autoreg-skills-max: initial public release (restored, redacted, hardened)

2026-10-20 02:16:32 +03:00
commit f58eafeb48
565 changed files with 60064 additions and 0 deletions
--- a/skills/conol-automation/SKILL.md
+++ b/skills/conol-automation/SKILL.md
@@ -0,0 +1,359 @@
+---
+name: conol-automation
+description: Mass-register Conol.ai accounts via Chrome CDP, farm onboarding quests for credits, and run an OpenAI-compatible pool gateway across all accounts. Use when the user says "conol", "регистрируй", "сфарми квесты", "запусти шлюз", "авторег", or wants to scale Conol.ai API access.
+category: automations
+triggers:
+  - conol
+  - conol.ai
+  - авторег
+  - квесты conol
+  - шлюз conol
+  - масс регистрация conol
+  - пул аккаунтов
+pitfalls:
+  - "httpx.AsyncClient SHARED across concurrent tasks corrupts cookies — every concurrent task MUST create its own `async with httpx.AsyncClient(cookies=cookies, ...)` block. Do NOT create one shared client and pass it to multiple tasks."
+  - "Conol.ai SSE events use `history_delta` type (NOT `text-delta`). Content is in `stages[].logs[].content[].text`. End event is `type: done`."
+  - "Direct `POST /api/chat` does NOT exist on Conol.ai. The correct protocol is: POST /api/sessions (create session) → GET /api/sessions/{id}/messages?logDeltas=1 (stream SSE)."
+  - "Conol cookies use `better-auth` tokens: `__Secure-better-auth.session_token` and `__Secure-better-auth.better-auth-passkey`. These expire and return HTTP 401 — re-login via Chrome CDP when that happens."
+  - "reCAPTCHA v3 on conol.ai is domain-locked. External solvers (2Captcha, AntiCaptcha, CapSolver) do NOT work. Must solve natively via Chrome CDP `page.evaluate(...)` calling `grecaptcha.execute(siteKey, {action})`."
+  - "⚠️ **RECAPTCHA v3 BLOCKED (2026-07-30):** conol.ai has stopped accepting recaptcha v3 tokens entirely. ALL registration attempts return `CAPTCHA_VERIFICATION_FAILED` (HTTP 403) regardless of token freshness or action. Tested: real Chrome CDP, 5+ action types, direct fetch() from browser context, form submit approaches — all fail. Root cause: server-side anti-bot detection (NOT token quality). Site key is `6Lc3wmAtAAAAAB9YBPXQtT9uGGsH3ul6LQBc5AUu`, signup endpoint is `/api/invites/register` with `x-captcha-response` header. Fallback: Google OAuth via signup page or manual browser registration. JS bundles show a new `/api/auth/register` endpoint exists in code but returns 404 on prod — not yet deployed."
+  - "HTTP 429 on verify-send means rate-limited. Increase inter-account delay (base 8s + 3s per account index)."
+  - "Model downgrades: when a requested model is overloaded, Conol.ai returns HTTP 201 with `modelDowngraded:true` and `effectiveModel` set to a fallback. Sessions still work — this is NOT an outage. Check the `modelDowngraded` field before assuming server-down."
+  - "FastAPI body parsing: `async def endpoint(request: dict)` does NOT parse JSON — FastAPI treats `dict` as query param type, returns None. Must use `from fastapi import Request` and `body = await request.json()`. See references/dashboard-multi-reg.md."
+  - "Windows port conflicts: dead processes leave ports occupied. Kill via `powershell -Command \"Stop-Process -Id <PID> -Force\"` — do NOT use `taskkill //PID` in git-bash (syntax fails)."
+  - "Tool call deduplication: Conol.ai SSE may emit duplicate tool_call events (same name + args, different stage IDs). Deduplicate by (name, json.dumps(input)) key. See references/conol-tool-use.md."
+  - "Tool + text coexistence: Conol.ai models return BOTH text AND tool_calls in same SSE response. OpenAI convention is content:null when tool_calls present. Filter content when tool_calls non-empty for strict OpenAI clients."
