sync#2576
Open
ozkancan-apk wants to merge 27 commits into
Open
Conversation
Batch 1: Simple providers (default executor, OpenAI-compatible) - api-airforce: 24M tokens/month (Grok, Claude, Gemini, DeepSeek) - bazaarlink: 3.6M tokens/month (Claude, GPT, Grok, Gemini) - bluesminds: 7.2M tokens/month (GPT-4o, Claude, Gemini) - deepinfra: free tier (Llama, Qwen, DeepSeek) - inclusionai: 15M tokens/month - inference-net: free tier (Llama, DeepSeek) - llm7: 4.3M tokens/month (GPT-4o-mini, DeepSeek) - nscale: free tier (Llama, DeepSeek) - ollama-cloud: 20M tokens/month (DeepSeek V4, Kimi K2.6) - sambanova: 6M tokens/month (Llama, Qwen, DeepSeek) - venice: free tier (Llama, Qwen, DeepSeek) Total free providers added: 11 new Total free providers: 18 → 29
Pollinations offers free keyless models (openai, qwen-coder, mistral, deepseek, grok, perplexity, gemini-flash-lite, kimi, qwen-vision via gen.pollinations.ai/v1). Default executor since OpenAI-compatible. Also: add noAuth: true transport flag for keyless operation.
- fix(cli): handle Next.js 16 nested standalone output path (decolua#1940) - fix: silence repetitive DATA_DIR fallback warnings (decolua#1937) - fix(opencode-go): strip Kimi K2.7 Code temperature (decolua#1935) - fix: add stripUnsupportedParams to OpenCode Go executor
- cli/cli.js: data dir, process detection use APP_NAME - cli/hooks/sqliteRuntime: DATA_DIR check restored, APP_NAME from pkg - cli/hooks/postinstall, trayRuntime: comments updated - cli/src/cli/tray/autostart: APP_NAME from pkg, log paths dynamic - cli/src/cli/api/client: APP_NAME dynamic - src/lib/dataDir, mitm/paths: APP_NAME → fullfree9router - src/lib/appUpdater, updater: path refs use APP_NAME - src/app/api/version: NPM_PACKAGE_NAME → fullfree9router
Free API key provider with GPT-5, Claude Opus/Sonnet 4.6, Qwen models. Default executor, OpenAI-compatible.
- Header: fullfree9router branding - Added fork notice with extra provider list - Updated badges and install commands - Added 'Extra Free Providers' section (13+ providers) - All path refs updated to fork
Full FREE fork runs on 20129 to coexist with original 9router. All port references updated across 27 source files.
# Conflicts: # cli/package.json # cli/scripts/build-cli.js # package.json # src/lib/db/repos/settingsRepo.js
- Dashboard UI: 9Router -> FF9Router (landing, auth, sidebar, topology, tool cards, CLI tray) - APP_CONFIG.name: '9Router Proxy' -> 'FF9Router Proxy' - Auto-migration: on first boot, copies providerConnections + apiKeys + settings from original 9router DB (%APPDATA%/9router/db/data.sqlite) to FF9Router DB - Marker file prevents re-import
- node:sqlite on Windows needs forward slashes (backslash = escape char) - import now runs even on non-fresh DB (marker-based, not fresh-based) - async/await fix for dynamic import
- New provider: uncloseai (hermes.ai.unturf.com) - free, no API key Hermes 3 8B, auto-fetches models - category: free, noAuth: true - Registered in providers registry index
Applied 12 upstream decolua/9router PRs (cherry-pick pattern): Bugfix PRs: - decolua#1902 init params in transformRequest - decolua#1986 fix gemini-tts 502 models/undefined - decolua#1958 fix antigravity image-to-image editing - decolua#1987 fix TTS minimax voices exposure - decolua#1898 fix usage duplicate zero-token entries - decolua#1955 fix kiro context window for claude-opus-4.8 - decolua#1935 fix opencode-go Kimi temperature (strip params + tests) - decolua#1919 fix quota collapse rows, sort by remaining Feature/improvement PRs: - decolua#1959 improve antigravity client fingerprint - decolua#1912 fix non-stream usage for provider-native responses - decolua#1973 fix headroom log skip diagnostics Migration fix: - Added combo copy from original 9router DB (3 combos: best, free-best, claude-mem) - uncloseai: removed duplicate model entry (v0.5.13 regression) Note: All PRs verified clean apply + build green. 2 pre-existing snapshot failures unrelated to changes.
…anded error rules (410/400/406/408 + text), removed dead models from nvidia
…it), decolua#2020 (cascade delete + token limits), decolua#2018 (dynamic model fetch) PR decolua#2046: SSE non-JSON satir + duplicate [DONE] fix. Stream kararlilik. PR decolua#2007: 5 guvenlik yamasi (API key leak, proxy URL validation, XSS, MITM race, lock file). PR decolua#2020: Provider silinince model alias cascade delete + custom model token limit. PR decolua#2018: Custom provider'dan model listesi dinamik cekme. + onceki: betterSqliteAdapter transaction fix (createProviderConnection undefined hatasi).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.