diff --git a/notes/fresh-workspace-handoff.md b/notes/fresh-workspace-handoff.md index 7b97899..9a0c849 100644 --- a/notes/fresh-workspace-handoff.md +++ b/notes/fresh-workspace-handoff.md @@ -1690,25 +1690,27 @@ materializing a `NewsIssue`. bounded round pressure, not a model-call or session count and not an assumption that one mutation yields one subject. Elaborator context now keeps stable identity and mandate in a prefix separate from the bounded - dynamic workbench snapshot. Pushed through `7ce721d`, persistent logical - title-by-realm sessions use digest-chained agentic compaction, both meaningful + dynamic workbench snapshot. Pushed `a017737` gives persistent logical + title-by-realm sessions digest-chained agentic compaction; both meaningful Gestalt fission and grounded named-person promotion are available, only failed dispatches resume from the exact frozen schedule, WorldKernel alone commits, and canonical complexity is remeasured after each round. - Run 78 reached live provider complexity pressure but admitted no mutation. - Its model actions had to restate inherited full previews, so workers failed - before deterministic admission. The current uncommitted cut makes the model - submit only a compact mutation draft and makes the deterministic tool bind - frozen parent, revision, location, inherited state, approval fields, and the - complete command before the existing validator. Preserve Run 78 as failure - evidence. Review and verify this ownership cut, run the full package and - strategic gates, commit and push, then obtain provider proof from preserved - canonical pre-mutation state without resuming Run 75. Do not assume a fixed - batch yield or one model call per useful subject. Keep Resolution as cover - owner. Nemesis receives + Run 78 reached live provider complexity pressure but admitted no mutation + because workers had to restate inherited full previews. Run 79 made those + proposals compact but returned an opaque fission finding. Terminal Run 80 + retried only Patina and Charter; complete deterministic findings proved both + omitted every parent resource assignment and named the exact three missing + resources for each parent. No mutation committed and live services remained + unchanged. The current uncommitted cut requires the exact frozen resource + and dormant-member IDs as action-schema map keys, rejects extras, and leaves + destination-child choice to the model. Full verification passes 495 library + and 16 strategic tests. Commit and push, then clone Run 80 into Run 81 and + resume only those same failed dispatches. Do not + assume a fixed batch yield or one model call per useful subject. Keep + Resolution as cover owner. Nemesis receives that cover and assigns causal decision windows inside it; it does not choose - cover membership. Preserve Runs 64 through 75 and both live services. This + cover membership. Preserve Runs 64 through 80 and both live services. This work does not wait for the Delvehold adapter because the Greathold remains an external sovereign boundary observer. 4. Build the Delvehold-owned adapter before any real Delvehold-owned player, diff --git a/state/map.yaml b/state/map.yaml index ed22b58..76da9d7 100644 --- a/state/map.yaml +++ b/state/map.yaml @@ -196,7 +196,7 @@ live_architecture: - Institution, faction, and consumer decision models active_subgoals: - - Complete the separate latent-world complexity and active-simulation budget cut before another full-world acceptance. Approximately 2,400 potentially acting entities under a 240-cell attention cover is a causal-complexity target, not a population-roster target. Iterative elaboration must raise admitted complexity by fissioning Gestalts and promoting causally meaningful individuals and institutions, then remeasure the remaining deficit; it may not assume one row or one model call equals one useful subject. Resolution owns cover selection, and Nemesis assigns causal decision windows inside an existing cover without gaining cover or commit authority. Preserve Runs 64 through 78 and treat the Greathold as an externally sovereign boundary observer. + - Complete the separate latent-world complexity and active-simulation budget cut before another full-world acceptance. Approximately 2,400 potentially acting entities under a 240-cell attention cover is a causal-complexity target, not a population-roster target. Iterative elaboration must raise admitted