airkjw/CLIProxyAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 670685139a fix(api): update route patterns to support wildcards for Gemini actions Luis Pater 2025-12-17 01:17:02 +08:00
  • 52b6306388 feat(config): add support for model prefixes and prefix normalization Luis Pater 2025-12-17 01:07:26 +08:00
  • 521ec6f1b8 fix(watcher): simplify vertex apikey idKind to exclude base suffix hkfires 2025-12-16 22:55:38 +08:00
  • b0c5d9640a refactor(diff): improve security and stability of config change detection hkfires 2025-12-16 22:39:19 +08:00
  • ef8e94e992 refactor(watcher): extract config diff helpers hkfires 2025-12-16 21:45:33 +08:00
  • 9df96a4bb4 test(thinking): add effort to budget coverage hkfires 2025-12-16 18:29:34 +08:00
  • 28a428ae2f fix(thinking): align budget effort mapping across translators hkfires 2025-12-16 18:07:20 +08:00
  • b326ec3641 feat(iflow): add thinking support for iFlow models hkfires 2025-12-16 14:22:05 +08:00
  • fcecbc7d46 Merge pull request #562 from thomasvan/fix/openai-claude-message-start-order Luis Pater 2025-12-16 16:54:58 +08:00
  • f4007f53ba fix(translator): emit message_start on first chunk regardless of role field Thong Van 2025-12-16 13:01:09 +07:00
  • 5a812a1e93 feat(remote-management): add support for custom GitHub repository for panel updates v6.6.18 Luis Pater 2025-12-16 13:09:26 +08:00
  • 5e624cc7b1 Merge pull request #558 from router-for-me/worker Chén Mù 2025-12-16 09:24:32 +08:00
  • 3af24597ee docs: remove Amp CLI integration guides and update references v6.6.17 Luis Pater 2025-12-15 23:50:56 +08:00
  • 0b834fcb54 fix(translator): preserve built-in tools across openai<->responses Muzhen Gaming 2025-12-15 21:15:56 +08:00
  • e0be6c5786 chore: ignore .bmad directory hkfires 2025-12-15 19:07:25 +08:00
  • 88b101ebf5 Merge pull request #549 from router-for-me/log Luis Pater 2025-12-15 20:43:12 +08:00
  • d9a65745df fix(translator): handle empty item type and string content in OpenAI response parser v6.6.16 Luis Pater 2025-12-15 20:35:52 +08:00
  • 97ab623d42 fix(api): prevent double logging for streaming responses hkfires 2025-12-15 18:00:32 +08:00
  • 14aa6cc7e8 fix(api): ensure all response writes are captured for logging hkfires 2025-12-15 17:45:16 +08:00
  • 3bc489254b fix(api): prevent double logging for error responses hkfires 2025-12-15 16:36:01 +08:00
  • 4c07ea41c3 feat(api): return structured JSON error responses hkfires 2025-12-15 16:18:44 +08:00
  • f6720f8dfa Merge pull request #547 from router-for-me/amp v6.6.15 Luis Pater 2025-12-15 16:14:49 +08:00
  • e19ab3a066 Merge pull request #543 from router-for-me/log Chén Mù 2025-12-15 15:59:16 +08:00
  • 8f1dd69e72 feat(amp): require API key authentication for management routes hkfires 2025-12-15 13:24:53 +08:00
  • f26da24a2f feat(auth): add proxy information to debug logs hkfires 2025-12-15 13:14:55 +08:00
  • 8e4fbcaa7d Merge pull request #533 from router-for-me/think v6.6.14 Luis Pater 2025-12-15 10:34:41 +08:00
  • 09c339953d fix(openai): forward reasoning.effort value hkfires 2025-12-14 20:30:26 +08:00
  • 367a05bdf6 refactor(thinking): export thinking helpers hkfires 2025-12-14 20:12:54 +08:00
  • d20b71deb9 fix(thinking): normalize effort mapping hkfires 2025-12-14 20:11:30 +08:00
  • 712ce9f781 fix(thinking): drop unsupported none effort hkfires 2025-12-14 18:45:03 +08:00
  • a4a3274a55 test(thinking): expand conversion edge case coverage hkfires 2025-12-14 18:32:20 +08:00
  • 716aa71f6e fix(thinking): centralize reasoning_effort mapping hkfires 2025-12-14 14:45:01 +08:00
  • e8976f9898 fix(thinking): map budgets to effort for level models hkfires 2025-12-14 13:18:35 +08:00
