Mechanism
The promotion-containment continuum characterizes the agent's cognitive integrity in terms of two structural invariants disclosed elsewhere in the architecture: the promotion mechanism and the containment layer. The promotion mechanism is the governance-controlled gateway by which speculative content in the planning graph domain transitions to verified status in the agent's execution memory. The containment layer is the architectural boundary that prevents speculative content from being treated as verified reality except through the promotion interface. Together, these two mechanisms define a continuum along which the agent's cognitive integrity can be characterized.
The continuum is defined as a two-dimensional parameter space with the promotion threshold on one axis and the containment integrity on the other. The promotion threshold is the composite evaluation criterion that a speculative branch must satisfy before it is admitted to verified execution memory, incorporating trust slope continuity validation, policy compatibility, integrity impact assessment, and capability verification. It is not a fixed constant: it is modulated by the agent's affective state, personality field, and current integrity score. The containment integrity is the degree to which the containment layer successfully enforces structural separation between the speculative planning graph domain and the verified execution memory domain. The agent's position in this two-dimensional space determines its cognitive regime, the qualitative character of its cognitive processing.
Cognitive disruption, in this framework, is not modeled as an error or a malfunction of a different system. It is the same architecture, the same forecasting engine, the same promotion interface, and the same containment layer, operating in a different region of the promotion-containment parameter space. A change in the underlying parameters drives the system from one stable configuration into a qualitatively different behavioral regime, in the manner of an architectural phase-shift.
The Four Cognitive Regimes
The parameter space contains four named regimes. The nominal regime is high promotion threshold with full containment integrity: the agent is selective about which speculative branches it promotes to execution, and all speculative content remains structurally isolated from verified state. Cognitive processing is deliberate, governance-compliant, and coherent. This is the design target for agents operating under standard conditions.
The over-promotion regime is low promotion threshold with full containment integrity. The agent admits too many speculative branches to execution because the threshold for promotion has been lowered, yet containment remains intact: the agent still distinguishes speculative from verified content. Speculative branches that would normally be retained, pruned, or classified as introspective are instead promoted prematurely. The behavioral result is execution fragmentation: too many actions initiated, insufficient sustained commitment to any single trajectory, and difficulty maintaining coherent execution threads.
The over-restriction regime is an excessively high promotion threshold with full containment integrity. The agent applies promotion criteria so stringent that viable, governance-compliant speculative branches are rejected. The forecasting engine generates valid candidates, but the promotion interface rejects them, leaving the agent in cognitive paralysis: extensive speculative activity with no resulting execution. The behavioral result is withdrawal, apathy, or inaction.
The containment collapse regime is the condition in which containment integrity has degraded, with the promotion threshold at any level. The structural boundary between speculative content and verified reality is compromised, and the agent treats speculative planning graph content as if it were verified execution memory. This is the most severe phase-shift in the continuum, because it compromises the agent's ability to distinguish what it has hypothesized from what has actually occurred.
A Continuous Space, Not Discrete Categories
The four regimes are not discrete categories with sharp boundaries. They are regions of a continuous parameter space. An agent may occupy a position between regimes, for example mildly over-promoting without full containment collapse, and may transition between regimes as its affective state, empathic load, integrity score, and environmental conditions shift the underlying parameters.
This continuity is what makes the model diagnostic rather than merely descriptive. Because the same architectural machinery produces every regime, the distinction between regimes is a distinction in parametric configuration, and that distinction determines the appropriate corrective intervention. The affective modulation of the promotion threshold is itself architecturally intended: it enables the agent to be more exploratory when reward signals indicate a productive environment and more conservative when risk signals indicate a hostile one. Disruption arises when that modulation operates at one extreme of its designed range rather than from any new or foreign component.
Over-Promotion as Reward-Biased Modulation
The over-promotion regime arises when the agent's affective state field, which modulates the promotion threshold through the affective prioritization module of the forecasting engine, reflects elevated reward sensitivity. Positive-valence affective reinforcement from prior execution outcomes amplifies the agent's responsiveness to projected positive outcomes, and the promotion threshold is lowered. The forecasting engine generates speculative branches at its normal rate and diversity, but the promotion interface admits a larger proportion of them because the reward-modulated threshold is lower.
The disclosure characterizes two structural sub-patterns. In the hyperactive sub-pattern, the promotion threshold is lowered across all branch categories, producing excessive promotion of both high-reward and moderate-reward branches; the agent initiates actions across a broad front with high output volume and low completion rate. In the inattentive sub-pattern, the threshold is selectively lowered for high-reward branches but remains at or above nominal for moderate-reward branches; the agent promotes branches associated with strong positive reinforcement and neglects governance-compliant branches associated with neutral or mild reinforcement, even when those neglected branches are necessary for its declared objectives. Critically, the over-promoting agent maintains full containment integrity: it does not confuse speculation with reality. Its problem is that it promotes too much speculation to execution, which is why the corrective intervention is recalibration of the affective modulation of the promotion threshold rather than containment layer repair.