complexity by fissioning Gestalts and promoting causally meaningful individuals and institutions, then remeasure the remaining deficit; it may not assume one row or one model call equals one useful subject. Resolution owns cover selection, and Nemesis assigns causal decision windows inside an existing cover without gaining cover or commit authority. Preserve Runs 64 through 80 and treat the Greathold as an externally sovereign boundary observer. - Connect a Delvehold-owned adapter to the admitted generic consumer contract: shared compiler/consumer WorldSeed admission, externally authoritative institution-or-Gestalt snapshots, attributed proposal acknowledgement, and committed-event newspaper composition over typed CultNet, without consumer-specific IDs or schemas in Ghostlight. - Extend strategic/offscreen named-person individuation beyond the proven emerge-then-act path so people plot across sustained political waves, acquire relationships, fold, and return without granting a cell, arena, or model commit authority. - Finish the semantic mutation migration: delete or demote remaining legacy model effect schemas and move aggregate campaign fields toward projection-only state. Seed publication and named-person presence now have explicit non-effect authority classifications. @@ -329,8 +329,8 @@ current_status: provider_acceptance_checkpoint: Exact pushed commit `139b8a6` completed Run 60 under `character-newsroom.v10` without world or per-wave replay. Its acceptance witness and terminal status bind the completed page and exact resume lineage. The independently dispatched blind reviewer, shown only the reader-facing fantasy newspaper, read it as a real left-populist civic broadsheet and did not immediately identify procedural generation, so the narrative reverse-Turing criterion passes. The review's substantive criticism is that the three stories feel like three rewrites of one briefing; accepted Run 60 remains immutable. The run used 96,902 prompt tokens and reported zero cache hits. Its delivered typeset artifact is `output/pdf/canopy-ledger-run-60-front-page.pdf`; frozen-source and visual verification remain accepted. Exact pushed `bc2ca39` then produced frozen-fact newsroom-only Run 61 Issues 13, 15, 16, 17, and 18 without world or wave model replay. Provider output proves `special_issue` convergence in Issues 13 and 15, independent `general_issue` beats in Issues 16 through 18, and assignment-selector cache hits. Blind review of Issues 13, 15, 16, and 17 passes both distinct recurring voices and issue-shape diversity, recognizing Ossan, Mera, Corin, and Lysa's biases plus modest cross-issue evolution. Run 62 exercised v12 without world or wave replay and failed only because two lead articles proposed invalid datelines; recurring reporter calls still recorded zero cache hits. Run 63 used exact pushed v13 `a52d57b`; Issues 17 and 18 completed before root stopped the final weekly recomposition, both repeated bylines again recorded zero cache hits, and live services remained unchanged. Preserve Runs 61 through 63 as stopped or completed immutable evidence. Copy defects remain later deadline-correction work rather than a reason to reopen accepted issue artifacts. implementation_checkpoint: Exact pushed v13 `a52d57b` keeps one stable reporter action schema, places a common stable house charter before recurring identity and dynamic assignment, and projects deterministic `allowed_datelines` from cited records while retaining copy-desk factual authority and deterministic cited-place admission; 480 library tests and the all-target check pass. Run 63 falsifies reporter-cache pursuit as a useful acceptance target for sporadic independent filings. The proposed v14 cache-floor prompt growth was removed. Append-only agent contexts remain the natural cache beneficiary; accepted Run 60 remains immutable. The strategic cut extracts one shared `validate_strategic_individuation_proposals` owner used by resolution validation and by the scheduler before it returns an optional proposal. An invalid optional identity emits a semantic-invalid receipt and produces no individuation instead of aborting the recoverable wave. Focused valid and invalid regressions pass, and exact-source Run 68 exercises the corrected provider path through twelve committed waves; no further validator implementation is pending. The newsroom-only cut adds a navigation-only directory of completed public