feat(research): ablations, broadcast and self-model experiments, counterfactuals

A framework for testing functional properties of the architecture
(Part C). None of it claims consciousness; every measure has an
operational definition in research.Measures.

- Ablations (attention, memory retrieval, affect, metacognition,
  commitments, volition, global workspace, curiosity, association, goals,
  narrative, notifications) and workspace overrides (force a matching
  candidate in or out of admission) live in a fork's cognitive
  configuration. Original minds refuse them on create and update; only
  snapshot restores may carry them, so they are part of the configuration
  digest. Excluded candidates are recorded with fate "excluded".
- Self-model experiments override a fork's self-model (capabilities,
  identity, goals, knowledge gaps) without touching policy. When an
  action's effective policy disagrees with the self-model, cognition
  records a self_model_mismatch and corrects the entry; experiments report
  self-model accuracy and correction latency.
- Counterfactual experiments replay a mind's recorded stimuli from a
  snapshot with chosen events omitted; the report lists what differed in
  beliefs, wants, intentions, memories, attention and capability
  decisions, in a form introspection can cite.
- Experiments record a protocol (kind, independent variable, controlled
  variables, measures), per-variant volition, plan, downstream-by-category
  (events reachable from each stimulus through recorded links),
  introspection and self-model measures and event ranges; comparisons add
  want, intention and plan-capability overlap, measure ranges, a
  descriptive architecture share and a downstream delta; reproducibility
  is labelled against the previous run of the same definition.
- research.Agency computes want→intention, intention→action, abandonment,
  commitment fulfilment and conflict, blocked intentions, replanning,
  outcome success and introspection accuracy; MetacognitiveCalibration
  relates confidence and expressed uncertainty in replies to later belief
  revision, with Brier scores for each half of the period.
- The sandbox test harness gains volition, planning, agency and research
  but not the motivation hook, whose wall-clock decay would make replay
  comparisons timing-dependent.

internal/minds/config.go

@@ -2,6 +2,7 @@ package minds
 
 import (
 	"fmt"
+	"strings"
 	"time"
 )
 
@@ -51,6 +52,53 @@ type CognitiveConfig struct {
 	// Ablations disable named cognitive components in a research fork
 	// (docs/cognitive-research.md). Only forks may carry them.
 	Ablations []string `json:"ablations,omitempty"`
+	// WorkspaceOverrides force candidates matching a text into or out of the
+	// global workspace in a research fork, for broadcast experiments.
+	WorkspaceOverrides []WorkspaceOverride `json:"workspace_overrides,omitempty"`
+}
+
+// WorkspaceOverride is one experimental manipulation of admission.
+type WorkspaceOverride struct {
+	Match string `json:"match"` // case-insensitive text in the candidate summary or its triggering event
+	Fate  string `json:"fate"`  // admit | exclude
+}
+
+// Ablations is the closed vocabulary of components a research fork may
+// disable, with what disabling means operationally.
+var Ablations = map[string]string{
+	"attention":        "every attention feature weight is 1 and drives do not modulate weights: admission no longer prioritises by learned weighting",
+	"memory_retrieval": "the retrieval process proposes no recalled memories",
+	"affect":           "drives and affect are neither updated by events nor used to modulate attention",
+	"metacognition":    "no self-checks are proposed",
+	"commitments":      "commitments do not shape formation, reconsideration or metacognition",
+	"volition":         "no wants are derived and no intentions are formed",
+	"global_workspace": "nothing persists in the workspace or working memory between cycles and nothing is broadcast; each admitted thought is handled in isolation",
+	"curiosity":        "the curiosity process proposes no questions",
+	"association":      "the association process proposes no hypotheses",
+	"goals":            "the goal monitor raises no stalled or relevant goals",
+	"narrative":        "the narrative is not updated",
+	"notifications":    "no notifications are raised",
+}
+
+// ResearchSettings reports whether the configuration carries research
+// manipulations that only forks may have.
+func (c CognitiveConfig) ResearchSettings() bool {
+	return len(c.Ablations) > 0 || len(c.WorkspaceOverrides) > 0
+}
+
+// ValidateResearch checks ablation names and override fates.
+func (c CognitiveConfig) ValidateResearch() error {
+	for _, a := range c.Ablations {
+		if _, ok := Ablations[a]; !ok {
+			return fmt.Errorf("unknown ablation %q", a)
+		}
+	}
+	for _, o := range c.WorkspaceOverrides {
+		if strings.TrimSpace(o.Match) == "" || len(o.Match) > 200 || (o.Fate != "admit" && o.Fate != "exclude") {
+			return fmt.Errorf("workspace override needs a match (≤200 chars) and fate admit or exclude")
+		}
+	}
+	return nil
 }
 
 // Ablated reports whether a component is disabled in this configuration.

internal/minds/store.go

@@ -89,6 +89,9 @@ type CreateParams struct {
 	Config      *CognitiveConfig
 	Notes       string
 	CreatedBy   string
+	// Research allows ablations and workspace overrides; only snapshot
+	// restores (forks, imports of research forks) set it.
+	Research bool
 }
 
 // Create inserts a mind with personality version 1 and an initial self-model.
@@ -127,6 +130,12 @@ func (s *Store) Create(ctx context.Context, p CreateParams) (Mind, error) {
 		cfg = *p.Config
 	}
 	cfg.Normalise()
+	if cfg.ResearchSettings() && !p.Research {
+		return Mind{}, fmt.Errorf("%w: ablations and workspace overrides are only allowed on research forks, never on an original mind", ErrInvalid)
+	}
+	if err := cfg.ValidateResearch(); err != nil {
+		return Mind{}, fmt.Errorf("%w: %v", ErrInvalid, err)
+	}
 	m := Mind{ID: ids.New(), Slug: p.Slug, DisplayName: p.DisplayName, Status: StatusActive, Config: cfg, Notes: p.Notes,
 		PersonalityVersion: 1, Personality: pers, TemplateID: p.TemplateID, CreatedAt: time.Now(), UpdatedAt: time.Now()}
 	err := storage.Tx(ctx, s.db, func(tx pgx.Tx) error {
@@ -237,6 +246,12 @@ func (s *Store) Update(ctx context.Context, id ids.ID, p UpdateParams) (Mind, er
 	if p.Config != nil {
 		c := *p.Config
 		c.Normalise()
+		if c.ResearchSettings() && m.ForkedFromSnapshot == nil {
+			return Mind{}, fmt.Errorf("%w: ablations and workspace overrides are only allowed on forks, never on an original mind", ErrInvalid)
+		}
+		if err := c.ValidateResearch(); err != nil {
+			return Mind{}, fmt.Errorf("%w: %v", ErrInvalid, err)
+		}
 		m.Config = c
 	}
 	cfgJSON, _ := json.Marshal(m.Config)