1224 Commits

Author	SHA1	Message	Date
이대희	a45c6defa7	Merge remote-tracking branch 'upstream/main' into feature/canceled	2026-02-13 15:07:32 +09:00
Luis Pater	ae1e8a5191	chore(runtime, registry): update Codex client version and GPT-5.3 model creation date	2026-02-13 12:47:48 +08:00
이대희	40bee3e8d9	Merge branch 'main' into feature/canceled	2026-02-13 13:37:55 +09:00
Franz Bettag	1ce56d7413	Update internal/registry/model_definitions_static_data.go ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2026-02-12 23:37:27 +01:00
Franz Bettag	41a78be3a2	feat(registry): add gpt-5.3-codex-spark model definition	2026-02-12 23:24:08 +01:00
Luis Pater	575881cb59	feat(registry): add new model definition for MiniMax-M2.5	2026-02-12 22:43:01 +08:00
hkfires	f361b2716d	feat(registry): add glm-5 model to iflow	2026-02-12 11:13:28 +08:00
이대희	93147dddeb	Improves error handling for canceled requests ... Adds explicit handling for context.Canceled errors in the reverse proxy error handler to return 499 status code without logging, which is more appropriate for client-side cancellations during polling. Also adds a test case to verify this behavior.	2026-02-12 10:39:45 +09:00
이대희	c0f9b15a58	Merge remote-tracking branch 'upstream/main' into feature/canceled	2026-02-12 10:33:49 +09:00
이대희	6f2fbdcbae	Update internal/api/modules/amp/proxy.go ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2026-02-12 10:30:05 +09:00
Luis Pater	58e09f8e5f	Merge pull request #1542 from APE-147/fix/gemini-antigravity-schema-sanitization ... fix(schema): sanitize Gemini-incompatible tool metadata fields	2026-02-11 21:34:04 +08:00
Luis Pater	a146c6c0aa	Merge pull request #1523 from xxddff/feature/removeUserField ... fix(codex): remove unsupported 'user' field from /v1/responses payload	2026-02-11 20:38:16 +08:00
Luis Pater	4c133d3ea9	test(sdk/watcher): add tests for excluded models merging and priority parsing logic ... - Added unit tests for combining OAuth excluded models across global and attribute-specific scopes. - Implemented priority attribute parsing with support for different formats and trimming.	2026-02-11 20:35:13 +08:00
RGBadmin	dc279de443	refactor: reduce code duplication in extractExcludedModelsFromMetadata	2026-02-11 15:57:16 +08:00
Nathan	166d2d24d9	fix(schema): remove Gemini-incompatible tool metadata fields ... Sanitize tool schemas by stripping prefill, enumTitles, $id, and patternProperties to prevent Gemini INVALID_ARGUMENT 400 errors, and add unit and executor-level tests to lock in the behavior. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-11 18:29:17 +11:00
RGBadmin	b93026d83a	feat: merge per-account excluded_models with global config	2026-02-11 15:21:15 +08:00
RGBadmin	5ed2133ff9	feat: add per-account excluded_models and priority parsing	2026-02-11 15:21:12 +08:00
Luis Pater	1510bfcb6f	fix(translator): improve content handling for system and user messages ... - Added support for single and array-based `content` cases. - Enhanced `system_instruction` structure population logic. - Improved handling of user role assignment for string-based `content`.	2026-02-11 15:04:01 +08:00
Chén Mù	c6bd91b86b	Merge pull request #1519 from router-for-me/thinking ... feat(translator): support Claude thinking type adaptive	2026-02-10 18:31:56 +08:00
이대희	ce0c6aa82b	Update internal/api/modules/amp/proxy.go ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2026-02-10 19:07:49 +09:00
hkfires	349ddcaa89	fix(registry): correct max completion tokens for opus 4.6 thinking	2026-02-10 18:05:40 +08:00
xxddff	bb9fe52f1e	Update internal/translator/codex/openai/responses/codex_openai-responses_request_test.go ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2026-02-10 18:24:58 +09:00
xxddff	afe4c1bfb7	更新internal/translator/codex/openai/responses/codex_openai-responses_request.go ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2026-02-10 18:24:26 +09:00
이대희	3c85d2a4d7	feature(proxy): Adds special handling for client cancellations in proxy error handler ... Silences logging for client cancellations during polling to reduce noise in logs. Client-side cancellations are common during long-running operations and should not be treated as errors.	2026-02-10 18:02:08 +09:00
xxddff	865af9f19e	Implement test for user field deletion ... Add test to verify deletion of user field in response	2026-02-10 17:38:49 +09:00
xxddff	2b97cb98b5	Delete 'user' field from raw JSON ... Remove the 'user' field from the raw JSON as requested.	2026-02-10 17:35:54 +09:00
