aa4bca4e679a-SJC
+      - 83d28cd70f9f1cd9-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -69,14 +69,14 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:33:41 GMT
+      - Fri, 29 Dec 2023 13:57:07 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
-        path=/; expires=Sat, 10-Feb-24 08:03:41 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        path=/; expires=Fri, 29-Dec-23 14:27:07 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000;
+      - _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
@@ -89,7 +89,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1673'
+      - '1725'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -98,39 +98,43 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299762'
+      - '299717'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299717'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 47ms
+      - 56ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 56ms
      x-request-id:
-      - req_e5461f12abf90cd87cea37b9c47989e0
-    status:
-      code: 200
-      message: OK
+      - 689757a1e38baf0844ec69f20525c5d7
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
-    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
-      ''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
-      int, second_number: int) -> float - Useful for when you need to multiply two
-      numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
-      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      3, \"second_number\": 5}\n\nThe output should be formatted as a JSON instance
-      that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
-      "n": 1, "stream": false, "temperature": 0.7}'
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
+      a tool, please use the exact following format:\n\n```\nThought: Do I need to
+      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
+      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: What is 3 times 5?\nThought: Do I need to use a tool?
+      Yes\nAction: multiplier\nAction Input: 3,5\nObservation: 15\nThought: \n"}],
+      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
    headers:
      accept:
      - application/json
@@ -139,16 +143,16 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1494'
+      - '1335'
      content-type:
      - application/json
      cookie:
-      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
-        _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -158,7 +162,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -166,20 +170,18 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SRO2/cMBCEe/2KBWtdIN0jF6t1kRQG7MApDISBjketJNrkUiFX8AUH/feAupfd
-        sNiZbzE7PGYAwjSiAqF7xdoNdvHtr76zT+XDy+HXz/v3t2e6f/xelHx4ennmpcgT4fevqPlCfdHe
-        DRbZeDrJOqBiTFvLbbHdbIr1spwF5xu0CesGXqwXxddydSZ6bzRGUcHvDADgOL8pGzV4EBUU+WXi
-        MEbVoaiuJgARvE0ToWI0kRWxyG+i9sRIc9wfGBBMBAXvaO2i9cEpZmzAUMI0gm+Be4Soe3SqkiRp
-        t9u9Rk+SjpIApGhH0unWmpRDKSqQwo2WzWANBinyk0uFbnRIHJNjJmfWhMg1jW6frBWs8osSUXtq
-        PkibpEySpjmBOJ8zXXuwvhuC36fOaLT2Om8NmdjXAVX0lG6O7IcTPmUAf+a+x08ViiF4N3DN/g0p
-        LVwtN6d94va1N3V9dxbZs7IfqO06OycU8V9kdHVrqMMwBDPXn3JmU/YfAAD//wMAtRBeM3UCAAA=
+    content: "{\n  \"id\": \"chatcmpl-8b7eG2qnUr6SZcankL5AqkwIJvYFc\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858228,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      3 times 5 is 15.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 297,\n    \"completion_tokens\":
+      22,\n    \"total_tokens\": 319\n  },\n  \"system_fingerprint\": null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532aa5709e5679a-SJC
+      - 83d28ce3ab3b1cd9-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -189,7 +191,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:33:44 GMT
+      - Fri, 29 Dec 2023 13:57:09 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -203,7 +205,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '2203'
+      - '1568'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -212,128 +214,24 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299661'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 67ms
-      x-request-id:
-      - req_a428e78fc8e9d475e463316f65950fa9
-    status:
-      code: 200
-      message: OK
- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      name.\nAction Input: Any and all relevant information input and context for
-      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      a response for your task, or if you do not need to use a tool, you MUST use
-      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 5?\nThought:
-      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      3, \"second_number\": 5}\nObservation: 15\nThought: "}], "model": "gpt-4", "n":
-      1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1191'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
-        _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQW0sDMRCF3/dXDHluy/aybd0XEYqiiKAiFFRKmp1uY7OZmMyipfS/S7bbiy95
-        OGfOyTezSwCELkQOQq0lq8qZ7vRbXRGrVz2fPPKd3z7MeSPty2r29uy06MQELb9Q8THVU1Q5g6zJ
-        HmzlUTLG1v4knWRZOhqMGqOiAk2MlY67o2467g/bxJq0wiByeE8AAHbNG9lsgb8ih7RzVCoMQZYo
-        8tMQgPBkoiJkCDqwtCw6Z1ORZbQN7ozgHixiAUxQBwQJTGSu4Yk+7K220sCNDT/ocxgC6woDZKAD
-        9LOeaAv3JxJDpfO0jNS2Nuakr7TVYb3wKAPZ+Gtgcof4PgH4bDau/y0hnKfK8YJpgzYWDsbDQ584
-        H/fCHbQmE0tzoU+zpCUUYRsYq8VK2xK987o5QORM9skfAAAA//8DACAb4vP3AQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8532aa66fd5c679a-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 10 Feb 2024 07:33:45 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - user-z7g4wmlazxqvc5wjyaaaocfz
-      openai-processing-ms:
-      - '1275'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
+      x-ratelimit-limit-tokens_usage_based:
      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
-      - '299728'
+      - '299693'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299693'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
-      - 54ms
+      - 61ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 61ms
      x-request-id:
-      - req_dd069a32b6514615a79356287e845a29
-    status:
-      code: 200
-      message: OK
+      - 66a02e3e08e3f6b5b29fb04cd19f50a0
+    http_version: HTTP/1.1
+    status_code: 200
 - request:
    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
      lines of conversation provided, adding onto the previous summary returning a
@@ -359,12 +257,12 @@ interactions:
      content-type:
      - application/json
      cookie:
-      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
