refactor(executor): split providers and preserve legacy entrypoints

feat: passthrough upstream response headers to clients

refactor(translator, executor): remove redundant `bytes.Clone` calls for improved performance

refactor(executor): optimize payload cloning and streamline SDK translator usage

refactor(util, executor): optimize payload handling and schema processing

Merge pull request #1248 from shekohex/feat/responses-compact

feat(openai): add responses/compact support

feat(auth): add support for request_retry and disable_cooling overrides

refactor(runtime): implement retry logic for Antigravity executor with improved error handling and capacity management

Merge pull request #1132 from XYenon/fix/gemini-models-displayname-override

feat(executor): apply payload rules using requested model

fix(executor): adjust model-specific request payload

refactor(util): reorder gemini schema cleaner helpers

Fix Gemini function-calling INVALID_ARGUMENT by relaxing Gemini tool validation and cleaning schema

fix(gemini): preserve displayName and description in models list

fix(executor): only strip maxOutputTokens for non-claude models

Fix antigravity malformed_function_call

feat(registry): support provider-specific model info lookup

fix(executor): stop rewriting thinkingLevel for gemini

feat(registry): expand antigravity model config

refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation

feat(runtime): add model alias support and enhance payload rule matching

feat(config): supplement missing default aliases during antigravity migration

Merge pull request #1033 from router-for-me/reasoning

refactor(thinking): extract antigravity logic into a dedicated provider

refactor(auth): simplify file handling logic and remove redundant comparison functions

refactor(thinking): improve budget clamping and logging with provider/model context

fix(thinking): map reasoning_effort to thinkingConfig

fix(thinking): improve model lookup and validation

refactor(antigravity): remove hardcoded model aliases

fix(executor): properly handle thinking application errors

refactor: improve thinking logic

feat(executor): add HttpRequest support across executors for better http request handling

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

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

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

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

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

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

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

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

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

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

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

Merge branch 'dev' into fix/antigravity-prompt-caching