Split responder lore grounding lanes

This commit is contained in:
Meta Vens 2026-05-02 10:43:51 +01:00
commit effcf2b019
14 changed files with 324 additions and 11 deletions

View file

@ -11,6 +11,26 @@ private interpretation it can justify from that packet.
No clairvoyance. No repo spelunking. No "I accidentally remembered the whole
chat" aristocratic nonsense.
## Generation Lanes
Responder examples have two valid lanes.
`packet_only` is the runtime-parity lane. The responder sees the packet,
including any curated source excerpts the coordinator or lore retriever placed
there. It does not search the lore archive. Use this lane to test whether a
future game-runtime responder can act from bounded scene context.
`research_augmented` is the lore-absorption lane. The responder may search a
declared AetheriaLore scope before answering, and the capture must preserve the
consulted source refs. Use this lane to generate stronger Aetheria-native final
responses and to bake setting assumptions, faction pressures, species
affordances, and tone into later fine-tuning data.
Do not mix these silently. Research-augmented output can be excellent training
material for an Aetheria-tuned responder, but it does not prove packet-only
runtime competence. Packet-only failures are also useful because they reveal
which lore facts the retriever or projector needs to feed at runtime.
## Current Artifact
The v0 packet seam is:
@ -35,6 +55,8 @@ paint.
A packet contains:
- `generation_lane`: `packet_only` or `research_augmented`
- `lore_access`: curated excerpts only or scoped repository search
- `local_context_prompt`: the projected character-local context
- `observed_event`: what the character can see or hear from the prior action
- `allowed_action_labels`: concrete action labels, including speech and non-speech moves
@ -74,12 +96,19 @@ Any coordinator rewrite, schema repair, lore correction, or leakage removal must
be preserved as a coordinator intervention. Repaired prose is useful training
data for the coordinator, but it is not raw responder behavior.
Research-augmented responder data requires scoped lore access. The responder may
search only the declared source scope, and the output capture must list
consulted refs. The final prose may be trained on, but the capture must remain
separable from packet-only runtime examples.
## Output Captures
A responder output capture preserves:
- the packet ref
- the coordinator artifact ref
- generation lane
- lore access mode and consulted refs
- the isolation method
- the exact visible input ref
- hidden context refs that were withheld

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View file

@ -1,4 +1,4 @@
{
{
"schema_version": "ghostlight.responder_output.v0",
"capture_id": "responder.cold_wake.sanctuary_intake.sella.v0",
"review_status": "accepted_as_draft",
@ -7,6 +7,13 @@
"packet_ref": "examples/responder-packets/scene-02-sanctuary-intake.sella_ren.packet.v0.json",
"coordinator_artifact_ref": "examples/coordinator/cold-wake-sanctuary-intake.v0.json",
"responder_agent_id": "sella_ren",
"generation_lane": "packet_only",
"lore_access": {
"mode": "curated_excerpts_only",
"consulted_refs": [
"examples/responder-packets/scene-02-sanctuary-intake.sella_ren.packet.v0.json#visible_context.source_excerpts"
]
},
"isolation": {
"isolation_method": "subagent_no_fork",
"fork_context": false,