-        _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
      host:
      - api.openai.com
      user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.6.1
      x-stainless-arch:
      - arm64
      x-stainless-async:
@@ -374,7 +272,7 @@ interactions:
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
-      - 1.12.0
+      - 1.6.1
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
@@ -382,19 +280,19 @@ interactions:
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SQT0/CQBDF7/0Ukz0XQgsV6E0TD2qiHtSYGEOW7dCu7D92p4lC+O5mS6F62cO8
-        93v7Zg4JAJMVK4GJhpPQTo0WO7F0ezl7549q+bx/eMp3t+v8Zlrdv27eWBoJu/5CQWdqLKx2Ckla
-        c5KFR04YU7P5ZF4Uk1ledIK2FaqI1Y5Gs9HkKpv2RGOlwMBK+EgAAA7dG7uZCr9ZCZP0PNEYAq+R
-        lRcTAPNWxQnjIchA3BBLB1FYQ2i6ui8NQtNqboCHbQBqEK7vgCwIrkSrOCFMgaTGAEUK3FRni8fg
-        rKkiwmnwgAyQFWPWf3a8tFS2dt6u40amVeoy30gjQ7PyyIM1sVEg6074MQH47K7R/luQOW+1oxXZ
-        LZoYmBXFKY8Nhx/UfN6LZImrP9QiT/qGLPwEQr3aSFOjd152x4k9k2PyCwAA//8DAHepd0ITAgAA
+    content: "{\n  \"id\": \"chatcmpl-8b7eIfmBgQoWGLW4jiQZTu3qzEBBL\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858230,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to calculate 3
+      times 5 and the AI responds that 3 times 5 is 15.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      155,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 181\n  },\n  \"system_fingerprint\":
+      null\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
-      - 8532aa703b92679a-SJC
+      - 83d28cf118221cd9-GRU
      Cache-Control:
      - no-cache, must-revalidate
      Connection:
@@ -404,7 +302,7 @@ interactions:
      Content-Type:
      - application/json
      Date:
-      - Sat, 10 Feb 2024 07:33:47 GMT
+      - Fri, 29 Dec 2023 13:57:12 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
@@ -418,7 +316,7 @@ interactions:
      openai-organization:
      - user-z7g4wmlazxqvc5wjyaaaocfz
      openai-processing-ms:
-      - '1667'
+      - '2188'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
@@ -427,17 +325,366 @@ interactions:
      - '10000'
      x-ratelimit-limit-tokens:
      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
      - '299794'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299794'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 41ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 41ms
      x-request-id:
-      - req_14ec03ab8500562c8eaac94fe2cec349
-    status:
-      code: 200
-      message: OK
+      - a644c703d416b1e4b06586e96e6d7297
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
+      a tool, please use the exact following format:\n\n```\nThought: Do I need to
+      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
+      of your work so far:\n    The human asks the AI to calculate 3 times 5 and the
+      AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
+      job depends on it!\n\nCurrent Task: What is 3 times 5?\n\n"}], "model": "gpt-4",
+      "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1317'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8b7eKehkNtTjrXJD0aFjiVUeXU7te\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858232,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      multiplier\\nAction Input: 3,5\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 290,\n    \"completion_tokens\":
+      23,\n    \"total_tokens\": 313\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28d007f461cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:14 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1885'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299697'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299697'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 60ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 60ms
+      x-request-id:
+      - 87959bfa6a029f7bcafb5095e66d4964
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
+      a tool, please use the exact following format:\n\n```\nThought: Do I need to
+      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
+      of your work so far:\n    The human asks the AI to calculate 3 times 5 and the
+      AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
+      job depends on it!\n\nCurrent Task: What is 3 times 5?\n\nI just used the multiplier
+      tool with input 3,5. So I already knwo the result of that.\nObservation: Invalid
+      or incomplete response\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1460'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8b7eME5fg1w8QcXUnl0FBcqxJWy7u\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858234,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      3 times 5 is 15.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 324,\n    \"completion_tokens\":
+      22,\n    \"total_tokens\": 346\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28d0fcfaf1cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:17 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2494'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299661'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299661'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 67ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 67ms
+      x-request-id:
+      - eb9704531634d4cd3c6652dff09914bc
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 3 times 5
+      and the AI responds that 3 times 5 is 15.\n\nNew lines of conversation:\nHuman:
+      What is 3 times 5?\nAI: 3 times 5 is 15.\n\nNew summary:"}], "model": "gpt-4",
+      "n": 1, "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '972'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8b7eP77MzprkbgjaMbeaEob0aDx39\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858237,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to calculate 3
+      times 5 twice, and both times the AI responds that 3 times 5 is 15.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 181,\n    \"completion_tokens\": 30,\n
+      \   \"total_tokens\": 211\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28d211f591cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:20 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2967'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299771'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299771'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 45ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 45ms
+      x-request-id:
+      - e3bbd11b2e9b28f76f8b43dc7a4d2b6d
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1
--- a/tests/crew_test.py
+++ b/tests/crew_test.py
@@ -160,7 +160,22 @@ def test_hierarchical_process():