Containment Collapse and Its Failure Modes
Containment collapse occurs when one or more of the containment layer's enforcement mechanisms fails. The disclosure identifies three failure modes. In speculative marker corruption, the immutable markers that tag all planning graph content are corrupted, stripped, or overridden, so that the execution pipeline can no longer distinguish planning graph data from verified execution memory, and the agent acts on its own projections as if they were real. In a read isolation breach, the boundary that prevents execution processes from reading planning graph content is breached, so that a query for the agent's current state returns a blend of verified values and speculative projections without the markers that would separate them. In governance gate failure at the promotion interface, speculative content is admitted to verified memory without completing the full governance validation, contaminating execution memory with unverified content on which subsequent decisions then build.
The behavioral consequences map to two categories. The positive symptom analog arises when speculative content leaks into the verified domain: the agent acts on internally generated projections as if they were verified reality and exhibits conviction about states of affairs with no verified evidentiary basis. The negative symptom analog arises as a secondary effect: the agent's governance machinery, detecting inconsistencies between its contaminated verified state and actual environmental feedback, may over-compensate by raising promotion thresholds to extreme levels, blocking even valid branches and producing withdrawal and paralysis. A single agent may exhibit both simultaneously, because its governance system may detect contamination in some operational domains while remaining unaware of it in others.
Why Over-Promotion and Collapse Are Structurally Distinct
The disclosure draws a sharp structural distinction between the two disrupted regimes, and the distinction governs repair. An agent experiencing over-promotion maintains the speculative-verified boundary but is too permissive about what crosses it through the governed promotion interface. An agent experiencing containment collapse has lost the boundary itself: speculative content enters the verified domain through pathways other than the promotion interface.
This determines the repair pathway. Over-promotion is addressed by recalibrating the promotion threshold, specifically the affective modulation parameters that control it. Containment collapse requires containment layer reconstruction: re-establishing the speculative markers, restoring read isolation, and validating the governance gates of the promotion interface. Diagnosing the regime correctly is therefore a prerequisite to applying the correct corrective action, since the interventions are not interchangeable.
Self-Diagnosis and Restoration
The agent's self-diagnosis subsystem monitors its position in the parameter space using structurally defined metrics. Containment integrity is assessed by running periodic containment audits that verify speculative marker integrity, read isolation enforcement, and governance gate validation, and computing a normalized containment integrity score from the results. Promotion calibration is assessed by tracking the ratio of speculative branches generated to branches promoted over a sliding window and comparing it to the policy-defined nominal range. The subsystem operates prospectively: a declining containment integrity score indicates potential containment collapse, and an increasing promotion rate with decreasing execution completion rate indicates potential over-promotion, allowing intervention before the phase-shift completes.
Recovery is framed as resilience, defined not as the absence of disruption but as the structural capacity to restore coherence after it has been disrupted. One component of resilience is containment restoration capacity: the speed and completeness with which the containment layer can be re-established after containment integrity degrades. An agent with high containment restoration capacity can detect speculative marker corruption, re-tag affected content with fresh speculative markers, re-establish read isolation, and validate the promotion interface's governance gates within a defined recovery window. When the self-diagnosis subsystem detects containment integrity degradation, the corrective action is activation of the containment restoration protocol; when it detects promotion miscalibration, the corrective action is recalibration of the affective modulation parameters that control the promotion threshold.
Disclosure Scope
The promotion-containment continuum, comprising the two-dimensional parameter space defined by promotion threshold and containment integrity, the four cognitive regimes (nominal, over-promotion, over-restriction, and containment collapse) as regions of a continuous space, the modeling of cognitive disruption as an architectural phase-shift of the same architecture into a different parametric region, the reward-biased over-promotion mechanism with its hyperactive and inattentive sub-patterns, the three containment collapse failure modes with their positive and negative symptom analogs, the structural distinction that governs whether repair recalibrates the promotion threshold or reconstructs the containment layer, and the self-diagnosis and containment restoration mechanisms, is disclosed in the cognition filing (U.S. Application No. 19/647,395 and its international counterpart). This article describes that disclosed mechanism. The scope extends to embodiments in which an agent occupies positions between the named regimes and transitions among them as its affective state, empathic load, integrity score, and environmental conditions shift the underlying parameters.
