This is the current forward plan for the next larger organs. It is not a changelog and it is not allowed to become a duplicate brain for the canonical map.
The typed moderation, mood, sleep, agency, and private self-state boundary is live. The current goal is to let ordinary scheduling run, inspect the next unattended direct reply and sleep cycle, and harden only the seams that show concrete failure. Void should answer Discord, remember useful social/project context, retrieve GameCult history/source/lore, and run an unattended moderation/participation loop without reviving JSON projection edits, legacy mirrors, or the swollen memory organ.
The next priority is observational hardening of the enabled typed loop. Agents and scheduled workers mutate typed CultCache-backed state through explicit operations, not by editing a whole-state JSON working copy. Sleep and memory distillation now preserve meaning-bearing claims/anchors/tensions in fixture and live-state passes, and short-term rumination has a clustering guard so repeated same-target/topic thoughts update one provisional memory instead of stacking duplicates. Keep checking ordinary cycles for abstraction sludge, duplicate speech, stale residue, or self-orbiting memories.
The center remains prevention, not legacy repair. The old brain is evidence of a failed boundary. The new brain rejects malformed memory at ingress so the runtime does not need a permanent cleanup bureaucracy to recover basic meaning.
CultCache does not need a separate physical store per state type; it is already polymorphic. The intended split is ownership by typed document kind and mutation contract, not a herd of little stores in fake mustaches. Each durable fact still has one owner. No top-level mirrors. No editable shadow copy pretending to be a harmless view.
If those fields are missing, the operation is invalid. This is the wall that keeps the next iteration from turning into topic sludge and asking cleanup to be its personality.
Short-term memory also has a self-novelty wall now. If a rumination write repeats an existing target/topic cluster, the state service keeps the existing source id, merges anchors/tags, and stores the incoming narrowed thought as the current working version. Same repo is not enough to merge; the topic pressure must overlap. This wall should preserve deepening, not forbid attention: saturation is about whether the thought is still gaining anchors, tension, and consequence, not whether the topic has appeared before.
- Prompt-facing recent chronology is derived as relative phrases. Exact timestamps remain state/status/cursor data and should not be fed to the child rumination loop unless a tool or parent-owned operation specifically needs them.
- Deterministic cleanup passes whose real job is compensating for whole-state JSON edits, permissive schemas, or sleep distillation that destroyed meaning.
- the old memory organ and legacy moderation-state wrapper have been removed from the codebase; their translation, retention/compaction, identity crystallization, candidate intervention, and value-pressure behavior must not be revived as compatibility scaffolding
- recent event timing in that bounded context now crosses a projection boundary first, so the child sees "5 minutes ago" language while the parent keeps exact timestamps for bookkeeping
- public artifact sharing now crosses the same boundary: repo activity exposes content hints, rumination verifies authorship through retrieval, and a configured `publicSpeechTarget` lets Void queue a normal typed candidate intervention instead of needing a blog-specific announcement path
- repo-scoped Discord participation now uses roles as the address boundary and registered webhook personas as the speech boundary. A role mention can summon a `repo-identity-mention` Codex job, but the worker suppresses base-bot auto-posting so the repo identity must speak through the `post_repo_identity_message` MCP tool.
- repo-scoped Faces now reuse the typed self-state machinery per identity. Role-addressed chats queue bounded `repo-face-rumination` jobs, and those jobs read/write only through `read_repo_face_state` / `apply_repo_face_state_operation` against the identity's `.cc` file.
- newborn repo Faces now get a repo-local `.voidbot` home on first chat. Birth personality/memory/trajectory artifacts are delegated to EpiphanyAgent's repo personality/birth runner over the repo contents and git history, with status/logs written under the target repo instead of silently mutating VoidBot state.
- repo-scoped Faces now also have standing heartbeats. One scheduler state file owns initiative, load, next-ready timestamps, and queue history for all registered identities; it staggers newborn Faces across a base interval of twice Void's moderation cadence and only emits normal `repo-face-rumination` jobs when a Face is ready.
- repo-activity cursor advancement is parent-owned after successful normal rumination passes, so the child can inspect read-only repo weather without stale commits haunting every future pass as fresh material
- the old memory-organ script family, legacy moderation state template, and legacy context exporter have now been deleted instead of preserved as forensic bait
- deterministic cleanup is mostly recent scar tissue from failed manual cleanup passes; it should stay deleted rather than be ported unless a future typed operation protects a real invariant in the new model
- hard-wired agency policy is mostly current scaffolding, not the final authority; identity, advocacy, and speech candidates should emerge from typed memory/state operations plus model-owned judgment under validation
- sleep/distillation has a typed maintenance runner, reviewed prompt boundary, fixture coverage, and one live-state pass proving short-term residue can become durable memory without losing meaning
Verdict: the foundation is coherent enough for cautious live operation. Do not add behavior by widening prompts or reviving compensators; harden only failures observed in ordinary scheduled cycles.
- Landed path: `scripts/void-self-state.mjs apply-operation` is the typed command surface for cursor, open cases, receipts, repo cursors, candidates, sleep, speaking pressure, incubation, and distilled memories.
- The CLI writes CultCache directly through `packages/core/src/void-self-state-service.ts`.
- The legacy `scripts/moderation-state-store.mjs` wrapper has been deleted.
- Verification: fixture tests and runner smokes should exercise operation application.
- Landed in the active path: routine self-state operations use `.voidbot/private/void-self-state.cc`, and the typed service no longer registers or mirrors the legacy moderation document.
-`scripts/run-void-moderator-rumination.ps1` restores rumination through `prompts/void-moderator-rumination.md` and typed operation output; it does not materialize `.json`.
