Measured the h_exact free pool from the bytes rather than trusting the frontier report's
numbers (R14 — its whale claim was 3/4 wrong: it said the whale was open in all four SC07
overlays; three were already banked and I closed the fourth earlier this session).
MEASURED: 215 open function-instances / 8,763 instructions are byte-identical (h_exact,
including reloc payloads) to an already-matched function. ONE class is 86% of that pool:
func_801758FC — 55 ins, same address in all 138 overlays, matched in ov_SC01_000 only,
OPEN in the other 137 => 7,535 instructions.
h_exact means identical INCLUDING jal/lui/%lo reloc immediates, so the matched body compiles
byte-identically at every member with NO remap (dedup_extend's correctness argument, §14).
dedup_propagate --addr authored it once as DEFINE_func_801758FC() in engine_core.h and
instantiated it at all 137 open sites in address order.
[ OK ] 138 overlays byte-identical after propagation; 1 new group in config/dedup.us.yaml
VERIFIED: make clean && make extract-all && make check-all -> 140 passed, 0 failed of 140.
Fleet instr 12411467 -> 12419002 = +7,535 EXACTLY; fn-count +137; instr-weighted crosses to
94.5%. distinct-code unchanged BY DESIGN -- the class was already matched in ov_SC01_000, so
the 137 add fleet instructions but no new DISTINCT function. audit-digest OK. 0 NON_MATCHING.
Note this function had been sitting in the stored-draft backlog for ov_SC06_030 and
ov_SC07_010 and re-gated "no" earlier tonight -- because gating a DRAFT is the wrong move for
an h_exact class. The right move is propagating the already-MATCHED body. Same function, two
routes, and only one of them is free.
Remaining free pool after this: 78 instances / 1,228 ins across 32 classes.
The 39 draft-exemplar families all have their exemplar still OPEN in ov_SC01_077 -- a
draft-exemplar family cannot propagate until its head banks. Re-gated the newest stored
ov077 draft per head, in 4 small batches (§61: a wide harvest broke a TU in S38).
Set aside the top 4 heads (65% of the pool's weight, all known-hard): func_801412A8 +
func_80178004 ARE S6's two giant walls (198x138 + 165x138 = 50,094 ins riding on 2 cracks),
func_8017C974 is today's byte-proven close=47, func_8017C294 its 246-ins neighbour.
batch 0 1/9 batch 1 3/9 batch 2 4/9 batch 3 0/8 = 8/35 (23%)
BANKED: func_8017EC7C func_8018281C func_801820DC func_80182988 func_80183BAC
func_80183AF0 func_80183CF4 func_80182E7C
(+474 ins x1 now; ~1,441 ins of templatable weight behind them once their families propagate.)
CALIBRATION REFINEMENT (docs/calibration.md, S39): this population re-gates at 23%, vs 8%
for the general stored pool and 4/6 for fresh post-repair drafts. Three different populations,
three different rates -- which is exactly why the rule is "re-gate what a repair plausibly
touched", not "re-gate the ledger". ov_SC01_077 is the split-heaviest overlay, so the S38
alias-deletion repair plausibly touched all of these.
VERIFIED: make clean && make extract-all && make check-all -> 140 passed, 0 failed of 140.
Fleet 12410275 -> 12410749 instr (+474), distinct +474 / +8 uniq, fn-count +8. audit-digest OK.
0 NON_MATCHING (G4).
Tested whether decision-log A10 ("stored drafts re-gate at 0/958", measured in T1) survives
S38's tool repairs. Three populations, plain re-gate, no draft edits:
fresh wave-6 drafts (diagnosed "blocked on a class") 4/6
stored pool, unbiased sample (every 96th of 1,155) 1/12 <- hit was in a REVERTED overlay
the two REVERTED overlays, targeted 3/17
A10 BROADLY STANDS. ~8% on the general stored pool is not a harvest, and a 1,155-wide sweep
(= 1,155 whole-binary builds) is not justified by it. Do NOT generalise the fresh-draft rate
(4/6) onto the stored pool -- different populations. The honest rule is narrower and cheaper:
after a tool repair, re-gate the drafts THAT DEFECT plausibly touched, targeted by its
blast radius -- not the whole ledger. (R35 applied to the backlog, not just to metrics.)
BANKED (+146 ins): ov_SC06_030 func_80161208 + func_80162CCC; ov_SC07_010 func_801506A4 +
func_8016F0AC. R22 clean-fleet 140 passed, 0 failed of 140 -- which also proves byte-neutral a
fleet-shared engine_core.h edit the bank required (extern s32 func_801506A4(s32,s32) -> the
no-prototype form), reaching all 138 overlays (T2 blast radius).
Fleet 12410129 -> 12410275 instr; distinct +95 / +1 uniq; fn-count +4. audit-digest OK.
Also documents the LEDGER MECHANICS in calibration.md (Drew asked): .run/backlog.jsonl is
append-only and nothing is deleted on bank -- open-ness is DERIVED from corpus.stubs at every
read (load_best drops now-banked rows per-binary, P9) and `make report` runs `backlog.py prune`.
Membership is therefore self-maintaining and currently clean: 863 rows, 0 already-banked, 14
duplicate-addr (was 6,867 rows / 98% banked before Phase-29 compaction). What pruning does NOT
re-validate is the VERDICT on surviving rows -- closeness + residual class are as old as the
tooling that wrote them (Phase 28 found a corrupt one: func_80178004 close=0 -> 91). That is
the staleness that matters, and it is exactly what this probe measured.
Propagation behind the crack banked this session. jtbl_family_bank.py over the 4 open
h_seq siblings of func_801878E8 (513 ins each):
ov_SC03_001 BANKED ov_SC03_124 BANKED
ov_SC04_019 BANKED ov_SC05_017 BANKED
ROUTE NOTE (§53, worth keeping): family_sweep --hseq REFUSED this family by design --
has_mid_jr => it needs the jtbl carve, not the remap sweep, and the interlock says plainly
that "a 0% from this path would be a TOOL artifact, not a wall". Taking the refusal at face
value and using the named tool banked 4/4 first try. This is the same lesson as the rest of
the session from the other side: the instrument told the truth about its own limits.
jtbl_family_bank also enforces a CLEAN tree (it reverts from HEAD per sibling, so an
uncommitted prior bank would be destroyed) -- which is why the ×1 banks committed first (H4).
VERIFIED: make clean && make extract-all && make check-all -> 140 passed, 0 failed of 140
(each sibling carves its own jtbl => config changed => fleet blast radius). Fleet
instr-weighted 12408077 -> 12410129 = +2,052, exactly 4 x 513; distinct +1,539 / +3 unique
fns (the 4th sibling shares an h_exact class already matched); fn-count +4. audit-digest OK.
0 NON_MATCHING (G4).
Session running total: +4,727 instructions (whale 770 + 4 drafts 1,905 + family 2,052),
12405402 -> 12410129, every step R22 clean-fleet 140/140.
The 6 still-open wave-6 drafts were triaged against S38's own diagnosis table; 4 banked,
R22 clean-fleet 140/140.
func_801919A0 ov_SC06_032 710 ins (was: undefined ref func_8018B878 -- "alias class")
func_80189030 ov_SC03_001 557 ins (was: undefined ref func_80186F88 -- "alias class")
func_801878E8 ov_SC04_018 513 ins (was: undefined ref func_801848DC -- "alias class")
func_8018A564 ov_SC02_027 125 ins (was: CC1-FAIL Error 33)
THE FINDING: all four banked with NO change to the drafts. S38 recorded them blocked on a
class that needed cracking ("cracking this one class frees 6 drafts at once"); they had
ALREADY been freed by S38's own tool repairs -- the jr_isolate_all/overlay_src_split
alias-DEFINITION-deletion blindness and harvest_verify._reload_corpus. The drafts were
correct all along; the instruments were failing them. That is the FIFTH recorded "wall"
this phase to resolve to our own tooling.
=> RE-GATE STORED DRAFTS AFTER ANY TOOL REPAIR before treating a stored verdict as a
fact about the code. A verdict is only as current as the instrument that produced it
(R35 applied to the backlog, not just to metrics).
Each bank also performed a jtbl carve, so config/ changed => fleet blast radius => full R22
(clean + extract-all + check-all) = 140 passed, 0 failed of 140.
Metrics move exactly as the model predicts: instr 12406172 -> 12408077 = +1,905, the exact
sum of the four (710+557+513+125); distinct +1,905 / +4 unique fns; fn-count +4.
audit-digest OK. 0 NON_MATCHING (G4).
