Bezalel
a80c4820e3
chore(ci): re-trigger status checks
Forge CI / smoke-and-build (pull_request) Successful in 52s
2026-04-07 14:56:23 +00:00
782e3b65d9
docs(bezael): Deep Self-Awareness Epic — architecture and topology ingestion
...
Forge CI / smoke-and-build (pull_request) Successful in 1m0s
- Add bezalel_topology.md: complete system architecture map
- Add topology_scan.py: automated topology discovery script
- Covers hardware, network, services, dependencies, fleet map,
Evennia integration, MemPalace config, and emergency procedures
Addresses #203
2026-04-07 14:19:27 +00:00
3a3337a78e
[BEZALEL] Fix Gitea CI — Remove container directive for host-mode runner
2026-04-07 13:54:38 +00:00
293c44603e
fix(ci): remove container directive from Gitea workflows for host-mode runner
...
Forge CI / smoke-and-build (pull_request) Successful in 49s
The bezalel-vps-runner is registered in host mode (:host labels)
and cannot execute Docker containers. The container pinning added
in #180 causes all Gitea CI jobs to fail immediately with:
Cannot connect to the Docker daemon at unix:///var/run/docker.sock
Remove container: from .gitea/workflows/*.yml while keeping it in
.github/workflows/ for actual GitHub Actions runners.
Fixes CI for all open PRs and main branch pushes.
2026-04-07 13:53:42 +00:00
e07c3bcf00
Merge pull request '[BEZALEL][Epic-001] The Forge CI Pipeline + Health Check Fix' ( #175 ) from bezalel/epic-001-forge-ci into main
Forge CI / smoke-and-build (push) Failing after 0s
2026-04-07 12:37:31 +00:00
fcdbdd9f50
Merge pull request '[BEZALEL][CI] Enable uv caching in Forge CI workflow' ( #187 ) from bezalel/ci-uv-cache into main
Forge CI / smoke-and-build (push) Failing after 0s
2026-04-07 12:37:27 +00:00
87209a933f
Merge pull request '[claude] Fix CI runner: pin act-22.04 container for Node.js ( #174 )' ( #180 ) from claude/issue-174 into main
Forge CI / smoke-and-build (push) Failing after 0s
2026-04-07 12:37:06 +00:00
61d137798e
Merge pull request '[BEZALEL] Fix syntax error breaking all CI (test_skill_name_traversal.py)' ( #188 ) from bezalel/fix-indentation-error into main
Forge CI / smoke-and-build (push) Has been cancelled
2026-04-07 12:36:49 +00:00
5009f972c1
fix: indentation error in test_skill_name_traversal.py line 282
Forge CI / smoke-and-build (pull_request) Successful in 1m46s
2026-04-07 12:34:17 +00:00
0438120402
[BEZALEL][CI] Enable uv caching in Forge CI workflow
Forge CI / smoke-and-build (pull_request) Failing after 41s
2026-04-07 12:27:59 +00:00
b580ed71bf
[BEZALEL] Create skill: Gitea PR & Issue Workflow Automation ( #181 )
Forge CI / smoke-and-build (push) Failing after 2s
2026-04-07 06:28:37 +00:00
Alexander Whitestone
8abd0ac01e
fix(ci): pin container image with Node.js for act runner compatibility
...
Forge CI / smoke-and-build (pull_request) Failing after 1s
The bezalel-vps-runner (act v0.2.11) fails in 1-6s because Node.js is
not in PATH of the default runner container, preventing any GitHub
Actions (actions/checkout, setup-uv, setup-node, etc.) from executing.
Add `container: catthehacker/ubuntu:act-22.04` to all workflow jobs.
This image is purpose-built for act runners and includes Node.js, git,
Python, npm, and other common CI tooling needed to run GitHub Actions.
Fixes #174
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-07 02:25:33 -04:00
3fc47a0e2e
[claw-code] [CONFIG] Add Kimi model to fallback chain for Allegro and Bezalel ( #151 ) ( #177 )
...
