- every wall's best draft re-run with rtu_match in its CURRENT real TU: func_80011380 DIFF 6 (--o0, §474 PROVED),
func_80020DA4 DIFF 2, func_8017DF28 DIFF 2, func_801834A4 DIFF 6 ×3 variants; leaf match_one re-measured the CC1 rows
(func_80032A74 1, func_80039DEC 2 permuter / 9 sonnet, func_800391D4 3)
- the three CC1-FAIL rows: func_80032A74 = 7 typedefs the TU provides via 800_shared.h + 4 decl spellings → synced copy
(.run/P32/t4/drafts/func_80032A74_tuclean.c) DIFF 1 in the real TU (idx 244 lh vs lhu); func_80039DEC = the TU's narrow
prototype (800_c.c:3496) vs the K&R def → sandbox TU (.run/P32/t4/tu/, no-proto decl) DIFF 2; func_800391D4 = the
load-bearing `D_80073140[][1]` vs the TU's `[]` → sandbox TU DIFF 3 (TU-compatible spellings regress to 65 @ 76)
- config/wave_exclude.txt: each of the 7 lines carries its S83 re-probe verdict; exclude_audit --assert-fresh 7/7
- backlog: rows for all 7 walls (the path-less func_80011380/func_801834A4 given existing drafts, R62; two rows re-logged
after a shell-quoting mangle); docs/backlog.md 16 open
- CURRENT_PHASE.md: T4 row DONE, the wall ledger table (row · ins · class · leaf/real-TU closeness · mechanism+citation ·
attempt record · verdict · best draft; func_800CF3E8 listed as an unpinned candidate), the T4 log entry, 🛑 block → T5
(R27 Max prompt + the gate-2 procedure)
- cookbook §500-I (the sandbox-TU re-probe method + the verdict table); accelerators (8); decision-log P32 S83 (R31)
- seed: the Opus NEAR-6 draft (.run/P32/t3/opus/func_8001BC6C.c; §500-C REGALLOC-PERM $v0<->$v1 across the six OT-chain insns,
local-alloc qty_compare one span unit). permuter_ils 8x150s -j3 --klass REGALLOC: cycles 6/7/8 = 6, 5, 1 (output-1-1)
- R63 read of the "1": three mutations — (a) `idx` computed AFTER `color`, (b) an early dead `tag = (a1 << 8) | k;` before
k's assignment, (c) `(D_800B9A02 & 0xFFu) << 14` — and (c) turns the target's `lhu` into an `lbu` (semantically WRONG:
the masked score rewards it; second witness after S80). (a)+(b) alone = leaf MATCH 69/69; (a) alone 8, (b) alone 21
- well-defined re-spelling: `k = 0; tag = (a1 << 8) | k;` at the top (I1) MATCHES; k-initialised-first (15), tag=a1<<8 (19),
tag=a1 (8), tag=(a1<<8)|K (20), tag=0 (8), tag-then-k (8) all regress — the lever is the early BIRTH of the tag/k pseudos
(§47 live-length: qty_compare = floor_log2(n_refs)·n_refs·size/(death−birth)), documented in the source comment
- rtu_match MATCH 69/69 in src/800.c; gate_main slate_main3: "slate 1 -> 1 compatible … BANKED 1 of 1 … 143dbb89 BYTE-IDENTICAL",
EXIT 0 (.run/P32/t3s3/gate/gate_main3.log); main open 7 -> 6 (5 pinned walls + func_80039308 NEAR 17)
- func_800CD674's ILS plateaued at the SAME $a3<->$t1 pair (output-2-1 = 2 rows, no drift) — ledgered with its cost (R41)
- variants kept under .run/P32/t3s3/p1bc6c/ (the 11 spellings measured)
- the census's best_draft (.run/wave_g0c/shard30, 174 ins, 7 pins) was a DIFFERENT, wrong body under the bare
name (R48); the journal (R38) named the real one — .run/O21/opus/func_800CB00C.c (88 lines, 7 BLOCK-scope
callee externs: gcc-2.7.2 demotes the later-definition type conflict to a warning at block scope). rtu_match
MATCH 123/123 in the real TU (the S75 redraft too); the S72 resolver had gated only the wrong file, 3x.
