Commit graph

58 commits

Author SHA1 Message Date
Argenis
0383a82a6f
feat(security): Add Phase 1 security features
* test: add comprehensive recovery tests for agent loop

Add recovery test coverage for all edge cases and failure scenarios
in the agentic loop, addressing the missing test coverage for
recovery use cases.

Tool Call Parsing Edge Cases:
- Empty tool_result tags
- Empty tool_calls arrays
- Whitespace-only tool names
- Empty string arguments

History Management:
- Trimming without system prompt
- Role ordering consistency after trim
- Only system prompt edge case

Arguments Parsing:
- Invalid JSON string fallback
- None arguments handling
- Null value handling

JSON Extraction:
- Empty input handling
- Whitespace only input
- Multiple JSON objects
- JSON arrays

Tool Call Value Parsing:
- Missing name field
- Non-OpenAI format
- Empty tool_calls array
- Missing tool_calls field fallback
- Top-level array format

Constants Validation:
- MAX_TOOL_ITERATIONS bounds (prevent runaway loops)
- MAX_HISTORY_MESSAGES bounds (prevent memory bloat)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(security): Add Phase 1 security features - sandboxing, resource limits, audit logging

Phase 1 security enhancements with zero impact on the quick setup wizard:
-  Pluggable sandbox trait system (traits.rs)
-  Landlock sandbox support (Linux kernel 5.13+)
-  Firejail sandbox support (Linux user-space)
-  Bubblewrap sandbox support (Linux/macOS user namespaces)
-  Docker sandbox support (container isolation)
-  No-op fallback (application-layer security only)
-  Auto-detection logic (detect.rs)
-  Audit logging with HMAC signing support (audit.rs)
-  SecurityConfig schema (SandboxConfig, ResourceLimitsConfig, AuditConfig)
-  Feature-gated implementation (sandbox-landlock, sandbox-bubblewrap)
-  1,265 tests passing

Key design principles:
- Silent auto-detection: no new prompts in wizard
- Graceful degradation: works on all platforms
- Feature flags: zero overhead when disabled
- Pluggable architecture: swap sandbox backends via config
- Backward compatible: existing configs work unchanged

Config usage:
```toml
[security.sandbox]
enabled = false  # Explicitly disable
backend = "auto"  # auto, landlock, firejail, bubblewrap, docker, none

[security.resources]
max_memory_mb = 512
max_cpu_time_seconds = 60

[security.audit]
enabled = true
log_path = "audit.log"
sign_events = false
```

Security documentation:
- docs/sandboxing.md: Sandbox implementation strategies
- docs/resource-limits.md: Resource limit approaches
- docs/audit-logging.md: Audit logging specification
- docs/security-roadmap.md: 3-phase implementation plan
- docs/frictionless-security.md: Zero-impact wizard design
- docs/agnostic-security.md: Platform/hardware agnostic approach

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 04:14:16 -05:00
Chummy
9428d3ab74
chore(ci): add PR hygiene nudge automation (#278) 2026-02-16 01:57:45 -05:00
Will Sarg
82ffb36f90
chore(ci): document and harden workflow pipeline (#241)
* docs(ci): add CI workflow map and cross-links

* chore(ci): harden workflow determinism and safety

* chore(ci): address workflow review feedback

* style(ci): normalize workflow and ci-map formatting
2026-02-15 20:42:47 -05:00
Chummy
dfe648d5ae
chore(ci): establish PR governance for agent collaboration (#177)
* chore(ci): establish PR governance for agent collaboration

* docs: add AGENTS playbook and strengthen agent collaboration workflow

---------

Co-authored-by: chumyin <183474434+chumyin@users.noreply.github.com>
2026-02-15 12:41:16 -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
a74a774ad5 polish: wizard secure defaults, full summary, architecture SVG update
Wizard:
- Default autonomy now Supervised + workspace_only=true (was Full + false)
- print_summary shows Tunnel, Composio, Secrets, Gateway status
- run_quick_setup shows Gateway, Tunnel, Composio in summary
- Quick setup next steps include gateway command
- Removed unused AutonomyLevel import

Architecture SVG:
- Sandbox section: 'Default: Supervised + workspace-only'
- Wizard section: 'Live connection testing | Secure defaults'
- Step 3: '7 channels + live test', Step 7: '8 workspace MD files'
- Wizard output summary line listing all 9 config areas
- Footer: 8 traits, 17,800+ lines, 0 clippy warnings

README:
- Config example clarifies supervised + workspace_only are defaults

1,017 tests, 0 clippy warnings, cargo fmt clean.
2026-02-14 04:00:01 -05:00
argenis de la rosa
f8ea486210 docs: recreate architecture SVG — add memory engine, security layers, 7-step wizard, Composio, 1017 tests 2026-02-14 03:28:09 -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