    assert (
        crew.kickoff()
-        == """Here are the five interesting ideas for an article with a highlight paragraph for each:\n\n1. The Evolution of Artificial Intelligence:\nDive deep into the fascinating journey of artificial intelligence, from its humble beginnings as a concept in science fiction to an integral part of our daily lives and a catalyst of modern innovations. Explore how AI has evolved over the years, the key milestones that have shaped its growth, and the visionary minds behind these advancements. Uncover the remarkable transformation of AI and its astounding potential for the future.\n\n2. AI in Everyday Life:\nUncover the unseen impact of AI in our every day lives, from our smartphones and home appliances to social media and healthcare. Learn about the subtle yet profound ways AI has become a silent partner in your daily routine, enhancing convenience, productivity, and decision-making. Explore the numerous applications of AI right at your fingertips and how it shapes our interactions with technology and the world around us.\n\n3. Ethical Implications of AI:\nVenture into the ethical labyrinth of artificial intelligence, where innovation meets responsibility. Explore the implications of AI on privacy, job security, and societal norms, and the moral obligations we have towards its development and use. Delve into the thought-provoking debates about AI ethics and the measures being taken to ensure its responsible and equitable use.\n\n4. The Rise of AI Startups:\nWitness the rise of AI startups, the new champions of innovation, driving the technology revolution. Discover how these trailblazing companies are harnessing the power of AI to solve complex problems, create new markets, and revolutionize industries. Learn about their unique challenges, their groundbreaking solutions, and the potential they hold for reshaping the future of technology and business.\n\n5. AI and the Environment:\nExplore the intersection of AI and the environment, where technology meets sustainability. Uncover how AI is being used to combat climate change, conserve biodiversity, and optimize resource utilization. Learn about the innovative ways AI is being used to create a sustainable future and the challenges and opportunities it presents."""
+        == """Here are the 5 interesting ideas with a highlight paragraph for each:
+
+1. "The Future of AI in Healthcare: Predicting Diseases Before They Happen"
+   - "Imagine a future where AI empowers us to detect diseases before they arise, transforming healthcare from reactive to proactive. Machine learning algorithms, trained on vast amounts of patient data, could potentially predict heart diseases, strokes, or cancers before they manifest, allowing for early interventions and significantly improving patient outcomes. This article will delve into the rapid advancements in AI within the healthcare sector and how these technologies are ushering us into a new era of predictive medicine."
+
+2. "How AI is Changing the Way We Cook: An Insight into Smart Kitchens"
+   - "From the humble home kitchen to grand culinary stages, AI is revolutionizing the way we cook. Smart appliances, equipped with advanced sensors and predictive algorithms, are turning kitchens into creative playgrounds, offering personalized recipes, precise cooking instructions, and even automated meal preparation. This article explores the fascinating intersection of AI and gastronomy, revealing how technology is transforming our culinary experiences."
+
+3. "Redefining Fitness with AI: Personalized Workout Plans and Nutritional Advice"
+   - "Fitness reimagined – that's the promise of AI in the wellness industry. Picture a personal trainer who knows your strengths, weaknesses, and nutritional needs intimately. An AI-powered fitness app can provide this personalized experience, adapting your workout plans and dietary recommendations in real-time based on your progress and feedback. Join us as we unpack how AI is revolutionizing the fitness landscape, offering personalized, data-driven approaches to health and well-being."
+
+4. "AI and the Art World: How Technology is Shaping Creativity"
+   - "Art and AI may seem like unlikely partners, but their synergy is sparking a creative revolution. AI algorithms are now creating mesmerizing artworks, challenging our perceptions of creativity and originality. From AI-assisted painting to generative music composition, this article will take you on a journey through the fascinating world of AI in art, exploring how technology is reshaping the boundaries of human creativity."
+
+5. "AI in Space Exploration: The Next Frontier"
+   - "The vast expanse of space, once the sole domain of astronauts and rovers, is the next frontier for AI. AI technology is playing an increasingly vital role in space exploration, from predicting space weather to assisting in interstellar navigation. This article will delve into the exciting intersection of AI and space exploration, exploring how these advanced technologies are helping us uncover the mysteries of the cosmos.\""""
    )


