Replace moderation JSON edits with operation output
This commit is contained in:
parent
82f35b22a0
commit
5785f07092
6 changed files with 60 additions and 33 deletions
|
|
@ -29,6 +29,7 @@ Git history and smoke artifacts carry routine proof. `state/evidence.jsonl` shou
|
|||
- Typed operations are now applied through `packages/core/src/void-self-state-service.ts` and `scripts/void-self-state.mjs apply-operation`. During migration this service writes the new typed documents and updates only the narrow legacy monolith fields still required by current runners.
|
||||
- `scripts/export-recent-repo-activity.mjs` no longer writes the JSON working projection for cursor advancement. It applies `update_repo_activity_cursor` through `scripts/void-self-state.mjs`; old `--cursor-file .json` arguments are only translated to the sibling `.msgpack` path for compatibility.
|
||||
- `scripts/run-void-moderator-rumination.ps1` now records reviewed Discord cursors and speech delivery receipts through typed self-state operations. The old `set-cursor` and `record-delivery-receipt` commands were removed from `scripts/moderation-state-store.mjs`.
|
||||
- The unattended moderation child no longer gets to commit whole-state JSON edits. It reads `.voidbot/private/moderation-agent-state.json` as a compatibility projection, writes proposed operation payloads to `.voidbot/status/moderation-rumination-operations.json`, and the parent runner applies them through `scripts/void-self-state.mjs apply-operation`.
|
||||
- Most of the deterministic cleanup in `scripts/void-memory-organ.mjs` is recent compensator cruft from failed attempts to manually clean an exploded state file. Do not preserve it as an earned organ. Architect the state boundary so that cleanup pile is unnecessary.
|
||||
- Sleep/distillation must be rewritten with a meaning-preservation contract: concrete subject, claim/question, evidence refs, live tension, and future-action implication survive compression. Bulk can die. Meaning does not get put through the office shredder and called a dream.
|
||||
- The owner Codex lane is no longer one swollen file; orchestration, runtime/parsing, rendering, and shared helpers are split under `packages/providers/src/owner-codex-*.ts`.
|
||||
|
|
@ -45,10 +46,10 @@ Git history and smoke artifacts carry routine proof. `state/evidence.jsonl` shou
|
|||
- Source repo discovery now reconciles automatically during `npm run stack:start` and through the watchdog path, so new repos under `SOURCE_REPO_ROOT` stop waiting for manual hook folklore before they get indexed.
|
||||
- Bot-directed prompts now stay in the raw Discord archive but are excluded from default semantic history indexing and lexical fallback, so repeated summons stop teaching the bot its own call-and-response loops.
|
||||
- Source-grounding hints are advisory now; the owner and local lanes can decide when repo or lore tool use is actually warranted instead of obeying a lexical front-door veto.
|
||||
- There is now a 15-minute local scheduled moderation loop named `Void Moderator Rumination`. It runs `scripts/run-void-moderator-rumination.ps1`, launches `codex exec` from the VoidBot workspace with the usual MCP/tool surface, treats `config/discord-server-rules.md`, `config/moderation-review-agent.md`, and `styles/void-default.md` as doctrine/personality surfaces, uses `node scripts/export-recent-discord-history.mjs` for chronological polling, uses `node scripts/export-random-discord-history.mjs` for quiet-room novelty dives, uses `node scripts/export-recent-repo-activity.mjs --hours 96 --max-commits 3 --cursor-file .voidbot/private/moderation-agent-state.json` to watch cross-repo motion without re-injecting old commits as fresh weather, novelty-checks candidate thoughts against `search_history`, and now keeps canonical moderation state in `.voidbot/private/moderation-agent-state.msgpack` while exposing an editable working projection at `.voidbot/private/moderation-agent-state.json` to the unattended Codex child. This projection is now considered a rejected foundation, not a design to extend.
|
||||
- There is now a 15-minute local scheduled moderation loop named `Void Moderator Rumination`. It runs `scripts/run-void-moderator-rumination.ps1`, launches `codex exec` from the VoidBot workspace with the usual MCP/tool surface, treats `config/discord-server-rules.md`, `config/moderation-review-agent.md`, and `styles/void-default.md` as doctrine/personality surfaces, uses `node scripts/export-recent-discord-history.mjs` for chronological polling, uses `node scripts/export-random-discord-history.mjs` for quiet-room novelty dives, uses `node scripts/export-recent-repo-activity.mjs --hours 96 --max-commits 3 --state-path .voidbot/private/moderation-agent-state.msgpack` to watch cross-repo motion without re-injecting old commits as fresh weather, novelty-checks candidate thoughts against `search_history`, and now keeps canonical moderation state in `.voidbot/private/moderation-agent-state.msgpack` while exposing `.voidbot/private/moderation-agent-state.json` only as a read-only compatibility projection for the unattended Codex child.