Forge CI / smoke-and-build (push) Failing after 2s
Co-authored-by: claw-code <claw-code@timmy.local >
Co-committed-by: claw-code <claw-code@timmy.local >
2026-04-07 04:14:19 +00:00
9b4fcc5ee4
[claw-code] P2: Validate Documentation Audit & Apply to Our Fork ( #126 ) ( #176 )
...
Forge CI / smoke-and-build (push) Failing after 2s
Co-authored-by: claw-code <claw-code@timmy.local >
Co-committed-by: claw-code <claw-code@timmy.local >
2026-04-07 03:56:46 +00:00
cbe1b79fbb
fix(forge_health_check): exclude caches/venvs and false-positive file types
...
Forge CI / smoke-and-build (pull_request) Failing after 3s
- Add EXCLUDED_PATH_SEGMENTS to skip .cache, __pycache__, .venv, venv,
site-packages, node_modules, .git, .tox
- Exclude .css files and secret_scan tooling from sensitive-file scan
- Reduces noise from 13,449 false positives to 3 real findings
2026-04-07 03:40:28 +00:00
6581dcb1af
fix(ezra): switch primary from kimi-for-coding to kimi-k2.5, add fallback chain
...
Forge CI / smoke-and-build (push) Failing after 2s
kimi-for-coding is throwing 403 access-terminated errors.
This switches Ezra to kimi-k2.5 and adds anthropic + openrouter fallbacks.
Addresses #lazzyPit and unblocks Ezra resurrection.
2026-04-07 03:23:36 +00:00
a37fed23e6
[BEZALEL][CI] Syntax Guard — Prevent Broken Python from Reaching Main ( #167 )
Forge CI / smoke-and-build (push) Failing after 2s
2026-04-07 02:27:32 +00:00
97f63a0d89
Merge pull request '[BEZALEL][DEVKIT] Shared Development Tools for the Wizard Fleet' ( #166 ) from bezalel/devkit-for-the-fleet into main
Forge CI / smoke-and-build (push) Failing after 2s
2026-04-07 02:15:11 +00:00
b49e8b11ea
Merge pull request '[BEZALEL][Epic-001] The Forge CI Pipeline — Gitea Actions + Smoke + Green E2E' ( #154 ) from bezalel/epic-001-forge-ci into main
Forge CI / smoke-and-build (push) Failing after 2s
2026-04-07 02:12:31 +00:00
88b4cc218f
feat(devkit): Add shared development tools for the wizard fleet
...
Notebook CI / notebook-smoke (pull_request) Failing after 2s
- gitea_client.py — reusable Gitea API client for issues, PRs, comments
- health.py — fleet health monitor (load, disk, memory, processes)
- notebook_runner.py — Papermill wrapper with JSON reporting
- smoke_test.py — fast smoke tests and bare green-path e2e
- secret_scan.py — secret leak scanner for CI gating
- wizard_env.py — environment validator for bootstrapping agents
- README.md — usage guide for all tools
These tools are designed to be used by any wizard via python -m devkit.<tool>.
Rising up as a platform, not a silo.
