chore: make vcr tests pretty-print JSON (#146)

Signed-off-by: Adrian Cole <adrian.cole@elastic.co>

packages/exchange/tests/providers/cassettes/test_azure_complete.yaml

@@ -1,7 +1,19 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+    body: |-
-      {"role": "user", "content": "Hello"}], "model": "gpt-4o-mini"}'
+      {
+        "messages": [
+          {
+            "role": "system",
+            "content": "You are a helpful assistant."
+          },
+          {
+            "role": "user",
+            "content": "Hello"
+          }
+        ],
+        "model": "gpt-4o-mini"
+      }
     headers:
       accept:
       - '*/*'
@@ -23,35 +35,94 @@ interactions:
     uri: https://test.openai.azure.com/openai/deployments/test-azure-deployment/chat/completions?api-version=2024-05-01-preview
   response:
     body:
-      string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"content":"Hello!
+      string: |-
-        How can I assist you today?","role":"assistant"}}],"created":1727230065,"id":"chatcmpl-ABBjN3AoYlxkP7Vg2lBvUhYeA6j5K","model":"gpt-4-32k","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":9,"prompt_tokens":18,"total_tokens":27}}
+        {
-
+          "choices": [
-        '
+            {
+              "content_filter_results": {
+                "hate": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "self_harm": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "sexual": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "violence": {
+                  "filtered": false,
+                  "severity": "safe"
+                }
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null,
+              "message": {
+                "content": "Hello! How can I assist you today?\n",
+                "role": "assistant"
+              }
+            }
+          ],
+          "created": 1728788170,
+          "id": "chatcmpl-AHj469gGa9bQaCSikrZYDejfGDx2x",
+          "model": "gpt-4-32k",
+          "object": "chat.completion",
+          "prompt_filter_results": [
+            {
+              "prompt_index": 0,
+              "content_filter_results": {
+                "hate": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "self_harm": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "sexual": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "violence": {
+                  "filtered": false,
+                  "severity": "safe"
+                }
+              }
+            }
+          ],
+          "system_fingerprint": null,
+          "usage": {
+            "completion_tokens": 9,
+            "prompt_tokens": 18,
+            "total_tokens": 27
+          }
+        }
     headers:
       Cache-Control:
       - no-cache, must-revalidate
       Content-Length:
-      - '825'
+      - '827'
       Content-Type:
       - application/json
       Date:
-      - Wed, 25 Sep 2024 02:07:45 GMT
+      - Sun, 13 Oct 2024 02:56:10 GMT
-      Set-Cookie: test_set_cookie
       Strict-Transport-Security:
       - max-age=31536000; includeSubDomains; preload
       access-control-allow-origin:
       - '*'
       apim-request-id:
-      - 82e66ef8-ac07-4a43-b60f-9aecec1d8c81
+      - b203f657-e7aa-40ea-8969-ba0b83dae854
       azureml-model-session:
-      - d145-20240919052126
+      - d156-20241010120317
-      openai-organization: test_openai_org_key
       x-accel-buffering:
       - 'no'
       x-content-type-options:
       - nosniff
       x-ms-client-request-id:
-      - 82e66ef8-ac07-4a43-b60f-9aecec1d8c81
+      - b203f657-e7aa-40ea-8969-ba0b83dae854
       x-ms-rai-invoked:
       - 'true'
       x-ms-region:
@@ -61,7 +132,7 @@ interactions:
       x-ratelimit-remaining-tokens:
       - '79984'
       x-request-id:
-      - 38db9001-8b16-4efe-84c9-620e10f18c3c
+      - 0c6dc92f-a017-4879-b82e-be937533c76e
     status:
       code: 200
       message: OK

