Add lore grounding digest seam

This commit is contained in:
Meta Vens 2026-05-01 21:39:00 +01:00
commit e4ccbb0521
12 changed files with 1234 additions and 16 deletions

View file

@ -102,6 +102,12 @@ The best scenes are small, local, and socially loaded:
Before producing training projection examples from a historical flashpoint,
create a lore grounding digest.
The digest format is defined in:
- `docs/architecture/lore-grounding-digest-format.md`
- `schemas/lore-grounding-digest.schema.json`
- `examples/lore-grounding/historical-flashpoint.template.json`
A digest should include:
- source files and relevant line or section notes
@ -116,6 +122,19 @@ A digest should include:
- author-only context that must not enter prompt text
- open questions needing lore elaboration
It should also include cultural and factional pressure fields:
- internal virtues
- internal shames
- prestige markers
- taboo triggers
- emotional display norms
- trust defaults
- speech register cues
- outsider stereotypes
- factional misread patterns
- role obligations and failure modes
The digest is not a replacement for the lore vault. It is a compiled working
slice for one fixture, so projection examples can cite grounded pressure
without dragging the whole archive into every prompt.
@ -156,7 +175,7 @@ with confident fog.
## Immediate Plan
1. Keep the Cat/Oz fixture as an Elysium procedural mechanics fixture.
2. Add a lore grounding digest format.
2. Add a lore grounding digest format. Done.
3. Choose one authored historical flashpoint from the Aetheria archive.
4. Build the first `historical_grounded` agent-state fixture from that slice.
5. Produce reviewed projection examples from that fixture.

View file

@ -0,0 +1,264 @@
# Lore Grounding Digest Format
The lore grounding digest is the bridge between authored Aetheria history and
Ghostlight projection training.
It distills a specific historical flashpoint into the cultural, institutional,
material, and factional pressures needed to build agent-state fixtures and
speaker-local projection prompts.
It is not a lore replacement. It is a working slice. Do not ask every prompt to
carry the whole vault in its teeth like an exhausted dog.
## Files
The schema lives at:
- `schemas/lore-grounding-digest.schema.json`
The starter template lives at:
- `examples/lore-grounding/historical-flashpoint.template.json`
Use the template for the first authored historical flashpoint, then save real
digests under `examples/lore-grounding/` with names tied to the flashpoint.
## Purpose
A digest should answer:
- What authored source material grounds this flashpoint?
- What history, institutions, factions, classes, roles, and material pressures
shape the scene?
- What cultural priors should affect how characters appraise events?
- What does each faction or class reward, shame, taboo, admire, and misread?
- What should each speaker know, believe, misread, or not know?
- What pressure should appear in `prompt_text`, and what should remain
author-only?
## Main Sections
### Source Refs
Use `source_refs` to cite the lore archive slices that constrain the digest.
References should be specific enough that a later reviewer can find the source
without spelunking through the entire vault with a dim headlamp and a worsening
personality.
### Historical Context
This section describes the time, place, public facts, and ambient pressures of
the flashpoint.
Good context is small and hard-edged:
- a clinic policy dispute
- a contract negotiation
- an upload continuity hearing
- an unsafe FTL signoff
- a workplace discipline meeting
- a factional aid intervention
Do not start with "the whole setting." Start with one room where history has
hands.
### Groups
`groups` describes factions, institutions, classes, professions, movements, or
subcultures active in the scene.
The group profile is where broad lore becomes usable social pressure:
- `institutional_logic`: what the group exists to preserve, control, repair, or
extract
- `material_incentives`: what the system rewards the group for doing
- `internal_virtues`: what insiders admire
- `internal_shames`: what insiders experience as disgrace
- `prestige_markers`: what reads as competence, status, holiness, care, or
discipline
- `taboo_triggers`: what provokes disgust, sanction, fear, or exclusion
- `emotional_display_norms`: what feelings can be shown, hidden, ritualized, or
punished
- `trust_defaults`: who the group tends to trust, distrust, pity, envy, use, or
fear
- `speech_register_cues`: how role and culture shape language
This is where "Dominion types read as cold" becomes something more useful than
a hat with a sneer glued to it.
### Cultural Pressure Fields
`cultural_pressure_fields` are reusable pressure atoms derived from lore.
They should not say:
```text
Dominion people are cold.
```
They should say something closer to:
```text
In this Dominion-coded role, visible personal need reads as loss of command.
Under status threat, the speaker is likely to compress emotion into procedure.
```
Pressure fields can represent:
- virtue
- shame
- prestige
- taboo
- threat model
- trust default
- speech norm
- status trigger
- material incentive
- outsider stereotype
### Factional Misread Matrix
The misread matrix models how groups translate each other's virtues into
insults.
Example shape:
```text
Observer: Dominion-coded institution
Target: Aya-coded care network
Observer read: sentimental, porous, slow to impose hard necessity
Target self-read: durable care infrastructure, consent discipline, refusal to
turn people into convenient losses
Projection use: Under conflict, Dominion-coded speakers may frame Aya restraint
as weakness; Aya-coded speakers may frame Dominion decisiveness as moral
amputation.
```
The point is not to canonize every stereotype as true. The point is to make
misperception available as social fuel.
### Role Pressure Fields
Roles are not the same as factions. A Dominion auditor, a Dominion heir, and a
Dominion maintenance officer may share cultural priors while facing different
obligations and failure modes.
Role fields should describe:
- obligations
- available masks
- failure modes
- what authority looks like
- what disgrace looks like
- what compromises the role can justify
### Speaker Lore Boundaries
This section controls leakage.
For each speaker, define:
- known context
- beliefs
- misreads
- must-not-know facts
If a speaker would not know a fact, it does not enter their prompt text. If a
speaker suspects something, encode it as a belief or misread with source
grounding. No little omniscient narrator gremlin in the vents.
### Author-Only Boundaries
Author-only boundaries constrain the fixture or future continuity but do not
enter speaker prompts.
Examples:
- future outcomes
- hidden institutional motives
- another speaker's private state
- facts known only to the author or simulation supervisor
- Elysium branch outcomes not yet promoted
### Open Questions
If the lore source is too thin, say so. Mark whether the question blocks
training.
Do not generate training data to cover a hole that should be filled by lore
elaboration. That is not creativity; that is drywall over a load-bearing ghost.
## Dominion And Aya Pressure Examples
These are examples of digest structure, not final faction doctrine.
### Dominion-Coded Pressure
Likely ingredients to verify against source:
- administrative continuity
- hierarchy
- AGI governance
- industrial planning
- duty under collapse
- controlled emotional display
- legitimacy through competence and command
Projection shape:
```text
The speaker is Dominion-coded and under status threat. They are likely to turn
distress into procedural language because visible need reads as command leakage.
They may experience compassion as legitimate only when subordinated to duty,
continuity, or strategic necessity.
```
Outsider misreads:
- cold
- arrogant
- authoritarian
- morally vacant
- inhumanly procedural
### Aya-Coded Pressure
Likely ingredients to verify against source:
- care as material politics
- sanctuary
- maintenance
- consent discipline
- expansive personhood
- refusal to solve suffering by writing people out of the ledger
Projection shape:
```text
The speaker is Aya-coded and facing coercive efficiency. They may treat care as
infrastructure rather than sentiment. They are likely to resist decisions that
make personhood conditional on convenience, even when outsiders frame that
resistance as softness.
```
Outsider misreads:
- weak-hearted
- sentimental
- indecisive
- inefficient
- unable to do what reality demands
## Promotion Rule
A digest becomes usable for grounded training when:
- source refs are specific
- major cultural pressure fields are filled
- factional misreads are explicit
- speaker knowledge boundaries are clear
- open questions do not block the scene
- a reviewer agrees the digest reflects authored lore rather than attractive
fog
Only then should it feed an agent-state fixture or projection example.

