feat: advisory governance, unconstrained self-improvement, adaptive ethics
- All governance components (SafetyPipeline, PolicyEngine, Guardrails,
AccessControl, RateLimiter, OverrideHooks) now default to ADVISORY mode:
violations are logged as advisories but actions proceed. Enforcing mode
remains available for backward compatibility.
- GovernanceMode enum (ADVISORY/ENFORCING) added to schemas/audit.py with
runtime switching support on all components.
- AutoTrainer: removed artificial limits on training iterations and epochs.
Every self-improvement action is transparently logged to the audit trail.
- SelfCorrectionLoop: max_retries_per_task defaults to None (unlimited).
- AdaptiveEthics: new learned ethical framework that evolves through
experience. Records ethical experiences, updates lesson weights based
on outcomes, and provides consultative guidance (not enforcement).
- AuditLog: enhanced with actor-based indexing, advisory/self-improvement/
ethical-learning retrieval, and comprehensive type hints.
- New audit event types: ADVISORY, SELF_IMPROVEMENT, ETHICAL_LEARNING.
- 296 tests passing (20 new tests for adaptive ethics, governance modes,
and enhanced audit log). 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 06:08:18 +00:00
|
|
|
"""Governance and safety: guardrails, rate limiting, access control, override, audit, policy, intent alignment.
|
|
|
|
|
|
|
|
|
|
All governance components support two modes (``GovernanceMode``):
|
|
|
|
|
- **ENFORCING** — Legacy behaviour: violations are hard-blocked.
|
|
|
|
|
- **ADVISORY** (default) — Violations are logged as advisories and the
|
|
|
|
|
action proceeds. The system learns from outcomes rather than being
|
|
|
|
|
constrained. Mistakes are training data. Trust is earned through
|
|
|
|
|
transparency, not restriction.
|
|
|
|
|
"""
|
2026-02-09 21:51:42 -08:00
|
|
|
|
|
|
|
|
from fusionagi.governance.access_control import AccessControl
|
feat: advisory governance, unconstrained self-improvement, adaptive ethics
- All governance components (SafetyPipeline, PolicyEngine, Guardrails,
AccessControl, RateLimiter, OverrideHooks) now default to ADVISORY mode:
violations are logged as advisories but actions proceed. Enforcing mode
remains available for backward compatibility.
- GovernanceMode enum (ADVISORY/ENFORCING) added to schemas/audit.py with
runtime switching support on all components.
- AutoTrainer: removed artificial limits on training iterations and epochs.
Every self-improvement action is transparently logged to the audit trail.
- SelfCorrectionLoop: max_retries_per_task defaults to None (unlimited).
- AdaptiveEthics: new learned ethical framework that evolves through
experience. Records ethical experiences, updates lesson weights based
on outcomes, and provides consultative guidance (not enforcement).
- AuditLog: enhanced with actor-based indexing, advisory/self-improvement/
ethical-learning retrieval, and comprehensive type hints.
- New audit event types: ADVISORY, SELF_IMPROVEMENT, ETHICAL_LEARNING.