LEFT ON THE BACKLOG as genuine codegen residuals, not forced (P9):
func_8017C974 (ov_SC01_077, 947 ins, close=47, REGALLOC-PERM, 12 permuter variants inert)
func_80188C68 (ov_SC03_124, 551 ins, close=370, the only target with no twin anywhere)
NEXT: the func_801878E8 family (4 open siblings x 513 ~= +2,052). family_sweep --hseq
correctly REFUSED it via the §53 interlock (has_mid_jr => jtbl carve route; "a 0% from this
path would be a TOOL artifact, not a wall"), and jtbl_family_bank.py requires a clean tree
because it reverts from HEAD per sibling -- which is why this commit lands first.
Closes the first of S38's two reverted R22 failures. ov_SC07_010 was the lone overlay
still shipping func_80144B9C (770 ins) as INCLUDE_ASM while the other 137 banked it.
Its _jr_80140608 object ran 0x184b0..0x2c2f4 straight through the whale; the sibling
ov_SC07_006 carves the same span into _o0d (0x1ca44) + _jr_801457A4 (0x1d64c). Note
0x1ca44 + 0x80128158 = 0x80144B9C exactly.
tools/o0_subsplit.py ov_SC07_010 --lo 0x80144B9C --hi 0x801457A4
-> 1 unmatched stub, 0 ALREADY-MATCHED in range (so no §126 island; K=0 => 3 regions)
-> split BYTE-NEUTRAL first (d7b5875d), then banked via ../shared/func_80144B9C.h
The S38 cause ("its -O0 split reused an EXISTING _o0c instead of a fresh _o0d") did NOT
recur: o0_subsplit.free_letters derives the unused suffix (_o0c is free in THIS overlay).
Two decl conflicts on the way, enumerated with `cdecl` in ONE pass (R33) rather than one
build at a time — of the whale header's 94 symbols the §8b carried layer re-declares 3,
and 2 conflict: D_801274D0 (layer `s32 (*)(s32)`) and D_801274CC (layer `void *`) vs the
header's canonical `s32`. Dropped both: nothing in the region uses them, they are carried
from an earlier region of the old object, and 0 of the 137 other whale-including files
carry either. Decls emit no code => byte-neutral (§8c), and byte-gated.
ov_SC06_030/func_8017E120 needed NO work — it is already banked (defined at
ov_SC06_030_jr_8017C8D0.c:3491). S38 reverted the surrounding batch, not that function.
VERIFIED: make clean && make extract-all && make check-all -> 140 passed, 0 failed of 140
(config changed => fleet blast radius, R22 mandatory). Fleet instr-weighted
12405402 -> 12406172 = +770, exactly the whale's size. distinct-code unchanged by design:
that h_exact class was already matched via the other 137, so the 138th adds fleet
instructions but no new DISTINCT function. audit-digest OK (the new S1e gate, on its first
real use). 0 NON_MATCHING (G4).
Metric note (R30, same class as S1e): a body banked by #include-ing a shared header is
invisible to fn-count's NUMERATOR (the definition is not in the .c) while its stub leaves
the denominator -- 341186/353718 -> 341186/353717. The weighted metrics counted it
correctly because they derive from corpus.stubs, not re-parsed C. Trust the weighted pair.
Still open from S3: the 61 SC07 -O0 members (untouched).
Refreshes a checkpoint that had gone stale (v3 predated S1d) — stale is worse than absent.
FLEET 96.46 / 94.4 / 89.2, +37,166 instructions this session, ~0 agent tokens after the opening
wave. R22 run thirteen times: 140/140 on eleven, TWO REAL FAILURES (ov_SC07_010, ov_SC06_030), both
caught by the clean-tree rebuild after passing their per-binary gate, both reverted and recorded.
Records the session's biggest find: the §37/§124 DEFINITION-SIDE ASM-LABEL ALIAS is a CLASS lever,
not a one-off. It cracked the 208-conflict narrow-parameter class 138/138 after cast_call_sites,
--normalize-self-decls and --fix-def-sig were each eliminated BY MEASUREMENT. S33 proved it once and
it was never generalised.
Carries the unresolved accounting anomaly prominently (new task #11 / S1e): distinct-code FELL
89.3 -> 89.2 across the alias harvest while fn-count ROSE, which no pure naming artifact explains.
The bytes are proven; the yield number is not. Next session starts there, before scaling the lever.
Also records eleven tool defects fixed (nine of ten "walls" were our own instruments, two of them
mine), that §134 has now appeared in SIX tools and wants cdecl._mask rather than a seventh patch,
and seven process errors of my own including piping away a gate summary I then could not report.
docs/progress.fleet.md is the authoritative metric source the checkpoint's staleness self-check
compares against — committing it keeps that check meaningful for the next session.
Families that returned 0/N before the 895-type lift now bank: 97 member-matches across 137 families
(1,138 failed; skipped 186 STRUCT-class by design, 106 unresolved-immediate, 6 not-stub).
R22 clean-fleet 140/140. Fleet 94.2 -> 94.3% instr / 88.9 -> 89.1% distinct / 96.29 -> 96.32% fn.
RESIDUE PRICED FROM THE SWEEP'S OWN .classified.txt PAYLOADS, not inferred: in the 400 most recent
failure records, 133 are genuine DIFF and the clear majority are `conflicting types for <sym>` —
the §103/§20 extern-conflict class, across ~12 overlays. That confirms S1b (wire reconcile_tu /
cast_call_sites into the --hseq path) is the correct next lever, and it is now justified by
measurement rather than by the plan's projection.
Method note worth keeping: those per-member diagnoses have been written on every sweep run for a
month and were never read — including by me, until after I had spent two probes and a manual
--stage-only round rediscovering one of them. Every remaining task now starts by reading the payload.
FLEET 96.29% fn / 94.2% instr / 88.9% distinct, R22 140/140 twice. Session banked 7 wave-6 heads
+ 25 propagated siblings = +10,616 instructions (12,368,236 -> 12,378,852; the digest delta matches
the hand-derivation exactly).
wave-metrics.md gains Findings 5 and 6:
- RANK WAVES BY INSTRUCTIONS, NOT HEADS. Wave 6 banked ~45% more instructions than wave 5 while
banking less than half as many heads, because a bigger head carries more instructions AND its
family propagates at the same cost per sibling (func_8017FEE0: ONE 299-ins head -> 4,485 ins
across 15 siblings, ~0 agent tokens). The metric to beat is POOL REALISATION (21%), not bank
rate — and wave 6's bank rate is NOT comparable to waves 3-5 because the difficulty knob moved
deliberately (median target 438 ins vs 143, mostly has_mid_jr).
- A WAVE TALLY IS A COVERAGE CLAIM and needs its own assertion.
The 9 unbanked drafts are diagnosed and preserved, and 6 of them are ONE class worth cracking
first: `undefined reference` to a sibling that IS defined in the overlay but only via a
definition-side __asm__ alias (§37/§124) — the carve repartitions the object and separates the call
site from the alias definition. One fix frees 6 already-paid-for drafts and will recur in every
carve-heavy wave. The other two are genuine near-misses (close=47 REGALLOC-PERM, close=370).
Tooling committed for reuse: w6_pool.py (the pool derivation, now a script), w6_diag.py (runs the
REAL gate path — s36_capture.py splices without the carve and is wrong for jr targets),
w6_jtbl_prop.py (carve-path propagation with the per-family commit jtbl_family_bank requires).
Fleet 96.27 -> 96.28% fn-count / 94.1% instr / 88.6 -> 88.7% distinct (77,765
uniq). R22 clean-fleet: 140 passed, 0 failed of 140. dedup 1910/0.
16 targets / 16,884 templatable ins. 19 agents, 2.71M tokens, 82 min wall.
The gate banked 16/16 — the FIRST perfect gate of the session, and the first
needing NO reconcile at all. Sweep: +26 members / 3 failed across 17 overlays.
NEW: docs/wave-metrics.md — the wave-by-wave performance log, with the derivation
commands so future rows are COMPUTED, not hand-transcribed (R33). Four findings,
each recorded with its caveat rather than as a bare number:
1. THE PROMPT IS THE LEVER, AND THE AGENTS WRITE IT. Bank rate 76 -> 77 -> 100
-> 100 -> 100% with models and gate held constant. The jump was STEP 0 (a
magic-literal grep of src/, ahead of engine_core.h) — which came from a
wave-2 agent's index_gap report. Caveat recorded: waves 3-5 targets also
trended easier, so the mechanism is the durable claim, not the exact %.
2. pipeline() vs batched parallel(): 136 min/14 targets -> 82 min/16 targets,
parallelism 2.5x -> 3.8x. The two-batch design was a hard barrier with 37-50
min dead gaps; the harness already caps at 16 so it bought nothing. Floor
recorded honestly: the slowest agent is still ~50 min of real match_one
iteration, so the lever there is target SELECTION, not concurrency.
3. ECONOMICS: ~170-300k tokens per banked head in the stable regime — but a head
is not the unit of value. Head + propagated members is, and sweep yield is
BIMODAL not average (21/21 vs 18/165), because it is a property of the FAMILY.
