Commit graph

248 commits

Author SHA1 Message Date
Weksa
2759c0f12d Round records carry a closed reason for every parse refusal and an own-family count
DraftClass (closed set from serde's category and leading words, never the
message) rides on DraftError; the round counts parse_reasons by code
('unreadable' for an answer that did not read as text) beside admit_rules.
RunRecord keeps the answerer's ModelFamily (loop open --answerer-family);
the round counts offered ModelWritten items of that family and the line
says own-family N. The corpus rule is documented as binding model judges:
the loop labels, it does not forbid. New fields and admit_rules are
cultcache default, so older run.cc records decode; schemas regenerated.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 17:05:07 +00:00
Weksa
2259b9f8c3 WIP (does not build): DraftClass on DraftError; create() call sites take a ModelFamily argument
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:26:14 +00:00
aa6385edc3 Merge pull request 'Original corpus for a non-memorised target; recall probes every item; encode prompt states the id form' (#40) from weksa-lowering/encode-id-form into main 2026-11-10 14:24:16 +00:00
Weksa
5ebdb3cff4 Soul s2 lows: the id-form test lists a real inventory; the floor reads 14 to 20
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:24:15 +00:00
Weksa
3d3ca915ea Encode prompt states the id form; recall line states the real chrF floor; probe test over data/original
Five of six encoders in the first original-corpus round wrote bare integer ids and
were refused at parse (encoder-prompt-concept-ids). The prompt now says ids are
written in full with their family prefix. Soul s1 on the original corpus: unrelated
English scores chrF 13 to 18, not near 0, so the recall line says so; a test runs the
probe over the real original items.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:21:31 +00:00
Weksa
1c08b2abac Original corpus (data/original): six passages written for the non-memorised target; recall probes every live item
Six short original sentences, model-written (Anthropic, claude-sonnet-5-5) and so
labelled, three Train and three Validation, over the Dao revision-3 inventory and
one live entity. The recall probe now covers every offered item, naming the work
only for a public-domain one, so it can show the original set reads near the
guessing floor.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:18:28 +00:00
31375b703a Merge pull request 'weksa loop recall: a recitation probe for public-domain items; admit_rules not required in the round schema' (#39) from weksa-lowering/recall-diagnostic into main 2026-11-10 14:15:29 +00:00
Weksa
0ead162d8e Recall tests: mean over every probe, unreadable answer scores 0, written and withdrawn items are not probed
Soul lows: the mean-to-max, skipped-for-0 and withdrawn-gate mutants survived.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:15:27 +00:00
Weksa
d954cfb9e9 weksa loop recall: a recitation probe for public-domain items; admit_rules not required in the round schema
Each live public-domain Train and Validation item is offered to a model by its
opening alone and the completion is scored by chrF against the item's second
half (lowering-recall-diagnostic). Answers live in <root>/recall; the reading is
printed, recorded nowhere, never a gate. The round schema stops requiring
admit_rules, which older records lack.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:12:30 +00:00
cbcfed6ede Merge pull request 'Round record names the admission rules that refused items' (#38) from weksa-lowering/admit-reason into main 2026-11-10 14:08:47 +00:00
Weksa
d502cb396a Admit rules are a set: one count per item per rule, pinned by a packet that breaks V5 many times
Soul s1 low: the per-item dedup was unpinned. A BTreeSet makes it structural.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:08:46 +00:00
Weksa
c527d0eb08 RoundRecord names the admission rules that refused items; the round line prints them
admit_rules (key 18) counts, over both splits, each rule an admission refusal
broke: validator codes (V2, V5) or a store refusal's variant name. Rule codes
only, no identifiers or text. The printed line gains admit-rules=... before the
lowerer-reach label.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 14:05:13 +00:00
3df878f4fa Merge pull request 'Lows: summary_line leaves the public surface; lowering bound pinned in bytes, CR refused' (#37) from weksa-lowering/golf-loop-first-round into main 2026-11-10 14:00:06 +00:00
Weksa
00250088a8 Lows: summary_line leaves the public surface; lowering bound pinned in bytes, CR refused
RoundRecord and Decision no longer expose an unlabelled summary_line; the only
public spellings are RunStores::round_line and cycle_line, which label with the
run's lowerer reach. The lowering bound tests now kill the chars-for-bytes and
CR-allowed mutants.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 13:58:28 +00:00
23bfb02593 Merge pull request 'golf-loop-model-lowerer: a Claude session lowers each packet behind the model port; the template lowerer leaves the loop' (#36) from weksa-lowering/golf-loop-model-lowerer into main 2026-11-10 09:47:43 +00:00
Weksa
b569028f48 Soul s1 fixes: pin the lowerer reach, bound lowering text, pin the build refusal and the I/O discard
RunRecord key 12 LowererReach set by a required --lowerer-reach flag and
shown in round and cycle lines. PROMPT_SOURCE_DIGEST covers packet.rs.