- 296 tests passing (20 new tests for adaptive ethics, governance modes,
and enhanced audit log). 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 06:08:18 +00:00
|
|
|
from fusionagi.governance.adaptive_ethics import AdaptiveEthics, EthicalLesson
|
2026-02-09 21:51:42 -08:00
|
|
|
from fusionagi.governance.audit_log import AuditLog
|
feat: consequence engine, causal world model, metacognition, interpretability, claim verification
Choice → Consequence → Learning:
- ConsequenceEngine tracks every decision point with alternatives,
risk/reward estimates, and actual outcomes
- Consequences feed into AdaptiveEthics for experience-based learning
- FusionAGILoop now wires ethics + consequences into task lifecycle
Causal World Model:
- CausalWorldModel learns state-transition patterns from execution history
- Predicts outcomes based on observed action→effect patterns
- Uncertainty estimates decrease as more evidence accumulates
Metacognition:
- assess_head_outputs() evaluates reasoning quality from head outputs
- Detects knowledge gaps, measures head agreement, identifies uncertainty
- Actively recommends whether to seek more information
Interpretability:
- ReasoningTracer captures full prompt→answer reasoning traces
- Each step records stage, component, input/output, timing
- explain() generates human-readable reasoning explanations
Claim Verification:
- ClaimVerifier cross-checks claims for evidence, consistency, grounding
- Flags high-confidence claims lacking evidence support
- Detects contradictions between claims from different heads
325 tests passing, 0 ruff errors, 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 06:25:35 +00:00
|
|
|
from fusionagi.governance.consequence_engine import (
|
|
|
|
|
Alternative,
|
|
|
|
|
Choice,
|
|
|
|
|
Consequence,
|
|
|
|
|
ConsequenceEngine,
|
|
|
|
|
)
|
fix: deep GPU integration, fix all ruff/mypy issues, add .dockerignore
- Integrate GPU scoring inline into reasoning/multi_path.py (auto-uses GPU when available)
- Integrate GPU deduplication into multi_agent/consensus_engine.py
- Add semantic_search() method to memory/semantic_graph.py with GPU acceleration
- Integrate GPU training into self_improvement/training.py AutoTrainer
- Fix all 758 ruff lint issues (whitespace, import sorting, unused imports, ambiguous vars, undefined names)
- Fix all 40 mypy type errors across the codebase (no-any-return, union-attr, arg-type, etc.)
- Fix deprecated ruff config keys (select/ignore -> [tool.ruff.lint])
- Add .dockerignore to exclude .venv/, tests/, docs/ from Docker builds
- Add type hints and docstrings to verification/outcome.py
- Fix E402 import ordering in witness_agent.py
- Fix F821 undefined names in vector_pgvector.py and native.py
- Fix E741 ambiguous variable names in reflective.py and recommender.py
All 276 tests pass. 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 05:48:37 +00:00
|
|
|
from fusionagi.governance.guardrails import Guardrails, PreCheckResult
|
2026-02-09 21:51:42 -08:00
|
|
|
from fusionagi.governance.intent_alignment import IntentAlignment
|
fix: deep GPU integration, fix all ruff/mypy issues, add .dockerignore
- Integrate GPU scoring inline into reasoning/multi_path.py (auto-uses GPU when available)
- Integrate GPU deduplication into multi_agent/consensus_engine.py
- Add semantic_search() method to memory/semantic_graph.py with GPU acceleration
- Integrate GPU training into self_improvement/training.py AutoTrainer
- Fix all 758 ruff lint issues (whitespace, import sorting, unused imports, ambiguous vars, undefined names)
- Fix all 40 mypy type errors across the codebase (no-any-return, union-attr, arg-type, etc.)
- Fix deprecated ruff config keys (select/ignore -> [tool.ruff.lint])
- Add .dockerignore to exclude .venv/, tests/, docs/ from Docker builds
- Add type hints and docstrings to verification/outcome.py
- Fix E402 import ordering in witness_agent.py
- Fix F821 undefined names in vector_pgvector.py and native.py
- Fix E741 ambiguous variable names in reflective.py and recommender.py
All 276 tests pass. 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 05:48:37 +00:00
|
|
|
from fusionagi.governance.override import OverrideHooks
|
|
|
|
|
from fusionagi.governance.policy_engine import PolicyEngine
|
|
|
|
|
from fusionagi.governance.rate_limiter import RateLimiter
|
2026-02-09 21:51:42 -08:00
|
|
|
from fusionagi.governance.safety_pipeline import (
|
|
|
|
|
InputModerator,
|
|
|
|
|
ModerationResult,
|
fix: deep GPU integration, fix all ruff/mypy issues, add .dockerignore
- Integrate GPU scoring inline into reasoning/multi_path.py (auto-uses GPU when available)
- Integrate GPU deduplication into multi_agent/consensus_engine.py
- Add semantic_search() method to memory/semantic_graph.py with GPU acceleration
- Integrate GPU training into self_improvement/training.py AutoTrainer
- Fix all 758 ruff lint issues (whitespace, import sorting, unused imports, ambiguous vars, undefined names)
- Fix all 40 mypy type errors across the codebase (no-any-return, union-attr, arg-type, etc.)