View file

@ -203,7 +203,7 @@ Minimum useful milestone:
2. Add `examples/projections/call-of-the-void.scene-broken-taxi-oz.jsonl` with
the first reviewed Cat and Oz examples. Done.
3. Add a lore grounding digest format for historical Aetheria projection
fixtures.
fixtures. Done.
4. Choose the first authored historical flashpoint for grounded training.
5. Add a deterministic projection input-slice tool that reads the agent-state
fixture and emits speaker-local input JSON.

View file

@ -0,0 +1,215 @@
{
"schema_version": "ghostlight.lore_grounding_digest.v0",
"digest_id": "template.historical-flashpoint.v0",
"source_status": "template",
"fixture_status": "historical_grounded",
"source_refs": [
{
"source_id": "source-short-id",
"path": "Aetheria/path/to/source.md",
"title": "Source Title",
"line_start": 1,
"line_end": 1,
"relevance": "Why this source constrains the digest."
}
],
"historical_context": {
"time_period": "TBD historical period",
"location": "TBD location or institution",
"summary": "Short description of the flashpoint and why it is grounded enough for training.",
"public_facts": [
{
"text": "Fact known to ordinary participants in this scene.",
"source_refs": [
"source-short-id"
]
}
],
"ambient_pressures": [
{
"text": "Large institutional or material pressure shaping the scene.",
"source_refs": [
"source-short-id"
]
}
]
},
"groups": [
{
"group_id": "observer-group-id",
"label": "Observer faction, institution, class, profession, or subculture label",
"group_type": "faction",
"institutional_logic": [
"What this group exists to preserve, control, repair, extract, or protect."
],
"material_incentives": [
"What the group is rewarded for doing under this system."
],
"internal_virtues": [
"What insiders admire."
],
"internal_shames": [
"What insiders experience as disgrace or loss of standing."
],
"prestige_markers": [
"Signals that read as competence, status, holiness, discipline, care, etc."
],
"taboo_triggers": [
"Acts or traits that provoke disgust, fear, sanction, or exclusion."
],
"emotional_display_norms": [
"What emotional expression is permitted, admired, punished, or disguised."
],
"trust_defaults": [
"Who this group is primed to trust, distrust, pity, envy, use, or fear."
],
"speech_register_cues": [
"Formality, compression, politeness, ritual, jargon, softness, command voice, etc."
],
"source_refs": [
"source-short-id"
]
},
{
"group_id": "target-group-id",
"label": "Target faction, institution, class, profession, or subculture label",
"group_type": "faction",
"institutional_logic": [
"What this group exists to preserve, control, repair, extract, or protect."
],
"material_incentives": [
"What the group is rewarded for doing under this system."
],
"internal_virtues": [
"What insiders admire."
],
"internal_shames": [
"What insiders experience as disgrace or loss of standing."
],
"prestige_markers": [
"Signals that read as competence, status, holiness, discipline, care, etc."
],
"taboo_triggers": [
"Acts or traits that provoke disgust, fear, sanction, or exclusion."
],
"emotional_display_norms": [
"What emotional expression is permitted, admired, punished, or disguised."
],
"trust_defaults": [
"Who this group is primed to trust, distrust, pity, envy, use, or fear."
],
"speech_register_cues": [
"Formality, compression, politeness, ritual, jargon, softness, command voice, etc."
],
"source_refs": [
"source-short-id"
]
}
],
"cultural_pressure_fields": [
{
"field_id": "observer-group-id.visible-need-as-status-leak",
"applies_to": [
"observer-group-id"
],
"pressure_type": "shame",
"summary": "Describe a reusable cultural pressure without reducing the group to a flat trait.",
"projection_use": "How this pressure should change a speaker-local prompt under scene stress.",
"source_refs": [
"source-short-id"
]
}
],
"factional_misread_matrix": [
{
"observer_group_id": "observer-group-id",
"target_group_id": "target-group-id",
"observer_read": [
"How the observer group tends to stereotype or misread the target."
],
"target_self_read": [
"How the target group understands the same behavior internally."
],
"misread_patterns": [
"Specific translation errors that can drive conflict."
],
"likely_insults": [
"Loaded words, euphemisms, or social accusations likely to appear."
],
"projection_use": "How to render this misread as pressure prose, not a command to be stereotypical.",
"source_refs": [
"source-short-id"
]
}
],
"role_pressure_fields": [
{
"role_id": "role-id",
"summary": "Social role within the flashpoint.",
"obligations": [
"What the role must do to remain legitimate."
],
"available_masks": [
"Performances this role can use under pressure."
],
"failure_modes": [
"How this role breaks, corrupts, freezes, overreaches, or betrays itself."
],
"source_refs": [
"source-short-id"
]
}
],
"speaker_lore_boundaries": [
{
"speaker_id": "speaker-id",
"known_context": [
{
"text": "What this speaker knows from the lore slice.",
"source_refs": [
"source-short-id"
]
}
],
"beliefs": [
{
"text": "What this speaker believes or assumes.",
"source_refs": [
"source-short-id"
]
}
],
"misreads": [
{
"text": "What this speaker gets wrong or overgeneralizes.",
"source_refs": [
"source-short-id"
]
}
],
"must_not_know": [
{
"text": "Author-only fact, future outcome, or other speaker's private context to exclude.",
"source_refs": [
"source-short-id"
]
}
]
}
],
"author_only_boundaries": [
{
"text": "Canon fact or planned outcome that constrains authors but must not enter speaker prompt text.",
"source_refs": [
"source-short-id"
]
}
],
"open_questions": [
{
"question": "What needs elaboration before this digest can produce training data?",
"blocks_training": true,
"notes": "Say whether this blocks examples or can wait."
}
]
}

