harald/zeroclaw
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3
61 commits 1 branch 0 tags 7.8 MiB
Commit graph

7 commits

Author SHA1 Message Date
Edvard
cc13fec16d fix: add provider warmup to prevent cold-start timeout on first channel message 
The first API request after daemon startup consistently timed out (120s)
when using channels (Telegram, Discord, etc.), requiring a retry before
succeeding. This happened because the reqwest HTTP client's connection
pool was cold — no TLS handshake, DNS resolution, or HTTP/2 negotiation
had occurred yet.

The fix adds a `warmup()` method to the Provider trait that establishes
the connection pool on startup by hitting a lightweight endpoint
(`/api/v1/auth/key` for OpenRouter). The channel server calls this
immediately after creating the provider, before entering the message
processing loop.

Tested on Raspberry Pi 5 (aarch64) with OpenRouter + DeepSeek v3.2 via
Telegram channel. Before: first message took 2-7 minutes (120s timeout +
retries). After: first message responds in <30s with no retries.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-14 18:43:26 -05:00
argenis de la rosa
ec2d5cc93d feat: enhance agent personality, tool guidance, and memory hygiene 
- Expand communication style presets (professional, expressive, custom)
- Enrich SOUL.md with human-like tone and emoji-awareness guidance
- Add crash recovery and sub-task scoping guidance to AGENTS.md scaffold
- Add 'Use when / Don't use when' guidance to TOOLS.md and runtime prompts
- Implement memory hygiene system with configurable archiving and retention
- Add MemoryConfig options: hygiene_enabled, archive_after_days, purge_after_days, conversation_retention_days
- Archive old daily memory and session files to archive subdirectories
- Purge old archives and prune stale SQLite conversation rows
- Add comprehensive tests for new features
 2026-02-14 11:28:39 -05:00
argenis de la rosa
3d91c40970 refactor: simplify CLI commands and update architecture docs 
1. Simplify CLI:
   - Make 'onboard' quick setup default (remove --quick)
   - Add --interactive flag for full wizard
   - Make 'status' detailed by default (remove --verbose)
   - Remove 'tools list/test' and 'integrations list' commands
   - Add 'channel doctor' command
2. Update Docs:
   - Update architecture.svg with Channel allowlists, Browser allowlist, and latest stats
   - Update README.md with new command usage and browser/channel config details
3. Polish:
   - Browser tool integration
   - Channel allowlist logic (empty = deny all)
 2026-02-14 05:17:16 -05:00
argenis de la rosa
976c5bbf3c hardening: fix 7 production weaknesses found in codebase scan 
Scan findings and fixes:

1. Gateway buffer overflow (8KB → 64KB)
   - Fixed: Increased request buffer from 8,192 to 65,536 bytes
   - Large POST bodies (long prompts) were silently truncated

2. Gateway slow-loris attack (no read timeout → 30s)
   - Fixed: tokio::time::timeout(30s) on stream.read()
   - Malicious clients could hold connections indefinitely

3. Webhook secret timing attack (== → constant_time_eq)
   - Fixed: Now uses constant_time_eq() for secret comparison
   - Prevents timing side-channel on webhook authentication

4. Pairing brute force (no limit → 5 attempts + 5min lockout)
   - Fixed: PairingGuard tracks failed attempts with lockout
   - Returns 429 Too Many Requests with retry_after seconds

5. Shell tool hang (no timeout → 60s kill)
   - Fixed: tokio::time::timeout(60s) on Command::output()
   - Commands that hang are killed and return error

6. Shell tool OOM (unbounded output → 1MB cap)
   - Fixed: stdout/stderr truncated at 1MB with warning
   - Prevents memory exhaustion from verbose commands

7. Provider HTTP timeout (none → 120s request + 10s connect)
   - Fixed: All 5 providers (OpenRouter, Anthropic, OpenAI,
     Ollama, Compatible) now have reqwest timeouts
   - Ollama gets 300s (local models are slower)

949 tests passing, 0 clippy warnings, cargo fmt clean
 2026-02-14 01:47:08 -05:00
argenis de la rosa
cc6fc6ce8d feat: BYOP provider + tunnel wizard + SVG architecture diagram 
Custom Provider (Bring Your Own):
- Add custom:URL format to provider factory (any OpenAI-compatible API)
- Works with LiteLLM, LocalAI, vLLM, text-generation-webui, LM Studio, etc.
- Example: default_provider = 'custom:http://localhost:1234'
- 4 new tests for custom provider (URL, localhost, no-key, empty-URL error)

Setup Wizard (6 steps, 5-year-old friendly):
- Add '🔧 Custom' tier to provider selection with guided BYOP flow
- Add Step 4: Tunnel setup (Cloudflare, Tailscale, ngrok, Custom, or skip)
- Emoji labels on all provider categories for visual clarity
- Renumber wizard to 6 steps (was 5)

Architecture Diagram:
- New SVG diagram at docs/architecture.svg (dark theme, color-coded)
- Shows: Chat Apps → Security → Agent Loop → AI Providers
- Shows: Tunnel layer, Sandbox, Context, Heartbeat/Cron
- Shows: Setup Wizard 6-step flow at bottom
- Replace ASCII art in README with SVG embed

657 tests passing, 0 clippy warnings, cargo fmt clean
 2026-02-13 16:32:27 -05:00
argenis de la rosa
bc31e4389b style: cargo fmt — fix all formatting for CI 
Ran cargo fmt across entire codebase to pass CI's cargo fmt --check.
No logic changes, only whitespace/formatting.
 2026-02-13 16:03:50 -05:00
argenis de la rosa
05cb353f7f feat: initial release — ZeroClaw v0.1.0 
- 22 AI providers (OpenRouter, Anthropic, OpenAI, Mistral, etc.)
- 7 channels (CLI, Telegram, Discord, Slack, iMessage, Matrix, Webhook)
- 5-step onboarding wizard with Project Context personalization
- OpenClaw-aligned system prompt (SOUL.md, IDENTITY.md, USER.md, AGENTS.md, etc.)
- SQLite memory backend with auto-save
- Skills system with on-demand loading
- Security: autonomy levels, command allowlists, cost limits
- 532 tests passing, 0 clippy warnings
 2026-02-13 12:19:14 -05:00