@@ -262,14 +277,18 @@ def test_crew_verbose_levels_output(capsys):

@pytest.mark.vcr(filter_headers=["authorization"])
 def test_cache_hitting_between_agents():
-    from unittest.mock import call, patch
+    from unittest.mock import patch

    from langchain.tools import tool

    @tool
-    def multiplier(first_number: int, second_number: int) -> float:
-        """Useful for when you need to multiply two numbers together."""
-        return first_number * second_number
+    def multiplier(numbers) -> float:
+        """Useful for when you need to multiply two numbers together.
+        The input to this tool should be a comma separated list of numbers of
+        length two, representing the two numbers you want to multiply together.
+        For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
+        a, b = numbers.split(",")
+        return int(a) * int(b)

    tasks = [
        Task(
@@ -289,16 +308,15 @@ def test_cache_hitting_between_agents():
        tasks=tasks,
    )

+    assert crew._cache_handler._cache == {}
+    output = crew.kickoff()
+    assert crew._cache_handler._cache == {"multiplier-2,6": "12"}
+    assert output == "12"
+
    with patch.object(CacheHandler, "read") as read:
        read.return_value = "12"
        crew.kickoff()
-        assert read.call_count == 2, "read was not called exactly twice"
-        # Check if read was called with the expected arguments
-        expected_calls = [
-            call(tool="multiplier", input={"first_number": 2, "second_number": 6}),
-            call(tool="multiplier", input={"first_number": 2, "second_number": 6}),
-        ]
-        read.assert_has_calls(expected_calls, any_order=False)
+        read.assert_called_with("multiplier", "2,6")


@pytest.mark.vcr(filter_headers=["authorization"])
@@ -338,34 +356,6 @@ def test_api_calls_throttling(capsys):
        moveon.assert_called()