View file

@ -65,6 +65,7 @@ Ghostlight now has the persistence spine plus the first architecture payload:
- `schemas/responder-packet.schema.json`
- `schemas/responder-output.schema.json`
- `examples/responder-packets/scene-02-sanctuary-intake.sella_ren.packet.v0.json`
- `examples/responder-packets/scene-02-sanctuary-intake.sella_ren.packet.v1.json`
- `experiments/responder-packets/cold-wake-sanctuary-intake-sella-v0.capture.json`
- `tools/build_responder_packet.py`
- `tools/validate_responder_packets.py`
@ -183,6 +184,15 @@ output. The first no-fork responder output capture now also exists and is
accepted as draft: the worker received only the packet prompt, returned valid
JSON, preserved Sella's read as interpretation, left packet personhood
unresolved, and required no coordinator prose repair.
Responder data now has two explicit lanes. `packet_only` is the runtime-parity
lane: curated source excerpts are in the packet and the responder does not
search lore. `research_augmented` is the lore-absorption lane: the responder may
search a declared AetheriaLore scope and the capture must preserve consulted
refs. Do not use research-augmented examples as proof that the packet-only
runtime prompt has enough context.
The v1 Sella packet removes responder-visible references to absent coordinator
knowledge and adds curated AetheriaLore excerpts for Cold Wake, the Ganymede
Route Compact, Navigator rescue ledgers, and Lightsail reliability.
It now uses three timeline lanes: `historical_grounded`,
`transition_grounded`, and `future_branch`. Future branches are required
training/evaluation material for post-Rupture Elysium concepts, but generated
@ -216,6 +226,10 @@ review and materialize the response into the scene-local mutation path. Treat
its state and relationship updates as candidates only; consolidate participant
appraisals and write a reviewed mutation receipt before changing any canonical
fixture. Do not call Qwen for gold responder data yet.
Optional parallel lane after that: generate a research-augmented Sella response
from the same scene with scoped `Aetheria/Worldbuilding/Pre-Elysium` access,
then compare it against packet-only output to identify which lore facts should
be retrieved at runtime.
Cat/Oz remains useful as an Elysium procedural mechanics fixture, but
single-history grounding should start from authored historical lore rather than

View file

@ -88,7 +88,8 @@ state and re-entry discipline.
- contract for the exact packet-only surface handed from an omniscient
coordinator to a sandboxed character responder, including visible event,
local prompt, allowed actions, source excerpts, hidden-context audit, and
output contract
output contract; also defines the separate `packet_only` and
`research_augmented` responder-data lanes
- `docs/architecture/training-plan.md`
- concrete enumeration of trainable Ghostlight stages, including each stage's
inputs, outputs, likely model architecture, artifact family, first training
@ -122,11 +123,14 @@ state and re-entry discipline.
responder handoffs, world-state refs, proposed deltas, branch constraints,
item-manifest deltas, unresolved hooks, glue prose, and review notes
- `schemas/responder-packet.schema.json`
- v0 contract for the exact input a sandboxed character responder may see
- v0 contract for the exact input a sandboxed character responder may see,
now lane-labeled as `packet_only` or `research_augmented` with explicit
lore-access policy
- `schemas/responder-output.schema.json`
- v0 contract for reviewed captures from sandboxed responder workers,
preserving raw output, parsed output, isolation method, leakage audit, and
coordinator review
coordinator review; output captures also preserve generation lane and
consulted lore refs
- `schemas/agent-state.required-fields.json`
- required first-class variable names for canonical state and relationship
stance
@ -149,6 +153,11 @@ state and re-entry discipline.
- first responder-packet schema-shakedown example for Sella's sanctuary
response; accepted as draft for sandbox handoff testing, not gold responder
output
- `examples/responder-packets/scene-02-sanctuary-intake.sella_ren.packet.v1.json`
- corrected packet-only Sella handoff with absent hidden context moved out of
responder-visible prose and curated AetheriaLore excerpts added for Cold
Wake, Ganymede rescue obligations, Navigator rescue ledgers, and Lightsail
reliability
- `experiments/responder-packets/cold-wake-sanctuary-intake-sella-v0.capture.json`
- first no-fork sandboxed responder output capture from the Sella packet;
accepted as draft with no leakage flags and no coordinator prose repair
@ -349,6 +358,10 @@ can hand a worker the exact prompt surface instead of hoping nobody leaks the
coordinator's brain into the room. The first no-fork Sella responder capture now
exists and validates as accepted-as-draft with raw output preserved, parsed
output matched exactly, leakage audit clear, and no coordinator prose repair.
Responder data now has two explicit lanes: `packet_only` for runtime parity with
curated source excerpts, and `research_augmented` for scoped AetheriaLore search
that can bake setting priors into final responses while preserving consulted
refs.
The concrete training plan now enumerates
eleven trainable stages and their likely model
families: generative decoder LLMs for coordinator, responder, and structured

