Merge pull request #947 from pykancha/fix-memory-leak

Merge pull request #938 from router-for-me/log

Merge pull request #943 from ben-vargas/fix-tool-mappings

Fixed: #942

Merge branch 'main' into plus

Use unprefixed Claude request for translation

fix(server): resolve memory leaks causing OOM in k8s deployment

Fix Claude OAuth tool name mapping

refactor(logging): clean up oauth logs and debugs

fix(executor): handle context cancellation and deadline errors explicitly

Merge pull request #787 from sususu98/fix/antigravity-429-retry-delay-parsing

Merge branch 'router-for-me:main' into main

feat(executor): centralize systemInstruction handling for Claude and Gemini-3-Pro models

Merge branch 'router-for-me:main' into main

fix(executor): update gemini model identifier to gemini-3-pro-preview

Merge branch 'router-for-me:main' into main

feat(executor): update system instruction handling for Claude and Gemini-3-Pro models

feat(executor): add model-specific support for "gemini-3-pro" in execution and payload handling

Merge branch 'router-for-me:main' into main

feat(executor): enhance Antigravity payload with user role and dynamic system instructions

Merge branch 'router-for-me:main' into main

fix(executor): remove unused `tokenRefreshTimeout` constant and pass zero timeout to HTTP client

feat(claude): add native request cloaking for non-claude-code clients

Merge branch 'main' into plus

feat(executor): add token refresh timeout and improve context handling during refresh

feat(executor): refine payload handling by integrating original request context

Merge branch 'router-for-me:main' into main

feat(executor): enhance payload translation with original request context

Merge branch 'router-for-me:main' into main

fix(iflow): remove thinking field from request body in thinking config handler

refactor(iflow): simplify thinking config handling for GLM and MiniMax models

fix(thinking): fallback to upstream model for thinking support when alias not in registry

fix(thinking): use model alias for thinking config resolution in mapped models

Merge branch 'main' into plus

refactor(executor): remove redundant upstream model parameter from translateRequest

refactor(executor): resolve upstream model at conductor level before execution

fix(executor): use upstream model for thinking config and payload translation

fix(antigravity): parse retry-after delay from 429 response body

feat(gemini): add per-key model alias support for Gemini provider

Merge branch 'router-for-me:main' into main

feat(cliproxy): introduce global model name mappings for improved aliasing and routing

Merge branch 'router-for-me:main' into main

Merge pull request #757 from ben-vargas/fix-thinking-toolchoice-conflict

Fix: disable thinking when tool_choice forces tool use

Merge branch 'router-for-me:main' into main

feat(cliproxy): implement model aliasing and hashing for Codex configurations, enhance request routing logic, and normalize Codex model entries

Merge branch 'router-for-me:main' into main

feat(iflow): add model-specific thinking configs for GLM-4.7 and MiniMax-M2.1

Merge branch 'router-for-me:main' into main

Fixed: #747