7.9 KiB
Ghostlight Fresh Workspace Handoff
Do not trust this file for the exact live HEAD. Use git for volatile truth.
Do not continue implementation automatically from a rehydrate-only request.
Immediate Re-entry Instruction
- Read
state/map.yaml. - Read
notes/ghostlight-current-system-map.md. - Read
notes/ghostlight-implementation-plan.md. - Run
npm run state:status. - Restate the persisted next action before touching code or docs.
Current Shape
Ghostlight now has the persistence spine plus the first architecture payload:
- canonical map
- scratch
- evidence ledger
- branch ledger
- compact re-entry note
- system map
- implementation plan
- Python helpers for state summary and compaction audits
- architecture notes for:
- personality structure
- signal classification
- state distributions and prompt projection
- Aetheria content generation targets
- population scaling for socially dense authored slices
- first schema seam:
schemas/agent-state.schema.jsonschemas/agent-state.required-fields.jsonexamples/agent-state.call-of-the-void.jsontools/validate_agent_state.py
- prompt projection and distillation docs:
docs/architecture/prompt-projection-contract.mddocs/architecture/projection-distillation-plan.mddocs/architecture/sequential-agent-runtime.mddocs/architecture/ink-branching-scenes.md
- evaluation follow-up docs:
docs/architecture/schema-future-mechanisms.md
- Aetheria lore grounding docs:
docs/architecture/aetheria-lore-grounding-architecture.mddocs/architecture/lore-grounding-digest-format.md
- lore grounding seam:
schemas/lore-grounding-digest.schema.jsonexamples/lore-grounding/historical-flashpoint.template.jsonexamples/lore-grounding/cold-wake-panic.ganymede-corridor.jsontools/validate_lore_grounding.py
- Cold Wake story-lab seam:
docs/experiments/cold-wake-story-lab.mdexamples/agent-state.cold-wake-story-lab.jsonexamples/projections/cold-wake-story-lab.jsonlexamples/projections/cold-wake-story-lab.pretty.jsonexperiments/cold-wake-story-lab/the-narrowest-possible-margin.mdexperiments/cold-wake-story-lab/scene-03-maer-veyr.qwen3-5-9b.capture.jsonexperiments/cold-wake-story-lab/scene-03-maer-veyr.qwen3-5-9b.v2.capture.jsonexperiments/cold-wake-story-lab/scene-03-maer-veyr.qwen3-5-9b.v3.capture.json- additional scene 1, 2, 3, and 4 Qwen captures under
experiments/cold-wake-story-lab/ tools/build_cold_wake_story_lab_fixture.pytools/run_qwen_projection.pytools/validate_qwen_captures.py
- Ink branching seam:
examples/ink/cold-wake-sanctuary-intake.inkexamples/ink/cold-wake-sanctuary-intake.training.jsontools/validate_ink_examples.pyinkjsdev dependency andnpm run ink:validate
- Cold Wake fixture note:
docs/architecture/aetheria-cold-wake-training-fixture.md
- first projection example seam:
schemas/projection-example.schema.jsonexamples/projections/call-of-the-void.scene-broken-taxi-oz.jsonlexamples/projections/call-of-the-void.scene-broken-taxi-oz.pretty.jsontools/validate_projection_examples.py
- visitor-facing README refreshed to explain Ghostlight's goals
There is still no full runtime yet. The live machine is design, state discipline, a cleaner repo boundary, the first executable state contract, a documented projection path, and the first Ink-backed playable branching scene with reviewed training annotations.
Current Direction
Use Ghostlight first for:
- content generation inside the Call of the Void slice described in
AetheriaLore - dialogue scaffolding and procedural drama for narrated Aetheria timeline stories
Cold Wake is now selected as the first historical grounding fixture because it is authored pre-Elysium lore. It is not the current game target. Treat it as training feedstock for projection and dialogue scaffolding.
Current Next Action
Build the next Ink-backed scene prototype pass: generate or project branch choices from local awareness, compile Ink, validate sidecar training annotations, and test one selected branch's reviewed state/memory/relationship mutation.
Cat/Oz remains useful as an Elysium procedural mechanics fixture, but grounded training data should start from authored historical lore rather than gameplay era Elysium outcomes.
The evaluation follow-up fixed the immediate v0 schema issues:
behavioral_dimensions.warmthbecameinterpersonal_warmthvoice_style.warmthbecameverbal_warmth- Cat now has a perceived-state overlay for Oz
- Cat and Oz now have relationship summary memories
event-drone-lienow includes observed exchange, private interpretations, and event effects
Completed projection path items:
- define
schemas/projection-example.schema.json - create reviewed Cat/Oz projection examples
- choose Cold Wake Panic as the first authored historical flashpoint
- fill the first draft lore grounding digest:
examples/lore-grounding/cold-wake-panic.ganymede-corridor.json - define the Cold Wake story lab as a four-scene arc with Maer Tidecall as protagonist
- add the first Cold Wake projection example and first Qwen response capture
- widen projection from dialogue-only turns to response turns that can include action, silence, withdrawal, violence, or mixed beats
- revise the first Maer/Veyr projection through v3 so unresolved personhood/claimant suspicion stays unresolved in Qwen output
- save both useful failed captures and the accepted v3 response as training material
- complete the first readable Cold Wake story,
experiments/cold-wake-story-lab/the-narrowest-possible-margin.md, with a receipts table tying accepted story beats to projection and capture artifacts - promote projection controls into the projection artifact shape:
frame_controls,authority_boundaries,object_custody,required_semantics, andforbidden_resolutions - add a Qwen projection runner and capture validator so response artifacts are reviewed training receipts, not loose logs
- adopt Ink as the standard playable branching scene format rather than inventing a parallel Ghostlight dialogue-tree format
- add the first Cold Wake Ink scene,
examples/ink/cold-wake-sanctuary-intake.ink, with a reviewed sidecar annotation tying branches to Ghostlight state, projection controls, consequence surfaces, and manual mutation policy
Remaining projection path:
- build a deterministic speaker-local input slicer
- build a renderer that emits projection controls before prompt prose
- build the first local-awareness-to-Ink generation pass so an agent can act from local awareness, produce branchable speech or non-speech choices, trigger NPC responses, and annotate mutations without replacing Ink
- keep the near-term product target to interactive dialogue trees and scene-local consequences
- preserve training-data hooks for future open-world behavior, iterated decisions, psychologically grounded consumer choices, scarcity/reputation pressure, and major faction or institution decision-making
- defer implementing world-scale simulation loops, autonomous offscreen factions, economy loops, and long-horizon plot machinery until the scene-local machine works
- use a frontier teacher model to generate/audit projection artifacts
- train a smaller student projector only after the artifact schema, input slicer, and evaluator stabilize
Warnings
- Do not let this repo become a mirror maze of notes that say the same thing in slightly different outfits.
- Keep canonical state small. If evidence starts turning into an activity feed, cut it back.
- Keep the prompt-projection doctrine intact: prompt text is projection, not truth storage.
- Do not accidentally re-promote the older corridor-crisis idea into a game MVP because an old doc had a strong chin and good lighting.
notes/evaluation.mdmay exist as an untracked user-supplied file for the next session. It was intentionally left unread and uncommitted during the compaction prep.