92 Commits

This Branch

This Branch

All Branches

• feat: persistent typing indicator — refreshes every 4s until first stream token
  admin · 2026-05-05 18:46:32 +00:00
  145f49b28a
• restore: 2026-05-05T18-26-18-915Z__index.js
  admin · 2026-05-05 18:26:20 +00:00
  eb158ce089
• test: full suite backup verification
  admin · 2026-05-05 18:26:19 +00:00
  6aadeb3a35
• checkpoint: before self-evolve self-evolve-1778005578572
  admin · 2026-05-05 18:26:18 +00:00
  d520d8d41e
• checkpoint: before self-evolve self-evolve-1778005525695
  admin · 2026-05-05 18:25:26 +00:00
  20c784597c
• restore: 2026-05-05T18-25-07-009Z__index.js
  admin · 2026-05-05 18:25:08 +00:00
  f3ff7a30ee
• test: full suite backup verification
  admin · 2026-05-05 18:25:07 +00:00
  e5256da10b
• checkpoint: before self-evolve self-evolve-1778005506674
  admin · 2026-05-05 18:25:06 +00:00
  b51d4fa59d
• docs: self-evolution section + feature comparison table
  admin · 2026-05-05 18:22:52 +00:00
  999770b75c
• checkpoint: before self-evolve self-evolve-1778005211558
  admin · 2026-05-05 18:20:11 +00:00
  73e3e0a439
• restore: 2026-05-05T18-18-15-895Z__index.js
  admin · 2026-05-05 18:19:22 +00:00
  26de119a1b
• fix: destructure backup_id in execute()
  admin · 2026-05-05 18:18:59 +00:00
  e80cd21973
• test: verify auto-backup before patch
  admin · 2026-05-05 18:18:16 +00:00
  1870635847
• checkpoint: before self-evolve self-evolve-1778005095485
  admin · 2026-05-05 18:18:15 +00:00
  076b30eda9
• fix: remove undefined logger reference in SelfEvolveTool
  admin · 2026-05-05 18:17:49 +00:00
  c97e42e052
• checkpoint: before self-evolve self-evolve-1778005033751
  admin · 2026-05-05 18:17:14 +00:00
  5ccae14bc7
• feat: file-level backups for self-evolve — auto-backup before every patch, backups/restore actions
  admin · 2026-05-05 18:15:29 +00:00
  8d904af246
• feat: SelfEvolveTool — self-modifying code with auto-rollback

  Safety chain: git stash → checkpoint → apply patch → syntax check → restart → health check → smoke test → rollback on ANY failure
  Protected files: SelfEvolveTool.js, stt.py cannot be self-modified
  Rate limit: 1 evolve per 60s
  Max file size: 50KB per edit

  admin · 2026-05-05 18:09:56 +00:00
  cfa92c81b0
• fix: voice STT path fix + execSync error handling + fetch download
  admin · 2026-05-05 17:56:22 +00:00
  3bfd842998
• feat: add Vosk STT - offline voice-to-text, no API key needed
  admin · 2026-05-05 17:50:50 +00:00
  3b6a7ec502
• docs: add Intelligence Routing section to README
  admin · 2026-05-05 17:46:24 +00:00
  6685f60855
• fix: rewrite chatWithAI as unified agentic tool loop

  OLD: streaming and non-streaming were separate paths. Streaming detected tool
  calls and recursively called non-streaming which only did ONE round of tool
  execution with no loop-back. This caused silent hangs.
  
  NEW: single chatWithAI with internal while loop (max 10 turns):
    1. Call API (stream or non-stream)
    2. If tool_calls → execute all → append results → loop
    3. If text content → return final answer
  
  Key fixes:
  - streamChat now ACCUMULATES tool_call deltas instead of aborting
  - Tool results are fed back to the AI in the same conversation
  - Multi-turn: AI can call tools multiple times before answering
  - Max 10 turns with forced final answer as safety net
  - Proper { content, tool_calls, error } return type from both paths
  - Non-streaming fallback if SSE fails
  - No more recursive calls between stream/non-stream

  admin · 2026-05-05 17:12:16 +00:00
  fe6d3f4db8
• fix: non-streaming tool calls now feed results back to AI for final answer

  Previously tool calls in non-streaming path returned raw tool output as the
  response. Now executes tool, sends results back to model for a synthesized
  answer. Fixes the 'silent after streaming fallback' bug.

  admin · 2026-05-05 17:09:32 +00:00
  78349bb22b
• feat: add DelegateTool with multi-turn agentic loop (18 tools total)

  - DelegateTool.js: multi-turn sub-agent (max 10 turns), feeds tool results back
  - Moved TOOL_DEFS to startBot scope so delegate handler can access tool schemas
  - Fixed scoping: delegate handler resolves model from svc.config instead of chatWithAI local
  - Wired into tools/index.js, TOOL_DEFS, and toolHandlers

  admin · 2026-05-05 16:59:59 +00:00
  092fefbc52
• feat: add vision, TTS, and browser tools (17 tools total)