- raw splice into src/md_MAIN_034/md_MAIN_034.c; module island pads derived at build (§303); make build
BINARY=md_MAIN_034 -j8 rc 0, sha 46153c06bca859dec05aff59fb1a77d3add3d02b == check (R53); verbatim strict ok
- config/wave_exclude.txt regenerated (exclude_audit --write): the md_MAIN_034 WALL pin labelled a wrong draft,
not a wall — 8 -> 7 entries; docs/backlog.md re-rendered (matched rows drop)
- 0 drafting tokens; no Sonnet agent needed (plan T1c adjusted: no redraft)
Stubs 35 -> 32 after the #7 banks (commit:3873 commit:3874); R22 fleet 213/213 (.run/S79_check_all_7.log).
ov_SC05_018:func_80180BE0 and ov_SC06_010:func_801809E4 have NO draft: their ledger drafts were other
overlays' same-named functions (.run/backlog_drafts/<fn>.c is keyed by bare fn name) -> drafting pool.
config/wave_exclude.txt: main:func_80011380 pinned WALL with the §474 proof (fold-const split_tree +
stupid.c adjacency), 4 entries.
T11 4/7, T12 13 banked of a 34-draft pool, T13 R22 213/213 twice (a green
baseline before the overlay banks and again after all 17).
main REAL 895 -> 899, stubs 46 -> 42. Fleet stubs 82 -> 65, distinct-code
99.3% -> 99.4%, MAIN game-code 57.1% -> 57.3%.
Provenance stated per row (CONFIRMED = banked through the whole-binary gate;
CLAIMED = the agent's own measurement on a function that did not bank), because
one of these came from a function that was adversarially upheld and then FAILED
the real gate.
A. reg_n_sets is a one-line scheduling dial (CONFIRMED, func_80180ABC 257 ins).
sched1 schedules backward; a pseudo set exactly once gets the birthing_insn_p
launch boost (priority = 7f000001 in cc1 -dS), which drags its load LATE.
Splitting the RMW as 't = t + 1; *p = t;' makes reg_n_sets 2, suppresses the
boost, and floats the load to the block head -- the block-local dual of §350's
shared temp, WITHOUT the global-allocno penalty that costs the in-place addiu.
Companions: 180 legal statement permutations all scored identically while one
cc1 -dS dump named the cause (diagnose, don't permute); a pin-free fix for
paired-register inversion; and gcc frame slot order is NOT declaration order
(BLKmode aggregates go in order at expand_decl, an addressable scalar is
forced to the stack later -- declare 's32 x[2]' to place a slot between two
aggregates).
B. A single-set local's VALUE is visible at a switch join and erases a
zero-extension (CONFIRMED, func_801806F8 241 ins). combine.c:10035 lets
get_last_value bypass the label_tick guard when reg_n_sets == 1, so all seven
narrowing spellings emit nothing. Diagnostic: a visible extension in the
target means the variable has MORE THAN ONE SET in the original source.
Verified against a matched sibling: andi is the multi-set zero-extend and
sll;srl is NEVER reachable from a single expression.
C. CORRECTION to §439 -- the sll 16; srl 16 pair lands AFTER the jal, not before
it (sched1 sinks the ashift past the call), and it works even for a KNOWN
CONSTANT, because the call-split defeats folding structurally rather than by
hiding the value.
D. An offline jtbl-rodata placement audit (CLAIMED, func_800CB00C -- did not
bank, which is the point: both matchers compare .text only, so a jtbl
function's MATCH says nothing about its table).
SaveLoadRoutine (1,165 ins) is the largest open function in the project, 9.2%
of all remaining work, and has been carried as the §434 WALL. Gated alone
through gate_main, with the §376/§378 chain already applied, the verdict layer
says: "SaveLoadRoutine is BYTE-IDENTICAL; all 3989 differing bytes are
ELSEWHERE". The body has been correct the whole time.