  • 8496cc2444 test(thinking): cover openai-compat reasoning passthrough hkfires 2025-12-14 13:00:34 +08:00
  • 5ef2d59e05 fix(thinking): gate reasoning effort by model support hkfires 2025-12-13 08:18:06 +08:00
  • 07bb89ae80 Merge pull request #542 from router-for-me/aistudio v6.6.13 Chén Mù 2025-12-15 09:13:25 +08:00
  • 27a5ad8ec2 Fixed: #534 hkfires 2025-12-15 09:00:14 +08:00
  • 707b07c5f5 Merge pull request #537 from sukakcoding/fix/function-response-fallback Luis Pater 2025-12-15 03:31:09 +08:00
  • 4a764afd76 refactor: extract parseFunctionResponse helper to reduce duplication sukakcoding 2025-12-15 01:05:36 +08:00
  • ecf49d574b fix: handle malformed json in function response parsing sukakcoding 2025-12-15 00:59:46 +08:00
  • 5a75ef8ffd Merge pull request #536 from AoaoMH/feature/auth-model-check v6.6.12 Luis Pater 2025-12-15 00:29:33 +08:00
  • 07279f8746 feat: using Client Model Infos; Test 2025-12-15 00:13:05 +08:00
  • 71f788b13a fix(registry): remove unused ThinkingSupport from DeepSeek-R1 model Luis Pater 2025-12-14 21:30:17 +08:00
  • 59c62dc580 fix(registry): correct DeepSeek-V3.2 experimental model ID Luis Pater 2025-12-14 21:27:43 +08:00
  • d5310a3300 Merge pull request #531 from AoaoMH/feature/auth-model-check v6.6.11 Luis Pater 2025-12-14 16:46:43 +08:00
  • f0a3eb574e fix(registry): update DeepSeek model definitions with new IDs and descriptions v6.6.10 Luis Pater 2025-12-14 16:17:11 +08:00
  • bb15855443 feat: add API endpoint to query models for auth credentials Test 2025-12-14 15:16:26 +08:00
  • 14ce6aebd1 Merge pull request #449 from sususu98/fix/gemini-cli-429-retry-delay-parsing Luis Pater 2025-12-14 14:04:14 +08:00
  • 2fe83723f2 Merge pull request #515 from teeverc/fix/response-rewriter-streaming-flush Luis Pater 2025-12-14 13:26:05 +08:00
  • cd8c86c6fb refactor: only flush stream response on successful write teeverc 2025-12-13 13:31:34 -08:00
  • 52d5fd1a67 fix: streaming for amp cli teeverc 2025-12-13 13:17:53 -08:00
  • b6ad243e9e Merge pull request #498 from teeverc/fix/claude-streaming-flush v6.6.9 Luis Pater 2025-12-13 23:58:34 +08:00
  • 660aabc437 fix(executor): add allowCompat support for reasoning effort normalization Luis Pater 2025-12-13 04:06:02 +08:00
  • 566120e8d5 Merge pull request #505 from router-for-me/think Luis Pater 2025-12-12 22:17:11 +08:00
  • f3f0f1717d Merge branch 'dev' into think Luis Pater 2025-12-12 22:16:44 +08:00
  • 7621ec609e Merge pull request #501 from huynguyen03dev/fix/openai-compat-model-alias-resolution v6.6.8 Luis Pater 2025-12-12 21:58:15 +08:00
  • 9f511f0024 fix(executor): improve model compatibility handling for OpenAI-compatibility Luis Pater 2025-12-12 21:57:25 +08:00
  • 374faa2640 fix(thinking): map budgets to effort levels hkfires 2025-12-12 21:33:20 +08:00
  • 1c52a89535 Merge pull request #502 from router-for-me/iflow v6.6.7 Luis Pater 2025-12-12 20:03:37 +08:00
  • e7cedbee6e fix(auth): prevent duplicate iflow BXAuth tokens hkfires 2025-12-12 19:57:19 +08:00
  • b8194e717c Merge pull request #500 from router-for-me/think v6.6.6 Luis Pater 2025-12-12 18:35:26 +08:00
  • 15c3cc3a50 fix(openai-compat): prevent model alias from being overwritten by ResolveOriginalModel huynguyen03.dev 2025-12-12 17:20:24 +07:00
  • d131435e25 fix(codex): raise default reasoning effort to medium hkfires 2025-12-12 18:18:48 +08:00
  • 6e43669498 Fixed: #440 Luis Pater 2025-12-12 16:50:56 +08:00
  • 5ab3032335 Update sdk/api/handlers/claude/code_handlers.go teeverc 2025-12-12 00:26:01 -08:00
  • 1215c635a0 fix: flush Claude SSE chunks immediately to match OpenAI behavior teeverc 2025-12-12 00:14:19 -08:00
