Commit History
-
refactor(logging): clean up oauth logs and debugs
hkfires1b26f4d -
fix(executor): handle context cancellation and deadline errors explicitly
Unverified signaturee7d2c44
-
Merge pull request #787 from sususu98/fix/antigravity-429-retry-delay-parsing
Unverified signaturefix(antigravity): parse retry-after delay from 429 response bodyc48b3b7 -
feat(executor): centralize systemInstruction handling for Claude and Gemini-3-Pro models
Unverified signature993d71e -
fix(executor): update gemini model identifier to gemini-3-pro-preview
hkfiresUpdate the model name check in `buildRequest` to target "gemini-3-pro-preview" instead of "gemini-3-pro" when applying specific system instruction handling.f8a2b48 -
feat(executor): update system instruction handling for Claude and Gemini-3-Pro models
Unverified signature450f409 -
feat(executor): add model-specific support for "gemini-3-pro" in execution and payload handling
Unverified signature9c76ae8 -
feat(executor): enhance Antigravity payload with user role and dynamic system instructions
Unverified signature85a84b1
-
fix(executor): remove unused `tokenRefreshTimeout` constant and pass zero timeout to HTTP client
Unverified signatured7e3e91
-
feat(claude): add native request cloaking for non-claude-code clients
maoring24 +1: Claude Opus 4.5integrate claude-cloak functionality to disguise api requests: - add CloakConfig with mode (auto/always/never) and strict-mode options - generate fake user_id in claude code format (user_[hex]_account__session_[uuid]) - inject claude code system prompt (configurable strict mode) - obfuscate sensitive words with zero-width characters - auto-detect claude code clients via user-agent 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>89d5f4d
-
feat(executor): add token refresh timeout and improve context handling during refresh
Unverified signatureIntroduced `tokenRefreshTimeout` constant for token refresh operations and enhanced context propagation for `refreshToken` by embedding roundtrip information if available. Adjusted `refreshAuth` to ensure default context initialization and handle cancellation errors appropriately.31d9182
-
feat(executor): enhance payload translation with original request context
Unverified signatureRefactored `applyPayloadConfig` to `applyPayloadConfigWithRoot`, adding support for default rule validation against the original payload when available. Updated all executors to use `applyPayloadConfigWithRoot` and incorporate an optional original request payload for translations.ae057e3 -
fix(iflow): remove thinking field from request body in thinking config handler
hkfires0fe2ad3 -
refactor(iflow): simplify thinking config handling for GLM and MiniMax models
hkfirese1b952f
-
fix(thinking): fallback to upstream model for thinking support when alias not in registry
hkfirescc7e585 -
fix(thinking): use model alias for thinking config resolution in mapped models
hkfiresd57c140
-
refactor(executor): remove redundant upstream model parameter from translateRequest
hkfires8628ab7 -
refactor(executor): resolve upstream model at conductor level before execution
hkfiresc37b7ba -
fix(executor): use upstream model for thinking config and payload translation
hkfires7559da4 -
fix(antigravity): parse retry-after delay from 429 response body
sususuWhen receiving HTTP 429 (Too Many Requests) responses, parse the retry delay from the response body using parseRetryDelay and populate the statusErr.retryAfter field. This allows upstream callers to respect the server's requested retry timing. Applied to all error paths in Execute, executeClaudeNonStream, ExecuteStream, CountTokens, and refreshToken functions.9433db3 -
feat(gemini): add per-key model alias support for Gemini provider
hkfirese4d3e38 -
feat(cliproxy): introduce global model name mappings for improved aliasing and routing
Unverified signaturee5e9477
-
Merge pull request #757 from ben-vargas/fix-thinking-toolchoice-conflict
Unverified signatureFix: disable thinking when tool_choice forces tool use603d11d
-
Fix: disable thinking when tool_choice forces tool use
Ben VargasAnthropic API does not allow extended thinking when tool_choice is set to "any" or a specific tool. This was causing 400 errors when using features like Amp's /handoff command which forces tool_choice. Added disableThinkingIfToolChoiceForced() that removes thinking config when incompatible tool_choice is detected, applied to both streaming and non-streaming paths. Fixes router-for-me/CLIProxyAPI#630af8d546 -
feat(cliproxy): implement model aliasing and hashing for Codex configurations, enhance request routing logic, and normalize Codex model entries
Unverified signaturefe1d7f4
-
feat(iflow): add model-specific thinking configs for GLM-4.7 and MiniMax-M2.1
leaph- GLM-4.7: Uses extra_body={"thinking": {"type": "enabled"}, "clear_thinking": false} - MiniMax-M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation - Added preserveReasoningContentInMessages() to support re-injection of reasoning content in assistant message history for multi-turn conversations - Added ThinkingSupport to MiniMax-M2.1 model definition9abfbc9
-
Fixed: #747
Unverified signaturefix(translators): rename and integrate `usageMetadata` as `cpaUsageMetadata` in Claude processing logic17a5260
-
feat(usage): add import/export functionality for usage statistics and enhance deduplication logic
Unverified signature0658eb9
-
refactor: extract parseGeminiFamilyUsageDetail helper to reduce duplication
08bea2c -
feat: add cached token parsing for Gemini API responses
ede3a49
-
Merge branch 'dev' into fix/antigravity-prompt-caching
Unverified signature302b826 -
fix(claude_executor): update header logic for API key handling
Unverified signatureRefined header assignment to use `x-api-key` for Anthropic API requests, ensuring correct authorization behavior based on request attributes and URL validation.65a5604
-
refactor(antigravity): add sandbox URL constant and update base URLs routine
Unverified signature9171f0b
-
Merge branch 'main' into fix/antigravity-prompt-caching
cb41cbf -
