%%{init: {'theme': 'base', 'themeVariables': { 'fontFamily': 'Space Mono', 'fontSize': '13px', 'primaryColor': '#34312d', 'primaryBorderColor': '#7e7f83', 'lineColor': '#d9c5b2', 'textColor': '#f3f3f4', 'background': '#14110f', 'edgeLabelBackground': '#34312d'}, 'flowchart': {'htmlLabels': true, 'useMaxWidth': false, 'nodeSpacing': 60, 'rankSpacing': 80, 'padding': 20}}}%%
graph TD
    %% Input Node
    IN([Task Schema v2.0]) --> GATE{Circuit Breaker 
 State Check}

    %% Layer 1: The Circuit
    GATE -- "backlog | todo | paused | done" --> BYPASS[Circuit Open 
 Weight 0 / Timer OFF]
    GATE -- "in_progress" --> ACTIVE[Circuit Closed 
 Weight 1 / Timer ON]

    %% Layer 2: The Control Plane Monitors (Parallel Symmetry)
    ACTIVE --> M_GHOST[Ghost Filter 
 Value Audit]
    ACTIVE --> M_EFF[Efficiency Monitor 
 Budget Audit]
    ACTIVE --> M_HEART[Heartbeat Monitor 
 Stagnation Audit]

    %% Layer 3: Penalty Triggers
    M_GHOST -- "0 Commits & >0 Hrs" --> P_GHOST[Ghost Penalty: -40 pts]
    M_EFF -- "Ratio > 2.5" --> P_EFF[Zombie Penalty: -20 pts]
    M_HEART -- "Index > 3.0" --> P_HEART[Stagnation Penalty: -30 pts]

    %% Layer 4: Convergence & Aggregation
    BYPASS --> GCS{Confidence Engine 
 Base 100 - Σ Penalties}
    P_GHOST --> GCS
    P_EFF --> GCS
    P_HEART --> GCS
    
    %% Valid Pass-Throughs (Dotted lines)
    M_GHOST -. "Valid Output" .-> GCS
    M_EFF -. "Normal Ratio" .-> GCS
    M_HEART -. "Active Pulse" .-> GCS

    %% Layer 5: Final Execution
    GCS --> EVAL{Is GCS < 50?}
    EVAL -- Yes --> HALT[Trigger Hallucination Brake 
 Suppress AI Projections]
    EVAL -- No --> PASS[Standard Output 
 AI Summary Generated]

    %% Design System Classes
    classDef default fill:#14110f,stroke:#7e7f83,stroke-width:1px,color:#f3f3f4;
    classDef decision fill:#34312d,stroke:#d9c5b2,stroke-width:2px,color:#d9c5b2;
    classDef trigger fill:#2a1b1a,stroke:#ff5f56,stroke-width:1px,color:#ff5f56;
    classDef healthy fill:#18281e,stroke:#27c93f,stroke-width:1px,color:#27c93f;
    classDef bypass fill:#14110f,stroke:#7e7f83,stroke-width:1px,stroke-dasharray: 4 4,color:#8b949e;

    class GATE,GCS,EVAL decision;
    class P_GHOST,P_EFF,P_HEART,HALT trigger;
    class PASS healthy;
    class BYPASS bypass;

AI Summary Logic Workflow

v2.0 Target Architecture

This architecture represents a "Physics-Based" Control Plane to actively manage human data entropy and prevent AI hallucinations caused by performative reporting.

Status Physics Matrix

Status	Weight	Timer	Ghost	Efficiency	Heartbeat
backlog	0	Off	SKIP	SKIP	SKIP
todo	0	Off	SKIP	SKIP	SKIP
in_progress	1	ON	RUN	RUN	RUN
paused	0	Off	RUN	SKIP	FREEZE
done	0	Off	RUN	Finalize	FREEZE

The Circuit Breaker

We manage circuit states via a State Pattern. When a task is in_progress, the circuit closes—temporal weight becomes 1, and auditing clocks engage.

Entropy Monitors (Mathematical Primitives)

Active tasks are subjected to three deterministic audits. Every anomaly subtracts from the base 100% confidence score.

1. The Ghost Filter (Forensic Auditor for Value)

This workflow acts like a forensic accountant auditing for value, rather than just volume. It asks: "Does the type of work delivered justify the time billed?" It divides Logged Effort (Hours) by Semantic Value (Sum of Commit Weights). Instead of counting lines of code, which can be gamed, it weighs the intent of the work. This prevents "Commit Spam" by correctly valuing low-line-count architectural work while flagging situations where high hours are logged against trivial activities.

$$Ghost\ Ratio = \frac{Logged\ Hours}{\sum(Commit\ Weight)}$$

Penalty: -40 pts if Logged Hours > 0 AND Commit Weight == 0.

2. The Efficiency Monitor (Budget Auditor)

This formula acts as a budget auditor, asking: "Is this task burning hours faster than the plan allowed?" It compares the Actual Cost (Time Spent) against the Approved Budget (Estimated Duration) set by the manager. If no budget was set, the system uses a safety fallback based on Task Scope. A high ratio signals Inefficiency (scope creep, roadblocks, or skill gaps)—distinct from fabrication.

$$Efficiency\ Ratio = \frac{Time\ Spent}{Estimated\ Hours}$$

Penalty: -20 pts if Ratio > 2.5.

3. The Heartbeat Monitor (Hospital Heart Monitor)

This workflow functions like a hospital heart monitor; it ignores the "size" of the patient (Scope) and focuses entirely on whether they have a pulse. It calculates how long a task has been silent relative to the team's standard "heartbeat" (e.g., 24 hours), then multiplies that silence by an "Urgency Factor" (Status Weight). If a high-priority task has no activity for several days, the index spikes, identifying tasks that are technically "Active" but practically dead.

$$Index = \left( \frac{Last\ Activity}{24h\ Threshold} \right) \times Status\ Weight$$

Penalty: -30 pts if Index > 3.0.

Confidence Score Logic (The Hallucination Brake)

The system's "Reliability Index" is designed to prevent the AI from sounding authoritative when the underlying data is corrupted. It functions as an aggregation layer that synthesizes the Stagnation, Zombie, and Ghost signals into a single trust metric (0–100%). Its primary purpose is to act as a Hallucination Brake: if the score drops below 50%, the logic strictly forbids the AI from making projections or using positive language. Instead, it forces a mandatory disclaimer stating that reported progress cannot be verified against physical output.

$$GCS = 100 - \sum(Penalties)$$