  • fc054db51a Merge pull request #494 from ben-vargas/fix-gpt-reasoning-none v6.6.5 Luis Pater 2025-12-12 08:53:19 +08:00
  • 6e2306a5f2 refactor(handlers): improve request logging and payload handling Luis Pater 2025-12-12 08:52:52 +08:00
  • b09e2115d1 fix(models): add "none" reasoning effort level to gpt-5.2 Ben Vargas 2025-12-11 15:26:23 -07:00
  • a68c97a40f Fixed: #492 v6.6.4 Luis Pater 2025-12-12 04:08:11 +08:00
  • cd2da152d4 feat(models): add GPT 5.2 model definition and prompts v6.6.3 Luis Pater 2025-12-12 03:02:27 +08:00
  • bb6312b4fc Merge pull request #488 from router-for-me/gemini v6.6.2 Luis Pater 2025-12-11 22:14:17 +08:00
  • 3c315551b0 refactor(executor): relocate gemini token counters hkfires 2025-12-11 10:27:30 +08:00
  • 27c9c5c4da refactor(executor): clarify executor comments and oauth names hkfires 2025-12-10 20:21:11 +08:00
  • fc9f6c974a refactor(executor): clarify providers and streams hkfires 2025-12-10 18:10:31 +08:00
  • a74ee3f319 Merge pull request #481 from sususu98/fix/increase-buffer-size v6.6.1 Luis Pater 2025-12-11 21:20:54 +08:00
  • 564bcbaa54 Merge pull request #487 from router-for-me/amp Luis Pater 2025-12-11 21:18:19 +08:00
  • 88bdd25f06 fix(amp): set status on claude stream errors hkfires 2025-12-11 20:12:06 +08:00
  • e79f65fd8e refactor(thinking): use parentheses for metadata suffix hkfires 2025-12-11 18:39:07 +08:00
  • 2760989401 Merge pull request #485 from router-for-me/think Luis Pater 2025-12-11 18:27:00 +08:00
  • facfe7c518 refactor(thinking): use bracket tags for thinking meta hkfires 2025-12-11 18:17:28 +08:00
  • 6285459c08 fix(runtime): unify claude thinking config resolution hkfires 2025-12-11 17:20:44 +08:00
  • 21bbceca0c docs(runtime): document reasoning effort precedence hkfires 2025-12-11 16:35:36 +08:00
  • f6300c72b7 fix(runtime): validate thinking config in iflow and qwen hkfires 2025-12-11 16:21:50 +08:00
  • 007572b58e fix(util): do not strip thinking suffix on registered models hkfires 2025-12-11 15:52:14 +08:00
  • 3a81ab22fd fix(runtime): unify reasoning effort metadata overrides hkfires 2025-12-11 14:35:05 +08:00
  • 519da2e042 fix(runtime): validate reasoning effort levels hkfires 2025-12-11 12:36:54 +08:00
  • 169f4295d0 fix(util): align reasoning effort handling with registry hkfires 2025-12-11 12:20:12 +08:00
  • d06d0eab2f fix(util): centralize reasoning effort normalization hkfires 2025-12-11 12:14:51 +08:00
  • 3ffd120ae9 feat(runtime): add thinking config normalization hkfires 2025-12-11 11:51:33 +08:00
  • a03d514095 feat(registry): add thinking metadata for models hkfires 2025-12-11 11:28:44 +08:00
  • 07d21463ca fix(gemini-cli): enhance 429 retry delay parsing sususu 2025-12-08 10:10:22 +08:00
  • 1da03bfe15 Merge pull request #479 from router-for-me/claude Luis Pater 2025-12-11 08:18:59 +08:00
  • 423ce97665 feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic v6.6.0 Luis Pater 2025-12-11 01:16:56 +08:00
  • e717939edb Fixed: #478 v6.5.65 Luis Pater 2025-12-10 23:55:53 +08:00
  • 76c563d161 fix(executor): increase buffer size for stream scanners to 50MB across multiple executors sususu 2025-12-10 23:20:04 +08:00
  • a89514951f fix(claude): prevent final events when no content streamed hkfires 2025-12-10 22:19:55 +08:00
  • 94d61c7b2b fix(logging): update response aggregation logic to include all attempts v6.5.64 Luis Pater 2025-12-10 16:53:48 +08:00
  • 1249b07eb8 feat(responses): add unique identifiers for responses, function calls, and tool uses v6.5.63 Luis Pater 2025-12-10 16:02:54 +08:00
  • 6b37f33d31 feat(antigravity): add unique identifier for tool use blocks in response v6.5.62 Luis Pater 2025-12-10 15:27:57 +08:00