Averaging those two predicts nothing.
4. A perfect gate is a signal the prompt rules landed. Waves 1-4 each needed 1-2
post-gate reconciles; wave 5 needed zero. The reconcile lane is the fallback,
not the plan. Lifetime 21/22.
Fleet: R22 clean-fleet 140 passed, 0 failed of 140. dedup 1910/0.
14 targets / 16,844 templatable ins. 17 agents, 3.0M tokens. Claimed 14/14; the
whole-binary gate banked 13, the 14th on reconcile. Sweep: +26 members / 0 failed
across 18 overlays. Reconcile lane 21/22 lifetime.
STEP 0 HAS BECOME THE AGENTS' DEFAULT MOVE. Nearly every wave-4 verdict cites the
cross-overlay magic-literal grep BY NAME, several reporting `index_gap: none`
because it resolved the target in one pass with no cookbook derivation needed:
- func_8018BED0: grep 0xE100000A -> func_80188C04 (ov_SC03_089), verbatim, MATCH first try
- func_8018BAB4: grep D_800A6610/D_800B9A02 -> func_801887E8, verbatim + callee swap
- func_8017ED54: grep named all 5 family members -> reused func_8017D9F0's body, 14 data remaps
- func_8017C290: grep found byte-identical twins ALREADY banked in two other overlays
Bank rate by wave, same models + same gate, prompt the only variable:
76% -> 77% -> 100% -> 100%.
THE ONE FAILURE IS THE §138 RECONCILE-DIRECTION RULE, in its purest form:
`redefinition of struct B16_8018A758` — the agent copied its sibling's struct tag
verbatim, and that sibling had banked into the SAME TU earlier in THIS wave. Decl
ABOVE the splice => DELETE the duplicate (do not rename it). Worth noting the
mechanism: a wave can create its own reconcile work when two targets share a TU.
func_8018A808's own family swept 0/14 — its members are the per-location kind
that do not template (the settled h_seq ceiling), not a plumbing failure.
Fleet 96.24 -> 96.25% fn-count / 94.0% instr / 88.4 -> 88.5% distinct.
R22 clean-fleet: 140 passed, 0 failed of 140. dedup 1910/0.
13 targets / 17,644 templatable ins. 14 agents, 2.7M tokens. Claimed 13/13;
the whole-binary gate banked 12, the 13th on reconcile (another §37/§124
SELF-axis alias — the TU declares `(void)`, the def takes an s32). Reconcile
lane 20/21 lifetime. Sweep: +21 members / 0 failed across 16 overlays.
THE FLYWHEEL, MEASURED ACROSS THREE WAVES (same models, same gate):
wave 1 baseline prompt 15/17 claimed -> 13 banked (76%)
wave 2 + the S33 rules 11/13 -> 10 (77%)
wave 3 + S34 magic-grep as STEP 0 13/13 -> 13 (100%)
Multiple wave-3 agents report the cross-overlay magic-literal grep landing the
answer on the FIRST search. One found a banked twin whose own header comment
already documented it as byte-identical to the new target, so the body
transferred verbatim with only file-local type suffixes renamed. That is the
wave-2 discovery paying off one wave later (R16).
Sweep quality also differed for a reason worth keeping: 21/21 here vs 18/165 in
wave 2. Wave 2's two big families are the per-location kind I then probed and
ruled out (BUILD OK + byte diff = genuine per-member codegen, not plumbing);
wave 3's are genuinely templatable. The sweep rate is a property of the FAMILY,
not of the wave.
TOOLING: an agent left 8 scratch files (test_licm*.c) in the drafts dir and the
gate driver died on `int('full', 16)`, taking the whole gate with it. Hardened to
treat a non-conforming filename as a NAMED, COUNTED skip rather than a crash
(R32) — a drafts dir is agent-writable by design, so it must not be trusted to
contain only deliverables.
Fleet 96.24% fn-count / 93.9 -> 94.0% instr / 88.4% distinct. R22 clean-fleet:
140 passed, 0 failed of 140. dedup 1910/0.
WAVE 2: 13 targets / 37,943 templatable ins. 19 agents, 4.5M tokens. Claimed 11
MATCH; the whole-binary gate banked 9, +1 on reconcile (func_8017E5D0 via the
§37/§124 DEFINITION-side alias — the TU declares it `(void)`, the byte-true def
takes a pointer). Reconcile lane now 19/20 lifetime. 18 members swept.
THE FINDING (an agent caught a hole in our own procedure). §136c's search order
— engine_core.h near-twin -> same-TU banked sibling -> the .s — is entirely
SAME-TU or SHARED-HEADER scoped, so no step can reach a banked twin in a
DIFFERENT overlay's TU. But the large template classes live cross-overlay by
construction. func_80188C04 (328 ins) turned out byte-identical to an
already-banked func_801833F0 in ov_SC02_028, and ONE command found it:
`grep -rn "E100000A" src/` — a magic word lifted from the target .s. The body was
then reused verbatim, only file-local suffixes renamed. Promoted to STEP 0 of
§136c, ahead of engine_core.h.
That compounds with the manifest finding this session: the family map's
`exemplar` is an IN-FAMILY pointer, so a family whose twin is banked elsewhere
looks un-cracked — and the pointer can itself name an ALREADY-BANKED instance,
hiding the family from any ranking built on it. Derive open sites from
corpus.stubs over the member list instead. Measured on this wave: ranking off the
map's exemplar gave 16,696 templatable ins; deriving from corpus.stubs gave
41,023, including a 55-ins family open in 138 overlays and a 46-ins one in 133.
HONEST ON THE SWEEP: those two big families templated 18/165. That is the known
h_seq refusal ceiling, not a new wall. One agent reported "all 10 members
distance 0" — that is NORMALIZED distance, not h_exact, which is why
dedup_propagate correctly answered reach<2. Do not read a normalized-distance
claim as an h_exact guarantee.
LEDGERED (real residual, not paperwork): func_8017F7B4 — needed its sibling's
type names AND a data asm-label alias for a u8-shaped symbol, and still refuses.
Plus func_8017C294 (DIFF close=12: 4 register/schedule permutations + a frame
where I can get the 0x138 size OR pEnd's slot at 0x108, not both) and
func_801898E4.
Fleet 96.23 -> 96.24% fn-count / 93.9% instr / 88.3 -> 88.4% distinct.
R22 clean-fleet: 140 passed, 0 failed of 140. dedup 1910/0.
func_8017D318 (184 ins) + func_80181EE0 (198 ins) both banked, + 6 members swept
(6 per-overlay variants failed — ledger material, not a lever).
THE RECONCILE DIRECTION DEPENDS ON WHERE THE TU'S DECL IS, and picking wrong
CREATES the next error (-> cookbook §138):
- decl ABOVE the splice point -> DELETE the draft's duplicate (§100).
func_8017D318: the TU defines MATRIX_/SVECTOR_8017C290, D_801EA8C0 AND a
`struct PW8017C290` tag above it; I missed the tag on the first pass, so it
took two rounds.
- decl BELOW the splice point -> KEEP a decl in the TU's EXACT shape and cast
at the use (§17a-1 D2). func_80181EE0: I removed its decl assuming the TU
provided one; the TU's `extern int func_80143C74(short *, int);` is at L5082,
~180 lines BELOW the splice at 4901, so the identifier went undeclared.
Grep the TU for the symbol and compare line numbers with the stub line first.
MY OWN §136a VIOLATION, recorded: the blocker-capture filtered the build log for
`error|conflicting|undefined reference` and reported "NO COMPILE ERROR" on a
build that was failing with `redefinition of struct PW8017C290` and
`'func_80143C74' undeclared` — neither phrase matched. A narrow keyword filter is
exactly how a real error goes unseen, which is the thing §136a exists to say.
Widened to keep any line naming a source position.
Fleet 96.21 -> 96.23% fn-count / 93.8 -> 93.9% instr / 88.0 -> 88.3% distinct
(+73 unique fns). R22 clean-fleet: 140 passed, 0 failed of 140. dedup 1910/0.
THE WAVE. Re-ran S10's 17 unbanked targets (26,227 templatable ins) at LOW
concurrency in two batches of ~9 — S10's finding was that 14 of 30 agents were
SERVER-throttled, i.e. the limiter is capacity, not capability. Targets
re-derived against corpus.stubs first (R35): all 17 still live, paths verified.
25 agents, 6.87M tokens, ~2.8h. Claimed 15 MATCH; the whole-binary gate — the
sole arbiter (G3/P9) — banked 13, then family_sweep propagated 65 members across
38 overlays.
