Tighten agent state schema from evaluation

This commit is contained in:
Meta Vens 2026-05-01 20:57:34 +01:00
commit 5f4e7c6bb2
14 changed files with 615 additions and 48 deletions

View file

@ -19,3 +19,4 @@
{"ts": "2026-05-01T19:13:15+00:00", "type": "design", "status": "accepted", "note": "Relationship stance is directional. Added Oz->Cat alongside Cat->Oz in the Call of the Void fixture and taught the validator to require reciprocal relationship edges for represented agent pairs."}
{"ts": "2026-05-01T19:18:05+00:00", "type": "design", "status": "accepted", "note": "Defined prompt projection as a six-stage contract: select speaker-local inputs, compute active pressure, detect tensions, derive response affordances, render compact prompt sections, then evaluate whether target verbal behaviors emerge from state interactions."}
{"ts": "2026-05-01T19:26:23+00:00", "type": "design", "status": "accepted", "note": "Persisted projection distillation plan: use a frontier teacher to generate reviewed projection artifacts, collect accepted and rejected examples, then train a smaller student projector only after the projection schema, input slicer, and evaluator stabilize."}
{"ts": "2026-05-01T19:57:04+00:00", "type": "design", "status": "accepted", "note": "Evaluation follow-up accepted immediate schema fixes: split interpersonal_warmth from verbal_warmth, add Cat perception of Oz, populate Cat/Oz relationship summaries, enrich event-drone-lie with observed exchange, private interpretations, and event effects, and park broader social-simulation mechanisms in docs/architecture/schema-future-mechanisms.md."}

View file

@ -83,7 +83,10 @@ accepted_design:
- Relationship stance is directional; reciprocal agent pairs need separate edges because trust, fear, obligation, dependence, and betrayal expectations are not symmetric by default.
- Prompt projection should compile state into speaker-local pressure prose through input selection, active-pressure scoring, tension detection, response affordance derivation, compact prompt rendering, and post-generation evaluation.
- Projection distillation is the long-term optimization path: a frontier teacher model generates reviewed projection artifacts, and a smaller student projector is trained only after the artifact schema, deterministic input slicer, and evaluator are stable.
- Behavioral warmth and verbal warmth are separate axes: `interpersonal_warmth` describes social care or welcome, while `verbal_warmth` describes soft or reassuring language surface.
- Events can carry lightweight observed exchange, private interpretation, and event-effect scaffolding so prompt projection can reason from appraisal and consequence without pretending the v0 schema is already a full transition engine.
- Future social-simulation mechanisms should be documented and tested through projection artifacts before promotion into the canonical schema.
current_status:
summary: Ghostlight now has the Epiphany-style persistence spine, the first architecture payload, the v0 canonical agent-state schema seam, a prompt projection contract, and a documented teacher/student distillation path for projection.
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, and a documented teacher/student distillation path for projection.
next_action: Define the projection example schema and create the first reviewed Cat/Oz projection artifacts from the Call of the Void fixture.