Subsystem · SRC
Sovereign Reasoning Core
Multi-step reasoning chain execution, strategy selection, depth control, and causal inference for autonomous and semi-autonomous agent operation.
Active — v9.0.0
Chains Completed
0
↑ Ready for a fresh run
Avg Reasoning Depth
6.4
→ Within target (max 10)
Strategy Success Rate
91.4%
↑ +3.2% vs last 24h
Depth Limit Hits
2
→ Depth cap: 10 steps
Live Reach Process
Waiting for a live reach event
Step --
No signal yet. Use New Chain to generate a live reach signal.
Live Conduit Feed
0 Active
Bandwidth
0 sig/s
Total Signals
0
Peak Reach
0%
Last Reach
—
Chains Completed
| Conduit ID | Layer | Reach | Latency | Status | Destination |
|---|
Chain-of-Thought Extended
DefaultLinear step-by-step reasoning with extended intermediate steps and self-consistency checking. Best for structured, well-defined problems.
Max Depth: 10Branching: 1Success: 91.4%
Tree-of-Thought
High DepthExplores multiple reasoning branches in parallel, evaluating and pruning at each node. Best for ambiguous or multi-solution problems.
Max Depth: 10Branching: 3Success: 88.7%
Monte Carlo Tree Search
ExploratoryUses simulation-based search to explore solution spaces probabilistically. Best for planning and optimization under uncertainty.
Max Depth: 8Simulations: 128Success: 86.2%
Reflexion
Self-CorrectingIterative self-evaluation loop where the agent critiques and refines its own reasoning output. Best for tasks requiring high accuracy.
Max Depth: 5Iterations: 3Success: 93.1%
Direct Inference
FastSingle-shot inference with no intermediate steps. Best for simple, well-scoped tasks where latency is critical.
Max Depth: 1Branching: —Latency: 18ms
Custom Strategy Builder
Strategy Events
0 live conduitsDepth Limits & Budgets
Live configGlobal Depth Cap
Hard stop at max depth regardless of strategy
10
Token Budget per Chain
Maximum tokens allocated to a single reasoning chain
32K
Auto-Summarize at Depth Limit
Compress chain to summary when depth cap is hit
Depth Limit Alerts
Notify when chain reaches 80% of depth cap
Parallel Chain Limit
Max concurrent reasoning chains
16
Reasoning Depth Distribution
Depth Utilisation
Deep (≥7)55%
Mid (3–6)30%
Shallow15%
Avg depth per strategy
CoT-Extended5.8
Tree-of-Thought8.1
MCTS7.4
Reflexion3.2
Reasoning Performance (Live)
Chain Completion Rate
LiveCompleted successfully91.4%
Hit depth limit5.2%
Timed out2.1%
Aborted by operator1.3%
Avg tokens/chain
12,420
Avg time/chain
842ms
Chains today
1,840
CBE round-trips
4,210
Live Reach Events