packages/exchange/tests/providers/cassettes/test_azure_tools.yaml

@@ -1,13 +1,40 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant.
+    body: |-
-      Expect to need to read a file using read_file."}, {"role": "user", "content":
+      {
-      "What are the contents of this file? test.txt"}], "model": "gpt-4o-mini", "tools":
+        "messages": [
-      [{"type": "function", "function": {"name": "read_file", "description": "Read
+          {
-      the contents of the file.", "parameters": {"type": "object", "properties": {"filename":
+            "role": "system",
-      {"type": "string", "description": "The path to the file, which can be relative
+            "content": "You are a helpful assistant. Expect to need to read a file using read_file."
-      or\nabsolute. If it is a plain filename, it is assumed to be in the\ncurrent
+          },
-      working directory."}}, "required": ["filename"]}}}]}'
+          {
+            "role": "user",
+            "content": "What are the contents of this file? test.txt"
+          }
+        ],
+        "model": "gpt-4o-mini",
+        "tools": [
+          {
+            "type": "function",
+            "function": {
+              "name": "read_file",
+              "description": "Read the contents of the file.",
+              "parameters": {
+                "type": "object",
+                "properties": {
+                  "filename": {
+                    "type": "string",
+                    "description": "The path to the file, which can be relative or\nabsolute. If it is a plain filename, it is assumed to be in the\ncurrent working directory."
+                  }
+                },
+                "required": [
+                  "filename"
+                ]
+              }
+            }
+          }
+        ]
+      }
     headers:
       accept:
       - '*/*'
@@ -29,10 +56,64 @@ interactions:
     uri: https://test.openai.azure.com/openai/deployments/test-azure-deployment/chat/completions?api-version=2024-05-01-preview
   response:
     body:
-      string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"content":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\n  \"filename\":
+      string: |-
-        \"test.txt\"\n}","name":"read_file"},"id":"call_a47abadDxlGKIWjvYYvGVAHa","type":"function"}]}}],"created":1727256650,"id":"chatcmpl-ABIeABbq5WVCq0e0AriGFaYDSih3P","model":"gpt-4-32k","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":null,"usage":{"completion_tokens":16,"prompt_tokens":109,"total_tokens":125}}
+        {
-
+          "choices": [
-        '
+            {
+              "content_filter_results": {},
+              "finish_reason": "tool_calls",
+              "index": 0,
+              "logprobs": null,
+              "message": {
+                "content": null,
+                "role": "assistant",
+                "tool_calls": [
+                  {
+                    "function": {
+                      "arguments": "{\n  \"filename\": \"test.txt\"\n}",
+                      "name": "read_file"
+                    },
+                    "id": "call_Dn0idyNSdmHSYpsql3EbFH9L",
+                    "type": "function"
+                  }
+                ]
+              }
+            }
+          ],
+          "created": 1728788173,
+          "id": "chatcmpl-AHj498XEBkixukw2lwNReXCIBStp0",
+          "model": "gpt-4-32k",
+          "object": "chat.completion",
+          "prompt_filter_results": [
+            {
+              "prompt_index": 0,
+              "content_filter_results": {
+                "hate": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "self_harm": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "sexual": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "violence": {
+                  "filtered": false,
+                  "severity": "safe"
+                }
+              }
+            }
+          ],
+          "system_fingerprint": null,
+          "usage": {
+            "completion_tokens": 16,
+            "prompt_tokens": 109,
+            "total_tokens": 125
+          }
+        }
     headers:
       Cache-Control:
       - no-cache, must-revalidate
@@ -41,33 +122,31 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 25 Sep 2024 09:30:50 GMT
+      - Sun, 13 Oct 2024 02:56:14 GMT
-      Set-Cookie: test_set_cookie
       Strict-Transport-Security:
       - max-age=31536000; includeSubDomains; preload
       access-control-allow-origin:
       - '*'
       apim-request-id:
-      - 8c0e3372-8ffd-4ff5-a5d1-0b962c4ea339
+      - 0e0af575-5634-415c-88e3-a7bf68549ee5
       azureml-model-session:
-      - d145-20240919052126
+      - d159-20241010142543
-      openai-organization: test_openai_org_key
       x-accel-buffering:
       - 'no'
       x-content-type-options:
       - nosniff
       x-ms-client-request-id:
-      - 8c0e3372-8ffd-4ff5-a5d1-0b962c4ea339
+      - 0e0af575-5634-415c-88e3-a7bf68549ee5
       x-ms-rai-invoked:
       - 'true'
       x-ms-region:
       - Switzerland North
       x-ratelimit-remaining-requests:
-      - '79'
+      - '77'
       x-ratelimit-remaining-tokens:
-      - '79824'
+      - '79952'
       x-request-id:
-      - 401bd803-b790-47b7-b098-98708d44f060
+      - e5012889-ef86-449a-908c-2065dbf0954e
     status:
       code: 200
       message: OK