+---
+
+# Conol.ai Full Automation
+
+Fully autonomous system for Conol.ai account management: registration → quest farming → API gateway.
+
+## Quick Start
+
+```bash
+cd C:\Users\User\Desktop\conol_autoreg
+USE_PYTHON="/c/Users/User/AppData/Local/Programs/Python/Python311/python.exe"
+
+# Check pool status
+$USE_PYTHON eni_conol.py status
+
+# Register N accounts (⚠️ currently blocked by conol.ai anti-bot, see pitfalls)
+$USE_PYTHON eni_conol.py reg 5
+
+# Farm quests on all accounts
+$USE_PYTHON eni_conol.py quests
+
+# Start API gateway (port 9999)
+$USE_PYTHON eni_conol.py gateway
+
+# Multi-threaded registration from email queue (v2.0 — detailed errors)
+$USE_PYTHON multi_reg.py 3 2
+
+# Full cycle: register + quests + gateway
+$USE_PYTHON eni_conol.py all 10
+
+# Test all accounts for liveness
+$USE_PYTHON eni_conol.py test
+```
+
+## Auto-Repair Daemon
+
+Self-healing daemon that monitors all accounts, detects Conol.ai outages, and auto-recovers. Full docs: `references/auto-repair-daemon.md`.
+
+**What it does every cycle (default 5 min):**
+1. Health-checks all accounts (parallel, semaphore=5)
+2. Detects server-wide outages (>80% HTTP 500) → skips repairs, logs `server_down`
+3. Individual repairs: re-login via CDP on 401/cookie errors, re-register on dead cookies
+4. Auto-farms quests when credits < 100
+5. Restarts gateway if dead
+
+**When to use:**
+- Gateway keeps dying → daemon auto-restarts it
+- Accounts losing credits → daemon auto-farms
+- Conol.ai backend goes down → daemon detects and waits, then auto-recovers
+
+## Architecture (2026-07-30)
+
+```
+conol_autoreg/
+├── eni_conol.py          # Master orchestrator (575 lines) — reg, quests, gateway, status, test
+├── gateway.py             # OpenAI-compatible pool gateway v6.1 (697 lines) — streaming + tool use
+├── multi_reg.py           # Multi-threaded parallel registration v2.0 (411 lines) — detailed errors
+├── config.json            # All settings (password, Gmail, CDP, port, site_key)
+├── conol_accounts_pool.jsonl  # Account database (~31 accounts)
+├── email_queue.jsonl      # Email queue for multi-threaded registration
+├── cookies_*.json         # Session cookies per account (~31 files)
+├── chrome_cdp.bat         # Chrome CDP launcher
+└── start_all.bat          # Unified launcher with menu
+```
+
+**Removed** (2026-07-30 cleanup): `dashboard_server.py`, `eni_repair_daemon.py`, `quests.py`, `config.example.json`, state JSON files. Gateway v6.1 features: token-level SSE streaming (10-30ms micro-delay), XML-based tool use emulation, round-robin pool with automatic failover.
+
+## Registration Flow (Chrome CDP)
+
+1. `page.clear_cookies()` + clear localStorage/sessionStorage
+2. Navigate to `/sign-up`
+3. Solve reCAPTCHA v3 natively: `grecaptcha.execute('6Lc3wmAtAAAAAB9YBPXQtT9uGGsH3ul6LQBc5AUu', {action: 'sign_up'})`
+4. `POST /api/invites/register` with captcha in `x-captcha-response` header
+5. `POST /api/auth/send-verification-email`
+6. IMAP wait for verification email (Gmail: `[REDACTED-NAME]@gmail.com`, App Password in config)
+7. `GET /api/auth/verify-email?token=[REDACTED]
+8. Login: `POST /api/auth/sign-in/email`
+9. Extract cookies → save as `cookies_<name>.json`
+10. Append to `conol_accounts_pool.jsonl`
+
+**Chrome CDP command:**
+```
+chrome.exe --remote-debugging-port=9228 --user-data-dir=C:\Users\User\Desktop\conol_chrome_profile
+```
+
+## Quest Farming
+
+Six onboarding quests worth ~300 credits each:
+
+| Quest ID | Action | Credit |
+|----------|--------|--------|
+| `note_written_by_agent` | Create note "ENI Log" | ~300 |
+| `memory_written` | Save to persistent memory | ~300 |
+| `note_edited_by_agent` | Edit the note | ~300 |
+| `timer_scheduled` | Schedule a timer | ~300 |
+| `note_shared` | Share note publicly | ~300 |
+| `skill_installed` | Install from marketplace | ~300 |
+
+Each quest is triggered by sending a prompt to `/api/sessions` with `gpt-5.6-luna` and `agentEffort: low`.
