CodexConnector is not a real option for Dungeon inference (operator ruling
2026-09-23): Bonsai 2 reaches Yggdrasil over a restricted reverse SSH tunnel
at loopback 127.0.0.1:18080. Rename
real_codex_connector_cognition_modes_commit_speech to
real_local_model_cognition_modes_commit_speech, open inference with
LocalBinding instead of ConnectorBinding, and read
GHOSTLIGHT_LOCAL_ENDPOINT/GHOSTLIGHT_LOCAL_MODEL_PREFIX in place of the
connector endpoint and credential. Update the Idunn recipe's acceptance step
and service required_environment to match (drop the connector env, add the
elaborator model var the test already required but the recipe omitted), and
drop the gamecult.codex.subscription-inference dependency: Dungeon no longer
depends on CodexConnector for inference. Update the remaining live references
to the old test name in notes/map.
CodexConnector's transport code and the v1 actuator are untouched; both are
separate follow-up cuts.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Operator ruling 2026-09-23: Dungeon on Yggdrasil via Idunn, Bonsai on
Raven over a restricted reverse tunnel on the WireGuard mesh;
CodexConnector is not a Dungeon inference option.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The map's next action and the handoff still described the world before the
play-agent pass.
Falsified against source: both claimed no local-model transport exists.
crates/ghostlight/src/local_inference.rs has existed since Cut 2, and
runtime.rs opens it on GHOSTLIGHT_LOCAL_ENDPOINT. Corrected to "exists,
unexercised" so the next session does not rebuild it.
Also retired: "world.speak is the only human action" and the story-card
description, both deleted by Cut 9 (f1732c0); and "the cut map is next",
written before Cuts 1 through 14 landed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The map, handoff, plan and Session Zero doc now name plan step 16, the play
agent, as the playtest gate. L2-L4, D1-D3 and the L1 follow-ups are
recorded as deferred by ruling, not dropped.
A source check corrected the map. Inference routes per lane by model name
to the SDK sidecar or CodexConnector, and no local transport exists. The
sidecar is a private msgpack pipe behind InferencePort, not the CultNet
connector API the map claimed every backend shares.
The handoff's session_zero.begin item is retired: the name is refused, and
only tests reference it. One evidence record covers the pivot.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The stock lenses pass is closed.
- The ghostlight library ships eight lenses.
- Worlds carry weights as world data, and the owner can replace them.
- Each elaborator session draws its lens replayably and records the lens and
its instruction text.
- Sessions run concurrently under their own permit ceiling.
- In-flight work is found again by reading the store.
All eight target invariants hold.
The cut map records the second Cut 4 fix batch, Soul's final pass, Cut 5's
verdicts and the ledger's actuals. The actuals are +4,907 / −266 in crates
against about +1,300 estimated, the overrun overwhelmingly tests that caught
real defects.
Recorded as follow-ups: an Uncovered case the tests do not pin (L1.f15), and
whether consumers may supply their own lens sets (L1.f16, the operator's).
The target is rewritten as reconciled. The ontology loop no longer claims
seed requests or Vault evidence for the Active sweep, the handoff says
lens weights, and map.yaml names L2 as next.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Plan step 15 records L1 as landed at 835ea4d..872ba35 with its cut map, and
its heading names L2 next. Step 6 calls the elaborator's flavor a lens.
The handoff and state/map.yaml name the live schemas, consumer.v5 and
controller_work.v16, and world_create.v4 in the handoff; both say L1 is
implemented and what it gave the machine, and the handoff names L2 next.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
map.yaml's next action listed the stock lens set as L1 and again inside
"the remaining library capabilities". The handoff still said the titled
elaborators "return as weighted lenses", which predates the ruling that
they ship as the library's stock lens set.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The kernel extraction is finished. The world kernel is the ghostlight
library crate; Dungeon consumes it across a boundary sealed by admission,
proven from outside the crate.
The cut map records the last two fix batches and Q1-10, defaulted: the
minter scanner stays a tripwire, with Clippy recorded as the fix. The
subtraction ledger missed its estimate, +210 net source lines against about
+65. The reasons: the scanner grew chasing evasions, the boundary needed
about 90 more public items than planned, and the rejection tests buy a
ruling made after the estimate.
The postmortem lists what Soul caught, the operator corrections, the
incidents, and the open follow-ups. The target states which invariants
hold and how. The plan, map.yaml and the handoff point at L1. The L0
evidence record is rewritten as its distilled lessons; the previous text is
archived.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Cut 1 landed at 108b691..f859d2c. Soul reran the builds, tests, census and
mutations itself and confirmed the behavior-unchanged claim; it found six
defects.
F1 is the one that matters: the seal is name-based. Public ID types,
ScopeDigest and DecisionOpportunity all derive Deserialize, so an external
crate can mint them from JSON and rebuild the fixture path ruling Q1-4
said must be unreachable. The reducer still rejects forged opportunities,
so kernel integrity holds while the invariant's wording does not. Q1-9 asks
the operator whether sealing means unforgeable admission or unconstructible
types.