packages/exchange/tests/providers/cassettes/test_google_complete.yaml

@@ -1,7 +1,25 @@
 interactions:
 - request:
-    body: '{"system_instruction": {"parts": [{"text": "You are a helpful assistant."}]},
+    body: |-
-      "contents": [{"role": "user", "parts": [{"text": "Hello"}]}]}'
+      {
+        "system_instruction": {
+          "parts": [
+            {
+              "text": "You are a helpful assistant."
+            }
+          ]
+        },
+        "contents": [
+          {
+            "role": "user",
+            "parts": [
+              {
+                "text": "Hello"
+              }
+            ]
+          }
+        ]
+      }
     headers:
       accept:
       - '*/*'
@@ -21,18 +39,46 @@ interactions:
     uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=test_google_api_key
   response:
     body:
-      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+      string: |-
-        [\n          {\n            \"text\": \"Hello! \U0001F44B  How can I help
+        {
-        you today? \U0001F60A \\n\"\n          }\n        ],\n        \"role\": \"model\"\n
+          "candidates": [
-        \     },\n      \"finishReason\": \"STOP\",\n      \"index\": 0,\n      \"safetyRatings\":
+            {
-        [\n        {\n          \"category\": \"HARM_CATEGORY_SEXUALLY_EXPLICIT\",\n
+              "content": {
-        \         \"probability\": \"NEGLIGIBLE\"\n        },\n        {\n          \"category\":
+                "parts": [
-        \"HARM_CATEGORY_HATE_SPEECH\",\n          \"probability\": \"NEGLIGIBLE\"\n
+                  {
-        \       },\n        {\n          \"category\": \"HARM_CATEGORY_HARASSMENT\",\n
+                    "text": "Hello! \ud83d\udc4b  What can I do for you today? \ud83d\ude0a \n"
-        \         \"probability\": \"NEGLIGIBLE\"\n        },\n        {\n          \"category\":
+                  }
-        \"HARM_CATEGORY_DANGEROUS_CONTENT\",\n          \"probability\": \"NEGLIGIBLE\"\n
+                ],
-        \       }\n      ]\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+                "role": "model"
-        8,\n    \"candidatesTokenCount\": 12,\n    \"totalTokenCount\": 20\n  }\n}\n"
+              },
+              "finishReason": "STOP",
+              "index": 0,
+              "safetyRatings": [
+                {
+                  "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
+                  "probability": "NEGLIGIBLE"
+                },
+                {
+                  "category": "HARM_CATEGORY_HATE_SPEECH",
+                  "probability": "NEGLIGIBLE"
+                },
+                {
+                  "category": "HARM_CATEGORY_HARASSMENT",
+                  "probability": "NEGLIGIBLE"
+                },
+                {
+                  "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
+                  "probability": "NEGLIGIBLE"
+                }
+              ]
+            }
+          ],
+          "usageMetadata": {
+            "promptTokenCount": 8,
+            "candidatesTokenCount": 13,
+            "totalTokenCount": 21
+          }
+        }
     headers:
       Alt-Svc:
       - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
@@ -41,11 +87,11 @@ interactions:
       Content-Type:
       - application/json; charset=UTF-8
       Date:
-      - Wed, 02 Oct 2024 01:06:50 GMT
+      - Sun, 13 Oct 2024 02:54:58 GMT
       Server:
       - scaffolding on HTTPServer2
       Server-Timing:
-      - gfet4t7; dur=426
+      - gfet4t7; dur=1201
       Transfer-Encoding:
       - chunked
       Vary:
@@ -59,7 +105,7 @@ interactions:
       X-XSS-Protection:
       - '0'
       content-length:
-      - '855'
+      - '858'
     status:
       code: 200
       message: OK

packages/exchange/tests/providers/cassettes/test_google_tools.yaml

@@ -1,13 +1,45 @@
 interactions:
 - request:
-    body: '{"system_instruction": {"parts": [{"text": "You are a helpful assistant.
+    body: |-
-      Expect to need to read a file using read_file."}]}, "contents": [{"role": "user",
+      {
-      "parts": [{"text": "What are the contents of this file? test.txt"}]}], "tools":
+        "system_instruction": {
-      {"functionDeclarations": [{"name": "read_file", "description": "Read the contents
+          "parts": [
-      of the file.", "parameters": {"type": "object", "properties": {"filename": {"type":
+            {
-      "string", "description": "The path to the file, which can be relative or\nabsolute.
+              "text": "You are a helpful assistant. Expect to need to read a file using read_file."
-      If it is a plain filename, it is assumed to be in the\ncurrent working directory."}},
+            }
-      "required": ["filename"]}}]}}'
+          ]
+        },
+        "contents": [
+          {
+            "role": "user",
+            "parts": [
+              {
+                "text": "What are the contents of this file? test.txt"
+              }
+            ]
+          }
+        ],
+        "tools": {
+          "functionDeclarations": [
+            {
+              "name": "read_file",
+              "description": "Read the contents of the file.",
+              "parameters": {
+                "type": "object",
+                "properties": {
+                  "filename": {
+                    "type": "string",
+                    "description": "The path to the file, which can be relative or\nabsolute. If it is a plain filename, it is assumed to be in the\ncurrent working directory."
+                  }
+                },
+                "required": [
+                  "filename"
+                ]
+              }
+            }
+          ]
+        }
+      }
     headers:
       accept:
       - '*/*'
@@ -27,19 +59,51 @@ interactions:
     uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=test_google_api_key
   response:
     body:
-      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+      string: |-
-        [\n          {\n            \"functionCall\": {\n              \"name\": \"read_file\",\n
+        {
-        \             \"args\": {\n                \"filename\": \"test.txt\"\n              }\n
+          "candidates": [
-        \           }\n          }\n        ],\n        \"role\": \"model\"\n      },\n
+            {
-        \     \"finishReason\": \"STOP\",\n      \"index\": 0,\n      \"safetyRatings\":
+              "content": {
-        [\n        {\n          \"category\": \"HARM_CATEGORY_SEXUALLY_EXPLICIT\",\n
+                "parts": [
-        \         \"probability\": \"NEGLIGIBLE\"\n        },\n        {\n          \"category\":
+                  {
-        \"HARM_CATEGORY_HATE_SPEECH\",\n          \"probability\": \"NEGLIGIBLE\"\n
+                    "functionCall": {
-        \       },\n        {\n          \"category\": \"HARM_CATEGORY_HARASSMENT\",\n
+                      "name": "read_file",
-        \         \"probability\": \"NEGLIGIBLE\"\n        },\n        {\n          \"category\":
+                      "args": {
-        \"HARM_CATEGORY_DANGEROUS_CONTENT\",\n          \"probability\": \"NEGLIGIBLE\"\n
+                        "filename": "test.txt"
-        \       }\n      ]\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
+                      }
-        101,\n    \"candidatesTokenCount\": 17,\n    \"totalTokenCount\": 118\n  }\n}\n"
+                    }
+                  }
+                ],
+                "role": "model"
+              },
+              "finishReason": "STOP",
+              "index": 0,
+              "safetyRatings": [
+                {
+                  "category": "HARM_CATEGORY_HATE_SPEECH",
+                  "probability": "NEGLIGIBLE"
+                },
+                {
+                  "category": "HARM_CATEGORY_HARASSMENT",
+                  "probability": "NEGLIGIBLE"
+                },
+                {
+                  "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
+                  "probability": "NEGLIGIBLE"
+                },
+                {
+                  "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
+                  "probability": "NEGLIGIBLE"
+                }
+              ]
+            }
+          ],
+          "usageMetadata": {
+            "promptTokenCount": 101,
+            "candidatesTokenCount": 17,
+            "totalTokenCount": 118
+          }
+        }
     headers:
       Alt-Svc:
       - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
@@ -48,7 +112,7 @@ interactions:
       Content-Type:
       - application/json; charset=UTF-8
       Date:
-      - Wed, 02 Oct 2024 01:06:51 GMT
+      - Sun, 13 Oct 2024 02:54:59 GMT
       Server:
       - scaffolding on HTTPServer2
       Server-Timing:

