Files
langchaingo/agents/testdata/TestExecutorWithMRKLAgent.httprr
Travis Cline 99951bca92 httprr: improve test recording stability and add utilities (#1368)
* build: add examples-updater tool and update examples to v0.1.14-pre.1

Add a new tool to automate updating langchaingo version references in example
projects and use it to update all examples to v0.1.14-pre.1. The tool also
removes temporary replace directives that are no longer needed.

- Add update-examples Makefile target that runs the new tool
- Create internal/devtools/examples-updater implementation
- Update all example go.mod files to reference v0.1.14-pre.1
- Remove replace directives in googleai and vertex examples
- Update dependencies in main go.mod/go.sum

* httprr: improve header normalization and test container setup

Add header normalization to make HTTP recordings more stable:
- Add normalizeGoogleAPIClientHeader and normalizeVersionHeader functions
- Normalize User-Agent, x-goog-api-client and other version headers
- Remove OpenAI-Project header for consistency
- Preserve body for both replay lookup and recording
- Add comprehensive tests for header normalization

Improve testcontainer environment detection:
- Better handling of non-standard Docker socket paths
- Disable Ryuk reaper by default for resource efficiency
- Add verbose logging option via environment variable

* httputil: add ApiKeyTransport for query parameter API keys

Add a reusable ApiKeyTransport that adds API keys to URL query parameters:
- Create ApiKeyTransport implementation in httputil package
- Add comprehensive tests for the new transport
- Refactor googleai_test.go to use the shared transport
- Update chains/llm_test.go to use ApiKeyTransport with proper key scrubbing

This improves how API keys are handled with client libraries that don't
properly set keys when using custom HTTP clients, particularly useful
with httprr for testing Google API integrations.

* openai: remove duplicate MaxTokens field assignment

Remove redundant assignment where both MaxTokens and MaxCompletionTokens
were being set to the same value. MaxCompletionTokens is the preferred
field name that reflects OpenAI's API changes, while MaxTokens was
previously kept for backward compatibility.

* vectorstores/maridadb: add test infrastructure for MariaDB vectorstore

Add TestMain function for MariaDB vectorstore tests that ensures the proper
test environment is set up using the testctr package. This enables consistent
test container setup and teardown for MariaDB integration tests.

* all: normalize all httprr recordings for consistency

Update test recordings across all packages to use normalized headers:
- Standardize User-Agent to 'langchaingo-httprr'
- Normalize version information in x-goog-api-client headers
- Remove OpenAI-Project headers for consistency
- Fix deprecated Anthropic completion API tests
- Update HuggingFace test recordings with valid responses

These changes make test recordings stable across dependency updates
and different environments, preventing test failures from version changes.

* devtools: add utility tool for normalizing httprr test recordings

Add a command-line tool that standardizes version information in httprr recordings:
- Normalizes x-goog-api-client headers to use placeholder versions
- Standardizes x-amz-user-agent headers for consistency
- Replaces Go version strings with generic placeholders
- Supports dry-run mode to preview changes without modifying files
- Includes verbose output option for detailed change reporting

This tool helps maintain consistent test recordings across different environments
and dependency versions, preventing test failures from version changes.

* llms/openai: update OpenAI embedding test to use text-embedding-3-small model

Update the embedding test to use the current text-embedding-3-small model:
- Change model from text-embedding-ada-002 to text-embedding-3-small
- Adjust dimensions parameter from 1234 to 256 to match model capabilities
- Update test recording with appropriate response data

This change ensures tests remain compatible with OpenAI's current embedding
models and prevents test failures from API version changes.
2025-08-18 19:41:52 +02:00

