Commit History
-
track binary files with git-lfs
Shinway Deploydb492de
-
feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests
hkfires1e87161
-
Merge pull request #1467 from dusty-du/fix/kimi-toolcall-reasoning-content
Unverified signatureFix Kimi tool-call payload normalization for reasoning_contente72ccc6 -
fix(kimi): reduce redundant payload cloning and simplify translation calls
Unverified signature349a004
-
fix(kimi): update base URL and integrate ClaudeExecutor fallback
Unverified signature- Updated `KimiAPIBaseURL` to remove versioning from the root path. - Integrated `ClaudeExecutor` fallback in `KimiExecutor` methods for compatibility with Claude requests. - Simplified token counting by delegating to `ClaudeExecutor`.a36e9ba -
Fix Kimi tool-call reasoning_content normalization
test60a69e4 -
feat: add Kimi authentication support and streamline device ID handling
Unverified signature- Introduced `RequestKimiToken` API for Kimi authentication flow. - Integrated device ID management throughout Kimi-related components. - Enhanced header management for Kimi API requests with device ID context.1ff5b6f -
Add Kimi (Moonshot AI) provider support
test +1: Claude Opus 4.6- OAuth2 device authorization grant flow (RFC 8628) for authentication - Streaming and non-streaming chat completions via OpenAI-compatible API - Models: kimi-k2, kimi-k2-thinking, kimi-k2.5 - CLI `--kimi-login` command for device flow auth - Token management with automatic refresh - Thinking/reasoning effort support for thinking-enabled models Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>88a36e2
-
refactor(executor): centralize Codex client version and user agent constants
Unverified signature- Introduced `codexClientVersion` and `codexUserAgent` constants for better maintainability. - Updated `EnsureHeader` calls to use the new constants.564ee15 -
refactor(translator, executor): remove redundant `bytes.Clone` calls for improved performance
Unverified signature- Replaced all instances of `bytes.Clone` with direct references to enhance efficiency. - Simplified payload handling across executors and translators by eliminating unnecessary data duplication.7e8afbe -
refactor(executor): optimize payload cloning and streamline SDK translator usage
Unverified signature- Replaced unnecessary `bytes.Clone` calls for `opts.OriginalRequest` throughout executors. - Introduced intermediate variable `originalPayloadSource` to simplify payload processing. - Ensured better clarity and structure in request translation logic.8953a28 -
refactor(util, executor): optimize payload handling and schema processing
Unverified signature- Replaced repetitive string operations with a centralized `escapeGJSONPathKey` function. - Streamlined handling of JSON schema cleaning for Gemini and Antigravity requests. - Improved payload management by transitioning from byte slices to strings for processing. - Removed unnecessary cloning of byte slices in several places.b7fd8ec
-
fix(executor): handle "global" location in AI platform URL generation
Unverified signature96d4e31
-
refactor(codex): remove codex instructions injection support
hkfiresf1597d6
-
feat(config): add payload filter rules to remove JSON paths
Unverified signatureIntroduce `Filter` rules in the payload configuration to remove specified JSON paths from the payload. Update related helper functions and add examples to `config.example.yaml`.272f0d9 -
Fixed: #1372 #1366
Unverified signaturefix(caching): ensure unique cache_control injection using count validationbf10a0c
-
Merge pull request #1248 from shekohex/feat/responses-compact
Unverified signaturefeat(openai): add responses/compact support1094f8a -
fix(caching): ensure prompt-caching beta is always appended and add multi-turn cache control tests
Unverified signature7808a6c
-
feat(caching): implement Claude prompt caching with multi-turn support
Martin Schneeweiss +1: Claude Opus 4.5- Add ensureCacheControl() to auto-inject cache breakpoints - Cache tools (last tool), system (last element), and messages (2nd-to-last user turn) - Add prompt-caching-2024-07-31 beta header - Return original payload on sjson error to prevent corruption - Include verification test for caching logic Enables up to 90% cost reduction on cached tokens. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>bc71fff
-
fix(codex): avoid empty prompt_cache_key
Shady KhalifaUnverified signatureb2f5f03 -
fix(openai): drop stream for responses/compact
Shady KhalifaUnverified signature9df2a02
-
feat(openai): add responses/compact support
Shady KhalifaUnverified signature642da09 -
feat(auth): add support for request_retry and disable_cooling overrides
Unverified signatureImplement `request_retry` and `disable_cooling` metadata overrides for authentication management. Update retry and cooling logic accordingly across `Manager`, Antigravity executor, and file synthesizer. Add tests to validate new behaviors.add7d68