  - VisionTool: image analysis via Z.AI GLM-4V multimodal API
  - TTSTool: text-to-speech via node-edge-tts (free, auto-sends audio to chat)
  - BrowserTool: web page content extraction via cheerio (strips HTML, extracts text)
  - All 3 wired into tools/index.js + bot tool definitions + handlers
  - TTS handler auto-sends generated audio as voice message to chat

  admin · 2026-05-05 16:52:12 +00:00
  e92e9f5b9d
• feat: real agent execution + real skill execution (system-prompt-driven)

  - delegate_agent: now makes actual AI call with role-specific system prompts
    (coder=code review, architect=system design, devops=infrastructure)
  - run_skill: now makes actual AI call with skill-specific system prompts
    (code_review, bug_fix, refactor, documentation, testing)
  - Both return structured AI-generated results instead of placeholder text

  admin · 2026-05-05 16:45:06 +00:00
  d7f1e3db90
• feat: wire 10 new tools — file_read, file_write, glob, grep, web_fetch, task CRUD, send_message, schedule_cron

  - 10 new JS tool classes in src/tools/ (clean, no framework deps)
  - tools/index.js: registry-based init with env toggles
  - bot/index.js: 16 tool definitions + 16 handlers (was 4)
  - Added glob npm dependency
  - Tools: bash, file_edit, file_read, file_write, glob, grep, web_search, web_fetch, git, task_create/update/list, send_message, schedule_cron, delegate_agent, run_skill

  admin · 2026-05-05 16:43:05 +00:00
  0a81aa2b82
• fix: handle tool calls in streaming mode - fall back to non-streaming

  Model says "let me research" then calls web_search tool.
  Streaming path ignored tool_calls entirely (no-op comment).
  Now: detect tool_calls delta, cancel stream, fall back to non-streaming
  which properly executes tools and returns results.

  admin · 2026-05-05 16:31:59 +00:00
  78d994fdda
• fix: markdownToHtml multiline bold — [\s\S] instead of dot

  GLM outputs multi-line **bold** blocks in essays. The dot regex .+?
  does not match newlines, so multiline bold rendered as raw **.

  admin · 2026-05-05 16:28:35 +00:00
  316f3115f6
• fix: delete+resend streaming draft instead of edit with HTML parse_mode switch

  Telegram rejects parse_mode changes on existing messages.
  Old: editMessageText with HTML on a plain-text message → silent fail, raw ** shown.
  New: deleteMessage + sendFormatted (fresh HTML) → always renders bold/italic correctly.

  admin · 2026-05-05 16:24:32 +00:00
  5cc00aa4fe
• fix: pidfile lock + port conflict guard + systemd ready

  - Pidfile lock prevents duplicate instances (auto-kills stale PIDs)
  - EADDRINUSE retry: kills port hog, retries up to 3x with 1.5s delay
  - releasePidfile() on graceful shutdown
  - Added fs/path imports needed by pidfile utilities

  admin · 2026-05-05 16:20:00 +00:00
  9537bf2dc4
• perf: 3-tier conversation context with LRU cache, keyword relevance, debounced I/O

  UPGRADE from naive JSON to production-grade conversation memory:
  
  Tier 1 — Compressed Summary (max 600 chars):
    Incrementally built from evicted messages. Preserves conversation
    topics across 100+ messages in a tiny budget.
  
  Tier 2 — Relevant Snippets (BM25-style keyword matching):
    Scores older messages against current query, injects top 3 matches.
    Zero external deps — keyword extraction is ~0.1ms.
  
  Tier 3 — Sliding Window (last 12 exchanges verbatim):
    Recent context preserved word-for-word, fitting within token budget.
  
  Performance optimizations:
    - In-memory Map cache with lazy-load from disk (0ms reads)
    - Debounced async disk writes (3s, non-blocking, never stalls response)
    - LRU eviction for cache (max 50 chats, prevents memory leak)
    - Keywords stripped before saving (smaller JSON files)
    - Backward-compatible: loads old format without keywords, backfills on load
    - Graceful shutdown flushes all pending saves to disk
    - Token-aware budget allocation: summary 15% + relevant 15% + recent 70%

  admin · 2026-05-05 15:51:24 +00:00
  4ebd7acca7
• feat: persistent conversation history across sessions and restarts

  - ConversationStore: per-chat JSON files in data/, survives restarts
  - 6000 token budget per chat context (fits ~20-30 exchanges)
  - Auto-trims old messages, always includes most recent
  - Wired into message handler: loads history before AI call, saves after
  - /reset command to clear chat history per chat
  - Cross-session, cross-model, cross-chat isolation

  admin · 2026-05-05 15:47:14 +00:00
  c1a3090f7d
• fix: delete raw-markdown draft and resend formatted on final edit failure

  When streaming produces a long essay that exceeds Telegram's edit limit,
  the final HTML edit silently fails, leaving the user with raw ** markers.
  Now: delete the draft message and send fresh formatted message(s) via
  sendFormatted which handles HTML conversion, splitting, and fallback.