-`Void Mood Drift` has been deliberately reinstalled after the typed sleep-maintenance fixture passed. It runs `scripts/run-void-mood-drift.ps1`, which calls the typed `scripts/simulate-void-mood.mjs` path.
-`Void Moderator Rumination` is re-enabled after typed operation quality, parent-owned speech closure, and an observed live scheduled pass. The runner has model-branch, parent-owned speech, and nap-skip fixtures.
- Verification: scheduled-task query shows mood and moderation enabled with Last Result `0`, and rebuilt direct dry runs operate only on `.voidbot/private/void-self-state.cc`.
- Landed cut: cleanup paths whose only job was repairing JSON projection edits, legacy mirrors, keyword sludge, or overgrown runtime residue have been deleted with the old memory-organ stack.
- Landed cut: hard-wired agency paths that turned heuristic scores into doctrine, advocacy, or speech candidates without an explicit typed-state contract have been deleted.
- Landed replacement boundary: `scripts/run-void-memory-maintenance.ps1` asks the model for memory/incubation/candidate typed operation proposals using `prompts/void-memory-maintenance.md`, rejects non-maintenance operations, and applies the rest through `scripts/void-self-state.mjs`.
- Landed sleep integration: `scripts/simulate-void-mood.mjs` invokes memory maintenance once per nap, and the maintenance runner fails a real sleep pass that returns no operations while memory pressure is present.
- Landed verification: `npm run moderation:memory-maintenance:sleep-fixture` exercises the non-skip model branch with a fake Codex child, proving `AquariumSynthCSharp: Workflow cannot own the body` promotes from short-term into durable memory while preserving subject, claim, anchor, tension, and action implication.
- Landed memory lifecycle: `revise_durable_memory`, `retire_durable_memory`, and `crystallize_memory_into_identity` make long-term memory durable but plastic instead of silently immutable.
- Landed lifecycle verification: `npm run moderation:memory-lifecycle:fixture` proves a short-term thought can promote into durable memory, revise into a replacement, retire superseded durable records, and crystallize into an identity memory plus self-profile value.
- Treat legacy brain mush as a migration problem, not the design center. New memory writes must cross the meaning-preserving typed operation schema before they reach CultCache.
- Landed agency ingress: `upsert_agency_pressure` / `retire_agency_pressure` store discomforts, active tensions, self-advocacy requests, and world-advocacy requests separately from candidate speech.
- Landed agency verification: `npm run moderation:agency-pressure:fixture` proves agency pressure enters typed state, appears in the self-state summary, and contributes to mood speaking pressure.
- Landed agency-to-speech accountability: strong active self/world advocacy pressure now appears as `speechPressureObligations` in rumination context. The parent runner rejects silent `[]` unless the model queues a candidate intervention or cools/retires the pressure. Deferred candidates do not satisfy the pressure by themselves, and existing queued candidates with delivery targets can be delivered by later runner passes instead of only during the pass that proposed them.
- Landed earlier advocacy release: speech-pressure obligations now start at 0.55 intensity instead of waiting for 0.65, only a live queued candidate satisfies an active pressure, and a previously spoken candidate no longer counts as permanent release while the pressure remains active. Mood drift also weights active advocacy more strongly so speaking pressure rises sooner.
- Landed rumination verification: `npm run moderation:rumination:fixture` routes the non-skip rumination branch through a fake Codex child and proves short-term memory, incubation, agency-pressure, and candidate-intervention proposals cross the parent-applied typed operation boundary without timestamp leakage.
- Landed controlled live rumination review: the first real-model `-NoPost` pass produced valid but self-orbiting readiness-test residue, which was pruned/retired and folded into a prompt guard; the second real-model `-NoPost` pass sampled non-VoidBot repo pressure, used retrieval, and correctly wrote `[]` when nothing earned persistence.
- Landed parent-owned speech closure: candidate interventions can include `deliveryTarget`, the prompt forbids child-side send scripts, the parent runner delivers at most one newly queued deliverable candidate per pass, records the receipt, and marks the candidate spoken with `mark_candidate_intervention_spoken`. `npm run moderation:rumination:speech-fixture` proves the loop with fake Codex and fake Discord send helpers.
- Landed receipt-backed duplicate direct-reply guard: before delivery, the parent runner now retires queued candidates whose `channelId + replyToMessageId` already appear in canonical speech receipts, so a later pass cannot answer the same direct ask twice just because the message remains visible. The speech fixture now seeds a prior receipt and proves both same-pass sibling retirement and already-answered target retirement.
- Landed scheduled rumination re-enable: one observed live scheduled pass completed with Last Result `0`, proposed one anchored short-term memory, delivered no speech, and kept exact timestamps out of the prompt-facing context.
- Landed live sleep-maintenance verification: a manual typed nap ran real memory maintenance on live state, promoted the scheduled rumination short-term memory into one durable `identity_seam`, and left `thoughtMemory.shortTerm` empty.
- Landed sleep brake: scheduled rumination now skips before model invocation during naps when there are no new room messages or open cases. `npm run moderation:rumination:nap-skip-fixture` proves the model path is not touched and no operation proposals are written.
- Landed short-term clustering guard: `record_short_term_memory` folds repeated same-target/topic pressure into one provisional memory with merged anchors, and `npm run moderation:short-term-clustering:fixture` proves the synth-boundary duplicate case without merging unrelated same-repo thoughts. The prompt now states explicitly that underexplored, low-saturation, newly anchored thoughts may keep deepening inside the cluster.
- Remaining work: let ordinary scheduling run and inspect the next unattended direct reply, next advocacy pass, and next sleep cycle for duplicate answers, fresh queued advocacy candidates, stale short-term residue, or ungrounded memory writes before calling the system broadly stable.
