Extends HeliconeLogger to properly log Vertex AI partner models (GLM, DeepSeek, etc.)
that don't contain "gemini" in their name. Uses custom_llm_provider to detect vertex_ai.
- Add "gemini" to helicone_model_list so Gemini models are recognized
- Use /custom/v1/log endpoint for Gemini models instead of /oai/v1/log
- Set correct provider_url for Google's generativelanguage API
- Add unit test for Gemini model recognition
Previously, Gemini models were logged as "gpt-3.5-turbo" with OpenAI
as the provider, corrupting analytics. Now they log correctly with
their actual model name and CUSTOM provider.
Extract and preserve provider-specific headers (llm_provider-*) when
handling error responses from LLM providers. This ensures that useful
debugging information from providers is available even when requests
fail with BadRequestError or similar exceptions.
Gemini API rejects JSON schemas with $defs/$ref references anywhere in
the conversation, including in function_response content. This causes
errors when tools return JSON containing schemas (e.g., toolbelt_inspect_tool
returning tool definitions).
The fix:
1. Apply unpack_defs() to all JSON tool responses before sending to Gemini
2. Recursively remove $defs sections after inlining references
3. Replace any remaining $ref (circular refs, external URLs) with placeholders
Edge cases handled:
- Circular $ref (self-referential types like TreeNode.left -> TreeNode)
- External $ref (URL-based like https://...)
- Deeply nested $ref in anyOf/oneOf/allOf
This ensures function_response content is clean before being sent to the
Gemini API.
Related issues:
- https://github.com/google-gemini/gemini-cli/issues/13326
- FastMCP #1372, #1426
OpenAI's 400k context window is split between input and output:
- GPT-5/5.1/5.2 models: 272k input + 128k output = 400k context
- GPT-5-pro models: 128k input + 272k output = 400k context
Reference: https://openai.com/index/introducing-gpt-5-for-developers/
"In the API, all GPT-5 models can accept a maximum of 272,000 input
tokens and emit a maximum of 128,000 reasoning & output tokens"
Fixes incorrect 400k max_input_tokens values across 32 models.
- Add cerebras/zai-glm-4.7 with same specs as 4.6 (128K context, $2.25/M input, $2.75/M output)
- Mark cerebras/zai-glm-4.6 with deprecation_date: 2026-01-20
- Both models support function calling, reasoning, and tool choice