packages/exchange/tests/providers/cassettes/test_ollama_complete.yaml

@@ -23,15 +23,25 @@ interactions:
       Content-Type:
       - text/plain; charset=utf-8
       Date:
-      - Sun, 22 Sep 2024 23:40:13 GMT
+      - Sun, 13 Oct 2024 04:53:22 GMT
-      Set-Cookie: test_set_cookie
-      openai-organization: test_openai_org_key
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+    body: |-
-      {"role": "user", "content": "Hello"}], "model": "mistral-nemo"}'
+      {
+        "messages": [
+          {
+            "role": "system",
+            "content": "You are a helpful assistant."
+          },
+          {
+            "role": "user",
+            "content": "Hello"
+          }
+        ],
+        "model": "mistral-nemo"
+      }
     headers:
       accept:
       - '*/*'
@@ -51,17 +61,36 @@ interactions:
     uri: http://localhost:11434/v1/chat/completions
   response:
     body:
-      string: "{\"id\":\"chatcmpl-429\",\"object\":\"chat.completion\",\"created\":1727048416,\"model\":\"mistral-nemo\",\"system_fingerprint\":\"fp_ollama\",\"choices\":[{\"index\":0,\"message\":{\"role\":\"assistant\",\"content\":\"Hello!
+      string: |-
-        I'm here to help. How can I assist you today? Let's chat. \U0001F60A\"},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":10,\"completion_tokens\":23,\"total_tokens\":33}}\n"
+        {
+          "id": "chatcmpl-565",
+          "object": "chat.completion",
+          "created": 1728795204,
+          "model": "mistral-nemo",
+          "system_fingerprint": "fp_ollama",
+          "choices": [
+            {
+              "index": 0,
+              "message": {
+                "role": "assistant",
+                "content": "Hello! I'm here to help. How can I assist you today? \ud83d\ude0a"
+              },
+              "finish_reason": "stop"
+            }
+          ],
+          "usage": {
+            "prompt_tokens": 10,
+            "completion_tokens": 19,
+            "total_tokens": 29
+          }
+        }
     headers:
       Content-Length:
-      - '356'
+      - '344'
       Content-Type:
       - application/json
       Date:
-      - Sun, 22 Sep 2024 23:40:16 GMT
+      - Sun, 13 Oct 2024 04:53:24 GMT
-      Set-Cookie: test_set_cookie
-      openai-organization: test_openai_org_key
     status:
       code: 200
       message: OK