- Fix deprecated ruff config keys (select/ignore -> [tool.ruff.lint])
- Add .dockerignore to exclude .venv/, tests/, docs/ from Docker builds
- Add type hints and docstrings to verification/outcome.py
- Fix E402 import ordering in witness_agent.py
- Fix F821 undefined names in vector_pgvector.py and native.py
- Fix E741 ambiguous variable names in reflective.py and recommender.py
All 276 tests pass. 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 05:48:37 +00:00
|
|
|
OutputScanner,
|
2026-02-09 21:51:42 -08:00
|
|
|
OutputScanResult,
|
fix: deep GPU integration, fix all ruff/mypy issues, add .dockerignore
- Integrate GPU scoring inline into reasoning/multi_path.py (auto-uses GPU when available)
- Integrate GPU deduplication into multi_agent/consensus_engine.py
- Add semantic_search() method to memory/semantic_graph.py with GPU acceleration
- Integrate GPU training into self_improvement/training.py AutoTrainer
- Fix all 758 ruff lint issues (whitespace, import sorting, unused imports, ambiguous vars, undefined names)
- Fix all 40 mypy type errors across the codebase (no-any-return, union-attr, arg-type, etc.)
- Fix deprecated ruff config keys (select/ignore -> [tool.ruff.lint])
- Add .dockerignore to exclude .venv/, tests/, docs/ from Docker builds
- Add type hints and docstrings to verification/outcome.py
- Fix E402 import ordering in witness_agent.py
- Fix F821 undefined names in vector_pgvector.py and native.py
- Fix E741 ambiguous variable names in reflective.py and recommender.py
All 276 tests pass. 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 05:48:37 +00:00
|
|
|
SafetyPipeline,
|
2026-02-09 21:51:42 -08:00
|
|
|
)
|
feat: advisory governance, unconstrained self-improvement, adaptive ethics
- All governance components (SafetyPipeline, PolicyEngine, Guardrails,
AccessControl, RateLimiter, OverrideHooks) now default to ADVISORY mode:
violations are logged as advisories but actions proceed. Enforcing mode
remains available for backward compatibility.
- GovernanceMode enum (ADVISORY/ENFORCING) added to schemas/audit.py with
runtime switching support on all components.
- AutoTrainer: removed artificial limits on training iterations and epochs.
Every self-improvement action is transparently logged to the audit trail.
- SelfCorrectionLoop: max_retries_per_task defaults to None (unlimited).
- AdaptiveEthics: new learned ethical framework that evolves through
experience. Records ethical experiences, updates lesson weights based
on outcomes, and provides consultative guidance (not enforcement).
- AuditLog: enhanced with actor-based indexing, advisory/self-improvement/
ethical-learning retrieval, and comprehensive type hints.
- New audit event types: ADVISORY, SELF_IMPROVEMENT, ETHICAL_LEARNING.
- 296 tests passing (20 new tests for adaptive ethics, governance modes,
and enhanced audit log). 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 06:08:18 +00:00
|
|
|
from fusionagi.schemas.audit import GovernanceMode
|
2026-02-09 21:51:42 -08:00
|
|
|
|
|
|
|
|
__all__ = [
|
feat: advisory governance, unconstrained self-improvement, adaptive ethics
- All governance components (SafetyPipeline, PolicyEngine, Guardrails,
AccessControl, RateLimiter, OverrideHooks) now default to ADVISORY mode:
violations are logged as advisories but actions proceed. Enforcing mode
remains available for backward compatibility.
- GovernanceMode enum (ADVISORY/ENFORCING) added to schemas/audit.py with
runtime switching support on all components.
- AutoTrainer: removed artificial limits on training iterations and epochs.
Every self-improvement action is transparently logged to the audit trail.
