Commit Graph

169 Commits

Author SHA1 Message Date
decolua
bd0cebcfff Merge pull request #80 from Blade096/fix/free-provider-not-found
fix(dashboard): resolve 'Provider not found' for free providers
2026-02-08 16:51:54 +07:00
decolua
e7dfdc9274 Merge pull request #77 from Blade096/fix/openai_to_claude_missingthinking
feat(translator): add thinking parameter support in OpenAI → Claude
2026-02-08 16:47:24 +07:00
Diego Souza
3d439839d9 feat(cloud): harden sync/auth flow, SSE fallback, and update changelog
Co-authored-by: Cursor <cursoragent@cursor.com>
v0.2.71
2026-02-08 16:45:31 +07:00
decolua
2e854bd4c9 feat(antigravity): integrate Antigravity tool with MITM support and update CLI tools 2026-02-08 16:28:13 +07:00
Blade096
45a4d3ba68 fix(dashboard): resolve 'Provider not found' for free providers 2026-02-08 01:19:50 +08:00
Blade096
54e01d617d feat(translator): add thinking parameter support in OpenAI → Claude
Preserve thinking configuration when converting OpenAI requests to Claude format.

- Handle thinking.type with 'enabled' as default

- Preserve thinking.budget_tokens when present

- Preserve thinking.max_tokens when present

This enables proper thinking mode support for o1-series models

when routed through 9Router to Claude endpoints.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
(cherry picked from commit 65d80e9269cc6789cb1522b276e8b8399fddbcab)
2026-02-07 21:45:50 +08:00
decolua
18712b24cf Delete debug log 2026-02-07 15:20:16 +07:00
decolua
20a86d6561 Merge pull request #67 from diegosouzapw/feature/docker-runtime-readme-updates
feat: add Docker runtime setup and README docs updates
v0.2.70
2026-02-07 11:24:10 +07:00
decolua
bdbe8162e7 feat(provider): add free providers and enhance error handling 2026-02-07 11:17:06 +07:00
decolua
53a5f43993 Merge pull request #68 from diegosouzapw/fix/logout-not-working
fix(auth): prevent auto-login after logout
2026-02-07 09:35:53 +07:00
Diego Souza
01c9410530 fix(login): avoid infinite loading on settings fetch failure 2026-02-06 23:41:29 +00:00
Diego Souza
49df3dce90 fix(auth): prevent auto-login after logout 2026-02-06 23:14:10 +00:00
Diego Souza
5e4a15bb0c feat(docker): add Docker setup, environment examples, and architecture docs 2026-02-06 22:45:03 +00:00
Diego Souza
6c41573203 feat(cli-tools): update default local endpoint port to 20128 2026-02-06 22:44:58 +00:00
decolua
ff2ba87161 Merge pull request #65 from ramhaidar/fix/provider-connection-ux
fix(api-key): auto-validate on save to improve UX
2026-02-06 21:21:03 +07:00
decolua
2e3eccf687 Update Readme v0.2.67 2026-02-06 21:05:52 +07:00
ram/haidar
e6ef8528fc fix(db): improve error handling and null checks
- Added null checks for undefined/null values in database operations
- Improved error handling for corrupt JSON recovery
- Added schema migration support for missing keys
- Target: database stability and data integrity
2026-02-06 20:54:42 +07:00
ram/haidar
b275dfdc9c feat(providers): auto-validate API keys on save
- AddApiKeyModal and EditConnectionModal now automatically validate API keys during save
- Sets testStatus to 'active' when validation succeeds, removing need for manual Check button
- Added saving state to prevent duplicate submissions during validation
- Target: provider connection management UX
2026-02-06 20:54:19 +07:00
decolua
a2122e3e48 feat(cli-tools): update CLI tools and add new models
- Add Droid and OpenClaw tool cards to CLI tools
- Enhance ClaudeToolCard and CodexToolCard to display current base URLs
2026-02-06 20:53:20 +07:00
decolua
f68ef4c933 Merge pull request #64 from Blade096/feature/iFlowAI-Kimi2.5-Support
feat(iflow): add kimi-k2.5 model support
2026-02-06 20:52:07 +07:00
Blade096
9e357a7ee6 feat(iflow): add kimi-k2.5 model support 2026-02-06 21:26:31 +08:00
decolua
01343c6325 Update ReadMe 2026-02-06 15:18:20 +07:00
Blade096
7c609d7a3e feat(providers): add Minimax Coding (China) provider
- Add minimax-cn provider with China endpoint (api.minimaxi.com)
- Add provider icon and configuration
- Add validation and test support
- Add API configuration in open-sse

Co-authored-by: Blade096 <46746496+Blade096@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-06 15:10:57 +07:00
Hellodebasishsahu
8c6e3b8b62 fix(codex): use user-agent detection for Droid CLI compatibility
The previous merge used sourceFormat check which broke Cursor when it
sends openai-responses format requests. Now uses user-agent detection:
- Droid CLI (user-agent contains 'droid' or 'codex-cli') → passthrough
- Other clients (Cursor, etc.) → translate to Chat Completions format

This fixes the API translation for both clients.