changes grouped by period and exact source timestamps to new v14 audit citations. The directory derives context from canonical records and gains no fact or world authority. Legacy empty source times are omitted from both rendering and serialization, preserving inherited v13 receipt bytes and digests; new v14 nonempty source times remain rendered and serialized. Exact-source Run 73 proves that compatibility path and final recomposition mechanically. Current source gives the assignment editor bounded full-ledger queries and explicitly asks it to search sideways for opposition and countermoves; Run 73 falsifies the stronger assumption that this access and instruction alone guarantee balanced selection. Exact pushed v15 source `b6787d909bd79b68ed3a4d143b7f6dd438e00fa2` binds accountability, opposition, and counter-narrative pitches to two distinct named parties and selected citations through a typed conflict axis, and preserves canonical ledger order. Run 74 falsifies the stronger v15 assumption: its lone accountability pitch used the same transfer citation for cultivators and a passive Tribunal, while four of five pitches avoided the adversarial axis through lead or consequence functions. Two cited names did not prove two moves. Exact pushed v16 `86fe6ed89d51da26b65ab6a031608075840b1527` binds each adversarial axis to two distinct cited public moves or positions and rejects one record presented as both sides; it adds no event writer, judge, process, dependency, or persistent authority. Formatting, 27 focused newspaper tests, 484 full library tests, and 16 strategic-smoke tests pass. full_world_acceptance_checkpoint: Run 68 at exact source `69c811a2669fc38f19f9199bf57088dc250bfc3e` is mechanically complete at world revision 27 with 12/12 strategic waves, 240 events, 514 public news rows, and a final newspaper. Independent editorial and grounding reviews both fail. Earlier per-wave papers prove the immutable record already contains dramatic completed facts, including an organ breaching the rail capital, a dead pump, and families crossing borders; the final paper failed to make that committed change legible. Preserve Run 68 unchanged. Run 69 at source `84b31e57a462710eb939c4559e0437eb5d6a7a28` failed before any model call when immutable recomposition verification encountered an empty rendered `Source time:` line in inherited v13 per-wave issues. Run 70 at source `ec45952b843e102dc2ebddda3a3bbb4058687175` also failed before any model call because v14 serialization changed the legacy recomposition digest. Exact-source Run 73 `b827d897b9579c2091a67c363d35b8695288ba2f` is terminal complete at `/var/lib/gamecult/ghostlight-dungeon/acceptance/full-world-delvehold-b827d89-73`: world revision 27, 12/12 waves, 240 events, 514 news rows, inherited artifacts byte-identical to Run 68, manifest valid, and archive SHA-256 `090d05f304c8f3d33c9dccd728bffbf3e5dc2969a7aeeffc2f9d7bafe701ac8a`. Exact-source Run 74 `b6787d909bd79b68ed3a4d143b7f6dd438e00fa2` is mechanically complete at `/var/lib/gamecult/ghostlight-dungeon/acceptance/full-world-delvehold-b6787d9-74`: revision 27, 12/12 waves, 240 events, 514 news rows, Run 68 inherited artifacts byte-identical, manifest valid, unchanged live services, and archive SHA-256 `957b11a5d584d27d23bf4d50ed1fbc8d067faf67953b03f80705bfb9587c496d`. Independent editorial review fails: the page has a coherent throughline and sharp prose but no sustained adversarial narrative; opposing decision-makers, motives, responses, and countermoves are largely absent, scandal and public reaction are missing, lived costs remain abstract, and the result reads as polished minutes with conclusions. Its post-press correction notice has two items: `The corridor had begun closing hours earlier` overstates a source that says the prolonged oath-route closure was diverting arrivals six hours before the breach; `no relief or assignment of liability has followed` must narrow to `no tribunal remedy is recorded yet`. Run 75 launched at exact source `86fe6ed89d51da26b65ab6a031608075840b1527` under the superseded 240-cell-only acceptance shape and was stopped cleanly at the operator's scale correction. Preserve `/var/lib/gamecult/ghostlight-dungeon/acceptance/full-world-delvehold-86fe6ed-75` as stopped non-acceptance evidence: preflight, world-region and titled-elaboration checkpoints, a wave-one cell terminal checkpoint, partial pulses 01/02, and two rejected pulse receipts