Add directive-first chain system redesign

Redesigns the chain system with a directive-first architecture where
Directive is the top-level entity (the "why/what") and Chains are
generated execution plans (the "how") that can be dynamically modified.

Backend:
- Add database migration for directive system tables
- Add Directive, DirectiveChain, ChainStep, DirectiveEvent models
- Add DirectiveVerifier and DirectiveApproval models
- Add orchestration module with engine, planner, and verifier
- Add comprehensive API handlers for directives
- Add daemon CLI commands for directive management
- Add directive skill documentation
- Integrate contract completion with directive engine
- Add SSE endpoint for real-time directive events

Frontend:
- Add directives route with split-view layout
- Add 6-tab detail view (Overview, Chain, Events, Evaluations, Approvals, Verifiers)
- Add React Flow DAG visualization for chain steps
- Add SSE subscription hook for real-time event updates
- Add useDirectives and useDirectiveEventSubscription hooks
- Add directive types and API functions

Fixes:
- Fix test failures in ws/protocol, task_output, completion_gate, patch
- Fix word boundary matching in looks_like_task()
- Fix parse_last() to find actual last completion gate
- Fix create_export_patch when merge-base equals HEAD
- Clean up clippy warnings in new code

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

1 files changed, 26 insertions, 0 deletions

diff --git a/makima/src/orchestration/mod.rs b/makima/src/orchestration/mod.rs
new file mode 100644
index 0000000..41913ca
--- /dev/null
+++ b/makima/src/orchestration/mod.rs
@@ -0,0 +1,26 @@
+//! Orchestration engine for directive-driven autonomous execution.
+//!
+//! This module provides the core orchestration capabilities:
+//! - [`DirectiveEngine`]: Main orchestration loop that manages directive lifecycle
+//! - [`ChainPlanner`]: LLM-based chain generation from directive goals
+//! - [`Verifier`]: Pluggable verification system for step validation
+//!
+//! # Architecture
+//!
+//! The orchestration system follows a directive-first approach:
+//! 1. Directives define goals, requirements, and acceptance criteria
+//! 2. Chains are generated execution plans (DAGs of steps)
+//! 3. Steps map to contracts that are created and monitored
+//! 4. Tiered verification (programmatic first, then LLM) determines confidence
+//! 5. Confidence scoring (green/yellow/red) drives autonomy decisions
+
+mod engine;
+mod planner;
+mod verifier;
+
+pub use engine::{DirectiveEngine, EngineError};
+pub use planner::{ChainPlanner, PlannerError};
+pub use verifier::{
+    auto_detect_verifiers, CompositeEvaluator, ConfidenceLevel, EvaluationResult, Verifier,
+    VerifierError, VerifierResult, VerifierType,
+};