View file

@ -42,6 +42,11 @@ Ghostlight now has the persistence spine plus the first architecture payload:
- `docs/architecture/schema-future-mechanisms.md`
- Aetheria lore grounding docs:
- `docs/architecture/aetheria-lore-grounding-architecture.md`
- `docs/architecture/lore-grounding-digest-format.md`
- lore grounding seam:
- `schemas/lore-grounding-digest.schema.json`
- `examples/lore-grounding/historical-flashpoint.template.json`
- `tools/validate_lore_grounding.py`
- first projection example seam:
- `schemas/projection-example.schema.json`
- `examples/projections/call-of-the-void.scene-broken-taxi-oz.jsonl`
@ -68,9 +73,8 @@ state unless explicitly revived.
## Current Next Action
Define the lore grounding digest format for historical Aetheria projection
fixtures, then use it to choose the first authored historical flashpoint for
grounded training.
Choose the first authored historical Aetheria flashpoint for grounded training,
then fill the first real lore grounding digest from the template.
Cat/Oz remains useful as an Elysium procedural mechanics fixture, but grounded
training data should start from authored historical lore rather than gameplay
@ -92,8 +96,9 @@ Completed projection path items:
Remaining projection path:
- add a lore grounding digest format for historical Aetheria fixtures
- choose the first authored historical flashpoint for grounded training
- fill the first real lore grounding digest from
`examples/lore-grounding/historical-flashpoint.template.json`
- build a deterministic speaker-local input slicer
- use a frontier teacher model to generate/audit projection artifacts
- train a smaller student projector only after the artifact schema, input

View file

@ -52,12 +52,18 @@ state and re-entry discipline.
- `docs/architecture/aetheria-lore-grounding-architecture.md`
- boundary and plan for grounding training data in authored Aetheria history
while treating Elysium gameplay-era outcomes as procedural branch space
- `docs/architecture/lore-grounding-digest-format.md`
- human-facing format guide for cultural, factional, institutional, role, and
speaker-boundary lore digests
- `schemas/agent-state.schema.json`
- v0 canonical agent-state contract for agents, relationships, events,
scenes, perceived overlays, and dialogue context packs
- `schemas/projection-example.schema.json`
- v0 reviewed projection artifact contract for speaker-local prompt
projection examples
- `schemas/lore-grounding-digest.schema.json`
- v0 contract for grounding historical fixtures in source-backed cultural and
factional pressure fields
- `schemas/agent-state.required-fields.json`
- required first-class variable names for canonical state and relationship
stance
@ -67,6 +73,8 @@ state and re-entry discipline.
- first reviewed Cat and Oz projection examples
- `examples/projections/call-of-the-void.scene-broken-taxi-oz.pretty.json`
- pretty-printed mirror for inspecting the first projection examples
- `examples/lore-grounding/historical-flashpoint.template.json`
- fillable template for the first historical Aetheria grounding digest
- `tools/ghostlight_state.py`
- compact state inspection and evidence or branch updates
- `tools/ghostlight_prepare_compaction.py`
@ -75,21 +83,21 @@ state and re-entry discipline.
- dependency-free validator for the current schema fixture invariants
- `tools/validate_projection_examples.py`
- dependency-free validator for projection example JSONL records
- `tools/validate_lore_grounding.py`
- dependency-free validator for lore grounding digest examples
## What Does Not Exist Yet
- a classifier pipeline
- a prompt renderer
- a full projection training corpus
- a lore grounding digest format
- a deterministic projection input slicer
- a student projection model
- a simulation/event loop
- a relationship engine
- a culture prior engine
The canonical agent-state schema and first projection example schema now exist
as v0 seams. The next implementation target is a lore grounding digest format
for historical Aetheria training fixtures, followed by the deterministic input
slicer that emits speaker-local state before a renderer turns that state into
compact pressure prose.
The canonical agent-state schema, first projection example schema, and first
lore grounding digest schema now exist as v0 seams. The next implementation
target is choosing the first authored historical Aetheria flashpoint for a real
grounding digest, followed by the deterministic input slicer.

View file

@ -44,6 +44,9 @@
the first reviewed artifact seam.
- Use authored historical Aetheria flashpoints, not malleable Elysium
gameplay outcomes, as the first grounded lore-training corpus.
- Maintain `schemas/lore-grounding-digest.schema.json`,
`examples/lore-grounding/`, and `tools/validate_lore_grounding.py` as the
cultural and factional pressure seam for grounded fixtures.
- Use a frontier teacher model to produce reviewed projection artifacts from
structured state and lore grounding digests.
- Save accepted and rejected projection examples as supervised data.