  admin · 2026-05-05 15:25:49 +00:00
  a076ae2d6d
• fix: restore SSE streaming via StreamConsumer for text messages
  admin · 2026-05-05 15:16:01 +00:00
  e49e379096
• fix: bypass StreamConsumer — use direct sendFormatted for reliable delivery
  admin · 2026-05-05 15:07:55 +00:00
  5312694f6d
• debug: add send logging to sendStreamingMessage
  admin · 2026-05-05 14:58:10 +00:00
  60ed5375de
• fix: bulletproof command handler + auto-restart + README overhaul

  - sendStreamingMessage: replaced broken simulated streaming with reliable
    HTML send + stripped plain text fallback (was silently failing)
  - Added global unhandledRejection guard (catches async errors that
    sequentialize middleware would swallow)
  - restart.sh: auto-restart loop on crash (3s delay) instead of bare node
  - README: comprehensive update with self-learning memory, curiosity engine,
    memory architecture diagram, updated command table, updated comparison

  admin · 2026-05-05 14:49:49 +00:00
  050dc6ebe3
• fix: correct logger import path in memory.js
  admin · 2026-05-05 14:44:37 +00:00
  a84df42932
• feat: persistent self-learning memory + curiosity engine

  - New memory.js: JSON-backed MemoryStore with 5 categories (lesson, pattern, preference, discovery, gotcha)
  - Memory injected into system prompt — bot sees past learnings every session
  - Curiosity engine: auto-detects errors/fixes, corrections, successful patterns, new tool discoveries
  - New commands: /memory (stats), /remember (save), /recall (search), /forget (delete)
  - Runs AFTER response delivery — zero latency impact
  - 500 memory cap with smart eviction (keeps gotchas/lessons, evicts old discoveries)
  - data/ directory gitignored (memory is local to each deployment)

  admin · 2026-05-05 14:39:33 +00:00
  c63a1c03ae
• security: remove all hardcoded paths, usernames, IPs, and chat IDs from tracked files

  - start.sh: use dirname instead of hardcoded path
  - src/zcode.js: remove hardcoded chat_id fallback
  - src/utils/rtk.js: use 'rtk' from PATH instead of hardcoded binary path
  - src/telegram-bot.ts: use process.cwd() instead of hardcoded path
  - TELEGRAM_SETUP.md: replace token/chat_id with placeholders
  - QUICKSTART.md: sanitize all references
  - SERVICE_MAP.md: use relative paths instead of absolute

  admin · 2026-05-05 14:30:57 +00:00
  d7107e162f
• docs: remove internal VPS paths from README
  admin · 2026-05-05 14:27:04 +00:00
  977dcc97c3
• docs: comprehensive README overhaul — streaming, self-correction, RTK, formatting

  - New streaming architecture section with ASCII pipeline diagrams
  - Self-correction loops documented (2 retries + backoff + auto-simplification)
  - RTK integration section (60-90% token savings)
  - Telegram HTML formatting system documented
  - Updated feature comparison table (all checkmarks accurate)
  - systemd service deployment guide added
  - Command reference table
  - Architecture flow diagrams

  admin · 2026-05-05 14:24:07 +00:00
  2a088cb0b9
• fix: beautiful Telegram formatting via HTML (no more raw **)

  - Add markdownToHtml() converter: **bold**, *italic*, code blocks, links, headings, quotes, lists
  - StreamConsumer: intermediate edits stay plain text, FINAL message gets full HTML formatting
  - sendFormatted() now uses HTML parse_mode with fallback to stripped plain text
  - stripMarkdown() for plain-text fallback (no raw syntax chars)
  - All Telegram sends now use HTML instead of legacy Markdown mode

  admin · 2026-05-05 14:22:55 +00:00
  a0549ac641
• feat: real-time SSE streaming via StreamConsumer (adapted from Hermes Agent)

  - StreamConsumer class: queued token buffer → rate-limited editMessageText loop
  - Adaptive flood control backoff (3 strikes → fallback to plain send)
  - Cursor indicator (▉) during typing, stripped on completion
  - chatWithAI now supports onDelta callback for SSE token streaming
  - Uses native fetch() for SSE (Node 18+), falls back to non-streaming on error
  - Message handler wires StreamConsumer into the chat pipeline
  - Graceful fallback: if streaming fails entirely, sends as plain message

  admin · 2026-05-05 14:13:03 +00:00
  ed4a4c35e8
• wip: before streaming refactor
  admin · 2026-05-05 14:09:28 +00:00
  e17af157ae
• fix: sentence-level streaming with proper Telegram rate limit throttling
  admin · 2026-05-05 14:04:04 +00:00
  78d4932b63
• debug: log sentMsg raw and Reflect.ownKeys
  admin · 2026-05-05 13:58:26 +00:00
  70815a73d2
• debug: check sentMsg constructor and result property
  admin · 2026-05-05 13:53:25 +00:00
  a4a9e31e79
• debug: check for 'result' wrapper in Telegram API response
  admin · 2026-05-05 13:51:40 +00:00
  fbc6b9a377