What rejects it is where its FOUR jump tables (jtbl_80072ED4/EEC/F0C/F24) land:
.data/.rodata (jump tables) 3,787 bytes 94.9%
.text (perturbed code) 202 bytes 5.1%
and the built image is 4 bytes SHORTER than retail (413,692 vs 413,696) --
§446's first diagnostic, firing on a function §446 was not written about.
main_diff_locate.classify() already HAD a TABLE REJECT class, added in S72 under
a docstring reading "THE THIRD CLASS EXISTS BECAUSE THE FIRST TWO MISLABELLED
IT". It could not fire here for two independent reasons:
* it keyed on the literal string `(.rodata)`, but main's section_order is
[.rodata, .text, .data, .bss] -- its rodata sits BELOW .text and its jump
tables live in `.data` objects, so TABLE REJECT was UNREACHABLE BY
CONSTRUCTION on the binary with the most jump-table functions left. A
section NAME is not a section ROLE.
* it demanded purity (ro == outside), so 5% perturbed code defeated an
all-or-nothing test and dropped the verdict through to PLUMBING REJECT --
whose advice (fix_arity_callers -> cast_self_callers) addresses the 5% and
cannot touch the 95% that is data. That chain was run on this function
TWICE today and fixed nothing, exactly as the evidence predicts.
Now: table bytes counted in (.data) OR (.rodata), and the test is DOMINANCE
(>=60%) rather than purity, reporting the split and naming which part is the
carve problem and which the declaration problem.
Negative control over all five pre-existing verdict shapes (pure BODY, pure
PLUMBING, pure TABLE, MIXED, NOT FOUND) plus the S75 shape: 5 of 6 verdicts
UNCHANGED, only the SaveLoadRoutine shape flips PLUMBING REJECT -> TABLE
REJECT (MIXED).
Cookbook §447. The law: a class that cannot fire is worse than a class that does
not exist -- it converts "I don't know" into confident, specific, wrong advice.
When a verdict names a subsystem, check that subsystem owns the MAJORITY OF THE
BYTES before acting on it.
tools/journal_notes.py mines the agent journals per (binary, fn) and appends a
PAST ATTEMPTS section to the pack; claude_wave_packs.py calls it automatically, so
it is the default rather than a step to remember. Idempotent, and R48-safe (a note
stamped with a different binary is never served — §238 homonyms).
Measured before adopting (S71 wave 1, 50 one-agent workflows over the 210-function
real frontier where every target had already refused an earlier wave):
* 38/39 MATCH at closeness 0 (97.4%) vs S70's 124/131 (94.7%) on an EASIER pool
* 29/39 agents cite a prior attempt as what they used
* 4/39 banked by RECOVERING a body that already matched, from a path a note named
* 11/39 matched on the first compile
The two costs it removes are re-testing a measured-inert lever (§406 lists twelve,
§407 fifteen, §410 four — each paid for by an agent and never seen again) and
re-deriving a body that already exists on disk.
Also: jr_isolate_all places file-local `static` definitions with the region that uses
them instead of refusing the whole file. A `static inline` helper (§82.1) has no
address by construction, which is not a defect; the R32 guard was refusing these and
blocking the isolate on 4 of the 6 overlays whose CARVE-REFUSED functions it is the
named remedy for. Two regions using one static is still a hard refusal (duplicating a
used static is a byte change, R43).
docs: cookbook §411, wave-playbook step 3b, accelerators entry.
Caught by Drew asking whether the last waves were harvested. They were not: I
banked 1 of 5 (§398b) and left four lever sets in the notifications. Also found
two paid-for MATCHes that were never staged or gated.
(a) a fence BETWEEN two prologue loads, where source reorder does nothing —
the order is fixed before statement order matters (md_MAIN_013/func_800CB56C)
(b) SINK a call into BOTH arms and let cross_jump keep only the jal suffix;
88ins/close86 -> 92/13, then §3-T2 field order let each sh $zero fill an lhu
load-delay. Duplicate in source so the compiler merges, rather than writing
the merged form yourself (ov_SC07_001/func_8017EDC0)
(c) a $v0->$a0->$s3 DOUBLE COPY is a two-pseudo tell: SImode temp for the compare
+ separate HImode var for the tail (70->37); plus §195-N precondition 5 —
nesting `return 1` with ONE trailing `return 0` blocks jump.c's store-flag
transform so reorg fills both delay slots (18->0) (ov_SC02_017/func_8018347C)
(d) the re-tie as a BIV KILLER: a second set makes n_times_set>1 so loop.c
refuses the pseudo as a biv, killing the combined address giv. volatile was
worse, a dead read did nothing (ov_SC07_001/func_8017E4DC)
(d) makes THREE distinct uses of the zero-byte re-tie in one session — §380
un-hoists a move_movables invariant, §393 kills the scheduler's birthing boost,
§399d denies a biv. One line, three passes: when a single-set pseudo is being
treated specially, give it a second set.