View file

@ -7,7 +7,8 @@
"state:status": "\"C:\\Users\\Meta\\.cache\\codex-runtimes\\codex-primary-runtime\\dependencies\\python\\python.exe\" .\\tools\\ghostlight_state.py status",
"state:prepare-compaction": "\"C:\\Users\\Meta\\.cache\\codex-runtimes\\codex-primary-runtime\\dependencies\\python\\python.exe\" .\\tools\\ghostlight_prepare_compaction.py",
"agent-state:validate": "\"C:\\Users\\Meta\\.cache\\codex-runtimes\\codex-primary-runtime\\dependencies\\python\\python.exe\" .\\tools\\validate_agent_state.py",
"schema:validate": "npm run agent-state:validate && npm run projection:validate",
"projection:validate": "\"C:\\Users\\Meta\\.cache\\codex-runtimes\\codex-primary-runtime\\dependencies\\python\\python.exe\" .\\tools\\validate_projection_examples.py"
"schema:validate": "npm run agent-state:validate && npm run projection:validate && npm run lore-grounding:validate",
"projection:validate": "\"C:\\Users\\Meta\\.cache\\codex-runtimes\\codex-primary-runtime\\dependencies\\python\\python.exe\" .\\tools\\validate_projection_examples.py",
"lore-grounding:validate": "\"C:\\Users\\Meta\\.cache\\codex-runtimes\\codex-primary-runtime\\dependencies\\python\\python.exe\" .\\tools\\validate_lore_grounding.py"
}
}

View file

@ -0,0 +1,490 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/GameCult/Ghostlight/schemas/lore-grounding-digest.schema.json",
"title": "Ghostlight Lore Grounding Digest Schema",
"description": "Compiled lore slice for grounding projection fixtures in authored historical context, culture, institutions, and factional pressure fields.",
"type": "object",
"required": [
"schema_version",
"digest_id",
"source_status",
"fixture_status",
"source_refs",
"historical_context",
"groups",
"cultural_pressure_fields",
"factional_misread_matrix",
"role_pressure_fields",
"speaker_lore_boundaries",
"author_only_boundaries",
"open_questions"
],
"additionalProperties": false,
"properties": {
"schema_version": {
"const": "ghostlight.lore_grounding_digest.v0"
},
"digest_id": {
"type": "string"
},
"source_status": {
"enum": [
"template",
"draft",
"reviewed",
"superseded"
]
},
"fixture_status": {
"enum": [
"historical_grounded",
"transition_grounded",
"procedural_branch",
"promoted_branch"
]
},
"source_refs": {
"type": "array",
"items": {
"$ref": "#/$defs/source_ref"
}
},
"historical_context": {
"$ref": "#/$defs/historical_context"
},
"groups": {
"type": "array",
"items": {
"$ref": "#/$defs/group_profile"
}
},
"cultural_pressure_fields": {
"type": "array",
"items": {
"$ref": "#/$defs/cultural_pressure_field"
}
},
"factional_misread_matrix": {
"type": "array",
"items": {
"$ref": "#/$defs/factional_misread"
}
},
"role_pressure_fields": {
"type": "array",
"items": {
"$ref": "#/$defs/role_pressure_field"
}
},
"speaker_lore_boundaries": {
"type": "array",
"items": {
"$ref": "#/$defs/speaker_lore_boundary"
}
},
"author_only_boundaries": {
"type": "array",
"items": {
"$ref": "#/$defs/sourced_text"
}
},
"open_questions": {
"type": "array",
"items": {
"$ref": "#/$defs/open_question"
}
}
},
"$defs": {
"source_ref": {
"type": "object",
"required": [
"source_id",
"path",
"relevance"
],
"additionalProperties": false,
"properties": {
"source_id": {
"type": "string"
},
"path": {
"type": "string"
},
"title": {
"type": "string"
},
"line_start": {
"type": "integer",
"minimum": 1
},
"line_end": {
"type": "integer",
"minimum": 1
},
"relevance": {
"type": "string"
}
}
},
"sourced_text": {
"type": "object",
"required": [
"text",
"source_refs"
],
"additionalProperties": false,
"properties": {
"text": {
"type": "string"
},
"source_refs": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"historical_context": {
"type": "object",
"required": [
"time_period",
"location",
"summary",
"public_facts",
"ambient_pressures"
],
"additionalProperties": false,
"properties": {
"time_period": {
"type": "string"
},
"location": {
"type": "string"
},
"summary": {
"type": "string"
},
"public_facts": {
"type": "array",
"items": {
"$ref": "#/$defs/sourced_text"
}
},