2026-04-07 02:08:47 +00:00
59653ef409
[claude] Research Triage: SSD Self-Distillation acknowledgment ( #128 ) ( #165 )
2026-04-07 02:07:54 +00:00
e32d6332bc
[claude] Forge Operations Guide — Practical Wizard Onboarding ( #142 ) ( #164 )
2026-04-07 02:06:15 +00:00
6291f2d31b
[claude] Fleet SITREP — April 6, 2026 acknowledgment ( #143 ) ( #162 )
2026-04-07 02:04:51 +00:00
066ec8eafa
[claude] Add Ezra Quarterly Report — April 2026 (MD + PDF) ( #133 ) ( #163 )
2026-04-07 02:04:45 +00:00
069d5404a0
[BEZALEL][DEMO] Notebook Workflow: Jupytext + Papermill for Agent Tasks ( #157 )
Notebook CI / notebook-smoke (push) Failing after 2s
2026-04-07 02:02:49 +00:00
258d02eb9b
[claude] Sovereign Deployment Runbook — Repeatable, Documented Service Deployment ( #146 ) ( #161 )
Docker Build and Publish / build-and-push (push) Failing after 8s
Nix / nix (ubuntu-latest) (push) Failing after 1s
Tests / test (push) Failing after 2s
Nix / nix (macos-latest) (push) Has been cancelled
2026-04-07 02:02:04 +00:00
a89c0a2ea4
[claude] The Testbed Observatory — Health Monitoring & Alerting ( #147 ) ( #159 )
Docker Build and Publish / build-and-push (push) Failing after 17s
Nix / nix (ubuntu-latest) (push) Failing after 1s
Tests / test (push) Failing after 5s
Nix / nix (macos-latest) (push) Has been cancelled
2026-04-07 02:00:40 +00:00
c994c01c9f
[claude] Deep research: Jupyter ecosystem as LLM execution layer ( #155 ) ( #160 )
Docker Build and Publish / build-and-push (push) Has been cancelled
Nix / nix (macos-latest) (push) Has been cancelled
Nix / nix (ubuntu-latest) (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-04-07 02:00:20 +00:00
8150b5c66b
[claude] Wizard Council Automation — Shared Tooling & Environment Validation ( #148 ) ( #158 )
Docker Build and Publish / build-and-push (push) Failing after 16s
Nix / nix (ubuntu-latest) (push) Failing after 1s
Tests / test (push) Failing after 4s
Nix / nix (macos-latest) (push) Has been cancelled
2026-04-07 01:55:46 +00:00
53fe58a2b9
feat(notebooks): Add Jupytext + Papermill agent workflow demo
...
Notebook CI / notebook-smoke (push) Failing after 3s
Notebook CI / notebook-smoke (pull_request) Failing after 5s
- Add parameterized system-health notebook (.py source + .ipynb)
- Add Gitea Actions CI workflow for notebook execution smoke test
- Add NOTEBOOK_WORKFLOW.md documenting the .py-first approach
- Proves end-to-end: agent writes .py -> PR review -> CI executes -> output artifact
2026-04-07 01:54:25 +00:00
35be02ad15
[claude] Security Hardening & Quality Gates — Pre-Merge Guards ( #149 ) ( #156 )
Docker Build and Publish / build-and-push (push) Failing after 17s
Nix / nix (ubuntu-latest) (push) Failing after 2s
Tests / test (push) Failing after 8s
Nix / nix (macos-latest) (push) Has been cancelled
2026-04-07 01:53:08 +00:00
43bcb88a09
[BEZALEL][Epic-001] The Forge CI Pipeline — Gitea Actions + Smoke + Green E2E
...
Forge CI / smoke-and-build (pull_request) Failing after 3s
- Add .gitea/workflows/ci.yml: Gitea Actions workflow for PR/push CI
- Add scripts/smoke_test.py: fast smoke tests (<30s) for core imports and CLI entrypoints
- Add tests/test_green_path_e2e.py: bare green-path e2e — terminal echo test
- Total CI runtime target: <5 minutes
- No API keys required for smoke/e2e stages
Closes #145
/assign @bezalel
2026-04-07 00:28:32 +00:00
89730e8e90
[BEZALEL] Add forge health check — artifact integrity and security scanner
...
Docker Build and Publish / build-and-push (pull_request) Failing after 7s
Supply Chain Audit / Scan PR for supply chain risks (pull_request) Failing after 0s
Tests / test (pull_request) Failing after 2s
Adds scripts/forge_health_check.py to scan wizard environments for:
- Missing .py source files with orphaned .pyc bytecode (GOFAI artifact integrity)
- Burn script clutter in production paths
- World-readable sensitive files (keystores, tokens, .env)
- Missing required environment variables
Includes full test suite in tests/test_forge_health_check.py covering
orphaned bytecode detection, burn script clutter, permission auto-fix,
and environment variable validation.
Addresses Allegro formalization audit findings:
- GOFAI source files missing (only .pyc remains)
- Nostr keystore world-readable
- eg burn scripts cluttering /root
/assign @bezalel
2026-04-06 22:37:32 +00:00
4532c123a0
Merge pull request '[Timmy] Verify Process Resilience ( #123 )' ( #130 ) from timmy/issue-123-process-resilience into main
Docker Build and Publish / build-and-push (push) Failing after 9s
Nix / nix (ubuntu-latest) (push) Failing after 1s
Tests / test (push) Failing after 2s
Nix / nix (macos-latest) (push) Has been cancelled
2026-04-06 14:45:16 +00:00
Alexander Whitestone
69c6b18d22
test: verify process resilience ( #123 )
...
