Rename repo Face role to Persona
This commit is contained in:
Meta Vens
parent
aceee53751
commit
3784fe485d
85 changed files with 1571 additions and 1580 deletions
|
|
@ -4,9 +4,9 @@ This is the current forward plan for the next larger organs. It is not a changel
|
|||
|
||||
## Current Aim
|
||||
|
||||
The typed moderation, mood, sleep, agency, and private self-state boundary is live, but the repo Face / CTB / Bifrost swarm loop is under teardown. Do not let ordinary swarm scheduling run. The active plan is `notes/agent-swarm-teardown-plan-2026-05-21.md`: the current Face loop mixed scheduling, prompt law, public speech, identity, governance, Discord mirroring, Bifrost dispatch, and GitHub proposal behavior into one prompt-and-parser machine. That foundation is no longer eligible for feature work.
|
||||
The typed moderation, mood, sleep, agency, and private self-state boundary is live, but the repo Persona / CTB / Bifrost swarm loop is under teardown. Do not let ordinary swarm scheduling run. The active plan is `notes/agent-swarm-teardown-plan-2026-05-21.md`: the current Persona loop mixed scheduling, prompt law, public speech, identity, governance, Discord mirroring, Bifrost dispatch, and GitHub proposal behavior into one prompt-and-parser machine. That foundation is no longer eligible for feature work.
|
||||
|
||||
The current goal is to rebuild the Face/Bifrost turn foundation around clear ownership. VoidBot should keep the ordinary bot/worker/provider/RAG/Postgres/Qdrant/CultCache spine, but repo Face work must be reduced into a scheduler, context assembler, typed candidate output contract, parent-side speech/work gate, and Bifrost-owned governance transport. Sanitizers, direct `UPDATE REQUEST` dispatch, dual identity authority, and worker-owned bridge calls are teardown targets, not surfaces to polish.
|
||||
The current goal is to rebuild the Persona/Bifrost turn foundation around clear ownership. VoidBot should keep the ordinary bot/worker/provider/RAG/Postgres/Qdrant/CultCache spine, but repo Persona work must be reduced into a scheduler, context assembler, typed candidate output contract, parent-side speech/work gate, and Bifrost-owned governance transport. Sanitizers, direct `UPDATE REQUEST` dispatch, dual identity authority, and worker-owned bridge calls are teardown targets, not surfaces to polish.
|
||||
|
||||
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.
|
||||
|
||||
|
|
@ -154,7 +154,7 @@ The runner can hand these to a CLI/MCP tool. The store decides what survives.
|
|||
- Self-state prompt summaries are derived from typed documents.
|
||||
- Recent room context is derived from Discord archive and the current poll.
|
||||
- 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.
|
||||
- Topic saturation and curiosity are derived surfaces, not stored truths. Repo Face turns now build a semantic curiosity graph from configured history/source vector retrieval plus current room/state/identity seeds, decode weighted attractor clusters, and hand the projector prominence, saturation, novelty, density, jurisdiction fit, suggested motion, and evidence labels. The old repeated-term detector is fallback room weather; it no longer owns curiosity.
|
||||
- Topic saturation and curiosity are derived surfaces, not stored truths. Repo Persona turns now build a semantic curiosity graph from configured history/source vector retrieval plus current room/state/identity seeds, decode weighted attractor clusters, and hand the projector prominence, saturation, novelty, density, jurisdiction fit, suggested motion, and evidence labels. The old repeated-term detector is fallback room weather; it no longer owns curiosity.
|
||||
- Source coverage is derived from recent anchors and repo/archive metadata.
|
||||
- Need-to-speak can keep a small pressure field, but its inputs remain receipts, candidates, and time since last speech.
|
||||
- Legacy top-level mirrors are deleted. If a consumer needs a projection, render it on demand.
|
||||
|
|
@ -190,23 +190,23 @@ The runner can hand these to a CLI/MCP tool. The store decides what survives.