"ambient_pressures": {
"type": "array",
"items": {
"$ref": "#/$defs/sourced_text"
}
}
}
},
"group_profile": {
"type": "object",
"required": [
"group_id",
"label",
"group_type",
"institutional_logic",
"material_incentives",
"internal_virtues",
"internal_shames",
"prestige_markers",
"taboo_triggers",
"emotional_display_norms",
"trust_defaults",
"speech_register_cues",
"source_refs"
],
"additionalProperties": false,
"properties": {
"group_id": {
"type": "string"
},
"label": {
"type": "string"
},
"group_type": {
"enum": [
"faction",
"institution",
"class",
"profession",
"movement",
"culture",
"subculture"
]
},
"institutional_logic": {
"type": "array",
"items": {
"type": "string"
}
},
"material_incentives": {
"type": "array",
"items": {
"type": "string"
}
},
"internal_virtues": {
"type": "array",
"items": {
"type": "string"
}
},
"internal_shames": {
"type": "array",
"items": {
"type": "string"
}
},
"prestige_markers": {
"type": "array",
"items": {
"type": "string"
}
},
"taboo_triggers": {
"type": "array",
"items": {
"type": "string"
}
},
"emotional_display_norms": {
"type": "array",
"items": {
"type": "string"
}
},
"trust_defaults": {
"type": "array",
"items": {
"type": "string"
}
},
"speech_register_cues": {
"type": "array",
"items": {
"type": "string"
}
},
"source_refs": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"cultural_pressure_field": {
"type": "object",
"required": [
"field_id",
"applies_to",
"pressure_type",
"summary",
"projection_use",
"source_refs"
],
"additionalProperties": false,
"properties": {
"field_id": {
"type": "string"
},
"applies_to": {
"type": "array",
"items": {
"type": "string"
}
},
"pressure_type": {
"enum": [
"virtue",
"shame",
"prestige",
"taboo",
"threat_model",
"trust_default",
"speech_norm",
"status_trigger",
"material_incentive",
"outsider_stereotype"
]
},
"summary": {
"type": "string"
},
"projection_use": {
"type": "string"
},
"source_refs": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"factional_misread": {
"type": "object",
"required": [
"observer_group_id",
"target_group_id",
"observer_read",
"target_self_read",
"misread_patterns",
"likely_insults",
"projection_use",
"source_refs"
],
"additionalProperties": false,
"properties": {
"observer_group_id": {
"type": "string"
},
"target_group_id": {
"type": "string"
},
"observer_read": {
"type": "array",
"items": {
"type": "string"
}
},
"target_self_read": {
"type": "array",
"items": {
"type": "string"
}
},
"misread_patterns": {
"type": "array",
"items": {
"type": "string"
}
},
"likely_insults": {
"type": "array",
"items": {
"type": "string"
}
},
"projection_use": {
"type": "string"
},
"source_refs": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"role_pressure_field": {
"type": "object",
"required": [
"role_id",
"summary",
"obligations",
"available_masks",
"failure_modes",
"source_refs"
],
"additionalProperties": false,
"properties": {
"role_id": {
"type": "string"
},
"summary": {
"type": "string"
},
"obligations": {
"type": "array",
"items": {
"type": "string"
}
},
"available_masks": {
"type": "array",
"items": {
"type": "string"
}
},
"failure_modes": {
"type": "array",
"items": {
"type": "string"
}
},
"source_refs": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"speaker_lore_boundary": {
"type": "object",
"required": [
"speaker_id",
"known_context",
"beliefs",
"misreads",
"must_not_know"
],
"additionalProperties": false,
"properties": {
"speaker_id": {
"type": "string"
},
"known_context": {
"type": "array",
"items": {
"$ref": "#/$defs/sourced_text"
}
},
"beliefs": {
"type": "array",
"items": {
"$ref": "#/$defs/sourced_text"
}
},
"misreads": {
"type": "array",
"items": {
"$ref": "#/$defs/sourced_text"
}
},
"must_not_know": {
"type": "array",
"items": {
"$ref": "#/$defs/sourced_text"
}
}
}
},
"open_question": {
"type": "object",
"required": [
"question",
"blocks_training",
"notes"
],
"additionalProperties": false,
"properties": {
"question": {
"type": "string"
},
"blocks_training": {
"type": "boolean"
},
"notes": {
"type": "string"
}
}
}
}
}