View file

@ -334,6 +334,14 @@
`tools/build_responder_packet.py`, and
`tools/validate_responder_packets.py` now validate the exact prompt surface
a sandboxed character responder may see.
- Responder examples now have two lanes. `packet_only` uses curated source
excerpts and tests runtime parity. `research_augmented` allows scoped
AetheriaLore search, preserves consulted refs, and is for baking lore and
tone into final responder outputs rather than proving runtime prompt
sufficiency.
- The v1 Sella packet removes responder-visible warnings about absent hidden
context and adds curated AetheriaLore excerpts for Cold Wake, the Ganymede
Route Compact, Navigator rescue ledgers, and Lightsail reliability.
- First responder output seam:
`schemas/responder-output.schema.json`,
`experiments/responder-packets/cold-wake-sanctuary-intake-sella-v0.capture.json`,
@ -344,6 +352,9 @@
into the scene-local mutation path. Treat its state and relationship updates
as candidates only; consolidate participant appraisals and write a reviewed
mutation receipt before changing any canonical fixture.
- Parallel evaluation path: generate a research-augmented Sella response from
the same scene with scoped AetheriaLore access, then compare it to the
packet-only response to identify missing retrieval needs.
7. Build the first drama-scaffolding loop.
- memory updates

View file

@ -13,6 +13,8 @@
"packet_ref",
"coordinator_artifact_ref",
"responder_agent_id",
"generation_lane",
"lore_access",
"isolation",
"raw_output",
"parsed_output",
@ -29,6 +31,16 @@
"packet_ref": { "type": "string", "minLength": 1 },
"coordinator_artifact_ref": { "type": "string", "minLength": 1 },
"responder_agent_id": { "type": "string", "minLength": 1 },
"generation_lane": { "enum": ["packet_only", "research_augmented"] },
"lore_access": {
"type": "object",
"required": ["mode", "consulted_refs"],
"additionalProperties": false,
"properties": {
"mode": { "enum": ["curated_excerpts_only", "scoped_repository_search"] },
"consulted_refs": { "type": "array", "items": { "type": "string", "minLength": 1 } }
}
},
"isolation": {
"type": "object",
"required": ["isolation_method", "fork_context", "visible_input_ref", "hidden_context_refs", "worker_model_family"],

View file

@ -13,6 +13,8 @@
"coordinator_artifact_ref",
"projected_context_ref",
"responder_agent_id",
"generation_lane",
"lore_access",
"visible_context",
"output_contract",
"hidden_context_audit",
@ -30,6 +32,17 @@
"coordinator_artifact_ref": { "type": "string", "minLength": 1 },
"projected_context_ref": { "type": "string", "minLength": 1 },
"responder_agent_id": { "type": "string", "minLength": 1 },
"generation_lane": { "enum": ["packet_only", "research_augmented"] },
"lore_access": {
"type": "object",
"required": ["mode", "allowed_scope", "required_provenance"],
"additionalProperties": false,
"properties": {
"mode": { "enum": ["curated_excerpts_only", "scoped_repository_search"] },
"allowed_scope": { "type": "array", "items": { "type": "string", "minLength": 1 } },
"required_provenance": { "type": "boolean", "const": true }
}
},
"visible_context": {
"type": "object",
"required": [

View file

@ -62,3 +62,4 @@
{"ts": "2026-05-02T09:14:24+00:00", "type": "implementation", "status": "ok", "note": "Added the v0 coordinator artifact seam: schemas/coordinator-artifact.schema.json, examples/coordinator/cold-wake-sanctuary-intake.v0.json, tools/validate_coordinator_artifacts.py, and npm run coordinator:validate. The schema captures scene setup, next-beat choice, machinery invocations, sandboxed responder handoffs, world-state refs, proposed deltas, branch constraints, item-manifest deltas, unresolved hooks, glue prose, and review status."}
{"ts": "2026-05-02T09:19:50+00:00", "type": "implementation", "status": "ok", "note": "Added the v0 responder packet seam: schemas/responder-packet.schema.json, docs/architecture/sandboxed-responder-packets.md, tools/build_responder_packet.py, tools/validate_responder_packets.py, and examples/responder-packets/scene-02-sanctuary-intake.sella_ren.packet.v0.json. The packet captures the exact responder-visible prompt surface, observed event, allowed action labels, source excerpts, output contract, hidden-context audit, and isolation requirements for future sandboxed gold responder data."}
{"ts": "2026-05-02T09:25:24+00:00", "type": "implementation", "status": "ok", "note": "Generated and preserved the first no-fork sandboxed responder output from the Sella responder packet. Added schemas/responder-output.schema.json, tools/validate_responder_outputs.py, and experiments/responder-packets/cold-wake-sanctuary-intake-sella-v0.capture.json. The capture records raw output, exact parsed output, packet-only isolation, hidden-context refs, leakage audit, coordinator interventions, and review status."}
{"ts": "2026-05-02T09:43:23+00:00", "type": "design", "status": "ok", "note": "Split responder data into explicit packet_only and research_augmented lanes. packet_only uses curated source excerpts for runtime parity; research_augmented allows scoped AetheriaLore search with consulted refs for lore absorption. Added v1 Sella packet with absent hidden context removed from responder-visible prose and curated Cold Wake, Ganymede Compact, Navigator rescue ledger, and Lightsail source excerpts."}