Correcting my own guidance from earlier today. §378 gave the self-caller chain;
three more variants appeared within hours and two of them BREAK the chain.
Variant 3 (NEW, byte-proven ov_SC04_018/func_8017F35C, banked): conflicting
RETURN type on a decl that is ALREADY no-proto, where the symbol is
ADDRESS-TAKEN rather than called. --any-proto has nothing to relax and
cast_self_callers has no call site to cast; --sync-decls ALONE fixes it, and is
safe precisely because an address-taken site has no arguments to convert.
Variant 4 (REFUTATION of what I wrote in the playbook this morning): "run the
same chain on the callee the diagnostic names" is wrong at scale. Applied to
func_8012AD44 in ov_SC07_000 it no-protoed 60 caller decls and the binary went
RED (265b24bb vs 9dbe4241); reverted via journal. The self case is safe because
step 2 casts the call sites so the decl change cannot alter argument conversion;
for a callee, cast_self_callers correctly refuses and the decl change runs
unprotected. It banked main/func_80021D38 only because that callee had ONE decl,
not sixty.
Rule added: never --any-proto a symbol whose call sites you are not also casting;
count the sites first. The chain is a DECISION TABLE, not a sequence to run
blindly.
tools/triage_ladder.py — the zero-token pre-agent pass, split PRE (target-side:
BANKED/WALL-332/PARKED, no build) from POST (residual_rules_b, needs a draft).
--escalate refuses a walled or banked target; --acceptance is the R39/R32 harness.
Refuses on a non-quiescent tree: a merging gate makes the stub oracle wrong in
both directions (measured, ov_SC01_004:func_8017EB30).
Acceptance, on the whole corpus: false-skip 0/1367 open stubs, recall 426/426
matched, wall tier fires on exactly the 10 enumerated walls (0 extra, 0 missing).
The first wall control asked for evidence that CANNOT exist — it scanned banked
functions' .s, which splat never writes — and printed '0 scanned / 0 tripped',
indistinguishable from a pass. The R32 empty-denominator assertion caught it on
its first run; replaced with a two-sided sweep over all open stubs.
tools/cast_self_callers.py — the §378 lever + --sync-decls for the narrow-param
case C89 forbids no-proto from reaching (§378a).
Wiring: wave_args drops walled/parked targets at draw time via pre_classify (one
implementation, R33); escalate_fable.js refuses any target without triage:'DRAFT'.
Tool fixes found by measurement:
* fix_arity_callers was blind to main entirely (globbed src/main/main*.c; main is
src/*.c) — reported success over an empty file set through three gates. Now
refuses when --binary selects no files.
* parallel_gate records each worker's 'failed by class' line (was truncated out of
the 200-char tail); gater_lane retries in-tree ONLY on the diagnostic-free
blind-worktree signature — S69 ran 22 serial retries against real cc1 errors.
docs: cookbook §376/§377/§378 (index 1033), SETUP.md, wave-playbook §4b.
The S67 FINAL-3 OPEN item, plus the two defects found while doing it.
* fix(dedup_propagate): the tool could not run AT ALL. S67's -j patch wrote
`os.environ` at module level in the one module that imports `os as _os`, so
every invocation died with NameError before doing any work. Propagation was
not deferred, it was impossible. Import-checked the other 7 -j-patched tools.
* propagation, honestly scoped: the real closable set is 11, not 32, derived two
independent ways that agree (seed_ref exact+same_addr, and a direct corpus
derivation). The 3,161-entry --auto-from plan over 53 overlays is dedup
hygiene over already-matched code and closes almost no open stub.
Applied: 2 banked byte-green (ov_SC04_018 func_80181270, func_80182AF8);
3 gate-refused and cleanly reverted; 6 blocked with named blockers
(3 CARRY-FIXABLE, 3 func_80144B9C not-inline-def -> needs the o0 whale carve).
R22 clean fleet: extract 212/212, check 213 passed 0 failed of 213, rc 0/0/0.
Frontier 453 -> 451.