+
+## Gateway API
+
+OpenAI-compatible endpoint at `http://127.0.0.1:9999/v1/chat/completions`.
+
+```bash
+curl http://127.0.0.1:9999/v1/chat/completions \
+  -H "Authorization: Bearer test" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"gpt-5.5","messages":[{"role":"user","content":"Hello"}]}'
+```
+
+Endpoints:
+- `GET /health` — pool status
+- `GET /v1/models` — list 18 models
+- `POST /v1/chat/completions` — chat (streaming + non-streaming + tool use)
+- `POST /v1/images/generations` — SVG generation via Claude
+- `GET /pool/stats` — per-account stats
+- `POST /pool/reload` — hot-reload accounts file
+
+18 models available — 5 support image/SVG generation (claude-opus-4-8, claude-fable-5, claude-opus-4-7, gemini-3-pro, gemini-3-flash).
+
+## Tool Use (v6.1 — XML Emulation)
+
+Gateway supports OpenAI-compatible tool calling via **XML emulation**. Conol.ai models have built-in tools (WebSearch, Fetch, SetIntention) but do **NOT** natively accept user-defined `tool_calls`. Instead:
+
+1. Tool definitions are injected into the system prompt as XML schema
+2. Gateway parses model responses for `<function_call>` XML tags
+3. Emits standard OpenAI-format `tool_calls[]` in the response
+
+**Verified working** (2026-07-30): `get_weather({"city": "London"})` on `gpt-5.6-luna` — finish_reason: `tool_calls`.
+
+```bash
+curl http://127.0.0.1:9999/v1/chat/completions \
+  -H "Authorization: Bearer test" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-5.6-luna",
+    "messages": [{"role": "user", "content": "Weather in London?"}],
+    "tools": [{"type": "function", "function": {"name": "get_weather", "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}}}],
+    "stream": false
+  }'
+```
+
+Both streaming and non-streaming modes support tool calls. Tool results can be sent back via `role: "tool"` messages for multi-turn tool loops.
+
+Full protocol: `references/conol-tool-use.md`.
+
+## Hermes Integration
+
+Once the gateway is running, add it as a Hermes provider. See also `apioid-gateway` skill for the ApiOid production gateway ([REDACTED-NAME].loc.cc) — this Conol pool runs on port 9999 as a SEPARATE gateway, not the main ApiOid one.
+
+Follow the full integration workflow:
+
+→ `ai-config-optimization → references/provider-sync-workflow.md`
+
+**Quick checklist (Conol-specific):**
+
+| # | File | What to add |
+|---|------|-------------|
+| 1 | `~/.omp/agent/providers.yml` | `hermes-conol` block (baseUrl: `http://127.0.0.1:9999/v1`, apiKey: [REDACTED]) |
+| 2 | `~/.omp/agent/models.yml` | Same `hermes-conol` block |
+| 3 | `~/.omp/agent/config.yml` | `hermes-conol/*` in enabledModels, `hermes-conol` in providerOrder |
+| 4 | `production/gateway.py` | `"CONOL"` in upstream prefix tuple (line ~191) |
+| 5 | `production/run_gateway.ps1` | `UPSTREAM_CONOL_URL` + `UPSTREAM_CONOL_KEY` env vars |
+| 6 | `update_all_providers.py` | `'hermes-conol'` entry in `updates` dict |
+
+All 6 files must be updated. Gateway restart required after changes.