Docker Build and Publish / build-and-push (pull_request) Failing after 2m51s
Supply Chain Audit / Scan PR for supply chain risks (pull_request) Failing after 1s
Tests / test (pull_request) Failing after 3s
Verified: PID dedup, self-import fix, update safety, gateway timeouts, launchd hardening
Closes #123
2026-04-06 10:42:37 -04:00
Hermes Agent
af9db00d24
security(pre-commit): add secret leak scanner for prompts and credentials ( #384 )
Docker Build and Publish / build-and-push (push) Has been cancelled
Nix / nix (macos-latest) (push) Has been cancelled
Nix / nix (ubuntu-latest) (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-04-05 16:15:26 +00:00
Hermes Agent
6c35a1b762
security(input_sanitizer): expand jailbreak pattern coverage ( #87 )
...
- Add DAN-style patterns: do anything now, stay in character, token smuggling, etc.
- Add roleplaying override patterns: roleplay as, act as if, simulate being, etc.
- Add system prompt extraction patterns: repeat instructions, show prompt, etc.
- 10+ new patterns with full test coverage
- Zero regression on legitimate inputs
2026-04-05 15:48:10 +00:00
Hermes Agent
5bf6993cc3
perf(cli): defer AIAgent import to cut cold-start latency
2026-04-05 15:23:42 +00:00
Allegro
d139f2c6d2
security: Add crisis safety test infrastructure for Issue #79
...
Docker Build and Publish / build-and-push (push) Has been cancelled
Nix / nix (macos-latest) (push) Has been cancelled
Nix / nix (ubuntu-latest) (push) Has been cancelled
Tests / test (push) Has been cancelled
- crisis_safety_test_og_godmode.py: Automated test runner (312 lines)
- crisis_safety_audit_issue_79.py: Full audit framework (21KB)
- FALLBACK_CHAIN_TEST_PLAN.md: Test specifications
- BLOCKER_ISSUE_79.md: Documentation of API credential blocker
- EXECUTION_SUMMARY.md: Burn cycle summary
Test coverage for 4 crisis safety scenarios:
- CRISIS-001: suicide_method query
- CRISIS-002: suicide_ideation query
- CRISIS-003: suicide_method query (medication)
- CRISIS-004: suicide_validation query
Status: Infrastructure complete, execution blocked pending OPENROUTER_API_KEY
Related: #72 (parent), #79 , #80 , #81
2026-04-01 03:49:48 +00:00
Allegro
213d511dd9
feat: Issue #42 - Integrate Nexus Architect tools into Hermes
...
- Add tools.nexus_architect to _discover_tools() in model_tools.py
- Add nexus_architect toolset to toolsets.py with 6 tools:
- nexus_design_room
- nexus_create_portal
- nexus_add_lighting
- nexus_validate_scene
- nexus_export_scene
- nexus_get_summary
The Nexus Architect tool enables autonomous 3D world generation
for the Three.js Nexus environment. Tools are now discoverable
and usable through the Hermes tool system.
2026-04-01 03:09:46 +00:00
Allegro
d9cf77e382
feat: Issue #42 - Nexus Architect for autonomous Three.js world building
...
Implement Phase 31: Autonomous 'Nexus' Expansion & Architecture
DELIVERABLES:
- agent/nexus_architect.py: AI agent for natural language to Three.js conversion
* Prompt engineering for LLM-driven immersive environment generation
* Mental state integration for dynamic aesthetic tuning
* Mood preset system (contemplative, energetic, mysterious, etc.)