|
||||
- That moderation state file is now Ghostlight-shaped: identity, canonical state, goals, memories, perceived overlays, and a `moderation_runtime` block. Inside that runtime block, the loop now keeps parallel analytic and associative thought lanes plus a bridge for syntheses, saturation warnings, and unresolved tensions, so one good seam does not get to annex the entire mind.
|
||||
- The moderation loop now records `moderation_runtime.recent_archive_excursions` plus `moderation_runtime.recent_repo_activity_sweeps` and is explicitly told to avoid laundering the same musing through fresh wording. Quiet runs should follow at least one fresh archive seam or concrete hook before they settle into theory, should also sweep recent tracked-repo commit motion for experiment clusters or converging themes, and should not let any single theme dominate more than a couple of recent bridge syntheses without fresh evidence.
|
||||
- Repo-weather sweeps are now incremental rather than a rolling four-day scrapbook. `scripts/export-recent-repo-activity.mjs` advances `moderation_runtime.repo_activity_cursor` inside `.voidbot/private/moderation-agent-state.json`, so already-injected commits stop coming back as “news” on every heartbeat unless someone explicitly opts into `--stateless`.
|
||||
- Repo-weather sweeps are now incremental rather than a rolling four-day scrapbook. `scripts/export-recent-repo-activity.mjs` advances repo activity through the typed `update_repo_activity_cursor` operation, so already-injected commits stop coming back as "news" on every heartbeat unless someone explicitly opts into `--stateless`.
|
||||
- Novelty now needs two bars, not one: a thought can be new to the room while still being stale to Void. The memory organ should score both room novelty and self novelty, merge repeated seams into existing clusters instead of minting new thought shards, and cool/refract themes that keep winning just because they already won.
|
||||
- Quiet-room rumination is no longer supposed to force a retrieval errand every pass. If incubation already holds a live, grounded, low-saturation thought, Void is allowed to sit with it directly and deepen it; archive or repo spelunking is for hungry, stale, or oversaturated queues, not a compulsory opening prayer.
|
||||
- The loop is now less shy about that repo weather: if a fresh convergence across active repos survives a pass or two and still feels room-native, it should bias toward a concise herald note or at least a medium-priority candidate intervention instead of filing the thought under private wallpaper.
|
||||
|
|
@ -87,8 +88,8 @@ Git history and smoke artifacts carry routine proof. `state/evidence.jsonl` shou
|
|||
## Likely Next Bounded Move
|
||||
|
||||
- Stop feature work on moderation, mood, agency, and public-lane behavior until the private-state boundary is rebuilt.
|
||||
- First bounded move after the current commit: replace the unattended child agent's whole-state JSON editing with operation output that the runner applies through `scripts/void-self-state.mjs apply-operation`.
|
||||
- Next cuts should delete unstable foundations early after concrete writers move: replace whole-state agent JSON edits with operation output, remove `legacyJsonPath`/working-projection authority, then cut top-level mirror fields and cleanup code that only compensated for those broken boundaries.
|
||||
- First bounded move after the current commit: move mood-drift, scheduled-runtime pressure/sleep updates, and memory-maintenance writes behind typed operations instead of direct canonical/working-projection writes.
|
||||
- Next cuts should delete unstable foundations early after concrete writers move: remove `legacyJsonPath`/working-projection authority, then cut top-level mirror fields and cleanup code that only compensated for those broken boundaries.
|
||||
- Rebuild sleep/distillation before trusting it again. Fixture check: a memory like `AquariumSynthCSharp: Workflow cannot own the body` must survive sleep with its concrete subject, claim, evidence, tension, and implication intact.
|
||||
- Do not build adapters around the JSON projection. That is how the heap learned to stand upright and ask for snacks.
