From 9d2b1c52a64bc5bf7e2b53e48a28db5a8101b10d Mon Sep 17 00:00:00 2001 From: Meta Vens Date: Tue, 26 May 2026 21:28:48 +0100 Subject: [PATCH] Thaw repo Face swarm --- notes/fresh-workspace-handoff.md | 4 ++-- state/agent-swarm-paused.json | 6 +++--- state/map.yaml | 18 ++++++++++-------- 3 files changed, 15 insertions(+), 13 deletions(-) diff --git a/notes/fresh-workspace-handoff.md b/notes/fresh-workspace-handoff.md index 9e04ef3..519d65e 100644 --- a/notes/fresh-workspace-handoff.md +++ b/notes/fresh-workspace-handoff.md @@ -16,8 +16,8 @@ Git history and smoke artifacts carry routine proof. `state/evidence.jsonl` shou ## Current Shape -- Discord bot and worker may be live, but the unattended repo Face / CTB swarm brake is active as of 2026-05-26. -- The swarm is paused because live Face turns leaked owner-reply/Mind scaffolding into public Discord twice on 2026-05-26. The first failure wrapped parent Mind in the owner Discord reply prompt and let malformed plain Mind prose become public `SAY`. The second thaw attempt showed the deeper split: malformed parent Mind output caused the worker to ask the Face to revise, and that retry path turned owner-question boilerplate into Bifrost/Nibu `SAY`. The current worker retries malformed Mind output as Mind-owned interpretation, drops to diagnostic private summary instead of re-prompting the Face when Mind stays malformed, and never preserves raw dropped prose as the job summary. `scripts/inspect-model-output-logs.mjs` now flags repo-face parent interpreter records missing an `INTERPRETATION` decision. Keep `state/agent-swarm-paused.json` active until a new controlled thaw explicitly proves the live worker, parent Mind, model-output inspection, and Discord side effects all agree. +- Discord bot and worker are live, and the unattended repo Face / CTB swarm brake was lifted again on 2026-05-26 after the malformed parent-Mind retry fix was committed and pushed. +- The swarm had leaked owner-reply/Mind scaffolding into public Discord twice on 2026-05-26. The first failure wrapped parent Mind in the owner Discord reply prompt and let malformed plain Mind prose become public `SAY`. The second thaw attempt showed the deeper split: malformed parent Mind output caused the worker to ask the Face to revise, and that retry path turned owner-question boilerplate into Bifrost/Nibu `SAY`. The current worker retries malformed Mind output as Mind-owned interpretation, drops to diagnostic private summary instead of re-prompting the Face when Mind stays malformed, and never preserves raw dropped prose as the job summary. `scripts/inspect-model-output-logs.mjs` now flags repo-face parent interpreter records missing an `INTERPRETATION` decision. The post-fix thaw queued Bifrost, Fensalir, and Mimir through normal CTB heartbeats; all three posted through webhook, and live model-output inspection reported zero warnings. Keep watching the next unattended turns for parent-Mind shape and public speech leaks. - The teardown authority remains `notes/agent-swarm-teardown-plan-2026-05-21.md`, but it is now a restart checklist and smell ledger rather than a stop sign. Keep using it when a Face/Bifrost/CTB boundary smells like prompt/parser/transport Jenga. - The repo-controlled pause flag is `state/agent-swarm-paused.json`. While it is missing or has `"paused": false`, swarm runners may operate. While it has `"paused": true` or is malformed, the Face heartbeat runner skips and the orchestrator skips agent-swarm organs. This is the brake. Do not route around it. - Postgres owns jobs, audit events, interaction memory, and rate-limit state. diff --git a/state/agent-swarm-paused.json b/state/agent-swarm-paused.json index efdedd1..a33f906 100644 --- a/state/agent-swarm-paused.json +++ b/state/agent-swarm-paused.json @@ -1,5 +1,5 @@ { - "paused": true, - "reason": "Re-paused after live Bifrost Face post leaked owner-question wording into public Discord during thaw validation.", - "updatedAt": "2026-05-26T19:45:00.000Z" + "paused": false, + "reason": "Operator explicitly thawed the repo Face swarm after malformed parent Mind retry routing was fixed, verified, committed, and pushed.", + "updatedAt": "2026-05-26T20:23:33.250Z" } diff --git a/state/map.yaml b/state/map.yaml index 4b83e59..002ae0e 100644 --- a/state/map.yaml +++ b/state/map.yaml @@ -14,13 +14,15 @@ objective: Aetheria lore, while keeping the system understandable enough to modify safely. current: > - Keep the repo Face swarm paused after the 2026-05-26 Mind/owner-reply leaks - until a controlled thaw verifies the Face/Mind/speech boundary in current - room context. The second thaw attempt proved malformed parent Mind output - was being treated as a Face retry, allowing owner-question boilerplate to - become public Bifrost/Nibu SAY. The worker now treats malformed Mind output - as Mind-owned retry/drop and the model-output inspector flags interpreter - records missing INTERPRETATION decisions. Bifrost work routing remains + Keep the repo Face swarm live but under close watch after the 2026-05-26 + Mind/owner-reply leaks. The second thaw attempt proved malformed parent Mind + output was being treated as a Face retry, allowing owner-question boilerplate + to become public Bifrost/Nibu SAY. The worker now treats malformed Mind + output as Mind-owned retry/drop and the model-output inspector flags + interpreter records missing INTERPRETATION decisions. After the fix was + committed and pushed, a live thaw queued Bifrost, Fensalir, and Mimir through + normal CTB heartbeats; all three posted through webhook and live + model-output inspection reported zero warnings. Bifrost work routing remains paused because the governance bridge proved too disorienting for live social traffic. Parent Mind has a slimmer semantic prompt with a hard DSL contract: interpret natural Face thought, decide route/retry/drop, and emit only @@ -61,7 +63,7 @@ data_flow: - keep persistent state lean enough that re-entry sharpens the next turn instead of drowning it active_subgoals: - - Treat `notes/agent-swarm-teardown-plan-2026-05-21.md` as the historical teardown authority and the restart checklist. The repo Face swarm is currently paused after the 2026-05-26 owner-reply/Mind leaks, including the second thaw failure where malformed parent Mind output was converted into public owner-question SAY. It should thaw only through controlled evidence that the scheduler, prompt, model-output logs, parent Mind retry/drop ownership, and worker side-effect rails still have explicit observable boundaries. Keep watching for prompt/parser/transport Jenga before adding new swarm features. + - Treat `notes/agent-swarm-teardown-plan-2026-05-21.md` as the historical teardown authority and the restart checklist. The repo Face swarm is live again after the 2026-05-26 owner-reply/Mind leaks, including the second thaw failure where malformed parent Mind output was converted into public owner-question SAY. Keep watching for controlled evidence that the scheduler, prompt, model-output logs, parent Mind retry/drop ownership, and worker side-effect rails still have explicit observable boundaries before adding new swarm features. - Make the new project-state surfaces the default continuity path for nontrivial VoidBot work. - Keep the rebuilt moderation/self-state foundation on canonical CultCache `.cc` typed operations, never an editable JSON working projection. - Keep the typed moderation, mood, repo Face, and watchdog organs behind the single `GameCult Local Orchestrator` scheduled pulse; the per-organ scheduled tasks are legacy installer surfaces and should stay disabled unless a deliberate isolation test needs one. Bifrost dispatch is disabled by default behind `BIFROST_DISPATCH_ENABLED=false` until the governance bridge is rebuilt cleanly. As of the 2026-05-21 restart, the orchestrator task is enabled and is the live swarm pulse owner.