HEADLINE: func_8017D174 (793 ins) — the largest single crack of this phase. Its
agent closed two compiler-internal residuals jointly: a §137 allocno-priority tie
between &g.sz0/&g.sz1 (R=7, L=607 vs 606 -> 230/231) that spilled the wrong one
and cost a load-delay nop in BOTH switch arms, and a sched2 rotation in the
outer-loop head block that survived 470+ statement orderings. Fix was four
zero-byte asms: two `"=r"/"0"` re-ties splitting wz's live range, plus two
volatile sliders placed in a DIFFERENT basic block so they lift the live-length
count without perturbing the head schedule.
THE 4 NON-BANKS SPLIT CLEANLY (§136b — none is a wall on one attempt):
- func_8017E2EC (close=20) and func_80186E24 (close=187): honest DIFF verdicts,
real codegen residuals, ledger material.
- func_8017D318 and func_80181EE0: claimed MATCH, gate refused -> the known
match_one->gate gap, which is DECLARATION plumbing (agents cannot run the
gate, so a TU-level conflict is invisible to them). Routed to the reconcile
lane, not retired.
AGENT-REPORTED INDEX GAPS worth acting on (the flywheel closing on itself):
- no symptom key for "schedule rotation at a loop-head block that NO statement
permutation reaches" — the index's nearest line points at §76 regalloc, and
the decisive doc was gcc-2.7.2-map/sched.md, which no scheduling symptom
cross-references.
- §137 is written as a two-compile arithmetic on ONE contender pair; the real
fix here was an N-zero-byte-insn budget that ties only for N in {1,3,4} and
splits the WRONG way for N=2, so a naive "add one slider, add another" walk
silently regresses.
- no key for "gcc hoists a loop-invariant SYMBOL_REF base out of a loop the
target keeps in the `sym(reg)` macro form" (~105 of func_80186E24's 187).
Fleet 96.17 -> 96.21% fn-count / 93.8% instr / 88.0% distinct; dedup 1909 -> 1910
groups, 0 failed, C1 241216/241216. R22 clean-fleet: 140 passed, 0 failed of 140.
The head is now 5/5 classes, 18,545 templatable ins, all banked this session from
a standing start of 0.
func_801466F0 had sat since S6b behind THREE separate blockers, each of which
looked sufficient on its own to explain the failure:
1. Its definition is under a §37/§73 ASM-LABEL ALIAS (`aF801466F0` in C, bound to
the real symbol by `__asm__`), and dedup_propagate.find_site anchored its head
regex on the literal `func_<ADDR>` — structurally blind to the form, returning
None, which every caller reads as "not matched". Now reuses
family_remap._alias_decl_for rather than growing a second matcher (R33).
2. That matcher was itself blind to the WRAPPED (multi-line) declaration — the
§134 shape, third tool. Fixed by matching over the joined text and mapping the
offset back to the decl's FIRST line (extract_unit carries from there).
Regression control: the single-line form still resolves. Fleet census after:
2,768 of 2,768 alias sites resolve, 0 missed.
3. Its record type was a draft-local typedef, so the body failed
compiles_standalone. Lifted Rec801466F0 to src/shared/engine_types.h INSIDE
the include guard (the SESSION-19 double-include note) and switched both the
macro and the exemplar to it — byte-neutral, gate-proven.
Probed on ONE member before the fleet run: byte-identical 9052dc0e first try.
MEASURED, NOT INHERITED (R37): the S6b note frames the alias-regex gap as a CLASS
of missed work. It is ONE function — 91 distinct alias decls fleet-wide, the
per-line matcher resolved 90. Recording it so a future session does not scope a
phase against a class that does not exist.
cookbook §138 extended with the alias-form tool boundary and the three-blocker
story; index regenerated.
Fleet 96.10 -> 96.17% fn-count / 93.7 -> 93.8% instr / 88.0% distinct.
dedup 1908 -> 1909 groups, 0 failed, C1 241078/241078.
R22 clean-fleet: 140 passed, 0 failed of 140.
func_80147364 4,110 x137 definition-side asm-label alias
func_8016BA68 3,886 x134 dedup_extend + the MIRROR decl relax
func_8012F274 3,973 x136 hand-authored macro, source overlay excluded
func_8012A598 3,288 x138 cdecl._mask backscan fix + shared-type switch
func_801466F0 3,288 OPEN the wrapped-alias regex — measured as ONE function
THREE DISTINCT CARRY VARIANTS were hiding in one "CARRY-FIXABLE" bucket, and
only one is a tool bug (-> cookbook §138):
- a MULTI-LINE comment halts the preamble backscan -> fix the tool (cdecl._mask)
- a draft-local `struct Tag {…}` -> switch the exemplar to the SHARED type
- a file-scope `static inline` helper -> hand-author, EXCLUDE the source overlay
The third is the sneakiest: gcc-2.7.2 accepts implicit function declarations, so
the extracted body PASSED compiles_standalone with the helper undeclared and the
miss surfaced only as a whole-binary byte DIFF 137 gates later. Instantiating
that macro in the SOURCE overlay is a duplicate definition (its file-scope helper
is still there), so the shape is `--source-overlay X --binaries <all-but-X>`;
`--binaries` alone removes the source from the scan pool and errors.
TOOL BOUNDARY: once a group's members are DEFINE_func_*() sites, dedup_propagate
cannot extend it (find_site never returns a `def`). dedup_extend is the tool for
an already-macro-ized group — and `dedup_extend --check-only` across ordinary
overlays is a cheap fleet-wide wiring census (measured: exactly 1 group per
overlay, so no hidden backlog).
MEASURED, NOT INHERITED (R37): the S6b note frames _alias_decl_for's single-line
regex as a CLASS of missed work. It is not — 91 asm-label alias decls exist
fleet-wide, the regex matches 90, and the single miss is func_801466F0. Worth
3,288 ins, but a one-function fix. Correcting the expectation so a future session
does not scope against it.
Fleet 96.06 -> 96.10% fn-count / 93.7% instr / 88.0% distinct; dedup 1907 -> 1908
groups, 0 failed, C1 240807/240807. R22 clean-fleet: 140 passed, 0 failed of 140.
func_8012A598 (3,288 templatable ins) was being written off as CARRY-FIXABLE.
It took TWO fixes; either alone leaves it skipped.
1. TOOL (R33) — find_site's preamble backscan. The SESSION-18 fix handled blank,
`//`, and SINGLE-LINE `/* … */` lines, but a MULTI-LINE block comment still
halted the walk: its middle lines start with `*` and its last line ends `*/`
without starting `/*`. So the three externs above the body were dropped and
the body then failed compiles_standalone on now-undeclared data. This is the
§134 multi-line-blindness class — S6b fixed the identical shape three times in
family_remap (D1/D2/D5) and this copy was never reached.
Fixed by deciding skippability on `cdecl._mask` — the project's ONE masking
oracle — instead of on line syntax: it subsumes every comment form at once and
cannot be fooled by a `/*` inside a string, with an R32 assertion on the
length-preservation invariant it rests on. Strictly monotone (it can only
carry MORE preamble), and dedup_propagate is a byte-gate feeder, so a bug here
can fail to bank but never falsely bank.
2. EXEMPLAR — the body also declared a draft-local `struct BigCopy164` tag, which
the tool refuses by design (two macros defining one tag would redefine it in a
single TU). The shared `struct BigCopy` (engine_types.h L312) is the identical
layout and is ALREADY used this exact way at engine_core.h:16158, so switching
the exemplar to it is byte-neutral and drops the alias too.
Probed on ONE member before scaling (R37/S29): byte-identical 9052dc0e first try;
then 138 overlays byte-identical.
PROPAGATE head accounting after this: 7,398 of 18,545 ins banked (func_80147364
4,110 + func_8012A598 3,288). Still open, each with a NAMED cause and none yet
diagnosed against a build: func_8012f274 (3,973, dropped), func_8016ba68 (3,886,
4/138), func_801466f0 (3,288, the S6b D4 wrapped-alias gap).
Continues the S11 lane. Fleet 96.01 -> 96.06% fn-count / 93.6 -> 93.7% instr /
88.0% distinct; dedup 1905 -> 1907 groups, 0 failed, C1 240669/240669.
R22 clean-fleet: 140 passed, 0 failed of 140. 0 NON_MATCHING (G4).
EXTEND (SC07): the 16 volatile-blocked DIFF slots banked on retry after the
data asm-label alias -> lane total 31/36.