F2 (bypassable minter count) and F3 (71 unused public items) are queued for
the fix batch. F4 names Eve in library error strings. F5 and F6 are
recorded, not fixed.
The map, map.yaml and the handoff now say the kernel is the ghostlight
crate.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A detail rule is a function from place to detail level. Each consumer
chooses its own level-of-detail rule. Dungeon uses ByDistance anchored on
important subjects, the player first. Delvehold starts from Uniform.
Rules are typed world data that the library evaluates, not consumer code.
The deficit a rule produces is an admission input, and journal replay
re-runs reduce, so a changed consumer function would break committed
history. WorldScaleIntent per-kind targets remain the ceiling a rule
distributes.
The eight titles move into the library doc as the stock lens set. The
kernel extraction is ordered as plan step 15 pass L0, ahead of every
library pass.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Ghostlight Dungeon is a consumer of the Ghostlight library. Session Zero,
Vault choice, players, sliders and starting locations are Dungeon authority
and do not shape the library.
The ontology doc gains consumer-neutral library targets: elaboration
lenses with weights, focus-weighted demand with a consumer-supplied detail
profile, one evidence source bound per world, and elaborator sessions in
Draft. The Session Zero doc now carries only Dungeon policy that consumes
those capabilities.
The map records the boundary as a hard rule. The plan splits into library
passes L1-L4 and Dungeon passes D1-D3. Two decisions stay open: extracting
the kernel from crates/ghostlight-dungeon, and whether the eight titles ship
as a library stock lens set.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The eight titles (Patina, Charter, Ledger, Hearth, Tangle, Veil, Ember,
Numen) were deleted with their titled verifier and quotas, and no operator
decision covered them. The ontology doc and evidence record 6 now say the
tribunal was the verifier and the quotas, not the titles. A new correction
record carries the history and the 2026-09-15 direction.
Session Zero is the player's path through a world's Draft phase. The player
chooses a Vault, describes the experience, and sets title weights. The seed
lane sketches the world and the player chooses a start. A swarm then draws a
title by weight for each session and elaborates by travel distance from the
player, before and after activation. It is plan step 15, and its fifth pass
closes the playtest gate.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The playtest gate goes ahead of the outbound consumer batch. The handoff
defines it and lists the walls found in source. The map no longer claims
co-op for up to eight players on the rebuilt kernel. It points the economy
spec at GameCult/Njordr and says CultCache comes from CultLib, not a
vendored copy.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The Claude SDK sidecar is the only live provider. Backends share one
standardized CultNet connector API with Epiphany; CodexConnector is isolated
and not live here; a generic OpenAI-compatible connector gates third-party use.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The elaborator swarm's GitHub branches were removed after verified bundling,
but its output is still wanted: the operator will integrate ideas into the
lore vaults as time allows. The durable record now lives in the repository
that owns the obligation instead of a Codex task folder and deleted branches.
experiments/elaboration/ carries the reviewed additions packet (A2 and D1-D3
approved, A1 demoted, K1/K2/Z1-Z3 pending), the per-world reviews, the
2026-09-05 shortlist with its 20 full candidates, and the 92 per-pass idea
ledgers, with a README naming where the bundled vault additions are and how
to restore one. The four reviewer-accepted first-generation world fixtures
return from their deleted codex/world-* branches to examples/ and
prompts/image-generation/ beside the existing fixtures. The map and handoff
point at the new home.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
CultLib's packages/cultcache-py is now published as cultcache-py==0.2.0 on
PyPI (MIT), so the standalone GameCult/cultcache-py fork that Ghostlight
vendored as a submodule is retired. Symbol-for-symbol and on-disk-format
verification against the pinned submodule commit 9b4bbb8 found no
incompatibility: every symbol tools/ghostlight_state_store.py imports
(CultCache, JsonLinesBackingStore, define_document_type) and every method it
calls kept its signature, and JsonLinesBackingStore's on-disk JSONL envelope
fields and sort order are unchanged, confirmed by a real round-trip against
Ghostlight's production state/ghostlight-state.cultcache.jsonl.
tools/ghostlight_state_store.py no longer pushes vendor/cultcache-py/src onto
sys.path; it imports cultcache_py directly. Since Ghostlight's session
bootstrap previously depended on the submodule needing no install step,
tools/requirements.txt now pins cultcache-py==0.2.0 and npm run
state:bootstrap (pip install -r tools/requirements.txt, idempotent) runs as a
pre-hook ahead of state:status and state:prepare-compaction; AGENTS.md's
Session Bootstrap protocol and Useful Commands section call it out explicitly
for the direct ghostlight_state.py CLI invocations that don't go through npm.
Verified for real: `python tools/ghostlight_state.py status` and `python
tools/ghostlight_prepare_compaction.py`, run from a venv with cultcache-py
installed from PyPI, against Ghostlight's actual production state file (22 ok
findings, 2 pre-existing unrelated warnings, exit 0 both times).