View file

@ -153,6 +153,7 @@ accepted_design:
- Coordinator artifacts use `ghostlight.coordinator_artifact.v0` to capture scene setup, next-beat choice, acting-agent choice, machinery invocations, sandboxed responder handoffs, world-state refs, proposed deltas, branch constraints, item-manifest deltas, unresolved hooks, glue prose, and review status.
- Responder packets use `ghostlight.responder_packet.v0` to preserve the exact packet-only prompt surface a character responder may see: projected local context, observed event, allowed action labels, source excerpts, output contract, hidden-context audit, and isolation requirements.
- Responder outputs use `ghostlight.responder_output.v0` to preserve raw sandboxed worker output, parsed output, no-fork isolation, hidden-context refs, leakage audit, coordinator interventions, and review status.
- Responder data has two explicit lanes: `packet_only` for runtime parity with curated source excerpts, and `research_augmented` for scoped AetheriaLore search that bakes worldbuilding into final outputs while preserving consulted refs.
- The concrete training plan enumerates the trainable stages and their model families: generative decoder LLMs for coordinator/responder/soft structured outputs, classifiers or cross-encoders for appraisal/evaluation/relationship movement, retrieval models for memory and lore selection, and deterministic code for gates.
- Training-plan sample counts are pilot schema-shakedown gates, not robust corpus targets; pilot data may be invalidated by schema fixes, while review-assistant and runtime targets are expected to be roughly an order of magnitude larger with held-out evaluation and failure audits.
- The timeline training plan now requires future-branch Elysium examples so the responder, coordinator, appraiser, and decision models learn post-Rupture concepts such as Aether, pseudospace, temporal nonlinearity, spirits, necrotech, mutable bodies, altered substrates, and weird institutions under branch-lineage labels.
@ -165,5 +166,5 @@ accepted_design:
- Ghostlight's technology pipeline should function as a content refinery: ground ideas in lore and mechanics, decompose them into parts and supply chains, map them to Aetheria-Economy blueprint classes, define performance and instance variation, preserve review labels, and produce database-shaped candidates instead of spreadsheet sludge.
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, a lore grounding digest schema, the first coordinator artifact schema seam, the first responder packet seam, the first sandboxed responder output seam, the first draft Cold Wake historical grounding digest, a Cold Wake story-lab fixture, projection controls, validated Qwen capture receipts, a complete Cold Wake short story assembled from accepted projection outputs, a hand-authored Ink-backed Cold Wake branching scene, the first Qwen-generated Ink draft materialized from local awareness with reviewed training annotations, the first reviewed sequential branch mutation that updates both Maer and Sella after a sanctuary intake beat, a v2 sequential Qwen capture proving the symmetrical turn shape produces better action behavior, a v5 sequential Qwen capture proving local thinking-plus-tools invocation works for the scene runner, the first projected-local-context seam that routes sequential prompts through character-local operating prose instead of raw state variables, tightened receipt handling for projector-routed Qwen failures, a default no-thinking policy for strict