PROPAGATE head, measured rather than projected. .run/s8_lag.json re-split: the
checkpoint's "45 classes / 20,837 ins" is really 5 classes carrying 18,545 ins
(89%) and 41 carrying 2,316. Per-class outcome:
func_80147364 30x137 = 4,110 BANKED x137 (definition-side asm-label alias)
func_8012f274 29x137 = 3,973 DROPPED — byte-diverges in ~130 overlays
func_8016ba68 29x134 = 3,886 4 of 138 banked; excluded from ~130
func_8012a598 24x137 = 3,288 SKIPPED, cause NAMED by the tool
func_801466f0 24x137 = 3,288 no source found — the S6b D4 gap, still open
func_80147364's byte-true definition is `(u16, u16)` while 4,046 fleet decls
say `(u16, s32)`. u16 is a default-promotion type, so the `()` no-prototype
escape is ILLEGAL (the documented gcc-2.7.2 dead-end) and conforming the decl
would change caller codegen. The DEFINITION-SIDE asm-label alias gives the def
a distinct C identifier while emitting the real symbol -- zero blast radius on
every caller. Probed on ONE member first (1 build, not 137 -- the S29
discipline): byte-identical 9052dc0e first try; then 137 overlays clean.
In-tree precedent for the form: 1,725 files.
MEASURED NEGATIVE, recorded not buried: `dedup_propagate --recover` banked only
4 of 138 on func_8016ba68 and dropped func_8012f274 entirely (137 [exclude]
lines). The caller-extern reconcile that is 16/16 lifetime ON DRAFTS does NOT
transfer to PROPAGATION of these two. Cause not yet diagnosed -- probe one
excluded overlay's build output before any further attempt (§136a), do not
re-run the lever hoping.
NAMED NEXT (cheapest first): func_8012a598 skips on `missing file-scope extern
(CARRY-FIXABLE): D_801151D4, D_80126DB8_a, D_80127504` -- the SESSION-18
preamble-backscan class. Its body is 2 statements and `struct BigCopy` is
ALREADY in the shared engine_types.h (L312) with the identical statement already
macro-ized at engine_core.h:16158, so a hand-authored macro (the func_80147364
path) should take it x137 for ~0 tokens.
Process errors recorded in CURRENT_PHASE.md, all three one mechanism -- the
signal sampled is not the thing waited for: (1) a `nohup CMD &` wrapper's exit
read as the fleet check finishing (it stood at 63/140); (2) a corpus.stubs probe
mid-rebuild, which R32's coverage assertion refused rather than answer wrongly;
(3) CORRECTION to the S10 checkpoint's own rule -- `pgrep -x make` is right for
one make and WRONG for a campaign of sequential makes (it fired in a gap and
reported a live campaign done), and `pgrep -f <pattern>` SELF-MATCHES so that
waiter can never exit. Wait on the campaign process or `treelock.sh --status`.
- DREW'S CALL (2026-08-03): route the 30-target x2-9 wave to SONNET instead of Opus. The §136i
>=120-ins Opus threshold was MY EXTRAPOLATION, never measured; this wave (125-793 ins) probes
exactly the region where there was no data.
- RESULT: 13 banked of 16 that ran = **81%**, vs Opus's 10/13 = 77% on the comparable S8-3 slice.
At least 8 banked SONNET-DIRECT (65 agents spawned: 60 sonnet, 5 opus escalations). Propagated
57 member-matches / 4 failed across 42 overlays. 70 instances. R22 clean-fleet 140/140.
FLEET 96.01% fn / 93.6% instr / 88.0% distinct (77,550 uniq).
=> **Sonnet is at least as capable as Opus on 125-793 ins. The ~120 boundary is too low.**
NOT rewriting it to a specific number yet: 16 samples under a throttle confound cannot name a
cliff. The controlled A/B (task #12) is how that number gets fixed properly.
- THE REAL LIMITER IS CAPACITY, NOT CAPABILITY: 14 of 30 agents were killed by SERVER-side
throttling ("Server is temporarily limiting requests (not your usage limit)") that 30 concurrent
Opus agents did not trigger. Practical rule: run Sonnet waves at ~12-16 concurrency, not 30.
The 14 unrun targets are listed in the checkpoint for a smaller-batch retry.
- Sonnet's work quality was not shallow — three examples: func_8018797C read local-alloc.c and
forced loads into an AGGREGATE to stop find_free_reg greedily taking 3 callee-saved regs;
func_8018D870 used §136c sibling-first for ~70% of the body then blocked a coalesce with a pin;
func_8017E3AC diagnosed an RC-3 callee-saved-order swap and noted the pin must be s32 or a stray
`andi 0xffff` appears.
- MY ERROR, RECORDED: `until [ -s <output> ]` fires at the FIRST LINE of output, not at completion.
It fired mid-propagation and I ran `make clean` on top of a live family_sweep, deleting asm/ and
aborting both the regen and the sweep (corpus's R32 assertion refused to answer rather than return
a wrong stub set — working as designed). No bad bytes: R22 verified 140/140 immediately after, and
the propagation simply re-ran clean. Correct waiter is `pgrep -x make` (exact process name), which
also cannot self-match the way `pgrep -f <pattern>` did when it leaked 4 waiter shells earlier.
Third instance today of ONE root cause: trusting a proxy instead of the thing itself (a weight
column vs a probe §136h; an exit status vs build output §136a; file-existence vs process exit).
- S8-3 (23 fresh x10-99 families, 121-328 ins — the hardest band this session): draft 16/23 ->
capture (1 PLUMBING / 6 DIFF) -> reconcile 1/1 -> redraft 6/6 => **23/23 (100%)**.
Propagated 206 + 81 = 287 member-matches across 80+54 overlays. R22 clean-fleet 140/140.
FLEET 95.97% fn / 93.4% instr / 87.5% distinct (77,404 uniq); dedup 1905/0; 0 NON_MATCHING.
- §136b CLOSES AT 15/15 — no function ledgered "genuine byte-DIFF" survived a redraft, all session.
- §137 (NEW, the session's most reusable result): REGALLOC-PERM — a clean 2-register swap — is a
TWO-COMPILE ARITHMETIC PROBLEM. global.c:allocno_compare ranks by floor_log2(R)*R/L*1e4*size;
read R and L out of `cc1 -dl -dg` for BOTH contenders AND their ranked neighbours to get the
admissible priority WINDOW, then place a zero-byte `__asm__ __volatile__("" ::"r"(v))` so L lands
inside it. func_801833F0: contenders ONE unit apart (1297 vs 1296), window (1228,1296), five
placements probed, only L=219 -> pri 1232 worked. R and L are FORCED BY THE EMITTED CODE (L is
recomputed post-sched1), which is exactly why source-reordering is a dead end for this class.
Converts a class the permuter banked 0 from all session into a deterministic calculation.
Companion: floor_log2 makes ref-count a STEP function (5/6/7 refs are worthless, you must reach 8)
— func_8017EFA8 closed 30 register-name mismatches by taking a pseudo 4 refs -> 8 with a dead read.
- §136j — the failure MIX FLIPS WITH SIZE: <=120 ins fails ~70% on declarations; 121-328 ins fails
86% on genuine codegen. Budget reconcile for the small band, redraft for the big one — and do NOT
read 70% on a big-function wave as a broken pipeline; that is the expected shape.
- §137a — a gate verdict has a TIMESTAMP. Two "DIFF" ledger entries were STALE (draft rewritten 28
min after the gate ran, never re-gated); both were already byte-perfect. Compare verdict time to
draft mtime before redrafting. Plus two offline oracles an agent built: a FULL RELOCATION RESOLVE
(catches wrong jal/%hi/%lo targets that match_one's mask hides) and a COLLATERAL CHECK (whole-TU
objdump with/without splice). Together they discriminate all three causes of "match_one says MATCH
but the overlay SHA differs" without running make.
- §136f addendum — the collider is often an already-banked SIBLING BELOW the splice; locate it by
arithmetic (draft grows the file N lines, so TU line L reports at L+N).
- cookbook-index 380 -> 382 sections.
- FINAL LANES: reconcile ×5 (5/5) + redraft ×1 (1/1) -> gate BANKED 6/6 -> propagated 50 members
across 28 overlays. **ALL 144 DRAFTED TARGETS BANKED (100%); zero stubs remain in the queue.**
R22 clean-fleet 140/140 (seventh time this session).
FLEET 95.88% fn / 92.9% instr / 86.5% distinct (77,106 unique fns); dedup 1905/0; 0 NON_MATCHING.
- LANE RECORDS: reconcile 15/15 lifetime · redraft 9/9 · §136b closes at 9 FOR 9 (every function
ever ledgered "genuine byte-DIFF" banked on redraft).
- THE CAPTURE CLASSIFIER, third and final defect (§136a): it decided PLUMBING by matching a regex
against cc1's PROSE, and cc1's vocabulary is open-ended — `too many arguments to function` matched
nothing, so a trivially reconcilable function sat UNKNOWN through two gate rounds. Now DERIVES the
class from the closed invariant (did the compile produce an object: `make ... Error N` +
`Deleting file`). Re-running it moved 5 PLUMBING / 1 UNKNOWN -> 5 PLUMBING / 1 DIFF, and BOTH
reclassified functions then banked. Three defects in one small tool in one session — an
unreachable exit-status branch, a missed phrasing, and the prose-matching design behind both —
each SILENTLY MIS-ROUTING REAL WORK. R33 in one line: if an invariant answers it, never re-parse.
