mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 22:33:48 +00:00
79bed44b04
Propagate test IDs from client to server via HTTP headers to maintain proper test isolation when running with server-based stack configs. Without this, recorded/replayed inference requests in server mode would leak across tests. Changes: - Patch client _prepare_request to inject test ID into provider data header - Sync test context from provider data on server side before storage operations - Set LLAMA_STACK_TEST_STACK_CONFIG_TYPE env var based on stack config - Configure console width for cleaner log output in CI - Add SQLITE_STORE_DIR temp directory for test data isolation
57 lines
2.5 KiB
JSON
57 lines
2.5 KiB
JSON
{
|
|
"test_id": null,
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai 0"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-c34cccb2af2f",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'm happy to help you with testing the Discord API but I can't test for you. You can use the following code to get started:\n\n```\nimport discord\nfrom discord.ext import commands\n\n# Replace these values with your own bot token and guild ID\nTOKEN = 'your_discord_bot_token'\nGUILD_ID = 'your_guild_id'\n\n# Create a new bot instance\nbot = commands.Bot(command_prefix='!')\n\n# Event that triggers when the bot is ready\n@bot.event\nasync def on_ready():\n # Print a message to indicate that the bot is online\n print(f'{bot.user.name} has connected to Discord!')\n\n# Command that says 'Hello, world!'\n@bot.command(name='hello')\nasync def hello(ctx):\n # Send a message with a greeting\n await ctx.send(':hello: Hello, world!')\n\n# Run the bot and keep it alive until it's stopped manually\nbot.run(TOKEN)\n```\n\nMake sure to replace `'your_discord_bot_token'` and `'your_guild_id'` with the appropriate values for your Discord API credentials.\n\nTo run this code, you'll need to install the `discord.py` library using pip:\n\n```bash\npip install discord.py\n```\n\nPlease note that you can't test the API since we are not logging in and testing on a bot.",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 275,
|
|
"prompt_tokens": 31,
|
|
"total_tokens": 306,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|