136 lines
6.1 KiB
Plaintext
Generated

httprr trace v1
1374 1685
POST https://api.openai.com/v1/chat/completions HTTP/1.1
Host: api.openai.com
User-Agent: langchaingo-httprr
Content-Length: 1171
Authorization: Bearer test-api-key
Content-Type: application/json
{"model":"gpt-4","messages":[{"role":"user","content":"Answer the following questions as best you can. You have access to the following tools:\n\n- GoogleSearch: \n\t\"A wrapper around Google Search. \"\n\t\"Useful for when you need to answer questions about current events. \"\n\t\"Always one of the first options when you need to find information on internet\"\n\t\"Input should be a search query.\"\n- calculator: Useful for getting the result of a math expression. \n\tThe input to this tool should be a valid mathematical expression that could be executed by a starlark evaluator.\n\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [ GoogleSearch, calculator ]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is 5 plus 3? Please calculate this.\n"}],"temperature":0,"stop":["\nObservation:","\n\tObservation:"]}HTTP/2.0 200 OK
Content-Length: 915
Access-Control-Expose-Headers: X-Request-ID
Alt-Svc: h3=":443"; ma=86400
Cf-Cache-Status: DYNAMIC
Content-Type: application/json
Date: Mon, 18 Aug 2025 12:47:11 GMT
Openai-Organization: lcgo-tst
Openai-Processing-Ms: 1857
Openai-Project: proj_qm9GQ7k7ESiwosypKZaDuaoq
Openai-Version: 2020-10-01
Server: cloudflare
Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
X-Content-Type-Options: nosniff
X-Envoy-Upstream-Service-Time: 2526
X-Ratelimit-Limit-Requests: 10000
X-Ratelimit-Limit-Tokens: 1000000
X-Ratelimit-Remaining-Requests: 9999
X-Ratelimit-Remaining-Tokens: 999744
X-Ratelimit-Reset-Requests: 6ms
X-Ratelimit-Reset-Tokens: 15ms
X-Request-Id: req_f2650eb5eee54909afd6b2d0fe33a25d
{
"id": "chatcmpl-C5tYT3pvaJbtNYkzj8AuekFBz6Eye",
"object": "chat.completion",
"created": 1755521229,
"model": "gpt-4-0613",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Thought: This is a simple arithmetic problem. I can use the calculator tool to solve it.\nAction: calculator\nAction Input: 5 + 3",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 229,
"completion_tokens": 35,
"total_tokens": 264,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default",
"system_fingerprint": null
}
1523 1622
POST https://api.openai.com/v1/chat/completions HTTP/1.1
Host: api.openai.com
User-Agent: langchaingo-httprr
Content-Length: 1320
Authorization: Bearer test-api-key
Content-Type: application/json
{"model":"gpt-4","messages":[{"role":"user","content":"Answer the following questions as best you can. You have access to the following tools:\n\n- GoogleSearch: \n\t\"A wrapper around Google Search. \"\n\t\"Useful for when you need to answer questions about current events. \"\n\t\"Always one of the first options when you need to find information on internet\"\n\t\"Input should be a search query.\"\n- calculator: Useful for getting the result of a math expression. \n\tThe input to this tool should be a valid mathematical expression that could be executed by a starlark evaluator.\n\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [ GoogleSearch, calculator ]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is 5 plus 3? Please calculate this.\n\nThought: This is a simple arithmetic problem. I can use the calculator tool to solve it.\nAction: calculator\nAction Input: 5 + 3\nObservation: 8\n"}],"temperature":0,"stop":["\nObservation:","\n\tObservation:"]}HTTP/2.0 200 OK
Content-Length: 854
Access-Control-Expose-Headers: X-Request-ID
Alt-Svc: h3=":443"; ma=86400
Cf-Cache-Status: DYNAMIC
Content-Type: application/json
Date: Mon, 18 Aug 2025 12:47:13 GMT
Openai-Organization: lcgo-tst
Openai-Processing-Ms: 877
Openai-Project: proj_qm9GQ7k7ESiwosypKZaDuaoq
Openai-Version: 2020-10-01
Server: cloudflare
Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
X-Content-Type-Options: nosniff
X-Envoy-Upstream-Service-Time: 976
X-Ratelimit-Limit-Requests: 10000
X-Ratelimit-Limit-Tokens: 1000000
X-Ratelimit-Remaining-Requests: 9999
X-Ratelimit-Remaining-Tokens: 999708
X-Ratelimit-Reset-Requests: 6ms
X-Ratelimit-Reset-Tokens: 17ms
X-Request-Id: req_b87a3934c78c45a293877082fa2a6abe
{
"id": "chatcmpl-C5tYXrnm33bGrlwQU7DjJtce5OgO7",
"object": "chat.completion",
"created": 1755521233,
"model": "gpt-4-0613",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Thought: I now know the final answer\nFinal Answer: The answer is 8.",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 267,
"completion_tokens": 18,
"total_tokens": 285,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default",
"system_fingerprint": null
}