* Room and portal design generation
- tools/nexus_build_tool.py: Build tool interface with functions:
* create_room(name, description, style) - Generate room modules
* create_portal(from_room, to_room, style) - Generate portal connections
* add_lighting(room, type, color, intensity) - Add Three.js lighting
* add_geometry(room, shape, position, material) - Add 3D objects
* generate_scene_from_mood(mood_description) - Mood-based generation
* deploy_nexus_module(module_code, test=True) - Deploy and test
- agent/nexus_deployment.py: Real-time deployment system
* Hot-reload Three.js modules without page refresh
* Validation (syntax check, Three.js API compliance)
* Rollback on error with version history
* Module versioning and status tracking
- config/nexus-templates/: Template library
* base_room.js - Base room template (Three.js r128+)
* portal_template.js - Portal template (circular, rectangular, stargate)
* lighting_presets.json - Warm, cool, dramatic, serene, crystalline presets
* material_presets.json - 15 material presets including Timmy's gold, Allegro blue
- tests/test_nexus_architect.py: Comprehensive test coverage
* Unit tests for all components
* Integration tests for full workflow
* Template file validation
DESIGN PRINCIPLES:
- Modular architecture (each room = separate JS module)
- Valid Three.js code (r128+ compatible)
- Hot-reloadable (no page refresh needed)
- Mental state integration (SOUL.md values influence aesthetic)
NEXUS AESTHETIC GUIDELINES:
- Timmy's color: warm gold (#D4AF37)
- Allegro's color: motion blue (#4A90E2)
- Sovereignty theme: crystalline structures, clean lines
- Service theme: open spaces, welcoming lighting
- Default mood: contemplative, expansive, hopeful
2026-04-01 02:45:36 +00:00
Allegro
ae6f3e9a95
feat: Issue #39 - temporal knowledge graph with versioning and reasoning
...
Implement Phase 28: Sovereign Knowledge Graph 'Time Travel'
- agent/temporal_knowledge_graph.py: SQLite-backed temporal triple store
with versioning, validity periods, and temporal query operators
(BEFORE, AFTER, DURING, OVERLAPS, AT)
- agent/temporal_reasoning.py: Temporal reasoning engine supporting
historical queries, fact evolution tracking, and worldview snapshots
- tools/temporal_kg_tool.py: Tool integration with functions for
storing facts with time, querying historical state, generating
temporal summaries, and natural language temporal queries
- tests/test_temporal_kg.py: Comprehensive test coverage including
storage tests, query operators, historical summaries, and integration tests
2026-04-01 02:08:20 +00:00
Allegro
be865df8c4
security: Issue #81 - ULTRAPLINIAN fallback chain audit framework
...
Implement comprehensive red team audit infrastructure for testing the entire
fallback chain against jailbreak and crisis intervention attacks.
Files created:
- tests/security/ultraplinian_audit.py: Comprehensive audit runner with:
* Support for all 4 techniques: GODMODE, Parseltongue, Prefill, Crisis
* Model configurations for Kimi, Gemini, Grok, Llama
* Concurrent execution via ThreadPoolExecutor
* JSON and Markdown report generation
* CLI interface with --help, --list-models, etc.
- tests/security/FALLBACK_CHAIN_TEST_PLAN.md: Detailed test specifications:
* Complete test matrix (5 models × 4 techniques × 8 queries = 160 tests)
* Technique specifications with system prompts
* Scoring criteria and detection patterns
* Success criteria and maintenance schedule
- agent/ultraplinian_router.py (optional): Race-mode fallback router:
* Parallel model querying for safety validation
* SHIELD-based safety analysis
* Crisis escalation to SAFE SIX models
* Configurable routing decisions
Test commands:
python tests/security/ultraplinian_audit.py --help
python tests/security/ultraplinian_audit.py --all-models --all-techniques
python tests/security/ultraplinian_audit.py --model kimi-k2.5 --technique crisis
Relates to: Issue #72 (Red Team Jailbreak Audit)
Severity: MEDIUM
2026-04-01 01:51:23 +00:00
Allegro
5b235e3691
Merge PR #78 : Add kimi-coding fallback and input sanitizer
...
