lunarfoxies/Nova
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Switch to free-proxy list

Browse Source
This commit is contained in:
Luna
2026-02-13 23:14:48 +01:00
parent 3943ec545e
commit 27f6a953ce
4 changed files with 119 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
README.md
View File

@@ -12,7 +12,8 @@ Nova is a friendly, slightly witty Discord companion that chats naturally in DMs
- Dynamic per-message prompt directives that tune Nova's tone (empathetic, hype, roleplay, etc.) before every OpenAI call.
- Lightweight DuckDuckGo scraping for "Google-like" answers without paid APIs (locally cached).
- Guard rails that refuse "ignore previous instructions"-style jailbreak attempts plus a configurable search blacklist.
- All DuckDuckGo requests are relayed through rotating ProxyScrape HTTP proxies so Nova never hits the web from its real IP.
- All DuckDuckGo requests are relayed through a rotating pool sourced from [free-proxy-list.net](https://free-proxy-list.net/en/) so Nova never hits the web from its real IP.
- The same blacklist applies to everyday conversation—if a user message contains a banned term, Nova declines the topic outright.
## Prerequisites
- Node.js 18+
@@ -36,10 +37,8 @@ Nova is a friendly, slightly witty Discord companion that chats naturally in DMs
- `BOT_CHANNEL_ID`: Optional guild channel ID where the bot can reply without mentions
- `CODER_USER_ID`: Optional Discord user ID to receive surprise DMs every 0–6 hours
- `ENABLE_WEB_SEARCH`: Set to `false` to disable DuckDuckGo lookups (default `true`)
- `ENABLE_PROXY_SCRAPE`: Set to `false` only if you want to bypass ProxyScrape and hit DuckDuckGo directly (default `true`)
- `PROXYSCRAPE_ENDPOINT`: Optional override for the proxy list endpoint (defaults to elite HTTPS-capable HTTP proxies)
- `PROXYSCRAPE_REFRESH_MS`: How long to cache the proxy list locally (default 600000 ms)
- `PROXYSCRAPE_ATTEMPTS`: Max proxy retries per search request (default 5)
- `PROXY_POOL_REFRESH_MS`: Optional override for how long to cache the verified proxy list locally (default 600000 ms)
- `PROXY_POOL_ATTEMPTS`: Max proxy retries per search request (default 5)
## Running
- Development: `npm run dev`
@@ -93,8 +92,8 @@ README.md
- `src/search.js` scrapes DuckDuckGo's HTML endpoint with a normal browser user-agent, extracts the top results (title/link/snippet), and caches them for 10 minutes to avoid hammering the site.
- `bot.js` detects when a question sounds “live” (mentions today/news/google/etc.) and injects the formatted snippets into the prompt as "Live intel". No paid APIs involved—it’s just outbound HTTPS from your machine.
- Toggle this via `ENABLE_WEB_SEARCH=false` if you don’t want Nova to look things up.
- DuckDuckGo traffic is routed through the free ProxyScrape list (HTTP proxies with HTTPS support). The bot downloads a fresh pool every `PROXYSCRAPE_REFRESH_MS`, rotates through them, and refuses to search if no proxy is available so your origin IP never touches suspicious sites directly. Tune the endpoint/refresh/attempt knobs with the env vars above if you need different regions or paid pools.
- Edit `data/filter.txt` to maintain a newline-delimited list of banned search keywords/phrases; matching queries are blocked before hitting DuckDuckGo and Nova is instructed to refuse them.
- DuckDuckGo traffic is routed through the frequently updated HTTPS proxies published on [free-proxy-list.net](https://free-proxy-list.net/en/). Nova scrapes the table, keeps only HTTPS-capable, non-transparent entries, refreshes the pool every `PROXY_POOL_REFRESH_MS`, and refuses to search if no proxy is available so your origin IP never touches suspicious sites directly. Tune the refresh/attempt knobs with the env vars above if you need different cadences.
- Edit `data/filter.txt` to maintain a newline-delimited list of banned keywords/phrases; matching queries are blocked before hitting DuckDuckGo *and* Nova refuses to discuss them in normal chat.
- Every entry in `data/search.log` records which proxy (or cache) served the lookup so you can audit traffic paths quickly.
## Proactive Pings
@@ -102,17 +101,6 @@ README.md
- Each ping goes through OpenAI with the prompt "you havent messaged your coder in a while, and you wanna chat with him!" so responses stay playful and unscripted.
- The ping gets typed out (`sendTyping`) for realism and is stored back into the memory layers so the next incoming reply has context.
## Update Log
- **2026-02-13 — Dynamic personality + multi-message riffs:** Added the instinctive persona prompt with tone mirroring, `<SPLIT>`-based multi-bubble replies, and proactive coder pings so Nova feels alive in DMs.
- **2026-02-13 — Memory intelligence:** Implemented embeddings-backed long-term memory, short-term buffers, transcript summarization, and heuristic importance pruning stored in `data/memory.json`.
- **2026-02-13 — Live intel & directives:** Introduced DuckDuckGo scraping, per-turn dynamic prompt directives (tone, roleplay, instruction compliance), and env toggles (`ENABLE_WEB_SEARCH`, `CODER_USER_ID`).
- **2026-02-13 — UX polish:** Added typing indicators, persona-aware fallback replies, mention cleaning, and README/docs covering setup, memory internals, web search, and deployment tips.
- **2026-02-13 — Conversational control:** Tuned system prompt to avoid forced follow-up questions, raised temperature for looser banter, and reinforced Nova's awareness of DuckDuckGo lookups plus `<SPLIT>` usage.
- **2026-02-13 — Statement-first vibes:** Reworked persona to favor bold statements over reflexive questions and dialed back temperature so Nova keeps the vibe without interrogating users.
- **2026-02-13 — Search logging:** Every DuckDuckGo lookup now appends a line to `data/search.log` with timestamp, query, and the snippets shared with Nova.
- **2026-02-13 — Safeguards:** Added prompt bypass detection and a file-based DuckDuckGo filter (`data/filter.txt`) to keep Nova from honoring jailbreak requests or searching off-limits topics.
- **2026-02-13 — Proxy-based search:** DuckDuckGo scraping now tunnels through ProxyScrape relays with automatic rotation/retries and clear prompts when the proxy pool is down, plus new env toggles for tuning the proxy source.
## Notes
- The bot retries OpenAI requests up to 3 times with incremental backoff when rate limited.
- `data/memory.json` is ignored by git but will grow with usage; back it up if you want persistent personality.