Lowering text is refused when blank, over 4096 bytes or holding a control
character. Unanswered lowering digests are listed once. Tests for the
Prompt::lower build refusal and the packets.cc discard after a port error.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 09:32:28 +00:00
Weksa
74ebafbc65 The round lowers through the ModelPort: Prompt::lower over a LoweringInput, two answer phases
run::score_round no longer calls lower::lower. Prompt::lower prints the
meaning of an admitted view, en-US entity forms and the inventory at the
view's revision, and no item text, key, group, speaker or packet key. The
answer is a LoweringDraft {text}, held in score_round's locals and scored,
never written to run.cc, a RoundRecord, a Decision or EditFeedback. A round
or cycle asks every encode prompt, then every lowering prompt, all or
nothing. An entry an edit adds can now be lowered.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 09:18:38 +00:00
Weksa
3b7a6803bc Retire the lowerer source pin: one prompt pin over context, split and lower
Deletes LOWERER_SOURCE_DIGEST, DriftOf::Lowerer, RunRecord key 7 and
RoundRecord key 3 (retired, never reused). PROMPT_SOURCE_DIGEST now covers
lower.rs, which the lowering prompt will read. Schemas regenerated.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 09:10:56 +00:00
3bdfb514ae Merge pull request 'Round-digest lows 2: length-framed source digest, lock cleanup, honest drift text, window tests' (#35) from weksa-lowering/round-digest-lows-2 into main 2026-11-10 08:56:20 +00:00
69e1f0dda3 Merge pull request 'Speaker-scene lows: with_scene enforces scene coverage at read, one owner' (#34) from weksa-lowering/speaker-scene-lows into main 2026-11-10 08:54:49 +00:00
Weksa
7a803f5cb5 Pin the read-side coverage filters; V16 says the scene covers every live speaker of the group
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 08:54:28 +00:00
Weksa
de46ced9ea Round lows 2: length-framed prompt source digest, refused create takes its lock, Prompts drift text, window pins for entities and head, one-write asserts Accepted
Recorded prompt digests change with the framing (they drift by design).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 08:40:35 +00:00
Weksa
da407e23af Scene coverage has one owner, Scene::uncovered, applied at put and at with_scene
with_scene now takes the corpus store and refuses (V16) a scene that no longer
lists the speaker of every live item of its group.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 08:40:17 +00:00
e93862a57f Merge pull request 'Round lows: split.rs joins the prompt source digest, stores re-checked after open' (#33) from weksa-lowering/golf-loop-round-lows into main 2026-11-10 08:36:12 +00:00
5a125fef4e Merge pull request 'Checkpoint-gate lows: pin the once rule and the elide branch, escape line breaks in item text' (#32) from weksa-lowering/checkpoint-gate-lows into main 2026-11-10 08:23:34 +00:00
Weksa
af35f72004 context: pin every line separator in item text with its own splitter
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 08:23:18 +00:00
Weksa
c1c19cc848 Run pins: prompt digest covers split.rs; stores are re-pinned after they open, so digest and open cannot straddle a change
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 08:22:12 +00:00
069820b323 Merge pull request 'One-write seam: pin 'accept is one batch' by behaviour, delete the source-text tripwire' (#31) from weksa-lowering/one-write-seam into main 2026-11-10 08:19:05 +00:00
Weksa
0b2f6ce43b context: item text cannot forge a prompt line or block; pin interleaved re-offers, long shared-prefix ids, near-prefix held turns
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:59:59 +00:00
Weksa
caaa3b0650 Accepting is one write, pinned by a store that refuses its second write
Delete the source-shape tripwire for one put_prepared_batch; run_cache_over
lets a unit test run cycle over a CacheBackingStore failing write 1 or 2:
the round and the decision land together or not at all.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:55:11 +00:00
Weksa
60e9cfca87 context: pin the once rule per key and for Train, the held-turn key equality, and item text inside its block
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:53:44 +00:00
f14d9d1592 Merge pull request 'golf-loop-edit-accept: a Train-only editor proposes an inventory edit, a candidate round scores it, a noise-floor rule accepts or rejects on Validation' (#30) from weksa-lowering/golf-loop-edit-accept into main 2026-11-10 07:50:03 +00:00
377adae7e9 Merge pull request 'Clippy: name the predication tuple, box PutArgs' (#29) from weksa-lowering/clippy-lints into main 2026-11-10 07:50:02 +00:00
Weksa
5f97aad6a2 run: create removes the inventory copy when a later step fails
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 07:49:15 +00:00
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
1c1fd3cf10 Clippy: name the predication tuple, box PutArgs in EntityCommand
Clears type_complexity in daodejing.rs and large_enum_variant in main.rs.
RoundOutcome's large_enum_variant in run.rs is left for golf-loop-edit-accept, which rewrites that file.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-10 06:23:09 +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