1664 Commits

This Branch

This Branch

All Branches

• feat(tui): add manager tui
  lhpqaq · 2026-02-15 14:52:40 +08:00
  54ad7c1b6b
• chore(runtime, registry): update Codex client version and GPT-5.3 model creation date
  Luis Pater · 2026-02-13 12:47:48 +08:00
  v6.8.15 ae1e8a5191
• Merge pull request #1574 from fbettag/feat/gpt-5.3-codex-spark

  feat(registry): add gpt-5.3-codex-spark model definition

  Luis Pater · 2026-02-13 12:46:08 +08:00
  b3ccc55f09
• Update internal/registry/model_definitions_static_data.go

  Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

  Franz Bettag · 2026-02-12 23:37:27 +01:00
  1ce56d7413
• feat(registry): add gpt-5.3-codex-spark model definition
  Franz Bettag · 2026-02-12 23:24:08 +01:00
  41a78be3a2
• docs(readme): add CLIProxyAPI Dashboard to project list
  Luis Pater · 2026-02-13 00:40:39 +08:00
  1ff5de9a31
• Merge pull request #1568 from itsmylife44/add-cliproxyapi-dashboard

  Add CLIProxyAPI Dashboard to 'Who is with us?' section

  Luis Pater · 2026-02-13 00:37:41 +08:00
  46a6853046
• Add CLIProxyAPI Dashboard to 'Who is with us?' section
  xSpaM · 2026-02-12 17:15:46 +01:00
  4b2d40bd67
• feat(registry): add new model definition for MiniMax-M2.5
  Luis Pater · 2026-02-12 22:43:01 +08:00
  v6.8.14 575881cb59
• feat(registry): add glm-5 model to iflow
  hkfires · 2026-02-12 11:13:28 +08:00
  v6.8.13 f361b2716d
• Merge pull request #1542 from APE-147/fix/gemini-antigravity-schema-sanitization

  fix(schema): sanitize Gemini-incompatible tool metadata fields

  Luis Pater · 2026-02-11 21:34:04 +08:00
  58e09f8e5f
• Merge pull request #1523 from xxddff/feature/removeUserField

  fix(codex): remove unsupported 'user' field from /v1/responses payload

  Luis Pater · 2026-02-11 20:38:16 +08:00
  v6.8.12 a146c6c0aa
• 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.

  Luis Pater · 2026-02-11 20:35:13 +08:00
  4c133d3ea9
• refactor: reduce code duplication in extractExcludedModelsFromMetadata
  RGBadmin · 2026-02-11 15:57:16 +08:00
  dc279de443
• refactor: simplify per-account excluded_models merge in routing
  RGBadmin · 2026-02-11 15:57:15 +08:00
  bf1634bda0
• 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>

  Nathan · 2026-02-11 18:29:17 +11:00
  166d2d24d9
• feat: read per-account excluded_models at routing time
  RGBadmin · 2026-02-11 15:21:19 +08:00
  4cbcc835d1
• feat: merge per-account excluded_models with global config
  RGBadmin · 2026-02-11 15:21:15 +08:00
  b93026d83a
• feat: add per-account excluded_models and priority parsing
  RGBadmin · 2026-02-11 15:21:12 +08:00
  5ed2133ff9
• 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`.

  Luis Pater · 2026-02-11 15:04:01 +08:00
  v6.8.11 1510bfcb6f
• Merge pull request #1519 from router-for-me/thinking

  feat(translator): support Claude thinking type adaptive

  Chén Mù · 2026-02-10 18:31:56 +08:00
  v6.8.10 c6bd91b86b
• fix(registry): correct max completion tokens for opus 4.6 thinking
  hkfires · 2026-02-10 18:05:40 +08:00
  349ddcaa89
• 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>

  xxddff · 2026-02-10 18:24:58 +09:00
  bb9fe52f1e
• 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>

  xxddff · 2026-02-10 18:24:26 +09:00
  afe4c1bfb7
• Implement test for user field deletion

  Add test to verify deletion of user field in response

  xxddff · 2026-02-10 17:38:49 +09:00
  865af9f19e
• Delete 'user' field from raw JSON

  Remove the 'user' field from the raw JSON as requested.

  xxddff · 2026-02-10 17:35:54 +09:00
  2b97cb98b5
• feat(translator): support Claude thinking type adaptive
  hkfires · 2026-02-10 16:20:32 +08:00
  938a799263
• refactor(sdk): simplify provider lifecycle and registration logic
  Luis Pater · 2026-02-10 15:39:26 +08:00
  v6.8.9 0040d78496
• docs(config): reorder antigravity model alias example
  hkfires · 2026-02-10 10:13:54 +08:00
  896de027cc
• docs(config): simplify oauth model alias example
  hkfires · 2026-02-10 10:12:28 +08:00
  fc329ebf37
• Merge pull request #1506 from masrurimz/fix-sse-model-mapping

  fix(amp): rewrite response.model in Responses API SSE events

  Luis Pater · 2026-02-10 02:08:11 +08:00
  v6.8.8 eaab1d6824
• ci: retrigger workflows

  Amp-Thread-ID: https://ampcode.com/threads/T-019c264f-1cb9-7420-a68b-876030db6716

  Muhammad Zahid Masruri · 2026-02-10 00:09:11 +07:00
  0cfe310df6
• 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

  Muhammad Zahid Masruri · 2026-02-09 23:52:59 +07:00
  918b6955e4
• Merge pull request #1502 from router-for-me/iflow

  feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests

  Luis Pater · 2026-02-09 19:56:12 +08:00
  v6.8.7 5a3eb08739
• Merge pull request #1492 from router-for-me/management

  fix(management): ensure management.html is available synchronously and improve asset sync handling

  Luis Pater · 2026-02-09 19:55:21 +08:00
  0dff329162
• feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests
  hkfires · 2026-02-09 19:29:42 +08:00
  49c1740b47
• fix(management): ensure management.html is available synchronously and improve asset sync handling
  hkfires · 2026-02-09 08:32:58 +08:00
  3fbee51e9f
• 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.

  Luis Pater · 2026-02-09 02:05:38 +08:00
  v6.8.6 63643c44a1
• Merge pull request #1479 from router-for-me/management

  refactor(management): streamline control panel management and implement sync throttling

  Luis Pater · 2026-02-08 20:37:29 +08:00
  v6.8.5 3b34521ad9
• fix(config): prune default descendants when merging new yaml nodes
  hkfires · 2026-02-08 19:05:52 +08:00
  7197fb350b
• fix(config): avoid writing known defaults during merge
  hkfires · 2026-02-08 18:47:44 +08:00
  6e349bfcc7
• refactor(management): streamline control panel management and implement sync throttling
  hkfires · 2026-02-08 10:42:49 +08:00
  234056072d
• Merge pull request #1467 from dusty-du/fix/kimi-toolcall-reasoning-content

  Fix Kimi tool-call payload normalization for reasoning_content

  Luis Pater · 2026-02-07 09:35:04 +08:00
  v6.8.4 7e9d0db6aa
• chore(docs): remove Cubence sponsorship from README files and delete related asset
  Luis Pater · 2026-02-07 08:55:14 +08:00
  2f1874ede5
• fix(kimi): reduce redundant payload cloning and simplify translation calls
  Luis Pater · 2026-02-07 08:51:48 +08:00
  v6.8.3 78ef04fcf1
• fix(translator): correct gemini-cli log prefix
  hkfires · 2026-02-07 08:40:09 +08:00
  b7e4f00c5f
• 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`.

  Luis Pater · 2026-02-07 06:42:08 +08:00
  v6.8.2 f7d0019df7
• Fix Kimi tool-call reasoning_content normalization
  test · 2026-02-06 14:46:16 -05:00
  52364af5bf
• Merge pull request #1390 from sususu98/fix/400-invalid-request-no-retry

  fix(auth): 400 invalid_request_error 立即返回不再重试

  Luis Pater · 2026-02-07 03:14:25 +08:00
  f410dd0440
• Merge pull request #1386 from shenshuoyaoyouguang/sync-auth-changes

  fix(auth): normalize model key for thinking suffix in selectors

  Luis Pater · 2026-02-07 03:12:01 +08:00
  eb5582c17c