View file

@ -23,3 +23,4 @@
{"ts": "2026-05-01T20:02:29+00:00", "type": "implementation", "status": "accepted", "note": "Added ghostlight.projection_example.v0 schema, first reviewed Cat/Oz projection JSONL examples for scene-broken-taxi-oz, projection example validator, and package scripts that validate both agent-state and projection seams. Next projection implementation step is deterministic speaker-local input slicing."}
{"ts": "2026-05-01T20:19:04+00:00", "type": "design", "status": "accepted", "note": "Projection prompt_text must be self-sufficient for the dialogue model: include speaker-local setting, historical, cultural, socioeconomic, and embodiment context needed for the turn rather than relying on source refs or the full projection artifact."}
{"ts": "2026-05-01T20:31:43+00:00", "type": "design", "status": "accepted", "note": "Revised Aetheria projection-training architecture: grounded training data should start from authored historical lore flashpoints, while Elysium gameplay-era scenes such as Cat/Oz are procedural branch material unless explicitly promoted. Next step is a lore grounding digest format and first historical flashpoint selection."}
{"ts": "2026-05-01T20:38:47+00:00", "type": "implementation", "status": "accepted", "note": "Added ghostlight.lore_grounding_digest.v0 schema, template, human format guide, and validator. Lore digests now explicitly model cultural pressure fields, factional misread maps, role pressures, speaker lore boundaries, and author-only exclusions. Next step is choosing the first authored historical Aetheria flashpoint and filling a real digest."}