Idunn's deployment/idunn/recipe.toml never declared vendor/cultcache-py in
required_gitlinks (only vendor/eve) and its build/test/service steps never
touch Python state tooling, so no recipe change is needed for admission.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Dimensions, materials, lots with provenance, recipes as roles, products as
property vectors; markets as Ghostlight mirrors; prices as a pure function
of committed state; both directions through the consumer contract. The
economy owner is the consumer that owns a world's market mirrors.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Runbook row 11 and the interrupted-cell section, evidence record, map and
handoff advanced: next is the outbound consumer batch.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Runbook row 10 and the interrupted-cell section; plan step 14 landed;
evidence record; map, handoff, and scratch reconciled (schemas v4/v14,
thirteen components, next action is the per-cell interrupted log line).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A visible act becomes Seen { by } knowledge on the co-located, kernel-lowered
from the invocation beside speech, quoted by the Interpreter as the visible
clause alone. Intent stays private. Authority map, cut line, budgets,
verification, and the three operator decisions are in the plan; map,
handoff, and scratch point at it. Not built.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
world_create.v3 carries a required brief, trimmed at ingress, stored on the
state and its snapshot, and projected as the guidance of the Projector,
Persona, Interpreter, operational, and grouped lanes and both authoring
prompts. The two narrative stages that rebuild prompts on resume carry it
(controller_work.v13). The smoke titles its world by the seed root label and
hands its brief to the world rather than to each seed session, so a vow can
no longer name a test fixture.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The membrane traced end to end: the Projector's borrowed voice, the
contentless commitment, the unbuilt PersonaMaterial, and the missing
co-presence are recorded as findings; the harness no longer claims to fail
on silence, which is now the honest baseline. The map and handoff point at
the decision the operator owns.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Run 3 proves speech cited by quote arrives whole with no quarantine. The
map, handoff, and runbook now say the SDK route is run; the remaining road
item is the live interrupted cell. One distilled evidence record carries
the day's belief-changing findings.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Item 1 had grown to three hundred lines of per-pass SHAs, line numbers, and
test counts that git and the ledger own. The handoff now carries what is
true of the tree, the constraints, the ordered next moves, the operator's
open decisions, and the deployment gate. Gating lessons move to the
re-entry warnings; the map points there instead of repeating them.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Docs describe the seed lane as landed: scale intent at creation, the
phase-free qualification with the Draft refusal in one owner, the owner
port bound to the Draft revision, the Vault reader's containment and
caps, obligations as the source of boundaries, evidence lifetime at
ingress. The session-zero and compiler language leaves the eve-native,
multiplayer, Delvehold, and mvp docs; plan step 8 is landed; the smoke
note's run block targets Kalsa Public at Low Sere. Steward folded the
boundary and cut the stale drift warning.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The plan carries the objective, current mechanism, and cut line; the
map's mission, boundaries, and subgoals speak the live admission
vocabulary; the session-zero document is teardown evidence; the draft
answer variant is marked representable but uninhabited. Steward folded
the task opening into the handoff and map.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The consumer-api doc is the live contract for the landed ingress; the
ontology's Current mechanism runs through pass 10 and its follow-ups;
the mvp doc names the live authority answer; the plan's step 6 is
complete with the outbound consumer response as the next seam; the map
and handoff carry the series-complete state, the world-v3 generation,
and the decisions the operator owns; one evidence record distils the
ten passes.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Current mechanism describes the budgeted connected cover, the tick
driver as the single clock owner, and the grouped-cell membrane rule;
the scale section carries the ceil(N/R) bound, the two reasons the cap
yields, and the contention finding with its open operator decision; the
two stale claims about AdmitPatch phase and EvidenceRef are corrected;
the consumer-api drift note names the decided transport; controller
model variables are documented. Steward folded passes 1 through 9 and
the pass 10 design state.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Current mechanism describes the two AdmitPatch authors, jurisdictional
confinement at answer and write, the tool surface as one schema spelling
per type, and the evidence-bounded repair loop; Invariant 11 and
Verification 16 carry the expansion rule; the consumer-api drift note
names pass 10's four debts. Steward folded passes 1 through 8 and the
in-flight pass 9.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Current mechanism describes the clock, commitments, pressure, causal
boundaries, scale deficit, and the structural answer rule; the Commitment
and Pressure rows and the twenty-seven operation count follow the cut;
the mvp doc no longer names a readiness partition. Steward folded passes
1 through 7 and the in-flight pass 8.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Current mechanism describes facts, channels, knowledge, speech fan-out
over the declared reach, the two homes of a statement, and the
controller port; the Channel row and Precondition block follow the cut.
Steward folded passes 1 through 6 and the in-flight pass 7.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Current mechanism describes authority, selection, and redress with the one
covering predicate, the admission-only nesting rule, and the shared
grant/revoke envelope; the selection row and operation count follow the
landed cut. Steward folded passes 1 through 5 and the in-flight pass 6
into the handoff and map.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