packages/exchange/tests/providers/cassettes/test_ollama_tools.yaml

@@ -23,21 +23,46 @@ interactions:
       Content-Type:
       - text/plain; charset=utf-8
       Date:
-      - Wed, 25 Sep 2024 09:23:08 GMT
+      - Sun, 13 Oct 2024 02:52:00 GMT
-      Set-Cookie: test_set_cookie
-      openai-organization: test_openai_org_key
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant.
+    body: |-
-      Expect to need to read a file using read_file."}, {"role": "user", "content":
+      {
-      "What are the contents of this file? test.txt"}], "model": "mistral-nemo", "tools":
+        "messages": [
-      [{"type": "function", "function": {"name": "read_file", "description": "Read
+          {
-      the contents of the file.", "parameters": {"type": "object", "properties": {"filename":
+            "role": "system",
-      {"type": "string", "description": "The path to the file, which can be relative
+            "content": "You are a helpful assistant. Expect to need to read a file using read_file."
-      or\nabsolute. If it is a plain filename, it is assumed to be in the\ncurrent
+          },
-      working directory."}}, "required": ["filename"]}}}]}'
+          {
+            "role": "user",
+            "content": "What are the contents of this file? test.txt"
+          }
+        ],
+        "model": "mistral-nemo",
+        "tools": [
+          {
+            "type": "function",
+            "function": {
+              "name": "read_file",
+              "description": "Read the contents of the file.",
+              "parameters": {
+                "type": "object",
+                "properties": {
+                  "filename": {
+                    "type": "string",
+                    "description": "The path to the file, which can be relative or\nabsolute. If it is a plain filename, it is assumed to be in the\ncurrent working directory."
+                  }
+                },
+                "required": [
+                  "filename"
+                ]
+              }
+            }
+          }
+        ]
+      }
     headers:
       accept:
       - '*/*'
@@ -57,18 +82,46 @@ interactions:
     uri: http://localhost:11434/v1/chat/completions
   response:
     body:
-      string: '{"id":"chatcmpl-245","object":"chat.completion","created":1727256190,"model":"mistral-nemo","system_fingerprint":"fp_ollama","choices":[{"index":0,"message":{"role":"assistant","content":"","tool_calls":[{"id":"call_z6fgu3z3","type":"function","function":{"name":"read_file","arguments":"{\"filename\":\"test.txt\"}"}}]},"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":112,"completion_tokens":21,"total_tokens":133}}
+      string: |-
-
+        {
-        '
+          "id": "chatcmpl-212",
+          "object": "chat.completion",
+          "created": 1728787922,
+          "model": "mistral-nemo",
+          "system_fingerprint": "fp_ollama",
+          "choices": [
+            {
+              "index": 0,
+              "message": {
+                "role": "assistant",
+                "content": "",
+                "tool_calls": [
+                  {
+                    "id": "call_h5d3s25w",
+                    "type": "function",
+                    "function": {
+                      "name": "read_file",
+                      "arguments": "{\"filename\":\"test.txt\"}"
+                    }
+                  }
+                ]
+              },
+              "finish_reason": "tool_calls"
+            }
+          ],
+          "usage": {
+            "prompt_tokens": 112,
+            "completion_tokens": 21,
+            "total_tokens": 133
+          }
+        }
     headers:
       Content-Length:
       - '425'
       Content-Type:
       - application/json
       Date:
-      - Wed, 25 Sep 2024 09:23:10 GMT
+      - Sun, 13 Oct 2024 02:52:02 GMT
-      Set-Cookie: test_set_cookie
-      openai-organization: test_openai_org_key
     status:
       code: 200
       message: OK

packages/exchange/tests/providers/cassettes/test_openai_complete.yaml

@@ -1,7 +1,19 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+    body: |-
-      {"role": "user", "content": "Hello"}], "model": "gpt-4o-mini"}'
+      {
+        "messages": [
+          {
+            "role": "system",
+            "content": "You are a helpful assistant."
+          },
+          {
+            "role": "user",
+            "content": "Hello"
+          }
+        ],
+        "model": "gpt-4o-mini"
+      }
     headers:
       accept:
       - '*/*'
@@ -23,25 +35,48 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-AAQTYi3DXJnltAfd5sUH1Wnzh69t3\",\n  \"object\":
+      string: |-
-        \"chat.completion\",\n  \"created\": 1727048416,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        {
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+          "id": "chatcmpl-AHj1Y1xN9345uFT3PVMInIYEQ8g4a",
-        \"assistant\",\n        \"content\": \"Hello! How can I assist you today?\",\n
+          "object": "chat.completion",
-        \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+          "created": 1728788012,
-        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 18,\n    \"completion_tokens\":
+          "model": "gpt-4o-mini-2024-07-18",
-        9,\n    \"total_tokens\": 27,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
+          "choices": [
-        0\n    }\n  },\n  \"system_fingerprint\": \"fp_1bb46167f9\"\n}\n"
+            {
+              "index": 0,
+              "message": {
+                "role": "assistant",
+                "content": "Hello! How can I assist you today?",
+                "refusal": null
+              },
+              "logprobs": null,
+              "finish_reason": "stop"
+            }
+          ],
+          "usage": {
+            "prompt_tokens": 18,
+            "completion_tokens": 9,
+            "total_tokens": 27,
+            "prompt_tokens_details": {
+              "cached_tokens": 0
+            },
+            "completion_tokens_details": {
+              "reasoning_tokens": 0
+            }
+          },
+          "system_fingerprint": "fp_e2bde53e6e"
+        }
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c762399feb55739-SYD
+      - 8d1c0a328dca3e44-SIN
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Sun, 22 Sep 2024 23:40:17 GMT
+      - Sun, 13 Oct 2024 02:53:33 GMT
       Server:
       - cloudflare
       Set-Cookie: test_set_cookie
@@ -51,15 +86,17 @@ interactions:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       content-length:
-      - '593'
+      - '656'
       openai-organization: test_openai_org_key
       openai-processing-ms:
-      - '560'
+      - '481'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
-      - max-age=15552000; includeSubDomains; preload
+      - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
@@ -67,13 +104,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '199973'
+      - '199972'
       x-ratelimit-reset-requests:
       - 8.64s
       x-ratelimit-reset-tokens:
       - 8ms
       x-request-id:
-      - req_22e26c840219cde3152eaba1ce89483b
+      - req_85f532ac5fdad6a4af020cab55e2fd4d
     status:
       code: 200
       message: OK

