12 Commits

Author	SHA1	Message	Date
hobokenchicken	e5ef39f327	feat: add OpenAI Responses API support (POST /v1/responses) ... Add full Responses API endpoint alongside existing Chat Completions, with identical logging/tracking/cost pipeline. New: - internal/models/responses.go — request/response/stream types + ToUsage() bridge - internal/providers/openai_responses.go — OpenAI Responses/ResponsesStream Modified: - provider.go — Responses()+ResponsesStream() added to Provider interface - helpers.go — BuildOpenAIResponsesBody, parsers, SSE stream reader - circuit_breaker.go — CB wraps Responses, passthrough for stream - server.go — POST /v1/responses route + handleResponses handler - all non-OpenAI providers — stub methods with clear error messages Logging: ResponsesUsage.ToUsage() bridges to models.Usage, feeding same logRequest() -> DB insert -> dashboard WS -> client stats -> cost calc pipeline. No schema or logger changes needed.	2026-05-02 16:38:17 -04:00
hobokenchicken	5ee539d95c	feat: add image generation for OpenAI DALL-E and Gemini Imagen ... New `/v1/images/generations` endpoint proxies DALL-E 2/3 (OpenAI) and Imagen 3 (Gemini). Same auth/logging as chat completions. - Add ImageGenerationRequest/Response models - Extend Provider interface with ImageGeneration() - OpenAI: forward to /v1/images/generations - Gemini: call /v1beta/models/{model}:predict, map OpenAI params - Circuit breaker wraps image gen like chat completions - Model routing: dall-e* -> openai, imagen*/gemini* -> gemini - Unsupported providers (deepseek/moonshot/grok/ollama) return error - Fix pre-existing CachedContentTokenCount bug in StreamGemini	2026-04-27 10:06:07 -04:00
hobokenchicken	af2c5b95f7	feat: Phase 3 - architecture & maintainability ... - Split 1474-line dashboard.go into 5 domain files (clients, providers, users, system) - Unit tests for ModelRegistry.FindModel and CalculateCost - go mod tidy + verify (deps clean) - .gitignore excludes tool cache dirs (.pi-lens/, .opencode/)	2026-04-26 14:52:10 -04:00
hobokenchicken	1f574d8134	feat: Phase 2 - reliability & observability ... - Circuit breaker: proper thresholds (3 failures, 30s timeout) - HTTP timeouts: 30s on all providers (was no timeout) - Structured logging: slog replaces fmt.Printf throughout - Stream errors: propagated as SSE error events to client - Registry fetch: retry with backoff (3 attempts) - Registry reads in dashboard protected by RWMutex	2026-04-26 14:48:56 -04:00
hobokenchicken	8a8d8d1477	fix: Phase 1 - security & stability patches ... - AuthMiddleware now requires auth on /v1/* routes (returns 401) - WebSocket origin check configurable via WSAllowedOrigin - Removed debug fmt.Printf leaks (config, ollama, server) - Registry access protected by sync.RWMutex (race condition fix) - Session cleanup goroutine runs every 15 min - RevokeSession returns error instead of silent no-op	2026-04-26 14:45:22 -04:00
hobokenchicken	21e5204abd	fix(ollama): improve tool-calling support and restore gemma/llama context limits ... - 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	2026-04-07 14:24:23 +00:00
hobokenchicken	4095c68822	fix(ollama): improve model detection and ensure robust token/context limits ... - 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	2026-04-07 14:05:21 +00:00
hobokenchicken	ef37dc5af0	fix(ollama): significantly increase context and prediction limits ... - Increase timeout to 15m - Set num_ctx to 32k for common models - Set default num_predict to 8192 for common models	2026-04-07 13:48:02 +00:00
hobokenchicken	fdbb068a6c	fix(ollama): map max_tokens to num_predict and increase context window ... - 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	2026-04-07 13:44:17 +00:00
hobokenchicken	dbbf48cb14	fix(ollama): increase timeout and add default max_tokens for large models ... - 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	2026-04-07 13:42:10 +00:00
hobokenchicken	1b5cd2815e	fix(ollama): improve error handling and add timeouts ... - 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	2026-04-06 15:05:31 -04:00
hobokenchicken	2f6b7deb2c	feat(providers): add Ollama provider support ... - 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	2026-04-06 14:38:35 -04:00