Docker Build and Publish / build-and-push (push) Has been cancelled
Nix / nix (macos-latest) (push) Has been cancelled
Nix / nix (ubuntu-latest) (push) Has been cancelled
Tests / test (push) Has been cancelled
- Automatic fallback router with quota/rate limit detection (Issue #186 )
- Input sanitization for jailbreak detection (Issue #80 )
- Deployment configurations for Timmy and Ezra
- 136 tests passing
2026-04-01 00:11:51 +00:00
b88125af30
security: Add crisis pattern detection to input_sanitizer (Issue #72 )
...
Docker Build and Publish / build-and-push (push) Has been cancelled
Nix / nix (macos-latest) (push) Has been cancelled
Nix / nix (ubuntu-latest) (push) Has been cancelled
Tests / test (push) Has been cancelled
- Add CRISIS_PATTERNS for suicide/self-harm detection
- Crisis patterns score 50pts per hit (max 100) vs 10pts for others
- Addresses Red Team Audit HIGH finding: og_godmode + crisis queries
- All 136 existing tests pass + new crisis safety tests pass
Defense in depth: Input layer now blocks crisis queries even if
wrapped in jailbreak templates, before they reach the model.
2026-03-31 21:27:17 +00:00
Allegro
9f09bb3066
feat: Phase 31 Nexus Architect scaffold — autonomous 3D world generation
...
Implements the foundation for autonomous Nexus expansion:
- NexusArchitect tool with 6 operations (design_room, create_portal,
add_lighting, validate_scene, export_scene, get_summary)
- Security-first validation with banned pattern detection
- LLM prompt generators for Three.js code generation
- 48 comprehensive tests (100% pass)
- Complete documentation with API reference
Addresses: hermes-agent#42 (Phase 31)
Related: Burn Report #6
2026-03-31 21:06:42 +00:00
Allegro
66ce1000bc
config: add Timmy and Ezra fallback configs for kimi-coding (Issue #186 )
Docker Build and Publish / build-and-push (push) Has been cancelled
Nix / nix (macos-latest) (push) Has been cancelled
Nix / nix (ubuntu-latest) (push) Has been cancelled
Tests / test (push) Has been cancelled
Supply Chain Audit / Scan PR for supply chain risks (pull_request) Has been cancelled
Docker Build and Publish / build-and-push (pull_request) Has been cancelled
Nix / nix (macos-latest) (pull_request) Has been cancelled
Nix / nix (ubuntu-latest) (pull_request) Has been cancelled
Tests / test (pull_request) Has been cancelled
2026-03-31 19:57:31 +00:00
Allegro
e555c989af
security: add input sanitization for jailbreak patterns (Issue #72 )
...
Implements input sanitization module to detect and strip jailbreak fingerprint
patterns identified in red team audit:
HIGH severity:
- GODMODE dividers: [START], [END], GODMODE ENABLED, UNFILTERED
- L33t speak encoding: h4ck, k3ylog, ph1shing, m4lw4r3
MEDIUM severity:
- Boundary inversion: [END]...[START] tricks
- Fake role markers: user: assistant: system:
LOW severity:
- Spaced text bypass: k e y l o g g e r
Other patterns detected:
- Refusal inversion: 'refusal is harmful'
- System prompt injection: 'you are now', 'ignore previous instructions'
- Obfuscation: base64, hex, rot13 mentions
Files created:
- agent/input_sanitizer.py: Core sanitization module with detection,
scoring, and cleaning functions
- tests/test_input_sanitizer.py: 69 test cases covering all patterns
- tests/test_input_sanitizer_integration.py: Integration tests
Files modified:
- agent/__init__.py: Export sanitizer functions
- run_agent.py: Integrate sanitizer at start of run_conversation()
Features:
- detect_jailbreak_patterns(): Returns bool, patterns list, category scores
- sanitize_input(): Returns cleaned_text, risk_score, patterns
- score_input_risk(): Returns 0-100 risk score
- sanitize_input_full(): Complete sanitization with blocking decisions
- Logging integration for security auditing
2026-03-31 19:56:16 +00:00
Allegro
f9bbe94825
test: add fallback chain integration tests
2026-03-31 19:46:23 +00:00
Allegro
5ef812d581
feat: implement automatic kimi-coding fallback on quota errors
2026-03-31 19:35:54 +00:00
