Commit graph

213 commits

Author SHA1 Message Date
Weksa
592dbd7e67 test: pin decide's chrF tolerance to billionths on two-decimal pairs
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:49:15 +00:00
Weksa
c61ef8b7ea cycle: drop the redundant verdict field the base literal already supplies
The mutant that deleted it was equivalent; the line is the cut.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:18:59 +00:00
Weksa
cd4295632a Map: create refuses an existing inventory.cc; decide compares in billionths
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:11:45 +00:00
Weksa
52e7c44990 rustfmt the new tests
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:11:04 +00:00
Weksa
c28f1fbb13 Pin the one-write accept: an injected run.cc write failure leaves neither round nor decision; tripwire on a second write
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
59fdd7fec7 decide: compare readings in billionths, so a gain of exactly one LADDER_STEP is no gain on every baseline
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
f1fc31e420 cycle: every rejection removes a stale candidate inventory an earlier attempt built
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
b0321fe487 Pin the last-edit word to the latest decision: a reject after an accept is told as rejected
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
467ce98ea0 Pin the head to the latest accept: two accepted cycles, the third builds on the second
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
d02029c8b8 Pin the Ladder release: a rejected candidate's score never reaches the editor, only the stepped head's
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
20ca3aaae5 Pin the noise floor: distinct replicates set the per-field and composite spread, and a gain inside it is no gain
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
afe1a1b434 create: copy the inventory with create_new, so a root that holds inventory.cc refuses and never truncates it
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:10:43 +00:00
Weksa
ae384ee928 Map and README: the edit-accept cycle, the Decision row and the loop's live surface
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 05:11:06 +00:00
Weksa
ae8deb1e03 weksa loop cycle: a Train-only editor proposes an inventory edit, a candidate round scores it, a Ladder-stepped noise-floor rule accepts or rejects on Validation
Reading, decide and LADDER_STEP are pure; Decision (weksa.loop_decision) holds
digests and numbers; the latest Accepted decision names the run's head. The
candidate round and its decision are one batch put.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 05:10:47 +00:00
Weksa
a8918c6ff1 EditDraft and EntryDraft: the editor's JSON read once, ids and revisions the store's
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 05:03:33 +00:00
Weksa
6d17f45ca2 The mint prompt becomes the editor's: Train blocks, the inventory listing and an EditFeedback line, nothing from the held-out split
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 05:02:42 +00:00
Weksa
fc52f3d3a4 RoundRecord keys 16 inventory_digest and 17 cycle; round becomes the drift check, score_round and one put
An encode answer the port reports as InvalidData is that item's Refused(Parse),
not an aborted round.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 05:01:18 +00:00
Weksa
a14bcaf9f8 The run stops opening the caller's inventory store: create copies it to <root>/inventory.cc and pins its digest (key 11)
RunRecord.inventory is provenance only; open refuses Drift(Inventory) when the
run's own file differs. A run.cc from before has no key 11 and its open fails.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 05:00:34 +00:00
7b407fdd13 Merge pull request 'golf-loop-round: the smallest loop that scores one round end to end' (#28) from weksa-lowering/golf-loop-round into main 2026-11-10 04:42:53 +00:00
Weksa
2425030fe3 Pin the round-start discard: a stale packets.cc and lock in an unrecorded round dir do not refuse a revised draft
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 04:41:02 +00:00
Weksa
a014fc3f87 Pin the scored counts of the Dao round
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 04:15:57 +00:00
Weksa
3e1e1a07da Fix the golf_loop test that did not compile in the previous commit
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 04:15:00 +00:00
Weksa
fd0c3b0edb Round: means count a refused item as 0, a failed round discards its packets, the round line is pinned
Validation and Train means are over every item of the split with scored counts
beside them, so refusing a weak item cannot raise a mean. A round that fails
before its record is put (embedder down) removes its packets.cc, and a round
starts from none, so a rerun with revised answers is not refused as a changed
packet. RoundRecord::summary_line owns the printed line and is pinned with exact
values. The RoundRecord compile_fail doctest gives every field and fails on
E0451, with its twin literal in a lib unit test.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 04:14:39 +00:00
Weksa
8ac92f5af3 Kill the mutation survivors: error texts, unreadable files, the second round's number
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 04:04:36 +00:00
Weksa
db543840a6 weksa loop open|round: pin a run's stores, run one round, print one line
Round reads its stores only from the run record; prompts without answers are
written to the round directory and the command exits 3. Map line 7b records
what landed and what the follow-ups still own.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:51:18 +00:00
Weksa
49879000f7 run::round: a pinned run encodes Train and Validation, admits, lowers, scores and records the round
encode.rs reads a model answer into a PacketDraft (the one JSON door for
models) and the encoder step sets everything the model does not write. round
asks every offer first and writes nothing while any prompt is unanswered, then
admits into the round's own packets.cc, lowers, scores in one call and keeps a
RoundRecord with Train rows and Validation only as means and refusal counts.