- §136f — two declaration sub-cases: (1) a symbol you call may be DEFINED, not just declared, BELOW
your splice point (func_8017D540 is defined 275 lines below as int(int); the draft guessed
void(s32) from a bare jal); (2) an ARITY clash on the symbol you are DEFINING cannot be fixed by a
cast — use the §37/§124 asm-label alias (func_801848DC; in-TU precedent at :8872).
- §136g — TWO INDEX ROUTINGS BYTE-REFUTED (func_801863B4). The index sends BRANCH-POLARITY to §3-T4
(invert) and §34 (zero-byte fence); the agent tested BOTH at zero, read the gcc-2.7.2 source, and
found jump.c:1806 `if (foo) bar; else break` range-swap — which runs long BEFORE reorg, so a fence
CANNOT block it. Real lever: put a label between the if-join and the return label (wrap the loop
in the guard). Also: same-address lh+lhu is MIPS LOAD_EXTEND_OP==ZERO_EXTEND (mips.h:1163), and
combine collapses the pair unless the HImode pseudo has two reaching defs.
REFUTED ROUTINGS ARE RECORDED NEXT TO THE CORRECT ONE — otherwise the next agent re-runs them.
- cookbook-index 375 -> 377 sections (§136 .. §136g earned this session).
- BATCH 3 (37 targets, 41 agents, 2.75M tok -> 35 claimed): gate BANKED 35; family_sweep propagated
305 member-matches / 39 failed across 77 overlays (14 STRUCT skipped by design). 340 instances.
R22 clean-fleet 140/140 (sixth time this session).
FLEET 95.86% fn / 92.9% instr / 86.5% distinct (77,061 unique fns); dedup 1905/0; 0 NON_MATCHING.
- WAVE 4b COMPLETE: b1 32/37 + b2 35/37 + b3 35/37; with wave 4a (30/33) the whole 144-family
B-shape queue that opened this session is worked through — 138 of 144 drafts banked (96%).
- §136e — batch 3's two HONEST NEGATIVES, worth as much as the wins:
(1) §136c SIBLING-FIRST HAS A PRECONDITION. func_801899AC's family has all 13 members still
unmatched and no engine_core.h twin, so there IS no byte-verified sibling and the search is
pure cost. Check a banked sibling EXISTS before spending the greps.
(2) A loop increment in the loop-back DELAY SLOT + a compensating negative addiu is a SOURCE
SHAPE, not a reorg artefact — MIPS1 has no annulling, so reorg CANNOT invent the
compensation. Write `p += 2; if (t == cur) break; ... p -= 2;`. combine's reg_n_sets==1 guard
stops the addiu folding into the following lw. The index's delay-slot entries point at reorg,
which is a dead end for this class.
Plus a new §136-L1 application on the RETURN axis (an over-scoped temp became a global allocno and
swapped $v0/$v1 with the returned local, collapsing the target's `j` + `addu` return).
- COMPOSITION, demonstrated on func_8017D5F4 (46 ins): flat early-returns -> dead-local frame pad ->
s16 locals -> operand order -> 3 register pins -> 2 zero-byte re-ties -> permuter for the last 2.
THE PERMUTER IS THE LAST STEP ON AN ALREADY-PINNED BASE, not the first.
- cookbook-index 374 -> 375 sections. 6 stubs remain; per §136b none is a wall on one attempt.
- THREE LANES: wave 4b batch 2 (37 targets, 46 agents, 3.44M tok -> 35 claimed) + the reconcile lane
on 3 PLUMBING failures (3/3) + a REDRAFT lane on 4 DIFF-ledgered failures (4/4). Combined gate
BANKED 41; family_sweep propagated 431 member-matches / 29 failed across 79 overlays.
103 of 107 drafts banked (96%). R22 clean-fleet 140/140 (fifth time this session).
FLEET 95.77% fn / 92.9% instr / 86.4% distinct (76,824 unique fns); dedup 1905/0; 0 NON_MATCHING.
- §136b CLOSES AT 8/8: every function ledgered "genuine byte-DIFF" banked on redraft — wave 3's
four, the THREE I classified from wave 4a's capture, and one from batch 1. The classifier is
right about what it measures ("this draft compiles clean and differs in bytes"); reading that as
"this function resists matching" is the error. A DIFF verdict is a fact about ONE DRAFT.
- §136a CORRECTED (a reconcile agent refuted me against the bytes): I wrote "70% of gate refusals
are paperwork, not codegen". WRONG. A declaration conflict ABORTS THE COMPILE, so a PLUMBING
verdict says NOTHING about the body. Two of three second-round PLUMBING drafts had a real codegen
residual behind the conflict (func_80188694 DIFF/4 SCHEDULE-REORDER, closed with a §21 zero-byte
re-tie after six other variants failed; func_8018C638 DIFF/6 ADDRESSING/cse). Both agents ran
match_one on the untouched draft FIRST and rejected my premise — which is what §135 asks for.
- §136c SIBLING-FIRST IS A DERIVATION SHORTCUT, not just a conflict fix: grep engine_core.h's
DEFINE_func_* bodies for a byte-verified NEAR-TWIN before deriving from the .s. func_801859D8
found DEFINE_func_80185978 (identical offset chain, 3 differing constants), reused its expression
forms verbatim -> FIRST-DRAFT MATCH, and the twin generalizes to its whole 10-member family.
Search order: near-twin -> banked same-TU sibling -> the .s -> the Ghidra seed LAST (byte-proven
an entirely different body twice this session).
- §136d, four new gcc-2.7.2 levers from the redraft lane, each with its REFUTED axis recorded:
RC-12 $0-add opaque copy (cse.c canonical-copy promotion; do NOT pin the pair to real regs);
jump.c if-then-else -> conditional-overwrite collapse (defeat with TWO SEPARATE CALLS, not a
ternary); fix the STORE not the load for a load hoisted above a constant-address store (the
INDIRECT_REF reshape is the wrong half of the /s lattice, 2 -> 32 mismatched); a branchless flag
is -(a != b) & 0xFF, never a ternary.
- cookbook-index 372 -> 374 sections. Batch 3 staged with all of the above promoted into its prompt.
- WAVE 4b BATCH 1 (37 volume-lane targets, 10-19 members, <=60 ins; wave 4a's §136 idioms promoted
into the drafting prompt per the measured 83%->93% law): 50 agents / 4.35M tokens / 32 min ->
34 claimed MATCH -> gate BANKED 32 -> family_sweep propagated 365 member-matches / 4 failed
across 84 overlays (3 STRUCT skipped by design). 397 function-instances from 37 targets.
- §136b — THE FINDING THAT CHANGES THE BACKLOG: all FOUR functions wave 3 ledgered as "genuine
byte-DIFF" BANKED on redraft. The recorded causes were never codegen:
func_801845B0 a branch to the EPILOGUE misread as an inner early-exit -> the whole tail was
hoisted out of its enclosing if (control-flow misread)
func_80184A94 a declaration conflict on a symbol declared BELOW the splice point; closed by
copying an already-banked family sibling's decl forms verbatim (§71)
func_8017BEBC the cached Ghidra seed was an ENTIRELY DIFFERENT body and the prior draft
followed it; the .s was the only usable source
func_8018480C re-derived clean
=> a DIFF verdict describes THE DRAFT THAT WAS ATTEMPTED, never the function's matchability.
Never retire a target on one; route it to REDRAFT. And re-GATING an unchanged draft is not a
retry — which is exactly why wave 4a's 3 DIFFs stayed stubs through this gate (same bytes
resubmitted); they still owe an actual redraft and are now likely winnable.
Corollary: backlog entries carrying an old closeness/class are stale by construction (P29
measured 77% of stored drafts decayed) — re-verify before valuing one.
- The wave-4b prompt handed each retry its prior verdict EXPLICITLY LABELLED "a data point, not a
verdict — re-derive from the .s". Every retry agent did exactly that and refuted it.
- R22 clean-fleet 140/140 (fourth time this session). FLEET 95.63% fn / 92.8% instr / 86.3% distinct
(76,499 unique fns); dedup 1905/0; C1 240496/240496; 0 NON_MATCHING (G4).
- Orchestration: this batch's workflow script was GENERATED from the manifest files rather than
hand-pasted — transcription had already cost this session one dead launch (args-as-string) and
cost the prior session three agents' time (hand-typed _jr_* paths). Generate the artifact; do not
ask yourself to be careful. cookbook-index 371 -> 372 sections.