View file

@ -91,7 +91,8 @@ accepted_design:
- Future social-simulation mechanisms should be documented and tested through projection artifacts before promotion into the canonical schema.
- Projection examples use `ghostlight.projection_example.v0` JSONL records with traceable known facts, active pressures, tensions, response affordances, voice surface, rendered prompt text, and audit checks.
- Aetheria projection training has two modes: historical grounded fixtures from authored lore, and procedural Elysium branch fixtures that test generation without canonizing gameplay-era outcomes.
- Lore grounding digests use `ghostlight.lore_grounding_digest.v0` records to distill authored lore into cultural pressure fields, factional misread maps, role pressures, speaker knowledge boundaries, and author-only exclusions.
current_status:
summary: Ghostlight now has the Epiphany-style persistence spine, the first architecture payload, the v0 canonical agent-state schema seam, prompt projection docs, immediate schema fixes from evaluation, first reviewed Cat/Oz projection examples, a revised Aetheria lore-grounding architecture, and a documented teacher/student distillation path for projection.
next_action: Define the lore grounding digest format for historical Aetheria projection fixtures, then choose the first authored historical flashpoint for grounded training.
summary: Ghostlight now has the Epiphany-style persistence spine, the first architecture payload, the v0 canonical agent-state schema seam, prompt projection docs, immediate schema fixes from evaluation, first reviewed Cat/Oz projection examples, a revised Aetheria lore-grounding architecture, a lore grounding digest schema, and a documented teacher/student distillation path for projection.
next_action: Choose the first authored historical Aetheria flashpoint for grounded training, then fill the first real lore grounding digest from the template.