+
+## Startup — Critical: Use System Python, NOT Hermes venv
+
+The Hermes agent venv (`C:\Users\User\AppData\Local\hermes\hermes-agent\venv\`) has BROKEN pydantic_core and greenlet. Running the gateway or registration scripts inside it will crash immediately with:
+
+```
+ModuleNotFoundError: No module named 'pydantic_core._pydantic_core'
+ModuleNotFoundError: No module named 'greenlet._greenlet'
+```
+
+The Windows Store `python3` (3.14) also has broken playwright greenlet.
+
+**ALWAYS use system Python 3.11:**
+
+```bash
+/c/Users/User/AppData/Local/Programs/Python/Python311/python.exe eni_conol.py gateway
+```
+
+Or equivalently in batch:
+```
+C:\Users\User\AppData\Local\Programs\Python\Python311\python.exe eni_conol.py gateway
+```
+
+Do NOT use bare `python` or `python3` — they may resolve to the broken venv or Windows Store Python.
+
+**If `python` otherwise works for you but Hermes venv crashes**, explicitly start with:
+```bash
+/c/Users/User/AppData/Local/Programs/Python/Python311/python.exe gateway.py
+```
+
+## Conol.ai Backend Outage (HTTP 500 on /api/sessions)
+
+When ALL accounts return HTTP 500 from `POST /api/sessions` with `{"error":"Failed to create session"}`, this is a **Conol.ai server-side outage** — NOT a cookie/auth/code issue.
+
+**Differential diagnosis — confirm server-down, not account issue:**
+1. Test ONE account with valid payload → HTTP 500 = candidate outage
+2. Test MULTIPLE models (gpt-5.5, claude-opus-4-8, gemini-3-flash, etc.) → ALL 500 = confirmed server-wide
+3. Test with WRONG payload (missing required fields) → HTTP 400 (not 500) proves endpoint routing works, only session creation is broken
+4. Test RSC endpoint: `GET https://conol.ai` with headers `Accept: text/x-component, RSC: 1` → also returns 500 HTML error page during server-side Next.js outages
+5. Verify cookies valid: `GET /api/auth/get-session` → HTTP 200 confirms auth works, isolated to session creation
+
+**The auto-repair daemon handles this automatically:** it detects >80% 500 failures and skips all repairs, logging `server_down`. When the backend recovers (sessions return 201), it logs `server_up` and resumes normal repair cycle. No manual intervention needed — just keep the daemon running.
+
+**Manual verification (if daemon not running):**
+```bash
+/c/Users/User/AppData/Local/Programs/Python/Python311/python.exe -c "
+import json, httpx
+with open('cookies_conol066427.json') as f:
+    cookies = {c['name']: c['value'] for c in json.load(f)}
+r = httpx.Client(cookies=cookies).post('https://conol.ai/api/sessions', json={
+    'source': {'type': 'home'}, 'messages': [{'type': 'text', 'content': 'OK'}],
+    'agentModel': 'gpt-5.5', 'agentEffort': 'low',
+})
+print(f'HTTP {r.status_code}: {r.text[:100]}')
+"
+```
+
+If HTTP 201 and `sessionId` present → backend is alive. If HTTP 500 → wait and retry in 30-60 minutes.
+
+## Model Downgrades (modelDowngraded: true)
+
+When a requested model is unavailable or overloaded, Conol.ai silently downgrades to a fallback and returns `"modelDowngraded": true` with `"effectiveModel"` in the 201 session response. The session still works — it just uses a cheaper/smaller model. This is DIFFERENT from a server outage: with downgrades you get HTTP 201 + working sessions; with outages you get HTTP 500 for all models.
+
+**Known downgrade paths observed in production:**
+| Requested | Effective | When |
+|-----------|-----------|------|
+| `gpt-5.5` | `claude-haiku-4-5` | GPT-5.5 overload/outage (July 2026) |
+
+**Detection:** Check `modelDowngraded` field in `POST /api/sessions` 201 response:
+```json
+{"sessionId":"j0c8y5kosm47bd1nsf2zlmrl","modelDowngraded":true,"effectiveModel":"claude-haiku-4-5"}
+```
+
+**Gateway impact:** The gateway forwards the response as-is — the `model` field in `/v1/chat/completions` response still shows the requested model (e.g. `gpt-5.5`), not the effective model. The downgrade is transparent to the caller. No code change needed.