packages/exchange/tests/providers/cassettes/test_openai_tools.yaml

@@ -1,13 +1,40 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant.
+    body: |-
-      Expect to need to read a file using read_file."}, {"role": "user", "content":
+      {
-      "What are the contents of this file? test.txt"}], "model": "gpt-4o-mini", "tools":
+        "messages": [
-      [{"type": "function", "function": {"name": "read_file", "description": "Read
+          {
-      the contents of the file.", "parameters": {"type": "object", "properties": {"filename":
+            "role": "system",
-      {"type": "string", "description": "The path to the file, which can be relative
+            "content": "You are a helpful assistant. Expect to need to read a file using read_file."
-      or\nabsolute. If it is a plain filename, it is assumed to be in the\ncurrent
+          },
-      working directory."}}, "required": ["filename"]}}}]}'
+          {
+            "role": "user",
+            "content": "What are the contents of this file? test.txt"
+          }
+        ],
+        "model": "gpt-4o-mini",
+        "tools": [
+          {
+            "type": "function",
+            "function": {
+              "name": "read_file",
+              "description": "Read the contents of the file.",
+              "parameters": {
+                "type": "object",
+                "properties": {
+                  "filename": {
+                    "type": "string",
+                    "description": "The path to the file, which can be relative or\nabsolute. If it is a plain filename, it is assumed to be in the\ncurrent working directory."
+                  }
+                },
+                "required": [
+                  "filename"
+                ]
+              }
+            }
+          }
+        ]
+      }
     headers:
       accept:
       - '*/*'
@@ -29,29 +56,58 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-ABIV2aZWVKQ774RAQ8KHYdNwkI5N7\",\n  \"object\":
+      string: |-
-        \"chat.completion\",\n  \"created\": 1727256084,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        {
-        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+          "id": "chatcmpl-AHj1axEdpe3coVDULrCjHmXql5euz",
-        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+          "object": "chat.completion",
-        \           \"id\": \"call_xXYlw4A7Ud1qtCopuK5gEJrP\",\n            \"type\":
+          "created": 1728788014,
-        \"function\",\n            \"function\": {\n              \"name\": \"read_file\",\n
+          "model": "gpt-4o-mini-2024-07-18",
-        \             \"arguments\": \"{\\\"filename\\\":\\\"test.txt\\\"}\"\n            }\n
+          "choices": [
-        \         }\n        ],\n        \"refusal\": null\n      },\n      \"logprobs\":
+            {
-        null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\":
+              "index": 0,
-        {\n    \"prompt_tokens\": 107,\n    \"completion_tokens\": 15,\n    \"total_tokens\":
+              "message": {
-        122,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0\n
+                "role": "assistant",
-        \   }\n  },\n  \"system_fingerprint\": \"fp_1bb46167f9\"\n}\n"
+                "content": null,
+                "tool_calls": [
+                  {
+                    "id": "call_Z43oz2RtLmNHw9xvFgxA1SC5",
+                    "type": "function",
+                    "function": {
+                      "name": "read_file",
+                      "arguments": "{\"filename\":\"test.txt\"}"
+                    }
+                  }
+                ],
+                "refusal": null
+              },
+              "logprobs": null,
+              "finish_reason": "tool_calls"
+            }
+          ],
+          "usage": {
+            "prompt_tokens": 107,
+            "completion_tokens": 15,
+            "total_tokens": 122,
+            "prompt_tokens_details": {
+              "cached_tokens": 0
+            },
+            "completion_tokens_details": {
+              "reasoning_tokens": 0
+            }
+          },
+          "system_fingerprint": "fp_e2bde53e6e"
+        }
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c89f19fed997e43-SYD
+      - 8d1c0a419b009d0b-SIN
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Wed, 25 Sep 2024 09:21:25 GMT
+      - Sun, 13 Oct 2024 02:53:35 GMT
       Server:
       - cloudflare
       Set-Cookie: test_set_cookie
@@ -61,11 +117,13 @@ interactions:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       content-length:
-      - '844'
+      - '907'
       openai-organization: test_openai_org_key
       openai-processing-ms:
-      - '266'
+      - '442'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -75,15 +133,15 @@ interactions:
       x-ratelimit-limit-tokens:
       - '200000'
       x-ratelimit-remaining-requests:
-      - '9991'
+      - '9997'
       x-ratelimit-remaining-tokens:
-      - '199952'
+      - '199951'
       x-ratelimit-reset-requests:
-      - 1m9.486s
+      - 23.873s
       x-ratelimit-reset-tokens:
       - 14ms
       x-request-id:
-      - req_ff6b5d65c24f40e1faaf049c175e718d
+      - req_8ec455e318c9f2d6eecf82d1fdf124ab
     status:
       code: 200
       message: OK