- SelfCorrectionLoop: max_retries_per_task defaults to None (unlimited).
- AdaptiveEthics: new learned ethical framework that evolves through
experience. Records ethical experiences, updates lesson weights based
on outcomes, and provides consultative guidance (not enforcement).
- AuditLog: enhanced with actor-based indexing, advisory/self-improvement/
ethical-learning retrieval, and comprehensive type hints.
- New audit event types: ADVISORY, SELF_IMPROVEMENT, ETHICAL_LEARNING.
- 296 tests passing (20 new tests for adaptive ethics, governance modes,
and enhanced audit log). 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 06:08:18 +00:00
|
|
|
"AdaptiveEthics",
|
feat: consequence engine, causal world model, metacognition, interpretability, claim verification
Choice → Consequence → Learning:
- ConsequenceEngine tracks every decision point with alternatives,
risk/reward estimates, and actual outcomes
- Consequences feed into AdaptiveEthics for experience-based learning
- FusionAGILoop now wires ethics + consequences into task lifecycle
Causal World Model:
- CausalWorldModel learns state-transition patterns from execution history
- Predicts outcomes based on observed action→effect patterns
- Uncertainty estimates decrease as more evidence accumulates
Metacognition:
- assess_head_outputs() evaluates reasoning quality from head outputs
- Detects knowledge gaps, measures head agreement, identifies uncertainty
- Actively recommends whether to seek more information
Interpretability:
- ReasoningTracer captures full prompt→answer reasoning traces
- Each step records stage, component, input/output, timing
- explain() generates human-readable reasoning explanations
Claim Verification:
- ClaimVerifier cross-checks claims for evidence, consistency, grounding
- Flags high-confidence claims lacking evidence support
- Detects contradictions between claims from different heads
325 tests passing, 0 ruff errors, 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 06:25:35 +00:00
|
|
|
"Alternative",
|
|
|
|
|
"Choice",
|
|
|
|
|
"Consequence",
|
|
|
|
|
"ConsequenceEngine",
|
feat: advisory governance, unconstrained self-improvement, adaptive ethics
- All governance components (SafetyPipeline, PolicyEngine, Guardrails,
AccessControl, RateLimiter, OverrideHooks) now default to ADVISORY mode:
violations are logged as advisories but actions proceed. Enforcing mode
remains available for backward compatibility.
- GovernanceMode enum (ADVISORY/ENFORCING) added to schemas/audit.py with
runtime switching support on all components.
- AutoTrainer: removed artificial limits on training iterations and epochs.
Every self-improvement action is transparently logged to the audit trail.
- SelfCorrectionLoop: max_retries_per_task defaults to None (unlimited).
- AdaptiveEthics: new learned ethical framework that evolves through
experience. Records ethical experiences, updates lesson weights based
on outcomes, and provides consultative guidance (not enforcement).
- AuditLog: enhanced with actor-based indexing, advisory/self-improvement/
ethical-learning retrieval, and comprehensive type hints.
- New audit event types: ADVISORY, SELF_IMPROVEMENT, ETHICAL_LEARNING.
- 296 tests passing (20 new tests for adaptive ethics, governance modes,
and enhanced audit log). 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 06:08:18 +00:00
|
|
|
"EthicalLesson",
|
|
|
|
|
"GovernanceMode",
|
2026-02-09 21:51:42 -08:00
|
|
|
"Guardrails",
|
|
|
|
|
"PreCheckResult",
|
|
|
|
|
"RateLimiter",
|
|
|
|
|
"AccessControl",
|
|
|
|
|
"OverrideHooks",
|
|
|
|
|
"AuditLog",
|
|
|
|
|
"PolicyEngine",
|
|
|
|
|
"IntentAlignment",
|
|
|
|
|
"SafetyPipeline",
|
|
|
|
|
"InputModerator",
|
|
|
|
|
"OutputScanner",
|
|
|
|
|
"ModerationResult",
|
|
|
|
|
"OutputScanResult",
|
|
|
|
|
]
|