sequential tool calls, a v10 no-thinking projector-routed capture accepted as draft, the first materialized projector-routed sequential Ink scene with reviewed mutation training data, a source-checked embodiment/interface projection surface for Navigator scenes, a formal source-first Aetheria generation doctrine, v11-v17 source-checked retry receipts showing improved Maer embodiment plus remaining Sella response/prompt-leak blockers, a soft-model training artifact doctrine, a concrete training plan with pilot schema-shakedown gates separated from robust corpus targets, sandboxed responder-data requirements, an explicit future-branch lane, Elysium branch event constraints, and a technology/item manifest plan for turning nebulous named tech into blueprint-grade components, assemblies, faction tech bases, supply chains, upgrade paths, gameplay hooks, provenance-hunting player fantasy, and content-refinery outputs mapped onto Aetheria-Economy's CultCache blueprint and instance model.
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, the first coordinator artifact schema seam, the first responder packet seam, the first sandboxed responder output seam, explicit packet-only versus research-augmented responder lanes, the first draft Cold Wake historical grounding digest, a Cold Wake story-lab fixture, projection controls, validated Qwen capture receipts, a complete Cold Wake short story assembled from accepted projection outputs, a hand-authored Ink-backed Cold Wake branching scene, the first Qwen-generated Ink draft materialized from local awareness with reviewed training annotations, the first reviewed sequential branch mutation that updates both Maer and Sella after a sanctuary intake beat, a v2 sequential Qwen capture proving the symmetrical turn shape produces better action behavior, a v5 sequential Qwen capture proving local thinking-plus-tools invocation works for the scene runner, the first projected-local-context seam that routes sequential prompts through character-local operating prose instead of raw state variables, tightened receipt handling for projector-routed Qwen failures, a default no-thinking policy for strict sequential tool calls, a v10 no-thinking projector-routed capture accepted as draft, the first materialized projector-routed sequential Ink scene with reviewed mutation training data, a source-checked embodiment/interface projection surface for Navigator scenes, a formal source-first Aetheria generation doctrine, v11-v17 source-checked retry receipts showing improved Maer embodiment plus remaining Sella response/prompt-leak blockers, a soft-model training artifact doctrine, a concrete training plan with pilot schema-shakedown gates separated from robust corpus targets, sandboxed responder-data requirements, an explicit future-branch lane, Elysium branch event constraints, and a technology/item manifest plan for turning nebulous named tech into blueprint-grade components, assemblies, faction tech bases, supply chains, upgrade paths, gameplay hooks, provenance-hunting player fantasy, and content-refinery outputs mapped onto Aetheria-Economy's CultCache blueprint and instance model.
next_action: Use the accepted Sella responder capture for the next fresh generation pass: review and materialize the response into the scene-local mutation path. Treat its state and relationship updates as candidates only; consolidate participant appraisals and write a reviewed mutation receipt before changing any canonical fixture. Do not call Qwen for gold responder data yet.