hkfires	938a799263	feat(translator): support Claude thinking type adaptive	2026-02-10 16:20:32 +08:00
Luis Pater	0040d78496	refactor(sdk): simplify provider lifecycle and registration logic	2026-02-10 15:39:26 +08:00
Muhammad Zahid Masruri	918b6955e4	fix(amp): rewrite model name in response.model for Responses API SSE events ... The ResponseRewriter's modelFieldPaths was missing 'response.model', causing the mapped model name to leak through SSE streaming events (response.created, response.in_progress, response.completed) in the OpenAI Responses API (/v1/responses). This caused Amp CLI to report 'Unknown OpenAI model' errors when model mapping was active (e.g., gpt-5.2-codex -> gpt-5.3-codex), because the mapped name reached Amp's backend via telemetry. Also sorted modelFieldPaths alphabetically per review feedback and added regression tests for all rewrite paths. Fixes #1463	2026-02-09 23:52:59 +07:00
Luis Pater	5a3eb08739	Merge pull request #1502 from router-for-me/iflow ... feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests	2026-02-09 19:56:12 +08:00
hkfires	49c1740b47	feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests	2026-02-09 19:29:42 +08:00
hkfires	3fbee51e9f	fix(management): ensure management.html is available synchronously and improve asset sync handling	2026-02-09 08:32:58 +08:00
Luis Pater	63643c44a1	Fixed: #1484 ... fix(translator): restructure message content handling to support multiple content types - Consolidated `input_text` and `output_text` handling into a single case. - Added support for processing `input_image` content with associated URLs.	2026-02-09 02:05:38 +08:00
hkfires	7197fb350b	fix(config): prune default descendants when merging new yaml nodes	2026-02-08 19:05:52 +08:00
hkfires	6e349bfcc7	fix(config): avoid writing known defaults during merge	2026-02-08 18:47:44 +08:00
hkfires	234056072d	refactor(management): streamline control panel management and implement sync throttling	2026-02-08 10:42:49 +08:00
Luis Pater	7e9d0db6aa	Merge pull request #1467 from dusty-du/fix/kimi-toolcall-reasoning-content ... Fix Kimi tool-call payload normalization for reasoning_content	2026-02-07 09:35:04 +08:00
Luis Pater	78ef04fcf1	fix(kimi): reduce redundant payload cloning and simplify translation calls	2026-02-07 08:51:48 +08:00
hkfires	b7e4f00c5f	fix(translator): correct gemini-cli log prefix	2026-02-07 08:40:09 +08:00
Luis Pater	f7d0019df7	fix(kimi): update base URL and integrate ClaudeExecutor fallback ... - 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`.	2026-02-07 06:42:08 +08:00
test	52364af5bf	Fix Kimi tool-call reasoning_content normalization	2026-02-06 14:46:16 -05:00
Luis Pater	1c6cb2bec3	Merge pull request #1239 from ThanhNguyxn/fix/gitstore-gc-after-squash ... fix(store): run GC after squashing history to prevent loose object accumulation	2026-02-07 02:51:27 +08:00
Luis Pater	80b5e79e75	fix(translator): normalize and restrict stop_reason/finish_reason usage ... - Standardized the handling of `stop_reason` and `finish_reason` across Codex and Gemini responses. - Restricted pass-through of specific reasons (`max_tokens`, `stop`) for consistency. - Enhanced fallback logic for undefined reasons.	2026-02-07 02:07:51 +08:00
Luis Pater	1187aa8222	feat(translator): capture cached token count in usage metadata and handle prompt caching ... - Added support to extract and include `cachedContentTokenCount` in `usage.prompt_tokens_details`. - Logged warnings for failures to set cached token count for better debugging.	2026-02-06 21:28:40 +08:00
Luis Pater	dc9b4dd017	Merge branch 'kimi-provider-support-v2' into dev	2026-02-06 20:51:48 +08:00
Luis Pater	68cb81a258	feat: add Kimi authentication support and streamline device ID handling ... - 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.	2026-02-06 20:43:30 +08:00
hkfires	c874f19f2a	refactor(config): disable automatic migration during server startup	2026-02-06 09:57:47 +08:00
test	f5f26f0cbe	Add Kimi (Moonshot AI) provider support ... - 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>	2026-02-05 19:24:46 -05:00
Luis Pater	4b00312fef	Merge pull request #1435 from tianyicui/fix/haiku-4-5-thinking-support ... fix: Enable extended thinking support for Claude Haiku 4.5	2026-02-06 05:44:14 +08:00
Luis Pater	c5fd3db01e	Merge pull request #1446 from qyhfrank/fix-claude-opus-4-6-model-metadata ... fix(registry): correct Claude Opus 4.6 model metadata	2026-02-06 05:43:32 +08:00