Co-authored-by: Hellodebasishsahu <itsyourboydevil@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-06 15:02:56 +07:00
decolua
fafa77316b Fix version 2026-02-06 11:38:52 +07:00
decolua
e8aa3e21fe - Added new model "Claude Opus 4.6" to the provider models. 2026-02-06 11:23:08 +07:00
decolua
39c555ca7e docs: clarify Droid CLI compatibility comment in Responses API translator
Co-authored-by: Emanuel Covelli <emanuel.covelli@netserv.it>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-06 09:56:57 +07:00
Hellodebasishsahu
127475df84 feat(codex): add GPT 5.3, fix API translation, add thinking levels
- Add GPT 5.3 Codex model with thinking level variants (none/low/medium/high/xhigh)
- Extract thinking level from model name suffix (e.g., gpt-5.3-codex-high)
- Fix Codex translation: preserve openai-responses format for Droid CLI
- Add effort level logging in request logs

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-06 09:46:11 +07:00
decolua
a7a52be2d4 feat(ui): add model support for custom providers and improve UX
- Support custom provider models in combos and model selection
- Display custom provider names instead of technical IDs
- Make model fields readonly (selected via modal)
- Only show connected providers (remove fallback)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-06 09:39:10 +07:00
decolua
c6127412a6 Fix Antigravity 2026-02-06 09:18:01 +07:00
decolua
95fd9508e8 fix: GitHub Copilot model 2026-02-05 22:26:14 +07:00
decolua
3c65e0c5f2 feat: Improve Antigravity quota monitoring and fix Droid CLI compatibility 2026-02-05 22:15:26 +07:00
decolua
32aefe5a76 feat(executors): Improved UI components for displaying provider limits and usage statistics in the dashboard. 2026-02-05 18:38:50 +07:00
decolua
249fc28c49 feat(auth): Enhance authentication flow and settings management 2026-02-05 11:26:11 +07:00
decolua
0a026c7af6 feat(cursor): Add cursor Provider 2026-02-05 11:06:20 +07:00
decolua
abaeb22863 Merge branch 'pr-50' 2026-02-05 11:02:50 +07:00
decolua
0a394d0d9a fix(auth): allow HTTP for local network 2026-02-04 12:39:26 +07:00
triadmoko
137f315bec feat(cursor): Integrate Cursor IDE support with OAuth import token flow
- Add CursorExecutor for handling requests to the Cursor API using protobuf over HTTP/2.
- Implement CursorAuthModal for user token import from local SQLite database.
- Update provider models and constants to include Cursor as a supported provider.
- Enhance API service with token validation and user info extraction from Cursor tokens.
- Introduce utility functions for checksum generation and protobuf encoding/decoding for Cursor API interactions.
2026-02-04 12:07:29 +07:00
decolua
f47dfcde1c Update Readme v0.2.56 2026-02-04 11:38:27 +07:00
decolua
677cabc850 Merge branch 'pr-44' 2026-02-04 10:00:46 +07:00
decolua
e6e44ac364 Fix : usage convert 2026-02-04 09:54:11 +07:00
ramhaidar
8ceb8f24c3 chore(providers): use Anthropic Compatible logo
- Update Anthropic Compatible provider configuration to use the new m-variant logo (anthropic-m.png) instead of the standard anthropic.png for consistent branding across the provider icons.
- Target: provider icons
2026-02-03 15:41:10 +07:00
ramhaidar
da5bdef4cb feat: Add Anthropic Compatible provider support
- Added support for 'anthropic-compatible' provider nodes in backend.
- Implemented isAnthropicCompatible logic in open-sse for /messages URL construction and headers.
- Added UI for creating and managing Anthropic Compatible providers in the dashboard.
- Updated validation logic for Anthropic-compatible endpoints.
- Sanitize base URL input (strip trailing /messages) to prevent 404s and improve UX.
- Improve validation: use GET /models (2xx success), and support x-api-key / Authorization Bearer hybrid proxies.
- Enable model import via /models for Anthropic Compatible providers.
- Ensure Authorization is omitted when x-api-key is present to avoid strict proxy conflicts.
- Resolve Anthropic-compatible credentials by prefix during model resolution (e.g., acx/model).
- Update default executor to match provider header/url behavior for Anthropic-compatible providers.
2026-02-03 15:11:41 +07:00
decolua
7881db81ec feat: Implement buffer addition to usage tracking for improved context handling 2026-02-03 10:39:20 +07:00
decolua
df0e1d6485 feat: Update response handling and logging for improved usage tracking 2026-02-03 10:22:43 +07:00
decolua
a33924b336 feat: Enhance usage tracking across response handlers 2026-02-03 00:29:22 +07:00
decolua
c1e88a9d01 Merge pull request #41 from ramhaidar/provider-icons
feat: add provider icons to dashboard
2026-02-03 00:25:10 +07:00
ramhaidar
60bd686fb0 feat(providers): add provider icons to dashboard
- Add provider logo icons for all supported providers
- Update provider detail and list pages to display icons with text fallback
- Target: providers UI
2026-02-02 22:26:40 +07:00
decolua
f59571a18b PR v0.2.52 2026-02-02 19:48:30 +07:00
decolua
fa06226972 fix: Correct indentation for clarity in chatCore and claude-to-openai response handlers 2026-02-02 19:47:09 +07:00