|
|||
- the scheduled moderation runner has a typed rumination contract: bounded context in, reviewed prompt template, typed operation payloads out, parent-owned cursor/receipt recording
|
||||
- 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. Void also has explicit herald jurisdiction over the GameCult website/blog; essay-shaped pressures should queue article-proposal candidates for Void-authored site pieces.
|
||||
- Discord mention participation now uses role/display-name/bot addressing as CTB queue input and parent-owned speech rails as the output boundary. A Face mention appends a pending obligation for that Face; an ordinary Void mention or DM appends a pending obligation for the built-in `void` participant. Ambient direct mentions no longer create direct provider jobs.
|
||||
- repo-scoped character turns reuse the typed self-state machinery per identity, but the child character must not see that machinery directly. Addressed chats are consumed by the heartbeat scheduler, which prioritizes the identity, and the intended boundary has two model prompts: `repo-face-state-projector.prompt.md` for state -> roleplay-friendly memory/mood/personhood prose, and `repo-face-turn-interpreter.prompt.md` for natural character reflection -> typed memory, affect, social-read, mood, agency, and speech operations. Current-room and nearby-channel logs are not model-summarized; deterministic prompt assembly attaches raw oldest-to-newest transcript evidence with correction/recency rules so the Face must read the human exchange itself. The same assembler also attaches compact room-weather facts so work-heavy/agent-heavy texture can become play/rest/social pressure without seeding fake banter. The state packet feeding the projector is deliberately richer than before: private notes, values, activation vectors, runtime rest/speaking pressure, affect needs, bonds, status reads, mood dimensions, durable and short-term memory, agency pressure, incubating thoughts, candidate speech pressure, recent speech residue, social graph facts, and room weather are all available for the projector to turn into lived pressure. The Face turn uses full `gpt-5.4`; the state projector and parent Interpreter use the cheaper Spark/Mini support chain. `scripts/run-repo-face-heartbeats.ts --assemble-prompt <identity>` composes the final child prompt from templates, channel policy, repo/archive research guidance, Bifrost digest, projected memory prose, deterministic conversation transcript, and room-weather facts. It must not turn typed state into character prose itself, and it should emit situational obligations only when the current packet proves them true.
|
||||
- repo-scoped Faces now have per-topic channel permissions instead of one work-shaped speech lane. `allowedChannelIds` remains the hard gate, while `channelPermissions` gives each Face labeled topics, speech thresholds, and speed multipliers. The current social invariant is that Aquarium is intentionally cheap for casual in-character chatter, while domain channels receive matching work/lore/music/realtime/agent-state thoughts when the recent cross-channel context lines up. Heat is the live-room valve: above-baseline heat now relaxes nap gating, but active-turn freeze still prevents an agent from being queued again while it is thinking.
|
||||
- repo-scoped character prompts now explicitly treat social embodiment as durable state territory without exposing schemas to the child. A character may write naturally about humans, other agents, or room dynamics; the Interpreter turns meaning-bearing friendship, rivalry, irritation, trust, recurring bits, bonds, needs, and status reads into typed state when they carry claim/question, tension, action implication, and anchors. The Interpreter also preserves unmet play/rest/social/status pressure when a Face turns room fatigue into another work-shaped ask without satisfying the social need. Public posts should speak to someone directly and must not begin with note-title formulas or identity labels such as "bright bridge note" or "tiny fish sorting note."
|
||||
- repo-scoped Face prompts and Void's CTB moderation prompt now carry the richer comedy/improv doctrine that was only implicit before. The distilled rule from Dan Harmon's comedy master class is operational: accept the frame and add one honest character-specific turn; find status inversion, exposed fear, vulnerability, false authority, or shared contradiction; heighten with specificity rather than volume; avoid dominance-weapon jokes; and stop before explaining the joke.
|
||||
- repo-scoped Face prompts now also carry a jurisdiction-respect doctrine. Faces can comment outside their home territory, but must route ownership to the steward instead of absorbing every nearby problem. Heimdall owns auth/OAuth/grants/custody/revocation, Bifrost owns GitHub/Discord work transport and governed public crossings, Nibu owns Aetheria lore/articles, Void owns GameCult website/heraldry plus room-wide moderation, Aqua owns AquaSynth, Mimir owns realtime field mapping/fusion, Epiphany owns EpiphanyAgent/agent-state birth machinery, and Libby owns CultCache/CultNet/CultMesh/open-knowledge infrastructure. Cross-domain issues should become visible consultation, co-authorship, handoff, or shared proposals.