* fix(seed_ref): REFUSE targets in LINKED subsegs. The playbook calls this tool
"the fleet-wide answer" and it reported 82 open stubs with a banked twin --
43 of them main stubs whose TUs the linker script never references. Any C
written there compiles, links and leaves the SHA1 green WHETHER OR NOT IT IS
CORRECT, so a mechanical twin lane fed from that list could have minted up to
43 gate-green FALSE matches the byte gate cannot see. draw_waves has refused
these since S66; this oracle did not. The refusal is counted and printed, not
silent. NC: guarded 39 subset of raw 82, all 43 dropped are main, the non-main
population is identical.
* wave drawn: .run/S68o1 (24 opus 187-770 ins) + .run/S68m1 (30 main), cards +
packs + wave_args asserted, queue of 53. Drafting opened at concurrency 5.
Seven sections from 30 single-function opus workflows on 187-297 instruction targets (30/30 MATCH):
§339 a 2-case switch OMITS gcc's low-bound range test (stmt.c emit_case_nodes) — so slti/bnez
between two beqs is a COUNT TELL that a case node is missing from your draft
§340 §194-K corollary: a 'scheduler' residual can be sched.c's ALIAS ORACLE inventing a false
true-dependence; source order picks the edge's DIRECTION, so reverse it into an anti-dep
rather than fighting it (10->0, zero bytes; 3 alternatives refuted with reasons)
§341 an HImode store temp reweights a sched2 tie no statement order can reach
§342 NEW LAW: a twin's param cast in a local is NOT byte-neutral when a later param also
needs a callee-saved reg — and the §333 converse does NOT hold (gcc may already pad the gap)
§343 decl_prior's fleet MAJORITY can be wrong about the true signature — read the RIVALS.
Measured: void(s32) x1374 vs the truth s32(s32) x163. The tool is honest, the corpus is wrong.
§344 raise a biv's global_alloc priority with a zero-byte REFERENCE; a register pin kills LSR
§345 volatile STORE evicts the MEM from cse and keeps sh; volatile LOAD blocks combine and
degrades lh into lhu+sll+sra — the qualifier is not symmetric
Also: seed_ref validated on a live A/B. The same 187-ins body cost 102,193 tokens / 476 s in
ov_SC03_107 when the card said 'no banked twin', and 72,077 tokens / 135 s in ov_SC07_006 once the
card carried the twin — 30% fewer tokens, 3.5x faster. A second instance (func_8017F62C) went
63,595 vs 118,485 tokens. others_open=137 on that one exemplar, so it compounds.
R22 caught it: 212/213 after the S67-cc1 gate run. `ov_SC04_018` was RED.
ROOT CAUSE (from the diff, not inferred). Commit commit:3354's propagation replaced three bodies in
`ov_SC04_018_jr_80135D20.c` with DEFINE_func_*() instantiations and deleted the 981 lines they
occupied — INCLUDING the TU's file-scope declaration layer, which the two surviving non-deduped
bodies still referenced. A duplicate copy of those decls survived at line 225, BELOW the function
that uses them at line 42, so C89 ordering made it fatal (`D_8018D7A4' undeclared).
THE STRUCTURAL GAP: gate_stage byte-gates the SOURCE binary, then propagation writes to N OTHER
binaries and nothing re-verifies them. "fleet 99.2%" in the commit subject is a metric, not a gate.
This is the blind spot R50 exists for, and only the periodic whole-fleet R22 could see it.
REPAIR: restored src/ov_SC04_018 to commit:3354^, re-extracted (banking had pruned the .s stubs the
restored INCLUDE_ASM lines need), rebuilt rc=0 at the locked SHA fe9b413f. dedup-check clean
(2193 validated, 0 failed, C1 255302/255302). Cost: the 2 banks in that binary.
NEW tools/restore_dropped_decls.py — compiler-driven recovery for this failure mode: build, read
which identifiers cc1 calls undeclared, look each one up in the pre-deletion git ref, insert it
above the leading #include block, repeat. Two defects found and fixed in it while using it:
* anchoring after "the last extern in the first 400 lines" inserts BELOW the point of use, so the
build fails identically and the loop re-inserts forever (measured: 25 rounds, 100 dead decls).
The only safe anchor is the top of the file.
* a no-progress guard now REFUSES when a round asks for what the last round already inserted.
It also correctly refused when the failure changed class (link-level undefined references), which
is how the wider damage was found rather than papered over.
NOT a defect of the S67 §8d rung: scope_demote_drafts only ever writes draft dirs under .run/.
FLEET: make clean + extract-all + check-all = 213 passed, 0 failed of 213.
FRONTIER: 530 -> 526 (4 functions closed this session, measured from corpus.stubs).
MEASURED (denominators in .run/S67_findings.md):
* 193 of the 530 open functions ALREADY have a draft on disk (1,885 wave targets seen,
1,521 banked, 171 open-no-draft, 166 never drawn). Classified in their real TUs:
37 MATCH / 67 NEAR / 89 CC1-FAIL.
* 159 open functions (30% of the frontier) reference a jump table; 96 are PLAN-REFUSED
by build_carve (non-contiguous same-subseg .rodata), 75 non-main across 38 subsegs.
Not a codegen wall and not a decl wall — carve plumbing.
NEW
* tools/strand_census.py — coverage-asserted census + rtu_match classifier + draft staging.
Keys binary:fn (R48); classifies each pair once after merging every manifest's view.
* tools/o0_detect.py — the -O0 prologue tell extracted from match_one (which parses argv at
import and therefore cannot be imported). match_one re-exports it; ONE definition (R33).
Wiring it into the classifier turned md_MAIN_003 from 8 NEAR (7 of them >20) into 6 MATCH.
Negative-controlled both directions.
* tools/scope_demote_drafts.py — §8d as an _xform-contract gate rung. NOT yet exercised.
FIXED
* jtbl_carve --probe now runs build_carve (a pure planner) and reports plan-refused. It
previously called only island_probe, which answers a necessary-not-sufficient question —
every blocked function probed "carveable", and S66 priced 32 of them as free on that.
* blocker_probe.macro_scope selects the LAST #define per macro name, matching cpp.
engine_core.h has 1,037 duplicate DEFINE_func_ names and 4 with DIFFERENT bodies.
NOT VALIDATED — DO NOT SCALE
* jr_isolate_all: two real defects fixed (carried types deduped by name; header-provided
types no longer re-emitted) but ov_SC02_000 STILL fails the byte gate after them.
Open lead: file_scope_types carries a block without its enclosing #if guard. 20 of 35
blocked overlays dry-run clean and that number means nothing until one round-trips.
0 functions banked this session. tools-health has ONE pre-existing cdecl defect
(1 of 74,749 declarations, func_8017EE08_p55352/struct ZnRec) — cdecl.py and its inputs
are byte-identical to HEAD, so it is not from this change.
Knowledge banked: cookbook §322/§323/§323a/§323b, decision-log pivot, accelerators #13/#14.
draw_waves.py gains --only-main (the main lane draws main and nothing else; implies --main so the
LINKED refusal still applies). Progress/backlog regenerated: fleet 99.2% instruction-weighted,
98.1% distinct.
The distill prompt asserted 'the whole-binary byte-gate ACCEPTED the final draft, so the final body is
ground truth' for EVERY target. With --with-unbanked now feeding it drafts the gate REFUSED, that
sentence would have laundered an unproven body into a byte-proven cookbook entry (R14/G3). A target
with banked=False now gets an explicit PROVENANCE WARNING telling the distiller to extract the lever
anyway (cookbook 52: a model that FAILS still distils the idiom that cracks its siblings) but to mark
every claim UNPROVEN and never assert byte-equality; the verifier is told the same so its
entry_markdown carries the label. Exercised this session: the one surviving ADDENDUM came from an
unbanked draft and is filed UNPROVEN.
Also regenerates the scoreboard after the day's banks.
.run/maintenance.sh (what runs) and tools/lanes/maintenance.sh (a pre-S59 copy) had
diverged. The 150->50 threshold tune landed on the stale copy and was then copied over
the live one, silently reverting five S59 fixes:
* the R47 shape filter (staging fell back to status=='AGREE' alone — the exact defect
that staged 82 hopeless drafts every 45 minutes)
* the R48 (binary, fn) keying (bare-fn keys collide across overlays)
* reloc --fix MISMATCH auto-repair (measured 4/4 repaired to AGREE)
* rtu_second_chance (re-judges standalone COMPILE-FAILs against the real TU)
* fix_tu_ret_decls (the return-type half of the stale-decl wall)
Rebuilt from the S59 lineage with the 150->50 threshold and the periodic fleet R22
re-applied, both paths now byte-identical, `bash -n` clean, and the two-path hazard
documented in the header so the next edit cannot repeat it.
Also: relaunch_drafter_shell.sh 30s -> 5s ready-marker poll; regenerated backlog and
fleet progress artifacts.
R42: gate_main reverted 61 byte-proven overlay banks it could not distinguish from its own
substitution (sweep_parallel gates commit=False by design). Fixed by committing overlay banks
before the main batch, chunking main at 8 to bound bisect cost, and replacing every blind
'git checkout -- src/ config/' with commit-or-refuse in ox_campaign and idiom_serial.
R43: sweep_parallel had an explicit branch admitting main, which cannot be gated incrementally
— wave ab banked 0/105 main cards while its non-main cards banked 94/115 (82%), and the wave
read as a drafting failure. sweep_parallel now refuses main and names gate_main.py.
Also: validate_targets now prefers the card's own addr field (named symbols like SYS_OBJ_F00
were MALFORMED and discarded whole 220-card waves); ox_campaign deals model lanes by
smallest-ratio scheduling (a 73-card wave had put 73 shards on ox and 0 on deepseek);
docs/accelerators.md gains the four vacuous-check defects.
An external-model bake-off, not a banking session. Nothing was banked; that is
the next session's first task.
FINDINGS
- CARD FUEL is the biggest lever, bigger than model choice: the same 10 cards
went 4/10 -> 9/10 when seed_ref/tu_ref/decl_prior were injected. The
"60-instruction ceiling" was an artifact of withholding fuel.
- Sub-50 is near-free: 19/19 verified MATCH at $0.007/function, blind.
7,724 sub-50 open functions = 73.5% of the remaining set.
- A free model (stealth/ox-alpha) cracked a 611-ins function and a jtbl
exemplar, and distilled §206 — whose two negative results were
independently byte-confirmed before banking.
- §206 transfers WITHIN a family (40 turns -> 11) but NOT across (56 turns,
0 compiles). jtbl costs ~40 turns of learning per family, not per class.
TOOL FIXES (all negative-controlled)
- family_remap.gather_externs: took the first ALPHABETICAL extern across the
overlay's TUs, carrying two types swapped (sh/lh vs lbu/sb). Now prefers
the extracted unit's own file. Blocked a 4-member/2,444-ins family.
- atlas.member_lever: aprop_card was loaded and never read while a bare
ledger DIFF forced needs-autopsy. PURE now outranks it — rescues 32
members / 11 families / 3,810 ins.
- decl_prior._ASM_SYM: the %hi/%lo arm had never fired (0 of 1,210 over four
waves). jal 306->306 zero regressions, data 0->299.
- api_agent.py (new): --cards, --brief, --max-cost, nudge loop, 429
attribution + backoff, transport retry, non-fatal tool faults, and a
repeated-call guard.
RULES PROPOSED: R40 (exonerate the instrument before attributing a failure to
its subject — seven instances this session) and R41 (a cost/rate/yield number
ships with its denominator — I quoted $0.30 against a $6.31 bill).
Wave Z: 74/75 MATCH, 72 banked first gate, 2 recovered for zero agent tokens
(§203 address-order typedef hoist; §202 alias on a DEFINITION for the §183.3
DEF-side return wall). Sibling sweep re-scoped after --only was keyed on the
atlas gid rather than family_hseq's exemplar: 3 -> 50 banked.
Harvest: 82 gap reports -> 5 laws, 16 rejected, 30 already-covered; the
adversarial verifier killed 7 of 12 claims. §204 written (510 lines).
Tooling, all negative-controlled:
- the S46 validity gate was off the path for waves T-Z; wired into
build_wave_atlas where cards are born, with the PRE-DRAFT-ONLY constraint
documented (it condemns banked work if run later)
- wave_snapshot honors the card's `sub` (9/9 legacy byte-identical, 66/66
split-TU recovered)
- §204-E: decl_prior's %hi/%lo arm had never fired (jal 306->306 zero
regressions, data 0->299)
Drew T