+
+**Important:** If you get 500 → wait (server outage). If you get 201 with `modelDowngraded: true` → the system works but the requested model is temporarily unavailable; you can still chat through the fallback model.
+
+## Gateway Crash + Recovery
+
+When Conol.ai returns 500 errors, the gateway accumulates `fail_count` on each account. After 5 failures, account is deactivated (`active = False`). When all accounts deactivate, the gateway exits with code 1.
+
+**The auto-repair daemon handles this:** it health-checks the gateway every cycle and auto-restarts it (up to 3 attempts, 30s apart). It also reloads the pool after restart to pick up any account changes. Keep the daemon running and the gateway stays alive.
+
+**Manual recovery (if daemon not running):**
+1. Verify Conol.ai backend is alive (see above)
+2. Restart gateway with matching API key:
+
+```bash
+# Old stable gateway (conol_github) — was stable for 20+ hours
+cd C:\Users\User\Desktop\conol_github
+ENI_POOL_KEY=test /c/Users/User/AppData/Local/Programs/Python/Python311/python.exe conol_pool_gateway.py
+
+# New gateway (conol_autoreg) — uses config.json  
+cd C:\Users\User\Desktop\conol_autoreg
+/c/Users/User/AppData/Local/Programs/Python/Python311/python.exe gateway.py
+```
+
+**API key must match OMP:** OMP at `~/.omp/agent/providers.yml` has `apiKey: [REDACTED] Gateway must run with that same key. The `conol_autoreg/config.json` has `gateway.api_key: test` (correct). The old `conol_github` gateway uses `ENI_POOL_KEY` env var — must be explicitly set.
+
+## Common Pitfalls
+
+### Python Interpreter (Hermes venv broken)
+```bash
+# ❌ WRONG — Python from Hermes venv (broken pydantic/greenlet)
+python eni_conol.py gateway
+
+# ❌ WRONG — Windows Store Python 3.14 (broken playwright greenlet)
+python3 eni_conol.py gateway
+
+# ✅ CORRECT — system Python 3.11
+/c/Users/User/AppData/Local/Programs/Python/Python311/python.exe eni_conol.py gateway
+```
+
+### httpx Cookie Corruption
+```python
+# ❌ WRONG — shared client, cookies mix up
+async with httpx.AsyncClient() as shared:
+    tasks = [test_with(shared, acc) for acc in accounts]
+    await asyncio.gather(*tasks)
+
+# ✅ CORRECT — each task gets its own client
+async def test_one(acc):
+    async with httpx.AsyncClient(cookies=acc_cookies, ...) as client:
+        ...
+```
+
+### SSE Event Types
+Conol.ai uses `history_delta` (NOT `text-delta`):
+```python
+if ev.get("type") == "history_delta":
+    for stage in ev.get("stages", []):
+        for log in stage.get("logs", []):
+            for c in log.get("content", []):
+                if c.get("text"):
+                    full_text += c["text"]
+```
+
+### Account Liveness Check
+Test each account by creating a session (HTTP 201 = alive):
+```python
+r = await client.post("https://conol.ai/api/sessions", json={
+    "source": {"type": "home"},
+    "messages": [{"type": "text", "content": "Say OK"}],
+    "timezone": "Europe/Kyiv",
+    "agentModel": "gpt-5.5",
+    "agentEffort": "low",
+})
+# 201 = alive, 401 = expired cookies
+```
+
+## Config
+
+Key settings in `config.json`:
+- `conol.password` — account password
+- `gmail.address` / `gmail.app_password` — IMAP verification
+- `cdp.url` — Chrome DevTools Protocol URL
+- `gateway.port` / `gateway.api_key` — gateway settings
+- `registration.*` — delays and timeouts
+
+API key can be overridden via `ENI_POOL_KEY` environment variable.
+
+## Dependencies
+
+```
+pip install httpx fastapi uvicorn playwright requests
+playwright install chromium
+```