View file

@ -0,0 +1,211 @@
"""Validate Ghostlight lore grounding digest examples.
This focused validator checks the structural invariants needed before lore
digests can feed grounded projection fixtures.
"""
from __future__ import annotations
import argparse
import json
from pathlib import Path
from typing import Any
ROOT = Path(__file__).resolve().parents[1]
DEFAULT_EXAMPLES = [
ROOT / "examples" / "lore-grounding" / "historical-flashpoint.template.json"
]
class ValidationError(Exception):
pass
def load_json(path: Path) -> Any:
with path.open("r", encoding="utf-8") as handle:
return json.load(handle)
def require(condition: bool, message: str) -> None:
if not condition:
raise ValidationError(message)
def require_keys(obj: dict[str, Any], keys: list[str], path: str) -> None:
missing = [key for key in keys if key not in obj]
require(not missing, f"{path} missing required keys: {', '.join(missing)}")
def require_nonempty_string(value: Any, path: str) -> None:
require(isinstance(value, str) and value.strip(), f"{path} must be a non-empty string")
def require_string_list(value: Any, path: str) -> None:
require(isinstance(value, list), f"{path} must be an array")
for index, item in enumerate(value):
require_nonempty_string(item, f"{path}[{index}]")
def validate_sourced_text(obj: Any, path: str) -> None:
require(isinstance(obj, dict), f"{path} must be an object")
require_keys(obj, ["text", "source_refs"], path)
require_nonempty_string(obj["text"], f"{path}.text")
require_string_list(obj["source_refs"], f"{path}.source_refs")
def validate_sourced_text_list(value: Any, path: str) -> None:
require(isinstance(value, list), f"{path} must be an array")
for index, item in enumerate(value):
validate_sourced_text(item, f"{path}[{index}]")
def validate_digest(document: dict[str, Any], source: Path) -> None:
require(document.get("schema_version") == "ghostlight.lore_grounding_digest.v0", f"{source} has wrong schema_version")
require_keys(
document,
[
"digest_id",
"source_status",
"fixture_status",
"source_refs",
"historical_context",
"groups",
"cultural_pressure_fields",
"factional_misread_matrix",
"role_pressure_fields",
"speaker_lore_boundaries",
"author_only_boundaries",
"open_questions",
],
str(source),
)
require(document["source_status"] in {"template", "draft", "reviewed", "superseded"}, f"{source}.source_status is invalid")
require(document["fixture_status"] in {"historical_grounded", "transition_grounded", "procedural_branch", "promoted_branch"}, f"{source}.fixture_status is invalid")
source_ids: set[str] = set()
for index, ref in enumerate(document["source_refs"]):
path = f"{source}.source_refs[{index}]"
require_keys(ref, ["source_id", "path", "relevance"], path)
require_nonempty_string(ref["source_id"], f"{path}.source_id")
require_nonempty_string(ref["path"], f"{path}.path")
require_nonempty_string(ref["relevance"], f"{path}.relevance")
source_ids.add(ref["source_id"])
require(source_ids, f"{source}.source_refs must not be empty")
context = document["historical_context"]
require_keys(context, ["time_period", "location", "summary", "public_facts", "ambient_pressures"], f"{source}.historical_context")
for key in ["time_period", "location", "summary"]:
require_nonempty_string(context[key], f"{source}.historical_context.{key}")
validate_sourced_text_list(context["public_facts"], f"{source}.historical_context.public_facts")
validate_sourced_text_list(context["ambient_pressures"], f"{source}.historical_context.ambient_pressures")
group_ids: set[str] = set()
for index, group in enumerate(document["groups"]):
path = f"{source}.groups[{index}]"
require_keys(
group,
[
"group_id",
"label",
"group_type",
"institutional_logic",
"material_incentives",
"internal_virtues",
"internal_shames",
"prestige_markers",
"taboo_triggers",
"emotional_display_norms",
"trust_defaults",
"speech_register_cues",
"source_refs",
],
path,
)
require_nonempty_string(group["group_id"], f"{path}.group_id")
group_ids.add(group["group_id"])
for key in [
"institutional_logic",
"material_incentives",
"internal_virtues",
"internal_shames",
"prestige_markers",
"taboo_triggers",
"emotional_display_norms",
"trust_defaults",
"speech_register_cues",
"source_refs",
]:
require_string_list(group[key], f"{path}.{key}")
require(group_ids, f"{source}.groups must not be empty")
for index, field in enumerate(document["cultural_pressure_fields"]):
path = f"{source}.cultural_pressure_fields[{index}]"
require_keys(field, ["field_id", "applies_to", "pressure_type", "summary", "projection_use", "source_refs"], path)
require_string_list(field["applies_to"], f"{path}.applies_to")
for group_id in field["applies_to"]:
require(group_id in group_ids, f"{path}.applies_to references unknown group: {group_id}")
require_nonempty_string(field["summary"], f"{path}.summary")
require_nonempty_string(field["projection_use"], f"{path}.projection_use")
require_string_list(field["source_refs"], f"{path}.source_refs")
for index, misread in enumerate(document["factional_misread_matrix"]):
path = f"{source}.factional_misread_matrix[{index}]"
require_keys(
misread,
[
"observer_group_id",
"target_group_id",
"observer_read",
"target_self_read",
"misread_patterns",
"likely_insults",
"projection_use",
"source_refs",
],
path,
)
for key in ["observer_group_id", "target_group_id"]:
require(misread[key] in group_ids, f"{path}.{key} references unknown group: {misread[key]}")
for key in ["observer_read", "target_self_read", "misread_patterns", "likely_insults", "source_refs"]:
require_string_list(misread[key], f"{path}.{key}")
require_nonempty_string(misread["projection_use"], f"{path}.projection_use")
for index, role in enumerate(document["role_pressure_fields"]):
path = f"{source}.role_pressure_fields[{index}]"
require_keys(role, ["role_id", "summary", "obligations", "available_masks", "failure_modes", "source_refs"], path)
require_nonempty_string(role["role_id"], f"{path}.role_id")
require_nonempty_string(role["summary"], f"{path}.summary")
for key in ["obligations", "available_masks", "failure_modes", "source_refs"]:
require_string_list(role[key], f"{path}.{key}")
for index, boundary in enumerate(document["speaker_lore_boundaries"]):
path = f"{source}.speaker_lore_boundaries[{index}]"
require_keys(boundary, ["speaker_id", "known_context", "beliefs", "misreads", "must_not_know"], path)
require_nonempty_string(boundary["speaker_id"], f"{path}.speaker_id")
for key in ["known_context", "beliefs", "misreads", "must_not_know"]:
validate_sourced_text_list(boundary[key], f"{path}.{key}")
validate_sourced_text_list(document["author_only_boundaries"], f"{source}.author_only_boundaries")
for index, question in enumerate(document["open_questions"]):
path = f"{source}.open_questions[{index}]"
require_keys(question, ["question", "blocks_training", "notes"], path)
require_nonempty_string(question["question"], f"{path}.question")
require(isinstance(question["blocks_training"], bool), f"{path}.blocks_training must be boolean")
require_nonempty_string(question["notes"], f"{path}.notes")
def main() -> int:
parser = argparse.ArgumentParser(description="Validate Ghostlight lore grounding digest examples.")
parser.add_argument("paths", nargs="*", type=Path, help="Lore grounding digest JSON files to validate.")
args = parser.parse_args()
paths = args.paths or DEFAULT_EXAMPLES
for path in paths:
validate_digest(load_json(path), path)
print(f"ok: {path}")
return 0
if __name__ == "__main__":
raise SystemExit(main())