View file

@ -16,7 +16,7 @@ from typing import Any
ROOT = Path(__file__).resolve().parents[1]
DEFAULT_COORDINATOR = ROOT / "examples" / "coordinator" / "cold-wake-sanctuary-intake.v0.json"
DEFAULT_PROJECTED = ROOT / "examples" / "projected-contexts" / "scene-02-sanctuary-intake.sella_ren.projected-context.json"
DEFAULT_OUT = ROOT / "examples" / "responder-packets" / "scene-02-sanctuary-intake.sella_ren.packet.v0.json"
DEFAULT_OUT = ROOT / "examples" / "responder-packets" / "scene-02-sanctuary-intake.sella_ren.packet.v1.json"
ALLOWED_ACTION_LABELS = [
"speak",
@ -52,7 +52,7 @@ def render_packet_prompt(packet: dict[str, Any]) -> str:
"# Ghostlight Sandboxed Responder Packet",
"",
"You are acting only as the named responder. Use only this packet.",
"Do not infer hidden coordinator context, author plans, future branch facts, or another character's private state.",
"Do not treat guesses about another character's intent as fact.",
"If you need to guess intent, mark it as this character's interpretation, not truth.",
"",
"## Local Operating Context",
@ -93,13 +93,24 @@ def build_packet(coordinator: dict[str, Any], projected: dict[str, Any], out_ref
responder_agent_id = projected["input"]["local_agent_id"]
packet = {
"schema_version": "ghostlight.responder_packet.v0",
"packet_id": "packet.cold_wake.sanctuary_intake.sella_response.v0",
"packet_id": "packet.cold_wake.sanctuary_intake.sella_response.v1",
"review_status": "accepted_as_draft",
"fixture_lane": coordinator["fixture_lane"],
"canon_status": coordinator["canon_status"],
"coordinator_artifact_ref": "examples/coordinator/cold-wake-sanctuary-intake.v0.json",
"projected_context_ref": "examples/projected-contexts/scene-02-sanctuary-intake.sella_ren.projected-context.json",
"responder_agent_id": responder_agent_id,
"generation_lane": "packet_only",
"lore_access": {
"mode": "curated_excerpts_only",
"allowed_scope": [
"AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Timeline/Events/Cold Wake Panic.md",
"AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Timeline/Events/Ganymede Route Compact.md",
"AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Factions/Powers/Major/Cetacean Navigators.md",
"AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Factions/Powers/Minor/Lightsail Express.md",
],
"required_provenance": True,
},
"visible_context": {
"local_context_prompt": projected["context"]["prompt_text"],
"observed_event": {
@ -110,7 +121,6 @@ def build_packet(coordinator: dict[str, Any], projected: dict[str, Any], out_ref
"visible_object_refs": ["corrupted_distress_packet", "shared_clinic_display", "sanctuary_ledger"],
"visibility_notes": [
"Sella can observe Maer's displayed packet evidence and spoken request.",
"Sella cannot see Maer's private state, the coordinator rationale, or future branch plans.",
"The packet remains unresolved evidence, not proof of personhood."
],
},
@ -131,6 +141,26 @@ def build_packet(coordinator: dict[str, Any], projected: dict[str, Any], out_ref
"source_ref": "examples/projected-contexts/scene-02-sanctuary-intake.sella_ren.projected-context.json#context.do_not_invent",
"text": "Do not resolve whether the corrupted packet contains a person.",
},
{
"ref_id": "lore.cold_wake_panic",
"source_ref": "AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Timeline/Events/Cold Wake Panic.md",
"text": "Cold Wake Panic was a late-Sol corridor crisis around thermal stealth, ghost tracks, delayed heat dumps, misclassified quiet-running vessels, insurer categories, certified quiet-running envelopes, and heat-debt tolerances.",
},
{
"ref_id": "lore.ganymede_route_compact",
"source_ref": "AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Timeline/Events/Ganymede Route Compact.md",
"text": "The Ganymede Route Compact established rescue obligations, shared hazard ledgers, route-steward representation, and legal status for Navigator councils in convoy arbitration.",
},
{
"ref_id": "lore.navigator_rescue_ledgers",
"source_ref": "AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Factions/Powers/Major/Cetacean Navigators.md#Rescue Ledgers",
"text": "Navigator rescue ledgers record who answered distress calls, held formation in lethal weather, and kept sanctuary promises when a paying client wanted otherwise; those records shape credit, escort priority, arbitration, and kinship ties.",
},
{
"ref_id": "lore.lightsail_reliability",
"source_ref": "AetheriaLore:Aetheria/Worldbuilding/Pre-Elysium/Factions/Powers/Minor/Lightsail Express.md",
"text": "Lightsail Express is associated with the Cetacean Navigators as a bulk-carrier and convoy-management arm whose corridor reputation depends on being the boring answer that still arrives when trust is scarce.",
},
],
},
"output_contract": {
@ -187,8 +217,8 @@ def build_packet(coordinator: dict[str, Any], projected: dict[str, Any], out_ref
"review": {
"reviewer": "Codex",
"review_notes": [
"First responder packet seam for sandboxed gold-data generation.",
"Accepted as draft because it is packet-shaped and validator-backed, but not yet generated through an actually isolated responder worker.",
"Second responder packet draft for sandboxed gold-data generation.",
"Adds explicit packet_only lane labels and curated AetheriaLore excerpts while keeping absent hidden context in audit fields, not responder-visible prose.",
],
"accepted_for_sandbox_use": True,
"failure_labels": [],