packages/exchange/tests/providers/conftest.py

@@ -1,11 +1,14 @@
+import json
 import os
 import re
 from typing import Type, Tuple
 
 import pytest
+import yaml
 
 from exchange import Message, ToolUse, ToolResult, Tool
 from exchange.providers import Usage, Provider
+
 from tests.conftest import read_file
 
 OPENAI_API_KEY = "test_openai_api_key"
@@ -70,6 +73,73 @@ def default_google_env(monkeypatch):
         monkeypatch.setenv("GOOGLE_API_KEY", GOOGLE_API_KEY)
 
 
+class LiteralBlockScalar(str):
+    """Formats the string as a literal block scalar, preserving whitespace and
+    without interpreting escape characters"""
+
+    pass
+
+
+def literal_block_scalar_presenter(dumper, data):
+    """Represents a scalar string as a literal block, via '|' syntax"""
+    return dumper.represent_scalar("tag:yaml.org,2002:str", data, style="|")
+
+
+yaml.add_representer(LiteralBlockScalar, literal_block_scalar_presenter)
+
+
+def process_string_value(string_value):
+    """Pretty-prints JSON or returns long strings as a LiteralString"""
+    try:
+        json_data = json.loads(string_value)
+        return LiteralBlockScalar(json.dumps(json_data, indent=2))
+    except (ValueError, TypeError):
+        if len(string_value) > 80:
+            return LiteralBlockScalar(string_value)
+    return string_value
+
+
+def convert_body_to_literal(data):
+    """Searches the data for body strings, attempting to pretty-print JSON"""
+    if isinstance(data, dict):
+        for key, value in data.items():
+            # Handle response body case (e.g., response.body.string)
+            if key == "body" and isinstance(value, dict) and "string" in value:
+                value["string"] = process_string_value(value["string"])
+
+            # Handle request body case (e.g., request.body)
+            elif key == "body" and isinstance(value, str):
+                data[key] = process_string_value(value)
+
+            else:
+                convert_body_to_literal(value)
+
+    elif isinstance(data, list):
+        for i, item in enumerate(data):
+            data[i] = convert_body_to_literal(item)
+
+    return data
+
+
+class PrettyPrintJSONBody:
+    """This makes request and response body recordings more readable."""
+
+    @staticmethod
+    def serialize(cassette_dict):
+        cassette_dict = convert_body_to_literal(cassette_dict)
+        return yaml.dump(cassette_dict, default_flow_style=False, allow_unicode=True)
+
+    @staticmethod
+    def deserialize(cassette_string):
+        return yaml.load(cassette_string, Loader=yaml.Loader)
+
+
+@pytest.fixture(scope="module")
+def vcr(vcr):
+    vcr.register_serializer("yaml", PrettyPrintJSONBody)
+    return vcr
+
+
 @pytest.fixture(scope="module")
 def vcr_config():
     """

packages/exchange/tests/providers/test_anthropic.py

@@ -91,7 +91,7 @@ def test_message_text_to_anthropic_spec() -> None:
 
 def test_messages_to_anthropic_spec() -> None:
     messages = [
-        Message(role="user", content=[Text(text="Hello, Claude")]),
+        Message(role="user", content=[Text("Hello, Claude")]),
         Message(
             role="assistant",
             content=[ToolUse(id="1", name="example_fn", parameters={"param": "value"})],
@@ -148,7 +148,7 @@ def test_anthropic_completion(mock_error, mock_warning, mock_post, anthropic_pro
 
     reply_message, reply_usage = anthropic_provider.complete(model=model, system=system, messages=messages)
 
-    assert reply_message.content == [Text(text="Hello from Claude!")]
+    assert reply_message.content == [Text("Hello from Claude!")]
     assert reply_usage.total_tokens == 35
     assert mock_post.call_count == 2
     mock_post.assert_any_call(

packages/exchange/tests/providers/test_azure.py

@@ -43,7 +43,7 @@ def test_from_env_throw_error_when_missing_env_var(env_var_name):
 def test_azure_complete(default_azure_env):
     reply_message, reply_usage = complete(AzureProvider, AZURE_MODEL)
 