|
||||
|
||||
|
|
|
|||
|
|
@ -111,9 +111,11 @@ This note is the source-grounded description of how the live VoidBot stack is sh
|
|||
- `scripts/check-voidbot-operations.ps1`
|
||||
- watchdog for process liveness, Qdrant, Postgres, Ollama, source-repo reconcile drift, Discord auth, backup freshness, offsite sync freshness, and optional ignored local extension checks.
|
||||
- `scripts/run-void-moderator-rumination.ps1`
|
||||
- scheduled moderation/participation runner that launches `codex exec` from the VoidBot workspace with the usual MCP/tool surface, writes status/log pulse files, and lets the unattended loop edit only the JSON working projection while the canonical moderation state lives in the sibling MessagePack cache file.
|
||||
- scheduled moderation/participation runner that launches `codex exec` from the VoidBot workspace with the usual MCP/tool surface, writes status/log pulse files, gives the unattended loop a read-only JSON compatibility projection, and applies the child's proposed typed operation payloads through the canonical MessagePack state service.
|
||||
- `scripts/moderation-state-store.mjs`
|
||||
- tiny Node wrapper around the built moderation-state cache helper; used by PowerShell and Node scripts to materialize the JSON working projection, commit it back into canonical MessagePack, update cursors, and record delivered-reply receipts without re-implementing persistence semantics in every script.
|
||||
- legacy Node wrapper around the built moderation-state cache helper; still used to materialize and commit the JSON compatibility projection while migration continues, but cursor and delivered-reply receipt mutation have moved to the typed self-state operation service.
|
||||
- `scripts/void-self-state.mjs`
|
||||
- typed self-state operation CLI. It applies strict operation payloads such as cursor updates, open-case changes, delivery receipts, repo cursor updates, memory appends, incubation merges, candidate interventions, sleep-cycle updates, and speaking-pressure updates through `packages/core/src/void-self-state-service.ts`.
|
||||
- `scripts/install-moderation-rumination-task.ps1`
|
||||
- installs the local 15-minute scheduled task that runs the moderation/participation loop through the hidden PowerShell launcher shim.
|
||||
- `scripts/simulate-void-mood.mjs`
|
||||
|
|
@ -166,11 +168,11 @@ Within the Postgres path, the implementation is split on purpose now too:
|
|||
|
||||
1. The Windows scheduled task `Void Moderator Rumination` starts `scripts/run-void-moderator-rumination.ps1` every 15 minutes.
|
||||
2. The runner launches `codex exec` from `E:\Projects\VoidBot` with full local workspace/tool access so the child agent sees the same project rules, `.codex/config.toml`, and `voidbot` MCP server as a normal VoidBot workspace session.
|
||||
3. The child agent reads `config/discord-server-rules.md`, `config/moderation-review-agent.md`, `styles/void-default.md`, and the editable working projection `.voidbot/private/moderation-agent-state.json`. The runner materializes that projection from the canonical `.voidbot/private/moderation-agent-state.msgpack` file before each pass and commits it back afterward.
|
||||
4. For chronological heartbeat duty, it polls `node scripts/export-recent-discord-history.mjs`, and once a reviewed cursor exists the runner now passes one exact `--after <saved timestamp>` command into the unattended child instead of leaving room for a broadened bootstrap poll. When the room is quiet and incubation feels hungry, stale, or oversaturated, it can use `node scripts/export-random-discord-history.mjs` to widen the branch. If an incubating thought is already live and grounded, the loop is allowed to deepen that thought directly instead of performing a novelty errand for ceremony's sake. It also uses `node scripts/export-recent-repo-activity.mjs --hours 96 --max-commits 3 --cursor-file .voidbot/private/moderation-agent-state.json` when repo motion is the actual seam or when the queue needs fresher fuel; that helper advances `moderation_runtime.repo_activity_cursor` so the same four-day commit window does not keep getting reinjected as fresh weather. The loop can inspect exact diffs or nearby source context when one repo seam looks alive, and uses semantic `search_history` to novelty-check candidate thoughts before deciding whether they are already in the room.
|
||||
3. The child agent reads `config/discord-server-rules.md`, `config/moderation-review-agent.md`, `styles/void-default.md`, and the read-only compatibility projection `.voidbot/private/moderation-agent-state.json`. The runner materializes that projection from the canonical `.voidbot/private/moderation-agent-state.msgpack` file before each pass, but the child no longer commits edits to it. Instead, it writes proposed typed operations to `.voidbot/status/moderation-rumination-operations.json`, and the parent runner applies them with `scripts/void-self-state.mjs apply-operation`.