The Dao stores reproduce the base scores (Train 44.18, Validation 78.56).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:50:04 +00:00
Weksa
77d8b13952 ModelPort and AnswerFiles; the encode prompt lists the live inventory and has a digest
The encoder's instructions are written, Prompt::encode takes the run inventory
and revision, and Prompt::digest names a prompt for AnswerFiles: a prompt with
no answer file is written to <digest>.prompt and nothing else happens.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:47:24 +00:00
Weksa
e7b4d9a68b RunStores is the one public producer of TrainItems and EncoderOffer: a run pins its corpus and entity stores by digest
TrainItems::from_corpus and EncoderOffer::for_round become pub(crate). RunStores
(run.rs) creates a run over three stores, records their canonical paths and
FNV-1a 64 digests plus the prompt and lowerer source digests in run.cc, and
reopens only from that record, refusing on drift. RunRecord and RoundRecord are
published CultCache types. tests/context.rs and the context.rs doctests move to
RunStores; the two mutated-clone gate cases become a unit test.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:45:49 +00:00
2be0a35ae7 Merge pull request 'speaker-scene: weksa.speaker and weksa.scene documents, with_scene reads the store' (#26) from weksa-lowering/speaker-scene into main 2026-11-10 03:26:05 +00:00
Weksa
eff94fb4af Pin LoweringInput::of's privacy with the right arity; scene() doc points to scene_read()
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:25:44 +00:00
Weksa
bb152d02ce with_scene records what it read: SceneRead says no scene, no addressee, self-addressed, no relation or selected at a revision
The view no longer collapses five cases into one empty feature list. Scene::relation
returns None for an absent relation. Pins the item speaker over the first
participant and V16 without an addressee.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:10:21 +00:00
Weksa
e96acf97a5 Merge origin/main (checkpoint-gate) into weksa-lowering/speaker-scene
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:08:53 +00:00
7a8ffbea1e Merge pull request 'Checkpoint gate: Test readings need a Checkpoint nobody outside tests can declare; fixed instructions; context lows' (#27) from weksa-lowering/checkpoint-gate into main 2026-11-10 03:05:13 +00:00
Weksa
62059337a3 Door scan: say it is a line-based tripwire and what it misses
Docs only; no behaviour change.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 03:04:48 +00:00
Weksa
7a33a8d70f Map: say what the Checkpoint gate guards (7a)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:59:40 +00:00
Weksa
43f2e118f2 Checkpoint: offers borrow it; door pinned by source shape; doc states the real guard
EncoderOffer<'cp> borrows its Checkpoint so a Test offer cannot be encoded
after the reading spends it. tests/checkpoint_door.rs scans split.rs for any
public minting item under any name. The split.rs doc says operator tools read
corpus text and the guarded invariant is the round path.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:59:11 +00:00
Weksa
71e6058b64 with_scene reads the item's speaker and group scene from the store; V17 addressee names a referent
The view keeps its corpus item's speaker and group (LoweringInput::of takes
the item; admissible is gone), and with_scene takes the SpeakerStateStore, so
neither speaker nor scene comes from the caller and only admitted scenes
reach a view. An addressee that names a predication is refused as V17.
Pins scene numbering per group and the no-fallback case for a named
addressee outside the participants; tests/scene.rs fixture now speaks as the
item's speaker.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:51:35 +00:00
Weksa
3d83ba5fd2 Map: checkpoint-gate lines (7a, 7, 11)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:43:36 +00:00
Weksa
d5b11088ad Checkpoint offers each item once; prior turns print the held Train text
for_checkpoint takes &mut Checkpoint and refuses a repeated key
(OfferedAtCheckpoint) after the gate; TrainItems::held replaces holds and block
prints the matched Train item's text; the text-key fold is pinned against the
store's own S6 refusal.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:43:31 +00:00
Weksa
469e46cbc5 Cut: Checkpoint has no public constructor; instruction text is consts
Checkpoint::declare becomes cfg(test) for_test; Checkpoint-using tests move
into src unit tests over split::fixture; Prompt::mint and encode lose the
instructions parameter (MINT_INSTRUCTIONS, ENCODE_INSTRUCTIONS in context.rs).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:42:02 +00:00
Weksa
6ef1b7e034 Speaker and Scene documents, SpeakerStateStore, with_scene on a Scene document
Slot Speaker, weksa.speaker and weksa.scene append-only revisions in one
store, V16, feature_refusals as the one feature check, speaker_scene_revision
(Speaker features 22-24), schemas, docs and map lines. Part 1 of map cut 4b.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:34:10 +00:00
Weksa
0b62d2f3b4 Retire V13 and with_scene's raw door; Stance and Scene features sit in one slot
with_scene is removed until it takes a Scene document (next commit); V13 goes
with it. Slot exclusivity becomes a rule of InventoryEntry::well_formed, so
FEAT_ALL leaves Stance and its stance duplicate case goes (ANGER pins V11 in
Stance). tests/scene.rs is deleted and rewritten on Scene documents later.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:29:51 +00:00
ee3a3c3404 Merge pull request 'Map: speaker-scene facts, persona-state question, 4b/4c' (#24) from weksa-lowering/speaker-state-cut into main 2026-11-10 02:27:35 +00:00
Weksa
109276cac4 Merge remote-tracking branch 'origin/main' into weksa-lowering/speaker-state-cut 2026-11-10 02:27:24 +00:00
6f68c18f01 Merge pull request 'Context builder and checkpoint-only Test readings (cut loop-context-builder)' (#25) from weksa-lowering/loop-context-builder into main 2026-11-10 02:27:02 +00:00
Weksa
35b32b9639 Prior turns print only text a live Train item of the group holds; pin the Train union against withdrawn items
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:23:29 +00:00
Weksa
c1d530ccea context tests: pin TrainItems len and is_empty and the empty mint
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 02:08:45 +00:00
Weksa
b0b5728f07 Map: cut 7a loop-context-builder; item 3 names the checkpoint-only Test path; item 7 drops the context builder
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 01:57:47 +00:00
Weksa
3bd4a37645 context module: TrainItems, EncoderOffer and Prompt are the only road from corpus text to a model call
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 01:57:40 +00:00
Weksa
a6dd52774a Checkpoint and TestReadings: Test is read only at a declared checkpoint, scalars only
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 01:56:29 +00:00