- Use resp.Body() instead of resp.RawBody() for non-streaming error responses
- Fall back to RawBody() for streaming responses
- Log the full request body on API errors for debugging
- Add promo discount system for deepseek-v4-pro (75% off until 2026-05-31)
- Rewrite StreamGemini to handle both SSE and JSON array response formats,
fixing 0-token logging for gemini-3-flash and gemini-3-flash-preview
- Fall back to model group name for cost lookup when concrete model
isnt in the registry (fixes $0 cost on deepseek-auto entries)
- Move registry lock before FindModel call to fix data race
The 40-character truncation of tool call IDs in helper.go caused collisions
when models (like deepseek-v4-flash) generated longer IDs, leading to
"Duplicate value for 'tool_call_id'" errors. Removed the limit to allow
full unique IDs.
DeepSeek: updated reasoning_content injection to use an empty string
instead of a space, better matching provider expectations for history.
Improved API error reporting across all providers by capturing raw body
content when response parsing fails or returns empty strings.
DeepSeek models default to Chinese for some prompts. The ensureEnglish()
function prepends 'Always respond in English' as a system message when
no system prompt is already set. Applied to both ChatCompletion and
ChatCompletionStream paths.
30-second resty client timeout was killing long streaming responses
mid-generation. Models with large output windows (e.g. deepseek-v4-pro
at 384K max_tokens) routinely exceed 30s. Raised all providers to
10 minutes (Ollama already at 15min, unchanged). Circuit breaker
recovery timeout raised from 30s to 5min.
- Add CachedContentTokenCount to UsageMetadata parsing for both
streaming (helpers.go) and non-streaming (gemini.go) requests
- CacheReadTokens now populated from Gemini cachedContentTokenCount
- Add uint32Ptr helper for nil-safe uint32 pointer creation
- Gemini requires function results to immediately follow the model message that called them
- Implemented look-ahead grouping to pair assistant calls with their tool results
- Standardized system and orphaned tool message handling for Gemini compatibility
- Group consecutive 'tool' messages into a single Gemini content message with multiple 'functionResponse' parts
- Ensure assistant tool calls are properly mapped and sent
- Maintain v1beta for preview and newer models
- Added debug logging for API errors
- Support tool definitions in Gemini requests
- Map tool role to 'function' in Gemini content
- Ensure tool results are wrapped in JSON objects for Gemini compatibility
- Parse FunctionCall from Gemini response and map to OpenAI-compatible ToolCalls
- Correctly map finish_reason for tool calls
- Explicitly set tool_choice: auto when tools are present to aid gemma/llama models
- Sync stop sequences into the options map for broader compatibility
- Restore gemma/llama to the high-context (32k) optimization list
- Use case-insensitive matching for model names and routing
- Default max_tokens/num_predict to 8192 for all Ollama models to prevent truncation
- Increase default context window and add more large-context model families
- Ensure DeepSeek routing handles Ollama-hosted variants correctly
- Map MaxTokens to num_predict in options map
- Set default num_ctx to 8192 for common models (gemma, llama, etc.)
- This ensures Ollama doesn't cut off responses early due to default limits
- Increase Ollama timeout to 5m for larger models (e.g. gemma4)
- Set default max_tokens to 4096 for common Ollama models
- Expand stream scanner buffer to 10MB to prevent truncation
- Improve model routing and prefix stripping in server
- Add timeouts (30s) and retries to resty client
- Add debug logging for Ollama requests and responses
- Import time package for timeout configuration
- This should fix 500 errors and provide better error messages
- Implement OllamaProvider with OpenAI-compatible API integration
- Add Ollama to provider initialization in server.go
- Update config.go to handle Ollama (no API key required)
- Configure .env with Ollama server at 172.20.1.222:11434
- Support models: glm-4.7-flash:latest, qwen3-coder:30b, gemma4:26b
Improved extraction of reasoning and cached tokens from OpenAI and DeepSeek responses (including streams). Ensured accurate cost calculation using registry metadata.
newkirk
hobokenchicken