feat(antigravity): add session ID generation and mutex for random source
1b0bbc3 -
Merge pull request #611 from soilSpoon/feature/antigravity
Unverified signaturefeat(antigravity): Improve Claude model compatibilitye05a2cd -
Remove interleaved-thinking header from requests
이대희Removes the addition of the "anthropic-beta: interleaved-thinking-2025-05-14" header for Claude thinking models when building HTTP requests. This prevents sending an experimental/feature flag header that is no longer required and avoids potential compatibility or routing issues with downstream services. Keeps request headers simpler and more standard.6a9882e -
Improve thinking/tool signature handling for Claude and Gemini requests
이대희Prefer cached signatures and avoid injecting dummy thinking blocks; instead remove unsigned thinking blocks and add a skip sentinel for tool calls without a valid signature. Generate stable session IDs from the first user message, apply schema cleaning only for Claude models, and reorder thinking parts so thinking appears first. For Gemini, remove thinking blocks and attach a skip sentinel to function calls. Simplify response handling by passing raw function args through (remove special Bash conversion). Update and add tests to reflect the new behavior. These changes prevent rejected dummy signatures, improve compatibility with Antigravity’s signature validation, provide more stable session IDs for conversation grouping, and make request/response translation more robust.b375e09
-
feat(antigravity): add payload config support to Antigravity executor
Ben VargasAdd applyPayloadConfig calls to all Antigravity executor paths (Execute, executeClaudeNonStream, ExecuteStream) to enable config.yaml payload overrides for Antigravity/Gemini-Claude models. This allows users to configure thinking budget and other parameters via payload.override in config.yaml for models like gemini-claude-opus-4-5*.c53de5b
-
fix(gemini): add optional skip for gemini3 thinking conversion
hkfiresbaafbd7 -
refactor(antigravity): regarding production endpoint caching
Unverified signatureacfcf85 -
feat(antigravity): enhance prompt caching support and update agent version
Unverified signature5d8639e -
fix(runtime/executor): Antigravity executor schema handling and Claude-specific headers
이대희71986bf
-
Merge pull request #582 from ben-vargas/fix-gemini-3-thinking-level
Unverified signaturefeat: use thinkingLevel for Gemini 3 models per Google documentation936d72c -
fix: apply thinkingLevel from model suffix metadata for Gemini 3
Ben VargasThe previous commit added thinkingLevel support but didn't apply it when the reasoning effort came from model name suffix (e.g., model(minimal)). This was because ResolveThinkingConfigFromMetadata returns nil for level-based models, bypassing the metadata application. Changes: - Add ApplyGemini3ThinkingLevelFromMetadata for standard Gemini API - Add ApplyGemini3ThinkingLevelFromMetadataCLI for CLI API format - Update gemini_cli_executor to apply Gemini 3 thinkingLevel from metadata - Update antigravity_executor to apply Gemini 3 thinkingLevel from metadata - Update aistudio_executor to apply Gemini 3 thinkingLevel from metadata - Add comprehensive test coverage for Gemini 3 thinkingLevel functionsa1a3463 -
feat: use thinkingLevel for Gemini 3 models per Google documentation
Ben VargasPer Google's official documentation, Gemini 3 models should use thinkingLevel (string) instead of thinkingBudget (number) for optimal performance. From Google's Gemini Thinking docs: > Use the thinkingLevel parameter with Gemini 3 models. While > thinkingBudget is accepted for backwards compatibility, using > it with Gemini 3 Pro may result in suboptimal performance. Changes: - Add model family detection functions (IsGemini3Model, IsGemini25Model, IsGemini3ProModel, IsGemini3FlashModel) - Add ApplyGeminiThinkingLevel and ApplyGeminiCLIThinkingLevel functions for applying thinkingLevel config - Add ValidateGemini3ThinkingLevel for model-specific level validation - Add ThinkingBudgetToGemini3Level for backward compatibility conversion - Update NormalizeGeminiThinkingBudget to convert budget to level for Gemini 3 models - Update ApplyDefaultThinkingIfNeeded to not set a default level for Gemini 3 (lets API use its dynamic default "high") - Update ConvertThinkingLevelToBudget to …965592d -
feat(antigravity): enable token counting via API with resilient routing
Unverified signatureIntroduces the capability to count tokens for Antigravity-backed requests. This implementation leverages the `countTokens` endpoint of the Antigravity API, replacing the prior unsupported stub. Key aspects of this update include: - **API Integration**: Direct integration with the Antigravity `countTokens` API, including necessary request payload translation and authentication. - **Resilient Infrastructure**: A fallback mechanism has been established, allowing the system to attempt connections across multiple Antigravity base URLs to ensure request success even in the event of temporary service interruptions. - **Model Aliasing**: Added mappings for `gemini-3-flash` and `gemini-3-flash-preview` to ensure compatibility with the latest model variants. - **Robust Error Handling**: Comprehensive error handling and logging are in place to manage failures during API interactions.f45d5be -
feat(antigravity): implement non-streaming execution for Claude model requests
Unverified signature892dae7 -
feat(antigravity): add streaming support for Claude model requests
Unverified signatured1285a5 -
feature: Improves Gemini JSON schema compatibility
이대희Enhances compatibility with the Gemini API by implementing a schema cleaning process. This includes: - Centralizing schema cleaning logic for Gemini in a dedicated utility function. - Converting unsupported schema keywords to hints within the description field. - Flattening complex schema structures like `anyOf`, `oneOf`, and type arrays to simplify the schema. - Handling streaming responses with empty tool names, which can occur in subsequent chunks after the initial tool use.9235ac8