- RECONCILE LANE: all 7 PLUMBING failures FIXED and banked (329K tokens — ~13x cheaper than the
drafting wave's 4.44M). Propagated +76 member-matches / 0 failed across 51 overlays.
Wave 4a final: 30/33 heads (91%) + 327 members = 357 function-instances from 33 drafted targets.
- THE CAPTURE CLASSIFICATION WAS EXACTLY PREDICTIVE: all 7 PLUMBING banked, all 3 DIFF stayed stubs
(func_8017E978 / func_80184494 / func_80184960 -> redraft lane, their C is wrong). That is what
makes the ~10-build capture step worth running before any reconcile fan-out. The lane is now
19/19 across three waves.
- EVERY reconciled draft had a HIDDEN SECOND CONFLICT cc1 never reached (it reports only the first)
-> "grep the whole TU in one pass" must be in the RECONCILE prompt, not just the drafting prompt.
One agent additionally assembled the spliced TU and masked-compared its function IN TU CONTEXT
(67/67) — proving the casts byte-neutral in situ, not merely standalone.
- NEW HAZARD, agent-surfaced (§136a corollary): an agent chose a SHARED scratch path, a concurrent
agent overwrote it, and its verification silently compiled ANOTHER agent's TU and returned a
meaningless rc=0. It caught the swap only because the emitted .s lacked its own function. A shared
scratch path yields a CONFIDENT WRONG VERDICT, and no tool fix reaches it — the choice happens
inside the agent, so the PROMPT must mandate a process-unique path. This is the Phase-28
match_one fake-isolation defect recurring one level up.
- R22 clean-fleet 140/140 (third time this session). FLEET 95.52% fn / 92.7% instr / 86.1% distinct
(76,273 unique fns); dedup 1905/0; C1 240496/240496; 0 NON_MATCHING in any default build (G4).
- .run/s7_extra.txt: wave 4a's idioms compiled into the wave-4b drafting prompt (the promotion that
measured 83%->93% between waves 1 and 2).
- S6c (deterministic, ~0 agent tokens): 12 sibling banks across 3 of 9 jr zero-crack families
(func_80178D40 890ins 4/4, func_801734BC 4/4, func_8012ACE0 4/4). The other 6 are ledgered:
5 gate-fail (genuine byte DIFF) + 1 carve-fail (span table starts do not fit the span).
R22 clean-fleet 140/140 over the whole S6c series.
- FINDING: all 12 banks landed in ov_SC07_006/007/010/011 — the four overlays P27 discovered and
P28 made citizens (R36). P28 drained their h_exact backlog via dedup_extend; the jr/h_seq
propagation lane was still owed. R14 GUARD AGAINST OVER-READING IT: the quartet are the top four
overlays by remaining zero-crack residue (2,190-2,355 ins each vs 500-870 typical) but hold only
7% of the 2,114 remaining slots — a per-overlay priority signal, NOT a bulk lever.
- BLOCKER CAPTURE for the 10 wave-4a gate failures -> .run/s7_blockers.json: 7 PLUMBING (all
`conflicting types for func_X`) / 3 genuine byte-DIFF. 70% of "the gate refused" is declaration
paperwork. New tool .run/s7_capture.py (any overlay/any draft dir; reverts the TU in a finally:).
- MY DEFECT, FIXED AND DISTILLED (§136a): the capture tool first classified on the EXIT STATUS, so
its `rc == 0 => byte DIFF` branch was UNREACHABLE — `make build` runs `check`, so a draft that
compiles perfectly and merely differs in bytes also exits non-zero, and all 3 real DIFFs were
filed as "unknown". Now classifies on the OUTPUT ([FAIL]/got/want vs a non-warning error line);
the warning-exclusion matters because `conflicting types` also appears benignly for builtins.
- Also probe-discipline: my first S6c probe reported 1/9, which was 1 bank + 8 CORRECT REFUSALS —
jtbl_family_bank refuses on a dirty config/+src/ (its per-sibling revert restores from HEAD).
Driver now commits between families. A uniform failure across N functions is a statement about
the mechanism, not the functions (§134).
- cookbook-index 364 -> 371 sections, --check green. CURRENT_PHASE SESSION-31 checkpoint refreshed
with the queue re-derived at HEAD (the S30 ROI-floor trigger stays REFUTED — do not close on it).
- WAVE 4a (T6, the 33 high-value B-shape families, 61-120 ins / >=10 members):
33 targets, 46 agents, 4.44M tokens, 29 min -> 29 claimed match_one MATCH.
Whole-binary gate BANKED 23/33 (70%); family_sweep --hseq --band all propagated
251 member-matches across 69 overlays (13 failed, 4 STRUCT skipped by design).
Total 274 function-instances from 33 drafted targets.
- R22 clean-fleet: make clean + extract-all + check-all -> 140 passed, 0 failed of 140.
make report: fn-count 95.49% / instr 92.6% / distinct 85.9% (76,180 unique fns);
dedup 1905 validated / 0 failed; 0 NON_MATCHING in any default build (G4).
- COOKBOOK §136 (R30, distilled in-session from 25 banked functions' index-gap reports):
the wave's finding is that in the 60-120-ins band most "regalloc residuals" are decided
by HOW MANY C LOCALS AND AT WHAT SCOPE, not by register pins (local-alloc.c:472 promotes
any pseudo with REG_N_DEATHS>1 to a global allocno). 19 byte-verified idioms: 6 splitting/
merging rules, 6 type-form rules, 5 scheduling rules refining §135-2/§135-4, 2 declaration-
surface rules. One case explicitly REFUTES the pin as the lever for a redundant copy.
cookbook-index regenerated 364 -> 370 sections, --check green.
- TWO SELF-CORRECTIONS (R37/R14), both caught before they could mislead sizing:
(1) I wrote the tier split from the workflow's by_tier, which counts CLAIMED matches (29)
not banks (23). Derived per-function: Opus-direct 10/14, Haiku-direct 3/8, Opus
escalation-after-Haiku-miss 10/11. The operative number is the 10-of-11 rescue rate;
on this band Haiku is triage, not a substitute (it is == Opus only at <=50 ins).
(2) The gate printed "1/1 banked FAILED: func_X" on single-draft groups (the known
double-list artifact) -> bank set DERIVED from corpus.stubs instead. Totals agreed.
- TOOLING: the wave scripts now parse args-as-string and assert Array.isArray, so the
roadmap's standing "args must be an array" gotcha cannot silently kill a future wave
(it killed wave 4a's first launch in 60ms with 0 agents).
- tools-health green + fail-closed before matching (corpus+resident 0 PHANTOM/0 TRUNCATED,
audit-binaries 140/140 citizens, cdecl, report/lint/dedup).
- 38 targets / 44,297 templ ins, model-routed (Haiku <=89 + Opus escalation, Opus direct >=90):
52 agents, ~4.1M tokens -> gate 27/38 (71%). All 11 failures captured + classified: 8 declaration/
link plumbing, 3 genuine byte-DIFF. An 8-agent Opus reconcile wave fixed 8/8 (7 banked) ->
wave-3 total 34/38 = 89%. Propagation +639 members / 1 failed / 83 overlays.
R22 clean-fleet 140/140. Fleet 95.42% fn / 92.4% instr / 85.5% distinct.
- DESIGN (S27 law applied BEFORE it bit): six of eight reconcile targets share ONE TU, so this wave
FORBADE agents any build — six concurrent splice-builds would have clobbered a tracked file.
- THE AGENTS OUT-DIAGNOSED MY BLOCKERS:
* func_801848B0 — an agent REJECTED MY PREMISE: I said byte-correct + decl-blocked; it ran
match_one first, found a real 1-ins DIFF, fixed both. R14 aimed back at me, correctly.
* func_8017C5F0 — the "invented symbol" D_801DA0F0 is an INTERIOR ADDRESS: offset 0x6C into
D_801DA084 (0x801DA084..0x801DA103). The lui/addiu pair builds an interior pointer.
* func_8018A860 — the TU declares memcpy THREE times with incompatible signatures, with a latent
byte bug behind it. One symbol declared three ways is a defect awaiting the next draft.
- Carried (4): func_80184A94 (match_one MATCH, gate-refused) + 3 genuine byte-DIFFs
(func_801845B0, func_8017BEBC@ov_SC02_026, func_8018480C).
- 15 targets (11 fresh Haiku + 4 gate-failed reconciles on Opus), 15 agents, ~0.74M tokens.
Gate banked 14/15 (93%) vs wave 1's 20/24 (83%); ALL 4 RECONCILES BANKED.
Propagation +328 members / 0 failed / 76 overlays. R22 clean-fleet 140/140.
Fleet 95.23% fn-count / 92.1% instr / 85.0% distinct (phase opened 92.00 / 87.5 / 78.0).