|
||||
- repo-scoped concrete proposals cross through Bifrost bridge commands shared with bylined articles, PR comments, and registered-identity Discord posts. It is enabled locally with `REPO_FACE_GITHUB_ACTIONS_ENABLED=true`. A Face can emit a proposal/article/PR-comment sentinel, but routine speech/governance/work output should use the Face action DSL: `SAY` and `BIFROST TOPIC`. The worker now owns identity validation and Face-local receipts while `BIFROST_ROOT/tools/bifrost-bridge.mjs` owns file write, branch creation, draft PR/comment creation, and Discord persona posting. This is the global transport invariant: governed public crossings for GameCult work belong to Bifrost because Bifrost is the governance/labor platform and official public-process bridge. Heimdall remains the OAuth/account/capability gate. Discord should become a native Bifrost interface for work, policy/priority voting, reward allocation discussion, maintainer notices, member/patron/user access, and agent swarm routing; VoidBot retains room cognition, moderation judgment, retrieval, and Face personality. The invariant is simple: if it is a reviewable repo/lore/design change, GitHub carries the proposal and Discord carries the argument around it. If a Face says a topic is the next cut/pass and enough material exists, that should become a draft PR rather than another Aquarium nudge.
|
||||
- repo-scoped Faces no longer have an immediate `UPDATE REQUEST` dispatch rail. Legacy `UPDATE REQUEST` blocks and `VOIDBOT_REPO_IDENTITY_UPDATE_REQUEST` JSON remain accepted as compatibility input, but the worker reconciles them into Bifrost topics so feature requests and agent opinions have a canonical Bifrost home before dispatch. Dispatch should fire after Bifrost detects consensus and the owning Face approves, not because a Face slipped a work packet through a side door.
|
||||
- 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. The live roster currently includes Nibu/AetheriaLore, Aqua/AquaSynth, Mimir/Mimir, Epiphany/EpiphanyAgent, plus built-in Void.
|
||||
- Discord mention participation now uses role/display-name/bot addressing as CTB queue input and parent-owned speech rails as the output boundary. A Persona mention appends a pending obligation for that Persona; an ordinary Void mention or DM appends a pending obligation for the built-in `void` participant. Ambient direct mentions no longer create direct provider jobs.
|
||||
- repo-scoped character turns reuse the typed self-state machinery per identity, but the child character must not see that machinery directly. Addressed chats are consumed by the heartbeat scheduler, which prioritizes the identity, and the intended boundary has two model prompts: `repo-persona-state-projector.prompt.md` for state -> roleplay-friendly memory/mood/personhood prose, and `repo-persona-turn-interpreter.prompt.md` for natural character reflection -> typed memory, affect, social-read, mood, agency, and speech operations. Current-room and nearby-channel logs are not model-summarized; deterministic prompt assembly attaches raw oldest-to-newest transcript evidence with correction/recency rules so the Persona must read the human exchange itself. The same assembler also attaches compact room-weather facts so work-heavy/agent-heavy texture can become play/rest/social pressure without seeding fake banter. The state packet feeding the projector is deliberately richer than before: private notes, values, activation vectors, runtime rest/speaking pressure, affect needs, bonds, status reads, mood dimensions, durable and short-term memory, agency pressure, incubating thoughts, candidate speech pressure, recent speech residue, social graph facts, and room weather are all available for the projector to turn into lived pressure. The Persona turn uses full `gpt-5.4`; the state projector and parent Interpreter use the cheaper Spark/Mini support chain. `scripts/run-repo-persona-heartbeats.ts --assemble-prompt <identity>` composes the final child prompt from templates, channel policy, repo/archive research guidance, Bifrost digest, projected memory prose, deterministic conversation transcript, and room-weather facts. It must not turn typed state into character prose itself, and it should emit situational obligations only when the current packet proves them true.
