Commit Graph
1511 Commits
Author SHA1 Message Date
Finessse 35e139bb3d models: always include context_length and max_completion_tokens in /v1/models 2025-12-18 15:56:33 +07:00
Finessse 358f7a6439 codex: synth SSE for huge/compaction responses with MAX_TOKENS retry 2025-12-18 14:18:28 +07:00
Finessse 9812ab3fb4 docs: update ProxyPilot and gemini-3 provider preference 2025-12-18 14:18:05 +07:00
Finessse 99eb979353 models: add gemini-3-flash and gemini-3-pro-low (antigravity) 2025-12-18 14:17:57 +07:00
Finessse 24edfc63ff proxypilot: tray OAuth helpers and in-app WebView2 dashboard 2025-12-18 14:17:44 +07:00
Finessse 70dd0cd283 api: add ProxyPilot local dashboard and diagnostics endpoints 2025-12-18 14:17:36 +07:00
Finessse c3b058a7af desktopctl: persist ProxyPilot state and management key 2025-12-18 14:17:27 +07:00
hkfires 393e38f2c0 chore: ignore gemini metadata files 2025-12-18 13:18:15 +08:00
Luis Pater 0f646800f6 Merge branch 'router-for-me:main' into main v6.6.26-0 2025-12-18 08:36:59 +08:00
Luis Pater ca993238f3 Merge pull request #42 from Ravens2121/master
feat(kiro): 新增授权码登录流程,优化邮箱获取与官方 Thinking 模式解析 预支持
2025-12-18 08:36:27 +08:00
Luis Pater d1220de02d chore(docs): remove legacy documentation and unused PR workflow file v6.6.26 2025-12-18 08:21:58 +08:00
Ravens2121andAmp cf9a246d53 feat(kiro): 新增 AWS Builder ID 授权码流程认证及用户邮箱获取增强
Amp-Thread-ID: https://ampcode.com/threads/T-019b2ecc-fb2d-713f-b30d-1196c7dce3e2
Co-authored-by: Amp <amp@ampcode.com>
2025-12-18 08:16:52 +08:00
Luis Pater 13eb5268de Merge pull request #582 from ben-vargas/fix-gemini-3-thinking-level
feat: use thinkingLevel for Gemini 3 models per Google documentation
2025-12-18 07:19:37 +08:00
Ben Vargas 88798816f2 fix: require dot in gemini25Pattern regex for precise matching 2025-12-17 16:09:50 -07:00
Ben Vargas 598f0af19b fix: apply thinkingLevel from model suffix metadata for Gemini 3
The 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 functions
2025-12-17 16:08:38 -07:00
Ben Vargas a33f5d31fc feat: use thinkingLevel for Gemini 3 models per Google documentation
Per Google's official documentation, Gemini 3 models should use
thinkingLevel (string) instead of thinkingBudget (number) for
optimal performance.

From Google's Gemini Thinking docs:
> Use the thinkingLevel parameter with Gemini 3 models. While
> thinkingBudget is accepted for backwards compatibility, using
> it with Gemini 3 Pro may result in suboptimal performance.

Changes:
- Add model family detection functions (IsGemini3Model, IsGemini25Model,
  IsGemini3ProModel, IsGemini3FlashModel)
- Add ApplyGeminiThinkingLevel and ApplyGeminiCLIThinkingLevel functions
  for applying thinkingLevel config
- Add ValidateGemini3ThinkingLevel for model-specific level validation
- Add ThinkingBudgetToGemini3Level for backward compatibility conversion
- Update NormalizeGeminiThinkingBudget to convert budget to level for
  Gemini 3 models
- Update ApplyDefaultThinkingIfNeeded to not set a default level for
  Gemini 3 (lets API use its dynamic default "high")
- Update ConvertThinkingLevelToBudget to preserve thinkingLevel for
  Gemini 3 models
- Add Levels field to all Gemini 3 model definitions:
  - Gemini 3 Pro: ["low", "high"]
  - Gemini 3 Flash: ["minimal", "low", "medium", "high"]

Backward compatibility:
- Gemini 2.5 models continue to use thinkingBudget as before
- If thinkingBudget is provided for Gemini 3, it's converted to the
  appropriate thinkingLevel
- Existing configurations continue to work
2025-12-17 15:28:20 -07:00
Ravens2121 54acd69e9d Merge branch 'router-for-me:main' into master 2025-12-18 04:39:17 +08:00
Ravens2121 d687ee2777 feat(kiro): implement official reasoningContentEvent and improve metadat 2025-12-18 04:38:22 +08:00
Luis Pater 54c2fefbad Merge branch 'router-for-me:main' into main 2025-12-18 03:29:00 +08:00
Luis Pater 506699fba1 ci(workflows): update pr-test-build workflow 2025-12-18 03:28:23 +08:00
Luis Pater f7b17ee6ec Merge pull request #36 from rezhajulio/feat/gpt-5.2
Add GPT-5.2 model support for GitHub Copilot
v6.6.25-1
2025-12-18 03:16:25 +08:00
Luis Pater 408614c74c Merge branch 'router-for-me:main' into main v6.6.25-0 2025-12-18 03:13:48 +08:00
Luis Pater 68a27772b3 feat(antigravity): enable token counting via API with resilient routing
Introduces the capability to count tokens for Antigravity-backed requests. This implementation leverages the `countTokens` endpoint of the Antigravity API, replacing the prior unsupported stub.

Key aspects of this update include:

- **API Integration**: Direct integration with the Antigravity `countTokens` API, including necessary request payload translation and authentication.
- **Resilient Infrastructure**: A fallback mechanism has been established, allowing the system to attempt connections across multiple Antigravity base URLs to ensure request success even in the event of temporary service interruptions.
- **Model Aliasing**: Added mappings for `gemini-3-flash` and `gemini-3-flash-preview` to ensure compatibility with the latest model variants.
- **Robust Error Handling**: Comprehensive error handling and logging are in place to manage failures during API interactions.
v6.6.25
2025-12-18 03:12:46 +08:00
Ben Vargas de87fb622b docs: add redirect info and disable Pull app auto-sync 2025-12-17 12:06:39 -07:00
Finessse b540106287 docs: rebrand to ProxyPilot with fork attribution 2025-12-18 01:58:36 +07:00
Finessse 3336d15282 management: apply ProxyPilot branding at serve-time 2025-12-18 01:58:28 +07:00
Finessse 6c39925728 proxypilot: rebrand tray and engine labels 2025-12-18 01:58:20 +07:00
Finessse dc17f8f600 proxypilotui: force Edge lang to en-US 2025-12-18 01:47:35 +07:00
Finessse 2151171175 packaging: inno installer + zip, remove legacy ps1 startup 2025-12-18 01:43:26 +07:00
Finessse e2fe9f2403 auth: primary email override, trace headers, and cooldown reset 2025-12-18 01:43:07 +07:00
Finessse a2e1849032 proxypilot: tray UX, desktop UI window, and updater 2025-12-18 01:42:56 +07:00
Finessse 8a570a471b desktopctl: persist auto-start proxy state 2025-12-18 01:42:43 +07:00
Luis Pater 0155a01bb1 Merge pull request #40 from router-for-me/plus
v6.6.24
v6.6.24-0
2025-12-18 01:04:17 +08:00
Luis Pater cfeee5d511 Merge branch 'main' into plus 2025-12-18 01:04:10 +08:00
Luis Pater f27672f6cf feat(antigravity): add Gemini 3 Flash Preview model definition with enhanced capabilities v6.6.24 2025-12-18 01:02:19 +08:00
Luis Pater 28420c14e4 Merge pull request #580 from router-for-me/chore
chore: ignore agent and bmad artifacts
2025-12-18 00:46:25 +08:00
Luis Pater 10e0ea1309 Merge main into pr-39 v6.6.23-0 2025-12-18 00:36:51 +08:00
Luis Pater 0bd221ff41 refactor(antigravity): optimize response handling in Claude model with JSON manipulation v6.6.23 2025-12-17 23:57:41 +08:00
Luis Pater 5fda6f8ef3 feat(antigravity): implement non-streaming execution for Claude model requests 2025-12-17 23:17:11 +08:00
hkfires 9b956f6338 chore: ignore agent and bmad artifacts 2025-12-17 23:15:15 +08:00
Finessse 7bef161e7e packaging: add proxypilotpack (no-ps1 builder) 2025-12-17 21:49:06 +07:00
Finessse 4cc8d086ff docs: add ProxyPilot overview and update memory docs 2025-12-17 21:43:31 +07:00
Finessse c5d64d807a memory: normalize escaped todo/pinned text 2025-12-17 21:31:40 +07:00
Luis Pater 09923f654c feat(antigravity): add streaming support for Claude model requests 2025-12-17 22:16:57 +08:00
Finessse 2f5bb3a501 docs: note caching-friendly packed state 2025-12-17 21:16:06 +07:00
Finessse 34082f2eef middleware: pack state into last user message 2025-12-17 21:15:58 +07:00
Finessse 1d000affec memory: add pinned+summary readers 2025-12-17 21:15:49 +07:00
Finessse 03da5113c3 docs: document persistent todo 2025-12-17 21:01:22 +07:00
Finessse 0a74cf7efb middleware: inject persistent todo 2025-12-17 21:01:14 +07:00
Finessse e1b9fa0a36 memory: add session todo file 2025-12-17 21:01:05 +07:00