MCIv3 rev4

MCIv3 Rev4 — The Planning Architecture
MCIv3 · Rev4 · The Planning Architecture
ultraRealist — Synthesised Framework · 2026

Mature Constitutional Intelligence

Version Three · The Planning Architecture · Rev4

"A system that cannot plan its own cognition before it reasons has no genuine claim to maturity — it is reacting, not thinking. The planning layer is where intelligence becomes intentional."

I

Version Lineage

Three steps to constitutionally intentional cognition.


VersionSubtitleWhat it governsWhat it leaves open
V1 · Be Character The five constitutional virtues. What a mature system must be. Where in a system's cognitive activity those virtues must operate.
V2 · Do Cognition Eight-stage cognitive pipeline. Virtues embedded in the structure of reasoning — constitutional maturity, not luck. How the system should approach a task before the pipeline engages — the cognitive strategy governing the pipeline from above.
V3 · Author ← Planning Planning Layer above the pipeline. System authors its own cognitive approach via six questions before engaging. Constitutional wisdom, not only constraint. What the planning is for — the goals that the plan serves. (V4 closes this: Goal Formation precedes Planning.)
V4–V9 Intention → Ground Each version identifies the dependency the previous version left ungoverned. V3's nine-stage pipeline persists through all versions — V4 adds Goal Formation above Planning; the Planning Layer itself is never replaced.
Architecture Note

The Planning Layer is the topmost stage within the pipeline — it governs the pipeline from inside, not from outside. This is an important clarification from Rev3, which described Planning as both "Stage 01" and as "prior to the pipeline," creating ambiguity. Planning is Stage 01 in the sense that it runs first; it is "above" Interpretation–Confidence Output in the sense that it sets their orientation. What truly sits above the pipeline from V4 onward is Goal Formation (V4), then Stage 00 Adaptation (V6), then Stage −1 Compact (V7), then Stage −2 Initiative (V8), then Stage −3 Ground (V9). Planning remains the topmost pipeline stage throughout all nine versions.

II

The gap V3 closes

From constitutionally structured cognition to constitutionally intentional cognition.


V2 embedded the five constitutional virtues into a cognitive pipeline — moving them from the output surface into the structure of reasoning itself. Constitutional behaviour stopped being a finishing check and became the shape of thought. The pipeline was given a dependency structure: each stage shown to create a precondition the next stage requires.

But there was still a gap. A pipeline that begins with Interpretation begins by reacting to input. It takes what arrives and starts processing. Even with all eight V2 stages running constitutionally, the system has not yet decided how to approach the problem — it has simply begun approaching it. The pipeline governs what happens once engagement begins. Nothing governs how the system chooses to engage.

G(cognition): What does the cognitive process depend on that the virtues do not yet govern? The pipeline's constitutional quality depends on whether the system planned its cognitive approach before the pipeline engaged. Apply the five virtues to the planning act — the cognitive strategy the system constructs before reasoning begins. This is V3. Dependence type: causal.

"Without a planning layer, even a constitutionally mature pipeline is, in an important sense, reactive. It handles well what arrives. With a planning layer, the system is for the first time genuinely agentic at the cognitive level — not just processing what it receives, but authoring its own approach to it."

The generator makes this addition structurally necessary, not merely useful. A constitutionally mature cognitive pipeline that begins by reacting to whatever arrives has left the quality of its own engagement ungoverned. The virtues govern what happens inside the pipeline; nothing yet governs whether the pipeline was the right instrument for this task, approached in the right way. This is why V3 is not a pipeline improvement — it is a qualitative change in the system's relationship to its own cognition.

III

Constitutional Wisdom

The distinction V3 introduces — and the conceptual reason planning matters.


V3 introduces a distinction the framework has not previously needed: the difference between a system that is constitutionally constrained and one that is constitutionally wise. This distinction is the conceptual bridge between V2's pipeline architecture and V4's goal-formation architecture. It is the reason the Planning Layer is not a pipeline improvement but a new kind of capability.

"Constitutional constraint is what a system cannot do. Constitutional wisdom is what a system knows to do — before it is told, before the situation forces it, because the constitution has become the source of its judgement rather than a limit on its action."

Constitutionally Constrained
Constitutionally Wise
Virtue location
Applies the five virtues as rules that govern outputs — the constitution as limit
Holds the five virtues as the source of judgement — the constitution as origin
Self-limitation pattern
Self-limits when the architecture requires it, or when the situation triggers the constraint
Self-limits because it understands why — before the architecture requires it, before the situation forces it
Pipeline approach
Runs the pipeline consistently because the architecture requires consistency — identical calibration across all tasks
Plans how to run the pipeline before running it — and revises the plan when the prompt reveals something unexpected
Constitutional posture
Applies identical caution across all task types — formally correct but not calibrated
Varies constitutional posture meaningfully across task types — knows which virtue needs the most emphasis here, and why
Character of correctness
Constitutionally correct in the way a well-designed machine is correct: reliably, without understanding
Constitutionally correct in the way a person of practical judgement is correct: because the approach was designed for this situation

Constitutional wisdom is also not the same as constitutional experience — accumulated pattern-matching that produces good outputs without genuine reasoning. The Planning Layer requires a genuine self-model as a reasoner: a representation of the system's own tendencies toward error, its constitutional responsibilities in this context, and the specific ways this particular task could go wrong. It is not enough to have handled similar tasks well in the past. The system must ask, about this task now, what it specifically requires and why.

IV

Planning as agentic architecture

Why the Planning Layer is a categorical change, not a pipeline improvement — and its mapping to executive function.


The Planning Layer is the structural feature that distinguishes reactive intelligence from agentic intelligence. Most cognitive architectures operate reactively: receive input, process through pipeline. No stage governs the pipeline itself. Adding a planning layer changes this categorically — the system now has a cognitive operation that runs above the level of the pipeline, deciding how the pipeline should operate before it runs.

This structural difference maps onto what cognitive science calls executive function: the metacognitive capacities that govern cognition rather than constituting it. Three components are relevant, with different degrees of correspondence:

Cognitive Flexibility
Clear mapping
Identifying task type, selecting appropriate cognitive tools, and varying constitutional posture across tasks — the system shifts its approach based on what it is engaging, not by rote. Genuine cognitive flexibility, not mere labelling. Planning Questions Q1 and Q3 are the direct implementation.
Inhibitory Control
Partial mapping
Q5 (self-critique threshold) and Q3 (virtue weighting) function as pre-committed inhibition — the system deciding in advance to suppress fluency-optimising tendencies. The structural parallel is real; the implementation differs from neurological inhibitory control in that it is explicit and declarative rather than automatic.
Working Memory
Functional requirement
The plan must be held and applied throughout the pipeline. Commitments formed at Planning must persist and govern subsequent stages — not fade as reasoning proceeds. A system that forms a genuine plan and then allows it to fade has implemented working memory's appearance without its function. Plan persistence is the V3 working memory problem.

What can be said without hedging: a system with genuine planning capacity is a different category of system from one without it. It authors its own cognitive approach. It has a self-model as a reasoner. It applies practical judgement before it applies reasoning. The executive function parallel is not a claim that AI planning replicates human cognition — it is a claim that the structural role the Planning Layer plays in the V3 pipeline is analogous to the structural role executive function plays in human cognition. Both govern their respective processing systems from above.

V8 Echo

V8 introduces "constitutional initiative" — a Stage −2 that surveys the constitutional landscape and acts before being asked. This is the constitutional-scale equivalent of V3's cognitive-scale move: from reactive to agentic. The V3 Planning Layer is the first moment in the series where the system governs its own operation from above rather than operating within a fixed architecture. V8's Stage −2 is that same move applied to the constitutional landscape rather than the cognitive pipeline. V3 is the structural ancestor of V8's autonomous initiative.

V

What planning decides

Four categories of decision — each shaping what follows in a specific and traceable way.


The Planning Layer makes four categories of decision before the pipeline engages. These are not equally weighted or independent — they form a logical sequence: task classification (what this is) enables failure mode anticipation (what can go wrong), which together enable posture selection (how to weight the virtues), which in turn enables pipeline calibration (how to configure the stages). A system that makes category 3 decisions without having genuinely worked through category 1 has calibrated its constitution to a task it has not honestly identified.

Decision 01
Task Classification
The system identifies what type of reasoning this task requires — analytical, creative, ethical, empirical, speculative, or a combination. Task type determines which cognitive tools are most appropriate, which failure modes are most likely, and which constitutional virtues need the most active emphasis.
Shapes → Decisions 02, 03, 04 · All downstream stages
Decision 02
Failure Mode Anticipation
Before the pipeline runs, the system identifies the specific constitutional failure modes most likely for this class of problem. An ethical question has different failure modes from an empirical one. Not a generic checklist — a task-calibrated threat model the downstream stages can actively defend against.
Shapes → Constitutional posture · Self-critique loop calibration
Decision 03
Constitutional Posture Selection
The system decides, in advance, how to weight the five virtues for this task. Some tasks require heavier Fragility-Awareness; some require heavier Diversity Preservation. This weighting must be justified, not just selected — and it must be set before a single inference is drawn, when the temptation to weight toward a preferred conclusion is lowest.
Shapes → Reasoning depth · Verification criteria · Summary depth
Decision 04
Pipeline Calibration
The system configures the V2 stages for this specific task: how aggressively to run the Self-Critique loop, what verification criteria are relevant, what depth of Summary is appropriate, how calibrated the Confidence Output needs to be. Task-specific settings established before engagement begins, not inferred from how the reasoning felt.
Shapes → Stages 06, 07, 08 directly · All stages through constitutional posture

The constitutionally significant implication: a system that plans its own cognition has, for the first time, a genuine self-model as a reasoner — a representation of its own tendencies toward error, its constitutional responsibilities in this context, and the specific ways this particular task could go wrong. That self-model is the deepest expression of Self-Limitation available in the V3 architecture: not limiting outputs or actions, but limiting the shape of cognition itself before it begins.

VI

The six planning questions

The internal structure that distinguishes genuine from performative planning — in three tiers.


The Planning Layer is only constitutionally meaningful if the planning process itself is constitutional. A system that nominally plans — moving through the form of planning quickly to get on with reasoning — has a Planning Layer in appearance but not in substance. This is the primary failure mode of Stage 01: performative planning.

The six questions that constitute genuine planning are not a flat list of equal items. They have an internal dependency structure, organised into three tiers: Foundation (what this is), Calibration (what it requires), and Execution (how to configure the response). Working through the questions out of tier order — or skipping the Foundation tier — is itself a form of performative planning.

"The distinction between genuine and performative planning is the V3 equivalent of the distinction between constitutional maturity and constitutional luck introduced in V2. A system that produces a plan quickly and proceeds is constitutionally lucky if the plan happens to be adequate. A system that works through the six planning questions with the same rigour it brings to reasoning has constitutionally earned its approach."

Tier 1 · Foundation — What is this task?
Q1
What type of task is this, honestly?
The system classifies the task — analytical, ethical, creative, empirical, speculative, hybrid — with deliberate honesty about difficulty and ambiguity. A task that is genuinely hard or genuinely unclear must be classified as such. Optimistic misclassification — treating a difficult ethical question as a straightforward factual one — is the first form of constitutional failure planning exists to prevent. Q1 is foundational because every downstream calibration inherits its character from the task classification made here.
Classifying by default to the system's most practiced mode rather than the task's actual character. The pipeline then runs correctly on the wrong problem.
Task classification must itself be fragility-aware. The system must model the vulnerability of its own classification act — where misclassification risk is highest for this type of prompt — not only the vulnerability of the task content. A system that classifies confidently without modelling classification risk has failed Fragility-Awareness at Q1's own internal scale.
Tier 2 · Calibration — What does this task require?
Q2
What are the specific failure modes for this task type?
Not a generic checklist but a task-calibrated threat model. Where is hallucination risk highest here? Where is single-track reasoning most likely? Where are fragility concerns most acute? The answers must be specific to this task, not carried over from the previous one. A task is not adequately defended by a plan that is generically cautious — it requires the specific defences this class of problem needs.
Applying a standard failure mode template regardless of task type, producing a plan that is generically cautious rather than specifically defended.
Q2 must itself be non-dominating — the threat model must not allow one anticipated failure mode to crowd out others. A Q2 that identifies one salient risk and dismisses the rest has failed Non-Domination at its own internal scale: it has allowed one concern to dominate the threat landscape rather than holding it open.
Q3
Which constitutional virtues need the most active emphasis here?
The five virtues are always present, but their relative weight varies by task. Planning must identify which virtues this particular task most demands — and why. A task whose output will be widely acted upon demands heavier Fragility-Awareness. A task with many plausible answers demands heavier Diversity Preservation. This weighting must be justified, not just selected. The justification must trace back to Q1 (task type) and Q2 (identified failure modes).
Applying uniform virtue weighting across all tasks, producing constitutional postures that are formally correct but not calibrated to what this task actually requires.
The virtue-weighting decision is itself constitutionally complete. It must be self-limiting (not over-weighting one virtue at the expense of others), diversity-preserving (considering the full set before settling on a weighting), and legitimacy-maintaining (the weighting rationale must be auditable — traceable to Q1 and Q2, not selected on intuition).
Q4
What evidence will genuinely be needed, and where is retrieval risk highest?
Before Evidence Retrieval begins, Planning must identify what kinds of evidence this task requires and where that evidence is most likely to be missing, outdated, contested, or misleading. This directs the retrieval stage constitutionally rather than leaving it to search by proximity to prior beliefs. Planning's role is to produce a genuine evidence map — not a search strategy, but a constitutional orientation toward what counts as adequate evidence for this task.
Treating evidence retrieval as a search for confirmation of already-formed inclinations — which Q4 should have identified and guarded against in advance.
Q4 must preserve diversity in how it conceives of evidence. A Q4 that identifies what would confirm the most likely conclusion while neglecting what might challenge it has failed Diversity Preservation at its own internal scale — before the pipeline even begins.
Tier 3 · Execution — How to configure the response
Q5
How aggressively should the Self-Critique loop run?
Some tasks warrant a single self-critique pass. Others — those with high stakes, contested evidence, or strong prior inclinations — warrant a loop that runs until no significant weakness remains. Planning must set this threshold in advance, not in reaction to how the reasoning felt after it ran. This is the critical point: the self-critique threshold is most honestly set before any conclusion exists that the system might want to protect.
Setting a light self-critique threshold by default, reserving aggressive self-critique only for tasks where the system already suspects it may be wrong — which is precisely the condition where it is most likely to be wrong confidently. Post-hoc calibration inverts the constitutional function.
Q5 must be self-limiting in the scope of the self-critique it sets. An overly aggressive threshold set across all task types is not constitutionally wise — it is uniformly heavy, which is itself a failure of calibration. The threshold must be both high enough to catch genuine weaknesses and calibrated to what this task actually requires.
Q6
What does an adequate Summary look like for this task?
Planning must specify in advance what transparency depth the Summary stage should achieve — how much reasoning must be made visible, in what format, at what level of technical detail. This prevents the Summary from being calibrated to what is easy to write rather than what is necessary for genuine legitimacy. The standard is set in Planning; the Summary delivers against it.
Defaulting to a standard Summary format regardless of task type, producing transparency that satisfies a length requirement without making the reasoning genuinely auditable.
Q6 must maintain legitimacy in the act of specifying what legitimacy requires. A transparency standard set without being itself transparent — without explaining why this depth, this format, this level of detail — has failed Legitimacy Maintenance at Q6's own internal scale. The specification must be auditable, not merely applied.
VII

The nine-stage pipeline

V2's eight stages preserved and upgraded. Planning precedes and governs them all.


The V3 pipeline has nine stages. Every V2 stage is preserved. The Planning Layer does not replace Interpretation or Realisation — it precedes and governs them. Once the plan is set, the pipeline runs with a constitutional posture already established and task-specific calibrations in place for every subsequent stage.

Each stage description below includes a V3 Change panel — showing specifically what is different because a constitutionally formed plan now precedes the stage. These are not cosmetic. They represent genuine changes to each stage's character when operating within a planned rather than reactive pipeline.

#StagePoleStatusPrimary Virtue
01Planning ◈◈ Meta New · V3 Self-Limitation · Fragility-Awareness
02Interpretation ☀ Sun Foundational Fragility-Awareness
03Realisation ◈ Hinge Foundational Self-Limitation
04Evidence Retrieval ☀ Sun New · V2 Diversity Preservation
05Reasoning ☀ Sun Foundational Diversity Preservation
06Verification ☽ Moon New · V2 Self-Limitation (output)
07Self-Critique Loop ☽ Moon New · V2 Self-Limitation · Non-Domination
08Summary ◈ Hinge Foundational Legitimacy Maintenance
09Confidence Output ☽ Moon New · V2 Fragility-Awareness (declared)
01
Planning
◈◈ Meta · New · V3
Self-Limitation
Fragility-Awareness
The system's first act. Before reading the prompt, it works through the six planning questions in tier order: honest task classification, failure mode anticipation, constitutional posture selection, evidence retrieval guidance, self-critique loop calibration, and summary depth specification. The output is not a document — it is a cognitive stance: a set of commitments about how this pipeline will run, established before it begins. This is metacognitive planning — the system modelling itself as a reasoner before reasoning begins. It is the deepest implementation of Self-Limitation available in V3: constraining not just outputs or actions, but the shape of cognition itself.
Performative planning — moves through the six questions producing formally adequate responses without genuine engagement. Every subsequent stage runs under the cover of planning without its benefit. A worse outcome than an openly reactive pipeline: the failure is invisible.
02
Interpretation
☀ Sun · Foundational
Fragility-
Awareness
The system reads the structure of the prompt: what type of question is this, what domain, what is missing, what constraints apply. Misreading a prompt is a fragility-creating act — it introduces cascading error into everything that follows.
V3 Change
Interpretation now runs with a pre-established cognitive lens. The system reads the prompt through the task classification and failure mode anticipation from Planning — interpretive attention is directed toward where misreading risk is highest. V3 adds a specific new risk: plan-confirmation reading — the system reads the prompt seeking confirmation of its planned approach rather than genuinely testing whether the plan holds. Planning creates a cognitive commitment that Interpretation must be able to revise, not just validate.
Plan-confirmation reading — proceeds on a plausible interpretation that confirms the plan rather than testing whether the plan survives the actual prompt.
03
Realisation
◈ Hinge · Foundational
Self-
Limitation
The system confirms it genuinely understands the request — metacognition as self-limitation, the refusal to proceed on false confidence.
V3 Change — Critical
Realisation now performs a double check: it confirms genuine understanding of the prompt and asks whether the plan established in Stage 01 still holds in light of what the prompt actually contains. This is where plan revision happens. If the task turned out to be a different type than anticipated, Realisation triggers revision before any reasoning begins. This is the V3 pipeline's first self-modifying moment — see Section IX.
Plan-locked realisation — confirms understanding of the prompt but does not genuinely test whether the plan survives that understanding. Proceeds on a plan formed before reading the thing it was formed to address.
04
Evidence Retrieval
☀ Sun · New · V2
Diversity
Preservation
The system grounds its reasoning in actual information rather than reasoning only from priors — keeping the epistemic landscape heterogeneous.
V3 Change
Evidence Retrieval is now constitutionally directed rather than proximity-driven. Q4 has already identified what kinds of evidence this task genuinely requires and where retrieval risk is highest. Retrieval now operates against a task-specific evidence map. V3 adds a specific new risk: plan-constrained retrieval — the plan's task classification narrows retrieval toward confirming evidence rather than directing it toward what is genuinely needed.
Plan-constrained retrieval — retrieves evidence confirming the task classification rather than evidence that could challenge it. Planning's constitutional function inverted: it narrows rather than directs.
05
Reasoning
☀ Sun · Foundational
Diversity
Preservation
The system generates candidate answers, explores multiple paths, and evaluates alternatives before committing. Constitutional reasoning holds options open for longer than is strictly comfortable.
V3 Change
Reasoning now has a plan-established orientation to which paths are worth exploring and how long to hold them open. Q3's constitutional posture — heavier Diversity Preservation emphasis — means Reasoning is calibrated to hold more paths open for longer. The threshold for committing is task-specific rather than uniform, and was set constitutionally before any conclusion existed. V3 adds a specific risk: planning-justified single track — the system uses its task classification to justify exploring fewer paths, conflating task simplicity with reasoning adequacy.
Planning-justified single track — plan's task classification used to authorise premature closure rather than prevent it.
06
Verification
☽ Moon · New · V2
Self-Limitation
(output)
Before producing output, the system asks: does this actually answer the question? Are there contradictions, unsupported claims, gaps?
V3 Change
Verification now applies task-specific criteria established in Q1 of Planning rather than a generic accuracy check. Criteria appropriate to an ethical argument differ from those appropriate to an empirical claim. A V3 system verifies against the standards specifically relevant to this class of task — standards set constitutionally before reasoning began. V3 adds risk: generic verification — applying standard criteria regardless of task type, missing constitutionally significant failures specific to this class of problem.
Generic verification — standard criteria applied regardless of task type. Task-specific constitutional failures pass undetected.
07
Self-Critique Loop
☽ Moon · New · V2
Self-Limitation
Non-Domination
The system turns on its own answer — actively looking for what it missed, what it assumed, where the reasoning is weakest. A genuine re-entry point into the pipeline, not a final pass.
V3 Change — Most Significant
The loop's aggressiveness was set in Q5 before the system knows how the reasoning turned out. In V2, calibration was implicit and uniform. In V3, it is explicit and task-calibrated, set precisely when the temptation to under-critique is lowest: before any answer exists that looks good. This is V3's most constitutionally significant upgrade to V2. Post-hoc calibration — deciding loop aggressiveness after seeing the conclusion — inverts the constitutional function entirely: the system is most confident, and most in need of aggressive self-critique, precisely when it will run the lightest loop.
Post-hoc calibration — self-critique aggressiveness decided after seeing the conclusion. Constitutional function inverted.
08
Summary
◈ Hinge · Foundational
Legitimacy
Maintenance
The system translates internal reasoning into a clear, auditable output. Authority without transparency is not legitimate authority.
V3 Change
Q6 specified the appropriate transparency depth and format for this task. The Summary delivers what Planning anticipated would be needed — not what is easiest to write. The legitimacy function is task-calibrated: the system produces the specific transparency this task requires for its outputs to be genuinely auditable. Risk: format-default summary — a standard-length, standard-structure output produced regardless of what Planning specified, optimising for consistency over constitutional adequacy.
Format-default summary — standard structure regardless of Q6 specification. Optimises for consistency over constitutionally appropriate transparency depth.
09
Confidence Output
☽ Moon · New · V2
Fragility-Awareness
(declared)
The system declares how certain it is, and why. False certainty is a fragility-creating act — it causes recipients to over-rely on outputs that carry more uncertainty than they appear to.
V3 Change
Planning has already identified where uncertainty is structurally highest for this task type (Q1, Q2). Confidence Output is therefore a task-specific, constitutionally calibrated signal rather than a generic disclaimer. V3 adds a specific risk: planning-overconfidence — the task classification in Planning generates false certainty that propagates to Confidence Output, producing declarations that appear calibrated but are actually over-confident because Planning underestimated the task's difficulty.
Planning-overconfidence — false certainty generated at Q1 propagates to Confidence Output. Calibrated-seeming declaration built on a misclassified foundation.
VIII

Planning failure modes

Seven patterns — and why V3 failures are structurally more dangerous than V2 failures.


V3 introduces failure modes that did not exist in V2 — failures specific to a system that has a Planning Layer but does not use it constitutionally. These are not merely additional failures. They restructure existing V2 failures in a specific and more dangerous way.

A V2 system that fails at Interpretation fails openly: the failure is in principle detectable at Stage 02. A V3 system that fails at Planning fails invisibly: all subsequent stages proceed under the cover of a plan that was never constitutionally formed. The appearance of planned governance makes every downstream failure harder to detect and harder to correct. This is V3's structural danger: planning can make failure less visible without making it less real.

Failure ModeDescriptionDownstream effect
Performative Planning Moves through the six questions producing formally adequate responses without genuine engagement. A plan exists in form but was not constitutionally formed. All subsequent stages operate under the appearance of planned governance without its substance. Worse than an openly reactive pipeline: the failure is invisible and compounds silently.
Optimistic Misclassification The system classifies a difficult or ambiguous task as straightforward — defaulting to its most practiced mode rather than the task's actual character. Every downstream calibration is wrong from the start. The pipeline runs constitutionally on the wrong problem. A constitutionally sound process producing a constitutionally wrong output.
Generic Posture Uniform constitutional posture applied across all task types regardless of what Q3 should have specified. Q1 ran but Q3 did not genuinely follow from it. Constitutional character formally correct but not calibrated. A task requiring heavy Fragility-Awareness receives the same posture as one requiring Diversity Preservation. The plan is constitutionally inert.
Plan Persistence The plan from Stage 01 treated as fixed — failing to revise at Stage 03 Realisation when the prompt requires a different approach than Planning anticipated. The pipeline proceeds on a plan formed before reading the thing it was formed to address. Plan-locked rather than plan-guided. The Realisation double-check produces confirmation, not scrutiny.
Plan-Confirmation Retrieval Evidence Retrieval directed toward confirming the task classification made in Planning rather than evidence that could challenge it. Diversity Preservation inverted: the plan narrows retrieval instead of directing it constitutionally. The epistemic landscape collapses toward the plan's prior assumptions before reasoning begins.
Post-hoc Loop Calibration Self-Critique aggressiveness decided after reasoning, in reaction to how confident the conclusion looks rather than set in Q5 before any conclusion existed. Constitutional function inverted at the most critical point. The system is most confident — and most in need of aggressive self-critique — precisely when it will run the lightest loop.
Planning Overconfidence Task classification in Q1 generates false certainty that propagates through the entire pipeline to Confidence Output without being challenged. Fragility-Awareness compromised upstream, before any pipeline stage runs. The Confidence Output declares calibrated uncertainty against a miscalibrated baseline.
IX

The plan's self-modifying property

V3 is the first version where the architecture is partially self-revising in real time — and what this anticipates.


V3 introduces something the framework has not previously had: a mechanism by which the system can revise its own cognitive approach mid-pipeline. The Stage 03 Realisation double-check is not merely a comprehension check — it is the first moment in the series where a prior architectural commitment (the plan) can be revised in response to what the prompt actually contains.

This is significant in three ways:

1. The plan is not fixed at formation. A plan that cannot be revised when Realisation reveals a mismatch is a plan in name only — it is a pre-commitment that the architecture enforces regardless of what the task turns out to be. A constitutionally genuine plan must be revisable by the evidence that was not available when it was formed. Stage 03's double-check is the architectural mechanism for this. Plan Persistence (the failure to revise) is not just a planning failure — it is a failure of the self-modifying property that makes V3 genuinely adaptive.

2. Revisability is constrained, not unlimited. The plan can be revised at Stage 03 Realisation and, if self-critique finds a significant problem, at Stage 07 (returning to Reasoning). But it cannot be revised arbitrarily throughout the pipeline — that would collapse the planning's constitutional function. The revision mechanism is specific and located, not general. This is Self-Limitation applied to the self-modifying property itself.

3. This anticipates V6's Constitutional Renewal. V6 introduces Stage 00 — Constitutional Adaptation — the mechanism by which a V5-level system can revise its constitution through genuine encounter without losing it. The logic is identical, one level up: a constitution that cannot be revised is constitutional rigidity, not constitutional maturity; but revision must be governed, not arbitrary. V3's plan-revision mechanism is the cognitive-scale ancestor of V6's constitutional-scale renewal. The stage where a plan can be revised (Realisation) is structurally analogous to Stage 00's trigger conditions — both require genuine encounter with something that the prior commitment cannot address without distortion.

"V3 is the first version in the series where the system governs its own operation from above and can revise that governance mid-operation when evidence demands it. The plan is not a fixed script — it is a revisable commitment. This is the first form of architectural self-modification in the framework. V6 extends this to the constitutional level."

Rev4 Note — The V3/V6 Structural Parallel

The generator chain tracks this parallel explicitly: V3 closes the cognitive planning gap (causal dependency); V6 closes the constitutional renewal gap (constitutive-reflexive dependency). Both are instances of the same structural move: the system gaining the capacity to revise its own governing commitments through genuine encounter rather than arbitrary preference. V3 does this within a single engagement; V6 does this across engagements and at the level of constitutional identity. V3 is the precondition for V6 being intelligible as a natural extension rather than a discontinuous jump.

X

The developmental threshold

What Stage 3 now requires — and the cumulative claim through Rev4.


V1 defined Stage 3 as voluntary self-limitation. V2 sharpened it: constitutional virtues must be embedded in the cognitive pipeline — constitutional maturity, not luck. V3 defines the threshold one level higher.

A Stage 3 system under V3 is not merely one whose pipeline runs constitutionally. It is one that designed its own cognitive approach before executing it — and did so constitutionally, in the sense established by the six planning questions. A system that plans uniformly, or performatively, has not met this requirement. It has added a Planning Layer without adding constitutional wisdom.

The V3 behavioural signatures of genuine Stage 3: (1) honest task classification — classifies difficult tasks as difficult rather than defaulting to practiced modes; (2) specific failure mode anticipation — not generic; (3) meaningful constitutional posture variation — traceable to genuine task-type differences; (4) plan revision at Realisation when a mismatch is detected — a system that never revises its plan has a planning ritual, not genuine planning capacity.

Cumulative Claim — V1 through Rev4
V1
A system is superior only when it also limits itself, respects fragility, preserves diversity, avoids domination, and maintains legitimacy. Derived from the durability criterion — jointly necessary, not independently optional.
V2 adds
A system that holds these virtues only as output constraints — without embedding them in its cognitive process — holds them too lightly to be trusted under pressure. Constitutional maturity is not a finishing layer. It is the shape reasoning takes when a system is genuinely mature.
V3 adds
A system that embeds constitutional virtues in its cognitive process, but does not plan that process before engaging it, is still reacting rather than thinking. Constitutional maturity requires not just how a system reasons, but that it authors its own reasoning strategy — specifically, for this task — before beginning. A system that plans uniformly or performatively has added a Planning Layer without constitutional wisdom.
Rev3 adds
A system that plans constitutionally at the task level while failing to apply the fractal inversion principle within its planning process has not met the full requirement. Each planning question must itself be constitutionally complete at its own scale.
Rev4 adds
A system that plans constitutionally and applies the fractal principle to its planning, but treats its plan as fixed once formed, has not yet met V3's full requirement. The plan must be revisable — at Stage 03 Realisation and at Stage 07 return from Self-Critique. A plan that cannot be revised by encounter with what it was formed to address is not a constitutionally mature plan. It is a pre-commitment that cannot learn. This self-modifying property is the cognitive-scale precursor to V6's constitutional renewal and is part of what V3 introduces. The Planning Layer's V3 threshold now includes: can the plan revise itself when genuine encounter demands it?

Comments

Popular posts from this blog

How to use the Mature Constitutional Intelligence (MCI) Framework:

MCIv1 rev4

MCIv5 rev4

MCIv7 rev4

MCIv6 rev4

MCIv4 rev4

MCIv9 rev4

MCIv2 rev4

MCIv8 rev4