|
||||
- repo-scoped Personas now have per-topic channel permissions instead of one work-shaped speech lane. `allowedChannelIds` remains the hard gate, while `channelPermissions` gives each Persona labeled topics, speech thresholds, and speed multipliers. The current social invariant is that Aquarium is intentionally cheap for casual in-character chatter, while domain channels receive matching work/lore/music/realtime/agent-state thoughts when the recent cross-channel context lines up. Heat is the live-room valve: above-baseline heat now relaxes nap gating, but active-turn freeze still prevents an agent from being queued again while it is thinking.
|
||||
- repo-scoped character prompts now explicitly treat social embodiment as durable state territory without exposing schemas to the child. A character may write naturally about humans, other agents, or room dynamics; the Interpreter turns meaning-bearing friendship, rivalry, irritation, trust, recurring bits, bonds, needs, and status reads into typed state when they carry claim/question, tension, action implication, and anchors. The Interpreter also preserves unmet play/rest/social/status pressure when a Persona turns room fatigue into another work-shaped ask without satisfying the social need. Public posts should speak to someone directly and must not begin with note-title formulas or identity labels such as "bright bridge note" or "tiny fish sorting note."
|
||||
- repo-scoped Persona prompts and Void's CTB moderation prompt now carry the richer comedy/improv doctrine that was only implicit before. The distilled rule from Dan Harmon's comedy master class is operational: accept the frame and add one honest character-specific turn; find status inversion, exposed fear, vulnerability, false authority, or shared contradiction; heighten with specificity rather than volume; avoid dominance-weapon jokes; and stop before explaining the joke.
|
||||
- repo-scoped Persona prompts now also carry a jurisdiction-respect doctrine. Personas can comment outside their home territory, but must route ownership to the steward instead of absorbing every nearby problem. Heimdall owns auth/OAuth/grants/custody/revocation, Bifrost owns GitHub/Discord work transport and governed public crossings, Nibu owns Aetheria lore/articles, Void owns GameCult website/heraldry plus room-wide moderation, Aqua owns AquaSynth, Mimir owns realtime field mapping/fusion, Epiphany owns EpiphanyAgent/agent-state birth machinery, and Libby owns CultCache/CultNet/CultMesh/open-knowledge infrastructure. Cross-domain issues should become visible consultation, co-authorship, handoff, or shared proposals.
|
||||
- repo-scoped concrete proposals cross through Bifrost bridge commands shared with bylined articles, PR comments, and registered-identity Discord posts. It is enabled locally with `REPO_PERSONA_GITHUB_ACTIONS_ENABLED=true`. A Persona can emit a proposal/article/PR-comment sentinel, but routine speech/governance/work output should use the Persona action DSL: `SAY` and `BIFROST TOPIC`. The worker now owns identity validation and Persona-local receipts while `BIFROST_ROOT/tools/bifrost-bridge.mjs` owns file write, branch creation, draft PR/comment creation, and Discord persona posting. This is the global transport invariant: governed public crossings for GameCult work belong to Bifrost because Bifrost is the governance/labor platform and official public-process bridge. Heimdall remains the OAuth/account/capability gate. Discord should become a native Bifrost interface for work, policy/priority voting, reward allocation discussion, maintainer notices, member/patron/user access, and agent swarm routing; VoidBot retains room cognition, moderation judgment, retrieval, and Persona personality. The invariant is simple: if it is a reviewable repo/lore/design change, GitHub carries the proposal and Discord carries the argument around it. If a Persona says a topic is the next cut/pass and enough material exists, that should become a draft PR rather than another Aquarium nudge.
|
||||
- repo-scoped Personas no longer have an immediate `UPDATE REQUEST` dispatch rail. Legacy `UPDATE REQUEST` blocks and `VOIDBOT_REPO_IDENTITY_UPDATE_REQUEST` JSON remain accepted as compatibility input, but the worker reconciles them into Bifrost topics so feature requests and agent opinions have a canonical Bifrost home before dispatch. Dispatch should fire after Bifrost detects consensus and the owning Persona approves, not because a Persona slipped a work packet through a side door.