exist. `ghostlight-full-world-run75.service` invocation `86bfe6a3ef504a7d99f579b3d67710ab` is inactive/dead after explicit stop; live services remain unchanged. Do not claim terminal success or failure. Preserve Runs 64 through 75. Mechanical completion of the earlier world is proven, but final newspaper acceptance under the corrected scale target is not. - scale_checkpoint: The active 240-cell entitlement is an attention budget, not the world-size claim. The approximately 2,400 potentially acting entities are a target for causally meaningful latent complexity, not a raw population or roster count. Multiresolution Gestalts compress the unresolved population; repeated admitted elaboration must fission them and promote individuals and institutions whose agency, relationships, resources, pressures, or authority can actually participate in consequences, then remeasure the deficit. Exact pushed `df66ec989c1e44a7a8b21ed159e9589778426238` defines consumer-authored `WorldScaleIntent` and deterministic `WorldElaborationDemand`; at 240 cells and 1,000 cover basis points it derives a numeric 2,400-subject target, current-subject deficit, weighted per-realm shares, and bounded `round_mutation_budget`. Pushed through `7ce721d`, the scale loop owns persistent logical elaborator sessions with agentic bounded compaction, exact failed-dispatch-only resume, both Gestalt fission and grounded named-person promotion, WorldKernel-only commit, and post-round canonical remeasurement. Run 78 reached that provider path but admitted no mutations: workers were required to restate inherited full previews and failed before deterministic admission. The current uncommitted cut narrows the model action to a compact mutation draft; deterministic tooling binds the frozen parent, revision, location, inherited state, approval fields, and complete command before existing validation. Session routing is title-by-realm, so one named elaborator preserves causal continuity without blending unrelated jurisdictions into a global transcript. Verification, review, commit/push, and provider proof of this corrected boundary remain pending. Resolution owns derived cover membership. Nemesis receives an existing cover and assigns bounded causal decision windows among eligible responders; it does not allocate that cover. + scale_checkpoint: The active 240-cell entitlement is an attention budget, not the world-size claim. The approximately 2,400 potentially acting entities are a target for causally meaningful latent complexity, not a raw population or roster count. Multiresolution Gestalts compress the unresolved population; repeated admitted elaboration must fission them and promote individuals and institutions whose agency, relationships, resources, pressures, or authority can actually participate in consequences, then remeasure the deficit. Exact pushed `df66ec989c1e44a7a8b21ed159e9589778426238` defines consumer-authored `WorldScaleIntent` and deterministic `WorldElaborationDemand`; at 240 cells and 1,000 cover basis points it derives a numeric 2,400-subject target, current-subject deficit, weighted per-realm shares, and bounded `round_mutation_budget`. Pushed `a017737` owns title-by-realm persistent logical elaborator sessions with agentic bounded compaction, compact mutation drafts, exact failed-dispatch-only resume, both Gestalt fission and grounded named-person promotion, WorldKernel-only commit, and post-round canonical remeasurement. Run 79 exposed opaque fission findings. Terminal Run 80 retried only Patina and Charter; the complete validator mismatch set proved both omitted every parent resource assignment and named the exact three missing resources for each parent. No mutation committed and live services remained unchanged. The current uncommitted cut structurally requires the exact frozen resource and dormant-member IDs as action-schema map keys, rejects extras, and leaves only destination-child choice to the model. Full verification passes 495 library and 16 strategic tests. Commit/push and provider resume remain pending. Resolution owns derived cover membership. Nemesis receives an existing cover and assigns bounded causal decision windows among eligible responders; it does not allocate that cover. presentation_checkpoint: The historical press-layout and seed-ownership split are complete. `notes/historical-newspaper-layout-grammar.md` remains the durable grammar. Manifest v2 at `output/tex/canopy-ledger-run-61-style-1847-flow-723.manifest.toml` independently binds `style_seed=1847`, `flow_seed=723`, frozen source SHA-256 `8f195140f52a40ba705d6a66987146a1500ae89668e5d82b01d1792eb3afb882`, and the final artifact `output/pdf/canopy-ledger-run-61-style-1847-flow-723.pdf`, SHA-256 `a457f4b1702a7a52480e42fce0039f0dbe677ff32958e98f1c412b346237190c`. An identical seed pair produces byte-identical TeX and PDF; changing only flow preserves the exact style section while materially changing a plausible layout, and changing only style preserves flow topology. Cut-first and cut-midstory templates pass visual inspection; the failed split-card template is deleted. Frozen copy/assets, actual PDF `/BM /Multiply`, and economic-layer advertising authority remain invariant. public_reference_checkpoint: Public architecture reference is complete. Canonical Ghostlight commit `15ea0f0` owns five pages under `docs/public-architecture` covering overview, authority, pipelines, 43 named production stages, and eight titled elaborators. Site commit `ea0b026` publishes exact projections under `F:\Projects\GhostlightDungeon-site\content\Documentation`, adds the sync/check script, explorer and table-of-contents navigation, scoped documentation layout, and homepage Architecture link. Local Quartz build and visual browser QA pass. GitHub Pages workflow `33408004480` succeeded. `https://ghostlight.gamecult.org/Documentation/` and the extensionless `Documentation/Agents-and-model-stages` route are live; the stage page exposes seven tables and 51 rows. Ghostlight remains technical authority; the site repository owns public composition and deployment. - next_action: Preserve Run 78 as a pre-mutation provider failure and do not resume Run 75. Review the compact world-complexity mutation-draft cut against the ownership map: elaborators own only new child identities, partition/member/resource assignments, or one grounded member delta; deterministic tooling must materialize every inherited and frozen command field before existing validation. Run focused, full-package, and strategic gates, correct findings without weakening persistent per-title sessions, bounded agentic compaction, failed-dispatch-only resume, WorldKernel-only commit, or post-round remeasurement, then commit and push. The next provider proof must start from preserved canonical pre-mutation state and show meaningful fission and promotion toward the 2,400-complexity target under the 240-cell entitlement without roster padding, assumed yield, or inherited-preview restatement. Preserve Resolution cover ownership, Nemesis's bounded causal-window role, immutable Runs 64 through 78, both live services, the completed public reference, the two-seed press checkpoint, and the economic-layer advertising boundary. + next_action: Preserve Runs 75 through 80. Commit and push the verified exact-key fission action-schema cut. Clone immutable Run 80 into Run 81 and resume only the same failed Patina and Charter dispatches; do not replay admitted world work or other completed dispatches. Require the exact frozen resource and dormant-member keys, model-selected destination children, deterministic full-command materialization, complete validator findings, and eventual WorldKernel admission before claiming complexity progress. Preserve title-by-realm logical sessions, bounded agentic compaction, failed-dispatch-only resume, post-round remeasurement, the 2,400-complexity target under 240-cell attention, Resolution cover ownership, Nemesis's bounded causal-window role, both live services, the completed public reference, the two-seed press checkpoint, and the economic-layer advertising boundary. gestalt_population: Gestalt Personas own shared population baselines; persistent member deltas own named individuality; WorldKernel materialization and approval-gated fission preserve lineage and identity. Materialisation/folding changes only representation and the exact member delta, advances resolution epoch, and retires the old cover; it has no Gestalt-wide effect authority. Selected actionable member exceptions are mandatory Projector perspective owners, so aggregation cannot silently erase their decision. Presence projection is limited to nearby active leaves and exact-location dormant members, includes reciprocal player relationship evidence, and may propose an earned cast without committing it. Simulation cells are derived covers only.