crewAI/lib/crewai/tests/cassettes/utilities/TestSummarizeDirectOpenAI.test_summarize_direct_openai.yaml

interactions:
- request:
    body: '{"messages":[{"role":"system","content":"You are a precise assistant that
      creates structured summaries of agent conversations. You preserve critical context
      needed for seamless task continuation."},{"role":"user","content":"Analyze the
      following conversation and create a structured summary that preserves all information
      needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Research
      the latest developments in large language models. Focus on architecture improvements
      and training techniques.\n\n[ASSISTANT]: I''ll research the latest developments
      in large language models. Based on my knowledge, recent advances include:\n1.
      Mixture of Experts (MoE) architectures\n2. Improved attention mechanisms like
      Flash Attention\n3. Better training data curation techniques\n4. Constitutional
      AI and RLHF improvements\n\n[USER]: Can you go deeper on the MoE architectures?
      What are the key papers?\n\n[ASSISTANT]: Key papers on Mixture of Experts:\n-
      Switch Transformers (Google, 2021) - simplified MoE routing\n- GShard - scaling
      to 600B parameters\n- Mixtral (Mistral AI) - open-source MoE model\nThe main
      advantage is computational efficiency: only a subset of experts is activated
      per token.\n</conversation>\n\nCreate a summary with these sections:\n1. **Task
      Overview**: What is the agent trying to accomplish?\n2. **Current State**: What
      has been completed so far? What step is the agent on?\n3. **Important Discoveries**:
      Key facts, data, tool results, or findings that must not be lost.\n4. **Next
      Steps**: What should the agent do next based on the conversation?\n5. **Context
      to Preserve**: Any specific values, names, URLs, code snippets, or details referenced
      in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your
      structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
    headers:
      User-Agent:
      - X-USER-AGENT-XXX
      accept:
      - application/json
      accept-encoding:
      - ACCEPT-ENCODING-XXX
      authorization:
      - AUTHORIZATION-XXX
      connection:
      - keep-alive
      content-length:
      - '1844'
      content-type:
      - application/json
      host:
      - api.openai.com
      x-stainless-arch:
      - X-STAINLESS-ARCH-XXX
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - X-STAINLESS-OS-XXX
      x-stainless-package-version:
      - 1.83.0
      x-stainless-read-timeout:
      - X-STAINLESS-READ-TIMEOUT-XXX
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.13.3
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    body:
      string: "{\n  \"id\": \"chatcmpl-D7RxGISdQet8JsWImiwzHQ2S9gSD4\",\n  \"object\":
        \"chat.completion\",\n  \"created\": 1770668126,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
        \"assistant\",\n        \"content\": \"<summary>\\n1. **Task Overview**: The
        agent is tasked with researching the latest developments in large language
        models, specifically focusing on architecture improvements and training techniques.\\n\\n2.
        **Current State**: The agent has identified several recent advances in large
        language models, including Mixture of Experts (MoE) architectures, improved
        attention mechanisms, better training data curation techniques, and advancements
        in Constitutional AI and Reinforcement Learning from Human Feedback (RLHF).\\n\\n3.
        **Important Discoveries**: \\n   - Recent advances in large language models
        include:\\n     1. Mixture of Experts (MoE) architectures\\n     2. Improved
        attention mechanisms like Flash Attention\\n     3. Better training data curation
        techniques\\n     4. Constitutional AI and RLHF improvements\\n   - Key papers
        on Mixture of Experts:\\n     - Switch Transformers (Google, 2021) - simplified
        MoE routing\\n     - GShard - scaling to 600B parameters\\n     - Mixtral
        (Mistral AI) - open-source MoE model\\n   - The main advantage of MoE architectures
        is computational efficiency, as only a subset of experts is activated per
        token.\\n\\n4. **Next Steps**: The agent should delve deeper into the Mixture
        of Experts architectures, reviewing the key papers mentioned and summarizing
        their contributions and implications for large language models.\\n\\n5. **Context
        to Preserve**: \\n   - Key papers: \\n     - Switch Transformers (Google,
        2021)\\n     - GShard\\n     - Mixtral (Mistral AI)\\n   - Focus on computational
        efficiency of MoE architectures.\\n</summary>\",\n        \"refusal\": null,\n
        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 368,\n    \"completion_tokens\":
        328,\n    \"total_tokens\": 696,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
        \"default\",\n  \"system_fingerprint\": \"fp_f4ae844694\"\n}\n"
    headers:
      CF-RAY:
      - CF-RAY-XXX
      Connection:
      - keep-alive
      Content-Type:
      - application/json
      Date:
      - Mon, 09 Feb 2026 20:15:32 GMT
      Server:
      - cloudflare
      Strict-Transport-Security:
      - STS-XXX
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - X-CONTENT-TYPE-XXX
      access-control-expose-headers:
      - ACCESS-CONTROL-XXX
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - OPENAI-ORG-XXX
      openai-processing-ms:
      - '5395'
      openai-project:
      - OPENAI-PROJECT-XXX
      openai-version:
      - '2020-10-01'
      set-cookie:
      - SET-COOKIE-XXX
      x-openai-proxy-wasm:
      - v0.1
      x-ratelimit-limit-requests:
      - X-RATELIMIT-LIMIT-REQUESTS-XXX
      x-ratelimit-limit-tokens:
      - X-RATELIMIT-LIMIT-TOKENS-XXX
      x-ratelimit-remaining-requests:
      - X-RATELIMIT-REMAINING-REQUESTS-XXX
      x-ratelimit-remaining-tokens:
      - X-RATELIMIT-REMAINING-TOKENS-XXX
      x-ratelimit-reset-requests:
      - X-RATELIMIT-RESET-REQUESTS-XXX
      x-ratelimit-reset-tokens:
      - X-RATELIMIT-RESET-TOKENS-XXX
      x-request-id:
      - X-REQUEST-ID-XXX
    status:
      code: 200
      message: OK
version: 1