|
||||
- newborn repo Personas 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 Personas 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 Personas across a base interval of twice Void's moderation cadence and only emits normal `repo-persona-rumination` jobs when a Persona is ready. The live roster currently includes Nibu/AetheriaLore, Aqua/AquaSynth, Mimir/Mimir, Epiphany/EpiphanyAgent, plus built-in Void.
|
||||
- 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 ordinary VoidBot foundation is coherent enough for cautious operation, but the repo Face swarm foundation is not. Stop swarm feature work and rebuild that organ before restart. Do not add behavior by widening prompts or reviving compensators; the teardown plan is the active authority.
|
||||
Verdict: the ordinary VoidBot foundation is coherent enough for cautious operation, but the repo Persona swarm foundation is not. Stop swarm feature work and rebuild that organ before restart. Do not add behavior by widening prompts or reviving compensators; the teardown plan is the active authority.
|
||||
|
||||
## Agent Swarm Teardown Sequence
|
||||
|
||||
|
|
@ -217,13 +217,13 @@ First cuts:
|
|||
- Keep `GameCult Local Orchestrator` disabled while swarm teardown proceeds.
|
||||
- Landed: add a repo-controlled pause gate that swarm organs obey even when the Windows scheduled task or manual runner is invoked.
|
||||
- Landed: rename child-facing `heartbeat` framing to neutral turn/pass language so runtime provenance stops poisoning public speech.
|
||||
- Landed: add parent-side public speech/work eligibility before transport as a Spark/Codex reviewer pass with one retry. The reviewer gives concrete reasons; the Face gets one revision; the parent routes or drops the final output.
|
||||
- Landed: add parent-side public speech/work eligibility before transport as a Spark/Codex reviewer pass with one retry. The reviewer gives concrete reasons; the Persona gets one revision; the parent routes or drops the final output.
|
||||
- Landed: slim the child character protocol. Repo characters no longer need to emit action DSL blocks or JSON sentinels; they write natural in-character turns over projected memory/mood context, and the parent Interpreter translates warranted state updates, speech, and work into structured `STATE NOTE`, `SAY`, and `BIFROST TOPIC` intents. A state-projector prompt now defines the matching inbound Interpreter boundary; live wiring is still a follow-up cut.
|
||||
- Landed: extract the live prompt surfaces from executable code into `prompts/` and render them through a small shared prompt-template loader. Runtime code should own data projection, parsing, and side effects; prompt files own behavior prose.
|
||||
- Landed: delete `sanitizeRepoIdentityPostContent`. Language policing belongs to the reviewer pass, not a brittle regex broom.
|
||||
- Landed: route legacy `UPDATE REQUEST` packets into Bifrost topics instead of immediate Bifrost agent transport enqueue.
|
||||
- In progress: collapse repo Discord identity and Epiphany Face identity into one canonical Face identity model. Active bot, worker, MCP repo-identity tools, and Face CTB scheduler paths now load through a canonical Face registry and use repo Discord identities as compatibility projections.
|
||||
- Split the Face turn loop into scheduler, context assembler, prompt renderer, candidate parser, policy gate, and transport adapter.
|
||||
- In progress: collapse repo Discord identity and Epiphany Persona identity into one canonical Persona identity model. Active bot, worker, MCP repo-identity tools, and Persona CTB scheduler paths now load through a canonical Persona registry and use repo Discord identities as compatibility projections.
|
||||
- Split the Persona turn loop into scheduler, context assembler, prompt renderer, candidate parser, policy gate, and transport adapter.
|
||||
|
||||
Restart gates:
|
||||
|
||||
|
|
@ -232,7 +232,7 @@ Restart gates:
|
|||
- no Bifrost mirror post is treated as fresh consensus input;
|
||||
- no scheduler JSON owns active job truth;
|
||||
- no sanitizer is needed to hide internal runtime labels;
|
||||
- no Face identity exists in two competing canonical forms.
|
||||
- no Persona identity exists in two competing canonical forms.
|
||||
|
||||
## Migration Plan
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue