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.

cmd/noemad/main.go

@@ -197,7 +197,7 @@ func run() error {
 		Motivation: deps.Motivation, Narrative: deps.Narrative, Notifications: deps.Notifications})
 	brainCfg := brain.Config{DB: db, Events: deps.Events, Minds: deps.Minds, Registry: registry, Pool: scheduler.NewPool(cfg.MaxWorkers),
 		Log: log, Metrics: metrics, Services: brain.Services{Events: deps.Events, Memory: deps.Memory, Beliefs: deps.Beliefs, LLM: deps.LLM, Prompts: deps.Prompts,
-			Goals: deps.Goals, Motivation: deps.Motivation, Predictions: deps.Predictions, Capabilities: deps.Capabilities, Volition: deps.Volition, Plans: deps.Plans, Executor: deps.Executor},
+			Goals: deps.Goals, Motivation: deps.Motivation, Predictions: deps.Predictions, Capabilities: deps.Capabilities, Volition: deps.Volition, Plans: deps.Plans, Executor: deps.Executor, Minds: deps.Minds},
 		AfterCommit: deps.Executor.WakeOn()}
 	deps.Brain = brain.NewManager(brainCfg, group)
 	// Sandbox runtimes (replay, experiments) share the registry but use a
@@ -214,7 +214,7 @@ func run() error {
 	deps.Snapshots = &snapshots.Store{DB: db, Events: deps.Events, Minds: deps.Minds, Identity: ident}
 	deps.Privacy = &privacy.Service{DB: db, Events: deps.Events, Audit: auditLog, Snapshots: deps.Snapshots, Log: log}
 	deps.Replay = &replay.Service{DB: db, Events: deps.Events, Minds: deps.Minds, Snapshots: deps.Snapshots, Brain: sandboxCfg, Identity: ident, Log: log}
-	deps.Experiments = &experiments.Service{DB: db, Minds: deps.Minds, Snapshots: deps.Snapshots, Brain: sandboxCfg, Identity: ident, Log: log, Routing: func(ctx context.Context) []map[string]any {
+	deps.Experiments = &experiments.Service{DB: db, Minds: deps.Minds, Snapshots: deps.Snapshots, Brain: sandboxCfg, Identity: ident, Log: log, Capabilities: deps.Capabilities, Routing: func(ctx context.Context) []map[string]any {
 		roles, _ := deps.LLMStore.ListRoles(ctx)
 		b, _ := json.Marshal(roles)
 		var out []map[string]any