umputun / mpt / 19909863023

Builds Branch Commit Type Ran Committer Via Coverage
19909863023 master chore(deps): bump golang.org/x/crypto from 0.43.0 to 0.45.0 (#32) Bumps [golang.org/x/crypto](https://github.com/golang/crypto) from 0.43.0 to 0.45.0. - [Commits](https://github.com/golang/crypto/compare/v0.43.0...v0.45.0) --- updated-dependenci... push web-flow github
88.11
19523707682 dependabot/go_modules/golang.org/x/crypto-0.45.0 chore(deps): bump golang.org/x/crypto from 0.43.0 to 0.45.0 Bumps [golang.org/x/crypto](https://github.com/golang/crypto) from 0.43.0 to 0.45.0. - [Commits](https://github.com/golang/crypto/compare/v0.43.0...v0.45.0) --- updated-dependencies: - ... Pull #32 web-flow github
88.11
19022956211 master refactor: improve robustness with response size limits and fail-fast error handling reduce MaxResponseSize from 100MB to 10MB for better memory management. add explicit detection for oversized responses before JSON parsing. change temp directory ... push umputun github
88.11
18990179488 refs/tags/v0.14.3 feat: add reasoning effort parameter support for GPT-5 models - add reasoning-effort CLI flag with choices: low, medium (default), high - add REASONING_EFFORT environment variable support - add reasoning effort to OpenAI provider request structur... push umputun github
88.21
18990163783 master feat: add reasoning effort parameter support for GPT-5 models - add reasoning-effort CLI flag with choices: low, medium (default), high - add REASONING_EFFORT environment variable support - add reasoning effort to OpenAI provider request structur... push umputun github
88.21
18989056683 refs/tags/v0.14.2 fix(provider): add HTTP status code validation for non-JSON error responses add validation to detect and properly handle non-JSON HTTP error responses (e.g., HTML error pages from proxies, cloudflare errors). the fix checks if non-2xx responses c... push umputun github
88.17
18989035214 master fix(provider): add HTTP status code validation for non-JSON error responses add validation to detect and properly handle non-JSON HTTP error responses (e.g., HTML error pages from proxies, cloudflare errors). the fix checks if non-2xx responses c... push umputun github
88.17
18987813992 master docs: update README with correct defaults and optional API key info - fix incorrect OpenAI default model (gpt-5-codex → gpt-5) - fix incorrect Google default model (gemini-2.5-pro-preview-06-05 → gemini-2.5-pro-exp-03-25) - document optional API ... push umputun github
88.06
18987774886 refs/tags/v0.14.1 fix: make API key optional for custom providers skip Authorization header when API key is empty to support custom providers that don't require authentication (local LLMs, development servers, etc.) previously, empty API key would send 'Authoriza... push umputun github
88.06
18987750623 master fix: make API key optional for custom providers skip Authorization header when API key is empty to support custom providers that don't require authentication (local LLMs, development servers, etc.) previously, empty API key would send 'Authoriza... push umputun github
88.06
18986734831 refs/tags/v0.14.0 Add GPT-5 support with dual endpoint implementation (#31) * feat: add GPT-5 support with v1/responses endpoint Implement native support for GPT-5 models by adding v1/responses endpoint handling alongside existing v1/chat/completions support. Ke... push web-flow github
88.06
18986698835 master Add GPT-5 support with dual endpoint implementation (#31) * feat: add GPT-5 support with v1/responses endpoint Implement native support for GPT-5 models by adding v1/responses endpoint handling alongside existing v1/chat/completions support. Ke... push web-flow github
88.06
18986495493 feature/add-gpt5-support feat(custom): add endpoint-type configuration for custom providers add endpoint-type option to allow custom OpenAI-compatible providers to specify which API endpoint to use (auto, responses, chat_completions). this enables GPT-5 support via custo... Pull #31 umputun github pending completion
18986496048 feature/add-gpt5-support feat(custom): add endpoint-type configuration for custom providers add endpoint-type option to allow custom OpenAI-compatible providers to specify which API endpoint to use (auto, responses, chat_completions). this enables GPT-5 support via custo... Pull #31 umputun github pending completion
18986197669 feature/add-gpt5-support chore: update dependencies and regenerate vendor Update all outdated dependencies to latest versions: - anthropic-sdk-go: v1.13.0 => v1.16.0 - mcp-go: v0.41.1 => v0.42.0 - google.golang.org/genai: v1.28.0 => v1.33.0 - google.golang.org/grpc: v1.7... Pull #31 umputun github pending completion