-
refactor(runtime): implement retry logic for Antigravity executor with improved error handling and capacity management
Unverified signaturedc4a94c -
feat(executor): add request_id to error logs
hkfiresExtract error.message from JSON error responses when summarizing error bodies for debug logsc122a46
-
Merge pull request #1132 from XYenon/fix/gemini-models-displayname-override
Unverified signaturefix(gemini): preserve displayName and description in models list2f5a938
-
fix(claude): skip built-in tools in OAuth tool prefix
Mauricio Allende339abb4 -
feat(executor): apply payload rules using requested model
hkfiresba27e38
-
fix(executor): adjust model-specific request payload
hkfires1b2edbc -
refactor(util): reorder gemini schema cleaner helpers
hkfiresd2f5bc1
-
Fix Gemini function-calling INVALID_ARGUMENT by relaxing Gemini tool validation and cleaning schema
sowar1987e4915f5 -
fix(gemini): preserve displayName and description in models list
XYenonPreviously GeminiModels handler unconditionally overwrote displayName and description with the model name, losing the original values defined in model definitions (e.g., 'Gemini 3 Pro Preview'). Now only set these fields as fallback when they are missing or empty.5ae9bf2 -
fix(executor): only strip maxOutputTokens for non-claude models
hkfiresdfde8e4
-
Fix antigravity malformed_function_call
bexcodex46083fd -
refactor(claude): remove redundant system instructions check in Claude executor
Unverified signature9ae0b9f -
Merge pull request #868
Unverified signature59ebdef -
feat(registry): support provider-specific model info lookup
hkfiresa0b18a6
-
feat(vertex): add Imagen image generation model support
Add support for Imagen 3.0 and 4.0 image generation models in Vertex AI: - Add 5 Imagen model definitions (4.0, 4.0-ultra, 4.0-fast, 3.0, 3.0-fast) - Implement :predict action routing for Imagen models - Convert Imagen request/response format to match Gemini structure like gemini-3-pro-image - Transform prompts to Imagen's instances/parameters format - Convert base64 image responses to Gemini-compatible inline datafec8f9a -
Merge pull request #1099 from router-for-me/claude
Unverified signaturerefactor(claude): move max_tokens constraint enforcement to Apply method96c699d -
fix(executor): stop rewriting thinkingLevel for gemini
hkfirescf2ec46 -
feat(registry): expand antigravity model config
hkfiresRemove static Name mapping and add entries for claude-sonnet-4-5, tab_flash_lite_preview, and gpt-oss-120b-medium configs15faa87 -
refactor(claude): move max_tokens constraint enforcement to Apply method
hkfires4300f05
-
refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation
hkfiresUpdate ApplyThinking signature to accept fromFormat and toFormat parameters instead of a single provider string. This enables: - Proper level-to-budget conversion when source is level-based (openai/codex) and target is budget-based (gemini/claude) - Strict budget range validation when source and target formats match - Level clamping to nearest supported level for cross-format requests - Format alias resolution in SDK translator registry for codex/openai-response Also adds ErrBudgetOutOfRange error code and improves iflow config extraction to fall back to openai format when iflow-specific config is not present.0d5d901
-
feat(runtime): add model alias support and enhance payload rule matching
Unverified signature- Introduced `payloadModelAliases` and `payloadModelCandidates` functions to support model aliases for improved flexibility. - Updated rule matching logic to handle multiple model candidates. - Refactored variable naming in executor to improve code clarity and consistency.cb7cfc9 -
feat(codex): enhance input transformation and remove unused `safety_identifier` field
Unverified signature- Added logic to transform `inputResults` into structured JSON for improved processing. - Removed redundant `safety_identifier` field in executor payload to streamline requests.8f87944 -
fix(codex): ensure instructions field exists
hkfires0407c8c -
feat(config): supplement missing default aliases during antigravity migration
hkfiresed8924a -
feat(config): add support for raw JSON payload rules
Unverified signature- Introduced `default-raw` and `override-raw` rules to handle raw JSON values. - Enhanced `PayloadConfig` to validate and sanitize raw JSON payload rules. - Updated executor logic to apply `default-raw` and `override-raw` rules. - Extended example YAML to include usage of raw JSON rules.6fe8677
-
Merge pull request #1033 from router-for-me/reasoning
Unverified signatureRefactor thinkinge2f37ed -
refactor(thinking): extract antigravity logic into a dedicated provider
hkfiresfdcdaf9