Commit History
-
feat(codex): expose fixed gpt-5.3 reasoning aliases
shinmentakezo07 +1: Claude Opus 4.6Expose gpt-5.3-codex-{medium,high,xhigh} in static model listings and map each alias to gpt-5.3-codex with a fixed reasoning level so /models visibility and request behavior stay consistent. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>ef25018
-
feat(translator): support Claude thinking type adaptive
hkfires0e703c6
-
fix(translator): correct gemini-cli log prefix
hkfiresd16ad6f
-
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>61bff8c
-
fix(test): rename test function to reflect behavior change for builtin tools
hkfires9eafd2d
-
feat(thinking): enable thinking toggle for qwen3 and deepseek models
hkfiresFix #1245a72e515
-
feat(registry): support provider-specific model info lookup
hkfires4771da8
-
fix(executor): stop rewriting thinkingLevel for gemini
hkfiresaeb8420
-
fix(thinking): update ValidateConfig to include fromSuffix parameter and adjust budget validation logic
hkfiresb8c994e -
refactor(thinking): add Gemini family provider grouping for strict validation
hkfires56b75fa
-
test(thinking): split E2E coverage into suffix and body parameter test functions
hkfiresRefactor thinking configuration tests by separating model name suffix-based scenarios from request body parameter-based scenarios into distinct test functions with independent case numbering. Architectural improvements: - Extract thinkingTestCase struct to package level for shared usage - Add getTestModels() helper returning complete model fixture set - Introduce runThinkingTests() runner with protocol-specific field detection - Register level-subset-model fixture with constrained low/high level support - Extend iflow protocol handling for glm-test and minimax-test models - Add same-protocol strict boundary validation cases (80-89) - Replace error responses with clamped values for boundary-exceeding budgetse7620c8
-
refactor(thinking): extract antigravity logic into a dedicated provider
hkfiresc549b59 -
feat(thinking): support zero as a valid thinking budget for capable models
hkfires61f17fe
-
test(thinking): remove legacy unit and integration tests
hkfires9904520 -
refactor: improve thinking logic
hkfiresee9e572
-
Merge pull request #553 from XInTheDark/fix/builtin-tools-web-search
Unverified signaturefix(translator): preserve built-in tools (web_search) to Responses APIda67a35
-
fix(thinking): fallback to upstream model for thinking support when alias not in registry
hkfirescc7e585 -
feat(thinking): add numeric budget to thinkingLevel conversion fallback
hkfires592bae1
-
feat(amp): add per-client upstream API key mapping support
hkfires261120f
-
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 -
Revert "Fix invalid thinking signature when proxying Claude via Antigravity"
Unverified signature4e381dc
-
Merge pull request #570 from fuguiKz/fix/antigravity-thinking-signature
Unverified signatureFix invalid thinking signature when proxying Claude via Antigravity3ddc429 -
Fix antigravity Claude thinking signature handling
kz9d846bd -
test(thinking): add effort to budget coverage
hkfiresd2aaec4 -
fix(thinking): align budget effort mapping across translators
hkfiresUnify thinking budget-to-effort conversion in a shared helper, handle disabled/default thinking cases in translators, adjust zero-budget mapping, and drop the old OpenAI-specific helper with updated tests.c54ab2f
-
fix(translator): preserve built-in tools across openai<->responses
Muzhen Gaming- Pass through non-function tool definitions like web_search - Translate tool_choice for built-in tools and function tools - Add regression tests for built-in tool passthrough3dfd3b1
-
refactor(thinking): export thinking helpers
hkfiresExpose thinking/effort normalization helpers from the executor package so conversion tests use production code and stay aligned with runtime validation behavior.ca524b4 -
fix(thinking): normalize effort mapping
hkfiresRoute OpenAI reasoning effort through ThinkingEffortToBudget for Claude translators, preserve "minimal" when translating OpenAI Responses, and treat blank/unknown efforts as no-ops for Gemini thinking configs. Also map budget -1 to "auto" and expand cross-protocol thinking tests.36f3ffa -
test(thinking): expand conversion edge case coverage
hkfires258ee6d -
fix(thinking): centralize reasoning_effort mapping
hkfiresMove OpenAI `reasoning_effort` -> Gemini `thinkingConfig` budget logic into shared helpers used by Gemini, Gemini CLI, and antigravity translators. Normalize Claude thinking handling by preferring positive budgets, applying budget token normalization, and gating by model support. Always convert Gemini `thinkingBudget` back to OpenAI `reasoning_effort` to support allowCompat models, and update tests for normalization behavior.af472cd -
test(thinking): cover openai-compat reasoning passthrough
hkfires3edf233
-
fix(thinking): gate reasoning effort by model support
hkfiresOnly map OpenAI reasoning effort to Claude thinking for models that support thinking and use budget tokens (not level-based thinking). Also add "xhigh" effort mapping and adjust minimal/low budgets, with new raw-payload conversion tests across protocols and models.eed5166
-
fix(thinking): map budgets to effort levels
hkfiresEnsure thinking settings translate correctly across providers: - Only apply reasoning_effort to level-based models and derive it from numeric budget suffixes when present - Strip effort string fields for budget-based models and skip Claude/Gemini budget resolution for level-based or unsupported models - Default Gemini include_thoughts when a nonzero budget override is set - Add cross-protocol conversion and budget range tests0784078
-
refactor(api): simplify request body parsing in ampcode handlers
hkfires4713619 -
feat(api): add comprehensive ampcode management endpoints
hkfiresAdd new REST API endpoints under /v0/management/ampcode for managing ampcode configuration including upstream URL, API key, localhost restriction, model mappings, and force model mappings settings. - Move force-model-mappings from config_basic to config_lists - Add GET/PUT/PATCH/DELETE endpoints for all ampcode settings - Support model mapping CRUD with upsert (PATCH) capability - Add comprehensive test coverage for all ampcode endpointsea789cd
-
refactor(config): improve OpenAI compatibility target matching logic
hkfiresb1c0cae