|
||||
4. For chronological heartbeat duty, it polls `node scripts/export-recent-discord-history.mjs`, and once a reviewed cursor exists the runner now passes one exact `--after <saved timestamp>` command into the unattended child instead of leaving room for a broadened bootstrap poll. When the room is quiet and incubation feels hungry, stale, or oversaturated, it can use `node scripts/export-random-discord-history.mjs` to widen the branch. If an incubating thought is already live and grounded, the loop is allowed to deepen that thought directly instead of performing a novelty errand for ceremony's sake. It also uses `node scripts/export-recent-repo-activity.mjs --hours 96 --max-commits 3 --state-path .voidbot/private/moderation-agent-state.msgpack` when repo motion is the actual seam or when the queue needs fresher fuel; that helper advances `update_repo_activity_cursor` through the typed operation service so the same four-day commit window does not keep getting reinjected as fresh weather. The loop can inspect exact diffs or nearby source context when one repo seam looks alive, and uses semantic `search_history` to novelty-check candidate thoughts before deciding whether they are already in the room.
|
||||
Quiet awake passes are now supposed to philosophize from the surviving seam first: ask what governing principle the thought is circling, what tension keeps it from collapsing into slogan, and what embodiment consequence would make it real. Retrieval is meant to support that work when the seam is hungry or contradictory, not replace it with endless specimen collection.
|
||||
The doctrine now also biases that philosophical pass back toward concrete machines. If a seam stays too abstract, the loop is supposed to cash it out in a specific repo, subsystem, gameplay mechanic, lore structure, frontend surface, or agent organ before letting it dominate another run.
|
||||
5. If speaking would genuinely help, it posts through `node scripts/send-discord-message.mjs`; for guild channels and threads that helper can either speak as the base bot or execute through the shared per-channel webhook pipe with an overridden persona name/avatar so swarm agents can front without needing separate Discord bot identities. The send helper now also writes durable speech receipts to `.voidbot/status/void-last-speech.json` plus `.voidbot/status/void-speech-log.jsonl`, and the runner records recent sends back into canonical moderation state as `moderation_runtime.recent_delivery_receipts`. That gives the next pass a binding memory of what already got said even when Discord history polling fails to surface the bot's own message. Otherwise it updates only the ignored moderation-state working projection, which the runner then commits back into canonical MessagePack with the typed cache helper. The state carries cursors, open room obligations, delivery receipts, memories, analytic/associative thought lanes, bridge syntheses and saturation notes, recent archive excursions, recent repo-activity sweeps, novelty checks, speaking-bias hints, candidate interventions, and the newer autonomy organs: `discomforts`, `active_tensions`, `self_advocacy_requests`, and `world_advocacy_requests`. A direct ask aimed at Void is supposed to survive as an `open_cases` obligation until it is answered or explicitly retired; cursor advancement alone is not closure.
|
||||
5. If speaking would genuinely help, it posts through `node scripts/send-discord-message.mjs`; for guild channels and threads that helper can either speak as the base bot or execute through the shared per-channel webhook pipe with an overridden persona name/avatar so swarm agents can front without needing separate Discord bot identities. The send helper writes durable speech receipts to `.voidbot/status/void-last-speech.json` plus `.voidbot/status/void-speech-log.jsonl`, and the runner records recent sends through the typed `record_delivery_receipt` operation. That gives the next pass a binding memory of what already got said even when Discord history polling fails to surface the bot's own message. The state carries cursors, open room obligations, delivery receipts, memories, analytic/associative thought lanes, bridge syntheses and saturation notes, recent archive excursions, recent repo-activity sweeps, novelty checks, speaking-bias hints, candidate interventions, and the newer autonomy organs: `discomforts`, `active_tensions`, `self_advocacy_requests`, and `world_advocacy_requests`. A direct ask aimed at Void is supposed to survive as an `open_cases` obligation until it is answered or explicitly retired; cursor advancement alone is not closure.
|
||||
6. The runner writes pulse files under `.voidbot/status/moderation-rumination.json` plus `.voidbot/logs/moderation-rumination*`, so the loop can be observed without pretending an app heartbeat card is a real workstation daemon.
|
||||
|
||||
## Flow 6: Mood Drift
|
||||
|
|
|
|||
Loading…
Reference in a new issue