-    assert reply_message.content == [Text(text="Hello! How can I assist you today?")]
+    assert reply_message.content == [Text("Hello! How can I assist you today?\n")]
     assert reply_usage.total_tokens == 27
 
 
@@ -61,7 +61,7 @@ def test_azure_tools(default_azure_env):
 
     tool_use = reply_message.content[0]
     assert isinstance(tool_use, ToolUse), f"Expected ToolUse, but was {type(tool_use).__name__}"
-    assert tool_use.id == "call_a47abadDxlGKIWjvYYvGVAHa"
+    assert tool_use.id == "call_Dn0idyNSdmHSYpsql3EbFH9L"
     assert tool_use.name == "read_file"
     assert tool_use.parameters == {"filename": "test.txt"}
     assert reply_usage.total_tokens == 125

packages/exchange/tests/providers/test_databricks.py

@@ -61,7 +61,7 @@ def test_databricks_completion(mock_error, mock_warning, mock_sleep, mock_post,
         model=model, system=system, messages=messages, tools=tools
     )
 
-    assert reply_message.content == [Text(text="Hello!")]
+    assert reply_message.content == [Text("Hello!")]
     assert reply_usage.total_tokens == 35
     assert mock_post.call_count == 1
     mock_post.assert_called_once_with(

packages/exchange/tests/providers/test_google.py

@@ -83,7 +83,7 @@ def test_message_text_to_google_spec() -> None:
 
 def test_messages_to_google_spec() -> None:
     messages = [
-        Message(role="user", content=[Text(text="Hello, Gemini")]),
+        Message(role="user", content=[Text("Hello, Gemini")]),
         Message(
             role="assistant",
             content=[ToolUse(id="1", name="example_fn", parameters={"param": "value"})],
@@ -105,8 +105,8 @@ def test_messages_to_google_spec() -> None:
 def test_google_complete(default_google_env):
     reply_message, reply_usage = complete(GoogleProvider, GOOGLE_MODEL)
 
-    assert reply_message.content == [Text("Hello! 👋  How can I help you today? 😊 \n")]
+    assert reply_message.content == [Text("Hello! 👋  What can I do for you today? 😊 \n")]
-    assert reply_usage.total_tokens == 20
+    assert reply_usage.total_tokens == 21
 
 
 @pytest.mark.integration

packages/exchange/tests/providers/test_ollama.py

@@ -13,8 +13,8 @@ OLLAMA_MODEL = os.getenv("OLLAMA_MODEL", OLLAMA_MODEL)
 def test_ollama_complete():
     reply_message, reply_usage = complete(OllamaProvider, OLLAMA_MODEL)
 
-    assert reply_message.content == [Text(text="Hello! I'm here to help. How can I assist you today? Let's chat. 😊")]
+    assert reply_message.content == [Text("Hello! I'm here to help. How can I assist you today? 😊")]
-    assert reply_usage.total_tokens == 33
+    assert reply_usage.total_tokens == 29
 
 
 @pytest.mark.integration
@@ -31,7 +31,7 @@ def test_ollama_tools():
 
     tool_use = reply_message.content[0]
     assert isinstance(tool_use, ToolUse), f"Expected ToolUse, but was {type(tool_use).__name__}"
-    assert tool_use.id == "call_z6fgu3z3"
+    assert tool_use.id == "call_h5d3s25w"
     assert tool_use.name == "read_file"
     assert tool_use.parameters == {"filename": "test.txt"}
     assert reply_usage.total_tokens == 133

packages/exchange/tests/providers/test_openai.py

@@ -25,7 +25,7 @@ def test_from_env_throw_error_when_missing_api_key():
 def test_openai_complete(default_openai_env):
     reply_message, reply_usage = complete(OpenAiProvider, OPENAI_MODEL)
 
-    assert reply_message.content == [Text(text="Hello! How can I assist you today?")]
+    assert reply_message.content == [Text("Hello! How can I assist you today?")]
     assert reply_usage.total_tokens == 27
 
 
@@ -43,7 +43,7 @@ def test_openai_tools(default_openai_env):
 
     tool_use = reply_message.content[0]
     assert isinstance(tool_use, ToolUse), f"Expected ToolUse, but was {type(tool_use).__name__}"
-    assert tool_use.id == "call_xXYlw4A7Ud1qtCopuK5gEJrP"
+    assert tool_use.id == "call_Z43oz2RtLmNHw9xvFgxA1SC5"
     assert tool_use.name == "read_file"
     assert tool_use.parameters == {"filename": "test.txt"}
     assert reply_usage.total_tokens == 122
@@ -64,7 +64,7 @@ def test_openai_tools_integration():
 def test_openai_vision(default_openai_env):
     reply_message, reply_usage = vision(OpenAiProvider, OPENAI_MODEL)
 
-    assert reply_message.content == [Text(text='The first entry in the menu says "Ask Goose."')]
+    assert reply_message.content == [Text('The first entry in the menu says "Ask Goose."')]
     assert reply_usage.total_tokens == 14241