hobokenchicken
e5ef39f327
feat: add OpenAI Responses API support (POST /v1/responses)
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
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
eb67287b56
fix: raise provider HTTP timeouts from 30s to 10min
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
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.
2026-04-30 10:17:45 -04:00
hobokenchicken
5ee539d95c
feat: add image generation for OpenAI DALL-E and Gemini Imagen
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
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
14e26a4323
feat: capture Gemini cached content tokens in cost tracking
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
- 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
2026-04-26 21:14:53 -04:00
hobokenchicken
1f574d8134
feat: Phase 2 - reliability & observability
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
- 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
e12418cc4c
fix(gemini): ensure strict 1:1 pairing of model calls and function responses
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
- 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
2026-04-07 18:57:13 +00:00
hobokenchicken
be4ec3482a
fix(gemini): group adjacent tool messages and ensure correct role sequence
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
- 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
2026-04-07 18:50:48 +00:00
hobokenchicken
e67aafdac1
fix(gemini): improve tool-calling support and handle function_call response
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
- 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
2026-04-07 18:37:57 +00:00
hobokenchicken
1e13b0376b
feat(ollama): improve configuration and dashboard integration
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
2026-04-07 12:53:17 +00:00
hobokenchicken
03dca998df
chore: rebrand project to GopherGate
...
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
Updated all naming from LLM Proxy to GopherGate. Implemented new CSS-based branding and updated Go module/binary naming.
2026-03-19 13:37:05 -04:00
hobokenchicken
6b10d4249c
feat: migrate backend from rust to go
...
CI / Check (push) Has been cancelled
CI / Clippy (push) Has been cancelled
CI / Formatting (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Release Build (push) Has been cancelled
This commit replaces the Axum/Rust backend with a Gin/Go implementation. The original Rust code has been archived in the 'rust' branch.
2026-03-19 10:30:05 -04:00
hobokenchicken