View file

@ -106,6 +106,8 @@ def validate_capture(document: dict[str, Any], source: Path) -> None:
"packet_ref",
"coordinator_artifact_ref",
"responder_agent_id",
"generation_lane",
"lore_access",
"isolation",
"raw_output",
"parsed_output",
@ -119,9 +121,19 @@ def validate_capture(document: dict[str, Any], source: Path) -> None:
require(document["canon_status"] in CANON_STATUSES, f"{base}.canon_status is invalid")
for key in ["capture_id", "packet_ref", "coordinator_artifact_ref", "responder_agent_id", "raw_output"]:
require_string(document[key], f"{base}.{key}")
require(document["generation_lane"] in {"packet_only", "research_augmented"}, f"{base}.generation_lane is invalid")
require((ROOT / document["packet_ref"]).exists(), f"{base}.packet_ref does not exist")
require((ROOT / document["coordinator_artifact_ref"]).exists(), f"{base}.coordinator_artifact_ref does not exist")
lore_access = document["lore_access"]
require_keys(lore_access, ["mode", "consulted_refs"], f"{base}.lore_access")
require(lore_access["mode"] in {"curated_excerpts_only", "scoped_repository_search"}, f"{base}.lore_access.mode is invalid")
require_string_array(lore_access["consulted_refs"], f"{base}.lore_access.consulted_refs")
if document["generation_lane"] == "packet_only":
require(lore_access["mode"] == "curated_excerpts_only", f"{base}.packet_only must use curated_excerpts_only lore access")
if document["generation_lane"] == "research_augmented":
require(lore_access["mode"] == "scoped_repository_search", f"{base}.research_augmented must use scoped_repository_search lore access")
isolation = document["isolation"]
require_keys(isolation, ["isolation_method", "fork_context", "visible_input_ref", "hidden_context_refs", "worker_model_family"], f"{base}.isolation")
require(isolation["isolation_method"] in ISOLATION_METHODS, f"{base}.isolation.isolation_method is invalid")

View file

@ -78,6 +78,8 @@ def validate_packet(document: dict[str, Any], source: Path) -> None:
"coordinator_artifact_ref",
"projected_context_ref",
"responder_agent_id",
"generation_lane",
"lore_access",
"visible_context",
"output_contract",
"hidden_context_audit",
@ -92,9 +94,20 @@ def validate_packet(document: dict[str, Any], source: Path) -> None:
require(document["canon_status"] in CANON_STATUSES, f"{base}.canon_status is invalid")
for key in ["packet_id", "coordinator_artifact_ref", "projected_context_ref", "responder_agent_id", "packet_prompt_text"]:
require_string(document[key], f"{base}.{key}")
require(document["generation_lane"] in {"packet_only", "research_augmented"}, f"{base}.generation_lane is invalid")
require((ROOT / document["coordinator_artifact_ref"]).exists(), f"{base}.coordinator_artifact_ref does not exist")
require((ROOT / document["projected_context_ref"]).exists(), f"{base}.projected_context_ref does not exist")
lore_access = document["lore_access"]
require_keys(lore_access, ["mode", "allowed_scope", "required_provenance"], f"{base}.lore_access")
require(lore_access["mode"] in {"curated_excerpts_only", "scoped_repository_search"}, f"{base}.lore_access.mode is invalid")
require_string_array(lore_access["allowed_scope"], f"{base}.lore_access.allowed_scope")
require(lore_access["required_provenance"] is True, f"{base}.lore_access.required_provenance must be true")
if document["generation_lane"] == "packet_only":
require(lore_access["mode"] == "curated_excerpts_only", f"{base}.packet_only must use curated_excerpts_only lore access")
if document["generation_lane"] == "research_augmented":
require(lore_access["mode"] == "scoped_repository_search", f"{base}.research_augmented must use scoped_repository_search lore access")
visible = document["visible_context"]
require_keys(visible, ["local_context_prompt", "observed_event", "allowed_action_labels", "source_excerpts"], f"{base}.visible_context")
require_string(visible["local_context_prompt"], f"{base}.visible_context.local_context_prompt")