-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_full_ouput():
-    agent = Agent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-        allow_delegation=False,
-        verbose=True,
-    )
-
-    task1 = Task(
-        description="just say hi!",
-        agent=agent,
-    )
-    task2 = Task(
-        description="just say hello!",
-        agent=agent,
-    )
-
-    crew = Crew(agents=[agent], tasks=[task1, task2], full_output=True)
-
-    result = crew.kickoff()
-    assert result == {
-        "final_output": "Hello!",
-        "tasks_outputs": [task1.output, task2.output],
-    }
-
-
 def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
    agent = Agent(
        role="test role",
@@ -421,7 +411,7 @@ def test_async_task_execution():
        with patch.object(threading.Thread, "start") as start:
            thread = threading.Thread(target=lambda: None, args=()).start()
            start.return_value = thread
-            with patch.object(threading.Thread, "join", wraps=thread.join()) as join:
+            with patch.object(threading.Thread, "join", wraps=thread.join()) as join:  # type: ignore
                list_ideas.output = TaskOutput(
                    description="A 4 paragraph article about AI.", result="ok"
                )
@@ -431,71 +421,3 @@ def test_async_task_execution():
                crew.kickoff()
                start.assert_called()
                join.assert_called()
-
-
-def test_set_agents_step_callback():
-    from unittest.mock import patch
-
-    researcher_agent = Agent(
-        role="Researcher",
-        goal="Make the best research and analysis on content about AI and AI agents",
-        backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
-        allow_delegation=False,
-    )
-
-    list_ideas = Task(
-        description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-        expected_output="Bullet point list of 5 important events.",
-        agent=researcher_agent,
-        async_execution=True,
-    )
-
-    crew = Crew(
-        agents=[researcher_agent],
-        process=Process.sequential,
-        tasks=[list_ideas],
-        step_callback=lambda: None,
-    )
-
-    with patch.object(Agent, "execute_task") as execute:
-        execute.return_value = "ok"
-        crew.kickoff()
-        assert researcher_agent.step_callback is not None
-
-
-def test_dont_set_agents_step_callback_if_already_set():
-    from unittest.mock import patch
-
-    def agent_callback(_):
-        pass
-
-    def crew_callback(_):
-        pass
-
-    researcher_agent = Agent(
-        role="Researcher",
-        goal="Make the best research and analysis on content about AI and AI agents",
-        backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
-        allow_delegation=False,
-        step_callback=agent_callback,
-    )
-
-    list_ideas = Task(
-        description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-        expected_output="Bullet point list of 5 important events.",
-        agent=researcher_agent,
-        async_execution=True,
-    )
-
-    crew = Crew(
-        agents=[researcher_agent],
-        process=Process.sequential,
-        tasks=[list_ideas],
-        step_callback=crew_callback,
-    )
-
-    with patch.object(Agent, "execute_task") as execute:
-        execute.return_value = "ok"
-        crew.kickoff()
-        assert researcher_agent.step_callback is not crew_callback
-        assert researcher_agent.step_callback is agent_callback
--- a/tests/task_test.py
+++ b/tests/task_test.py
@@ -74,7 +74,7 @@ def test_task_prompt_includes_expected_output():
    with patch.object(Agent, "execute_task") as execute:
        execute.return_value = "ok"
        task.execute()
-        execute.assert_called_once_with(task=task, context=None, tools=[])
+        execute.assert_called_once_with(task=task._prompt(), context=None, tools=[])


 def test_task_callback():
@@ -115,7 +115,7 @@ def test_execute_with_agent():

    with patch.object(Agent, "execute_task", return_value="ok") as execute:
        task.execute(agent=researcher)
-        execute.assert_called_once_with(task=task, context=None, tools=[])
+        execute.assert_called_once_with(task=task._prompt(), context=None, tools=[])


 def test_async_execution():
@@ -135,4 +135,4 @@ def test_async_execution():

    with patch.object(Agent, "execute_task", return_value="ok") as execute:
        task.execute(agent=researcher)
-        execute.assert_called_once_with(task=task, context=None, tools=[])
+        execute.assert_called_once_with(task=task._prompt(), context=None, tools=[])