- THE 83->93% CAME FROM THREE FIXES, ONE PER WAVE-1 FAILURE (the S27 finding reproducing):
(1) args pasted from the DERIVED manifest, never typed — all 30 paths verified on disk first;
(2) blocker-capture BEFORE the reconcile fan-out (S29 law: agents cannot run the gate, so a
match_one-MATCH draft dying on `conflicting types` reads to them as a codegen wall) —
each got the exact symbol+line plus the two byte-neutral levers;
(3) wave-1's Opus DISCOVERIES became wave-2's Haiku INSTRUCTIONS (ori-vs-addiu unsigned
destination; store-sinking scheduler order).
- THE RECONCILES OUT-DIAGNOSED MY CAPTURE: func_80189B78's error named ONE symbol; the agent found
SIX invented prototypes, two AFTER the splice point where cc1 had not yet reached — all fixed by
copying the TU's decls verbatim + casting at the call site, zero bytes changed. func_8018584C had
lever (A) blocked in BOTH directions (the draft must also compile standalone for match_one) and
closed with the DATA form of the asm-label alias. func_80180A4C was one character class (s32[] vs
the TU's u8[], declared 11 lines after the splice point).
- Carried: func_80189C4C (the one agent that returned no structured result; gate refused).
- POOL (derived from the regenerated map): 36 families / 28,829 templatable ins, kind=modal (no
member matched ANYWHERE so no sweep could reach them), >=20 members, <=60 ins, non-jr, and NOT
ONE exemplar in ov_SC01_077. Hand-calibrated 3/3 one-shot before scaling (Phase-15/18 discipline).
- WAVE (ultracode; Haiku drafters + Opus escalation, 24 targets): 31 agents, 0 errors, ~2.0M tokens,
12.5 min. Agents claimed 24/24 MATCH; the whole-binary gate banked 20/24 (83%); propagation
+524 members / 0 failed / 91 overlays. 17 of 20 banks were HAIKU, 3 Opus — the
cheap-tier-ab-validated call (Haiku == Opus at <=~50 ins, ~4.8x cheaper) held on real work.
- WHAT OPUS BOUGHT: (1) a `sh` of a constant with the stored width's top bit set needs a u16
destination — via s16 gcc folds it sign-extended and li emits addiu, via u16 force_fit_type keeps
it positive and li emits ori; (2) a schedule-reorder closed by STATEMENT ORDER not the permuter
(gcc's list scheduler preserves relative order of disambiguable stores); (3) three loose-typing
fn-ptr casts a cheap drafter had misread as delay-slot/permuter residuals.
- MY ERROR (R37/R14): I generated the manifest to .run/s6f_wave_targets.json then HAND-TRANSCRIBED
the args into the Workflow call, pattern-filling _jr_8017BEBC across overlays where no such split
exists (corpus.stubs says _jr_8017AE2C). Three agents lost time rediscovering real paths. The gate
driver written after (.run/s6f_gate.py) DERIVES every TU/split from corpus.stubs and asserts
nothing. Assert nothing you can derive.
- The 24->20 gap is the known match_one->gate gap (standalone compile cannot see a TU decl conflict;
Phase 19 measured 88-92% -> 60-71%). 4 carried: func_8018584C, func_80180A4C, func_8017CC80,
func_80189B78.
- R22 clean-fleet 140/140. Fleet 95.13% fn-count / 92.0% instr / 84.9% distinct
(phase opened 92.00 / 87.5 / 78.0).
- func_8017E934 (ov_SC05_001, 29 ins x65): hand-drafted off the .s, match_one MATCH first try,
whole-binary gate byte-identical, propagated 64 members / 0 failed across 63 overlays.
- That makes the B-shaped lane 3-for-3 one-shot (func_8017CDD8 17ins, func_8017CE7C 16ins,
func_8017E934 29ins) for ~0 agent tokens = 330 member-matches from 62 instructions of C.
- THE POOL (derived from the regenerated map): 36 families / 28,829 templatable ins that are
kind=modal (NO member matched anywhere, so no sweep could ever reach them) with >=20 members
and <=60 ins, non-jr. NOT ONE exemplar is in ov_SC01_077 — they are invisible to exactly the
two habits this phase already corrected (the ov077-source default and --band substantial).
- The calibrated recipe, now the wave prompt: read the .s as ground truth (a cached Ghidra-C seed
was measured this session decompiling a DIFFERENT body) -> conform every callee decl to what the
TU already says (the PLUMBING class: standalone-MATCH C is gate-REJECTED as `conflicting types`
when it redeclares a callee the TU defines as (void)) -> match_one -> whole-binary gate.
- R22 clean-fleet 140/140; fleet 94.96% fn-count / 91.9% instr / 84.7% distinct.
- A: frontier regen at HEAD (sigs + family_hseq) before pricing anything (R35). Also the reason
it was needed: .run/hseq_verified.*.txt has accumulated 22,841 files across every sweep ever
run, so any per-family analysis globbing them over-counts; the regenerated map derives state
from sigs + corpus.stubs (R33), which is the authority.
- B / THE FINDING (third §133-class miss in a row): the S29 checkpoint's structural signal
"after S2 the x138 era ENDS — those are the last two crackable fleet-wide families" — the stated
TRIGGER for the phase close — is wrong. Two fresh-crack families with >=126 members were open:
0x8017cdd8 ov_SC02_039 17 ins x 142 members PURE
0x8017ce7c ov_SC03_114 16 ins x 126 members IMM
Both kind=modal (NO member matched anywhere, so no sweep could reach them) and neither exemplar
in ov_SC01_077 — invisible to exactly the two habits this phase already corrected.
- Both hand-drafted off the .s, match_one MATCH on the FIRST try, ~0 agent tokens. First gate
attempt failed PLUMBING (not DIFF): the draft declared `extern void func_8017CFCC(s32 a0)` while
the TU DEFINES `void func_8017CFCC(void)` — the target passes $a0 only because the caller's
incoming argument still sits in the register (loose typing). Byte-true C calls it with no
argument; re-verified MATCH, gated byte-identical, propagated 266 members / 0 failed / 118 overlays.
- R14 on the seed: the cached Ghidra-C for func_8017CE7C decompiled an entirely DIFFERENT body
(three calls absent from the asm). Reading the .s is what made it one-shot.
- R22 clean-fleet 140/140. Fleet 94.88->94.96% fn-count, 91.9% instr, 84.6->84.7% distinct.
- ONE root cause, four faces (cookbook §134): extract_unit's preamble scanner reads C
one line at a time, so every construct that WRAPS was misread.
D1 the {-guard fired on a documentation comment mentioning a brace -> carry truncated
mid-comment -> `parse error before 'the'`.
D2 _def_head_at's "param list continues -> ANSI definition" fallback accepted a WRAPPED
DECLARATION as a definition head -> a 16-line fragment with no body, closed by a brace
pair inside a comment -> a silent 0/137 that reads exactly like a compiler wall.
D5 the backscan met a multi-line typedef's CLOSING line `} T;` first and stopped -> the
type never travelled -> `T undeclared` across 17 families / 24,332 templatable ins.
(The code comment claimed they "route through the engine_types.h lift"; measured, they
routed nowhere.)
D4 wrapped __asm__("func_...") alias invisible to a single-line regex — MEASURED (1 exemplar,
3,288 ins, second blocker behind it) and deliberately NOT fixed; it now returns None so the
sweep reports a VISIBLE skip instead of 137 silent failures (R32).
- Fixes: _def_head_at(ln, idx, more=()) lookahead (no-lookahead keeps the historical answer);
{-guard exempts comment-only lines + an R32 dangling-comment backstop; forward brace scan
counts over cdecl._mask (R33, one masking oracle); _typedef_block_start carries whole blocks.
- BLAST RADIUS (R14): extract_unit diffed vs the pre-fix tool over all 181 zero-crack exemplars
-> 157 byte-IDENTICAL, 24 changed, all in the intended direction.
- PAYOFF: D1+D2 +323 members from families that banked ZERO; D5 +417 incl. func_8012B77C 139/139
(8,062 ins) and func_80128C98 137/275. S6 total 1,582 members (pre-fix tool scored 842).
- R22 clean-fleet 140/140. Fleet 94.43->94.88% fn-count, 91.4->91.9% instr, 84.0->84.6% distinct.
- TELL worth keeping (§134): bimodal bank rates (57 all / 52 zero / 8 partial) are a TOOLING
signature, not codegen. Probe one member and read one compiler error before writing a family off.
- family_sweep --hseq --band all (no --source override), 117 pre-classified families:
staged 2735 drafts / 1239 groups / 0 skips -> BANKED 842, R22 clean-fleet 140/140.
Fleet 94.43->94.67% fn-count, 91.4->91.6% instr, 84.0->84.5% distinct.
- R37 setup: the 190 zero-crack families decomposed with ZERO builds — 117 sweepable /
17 §94-§100 multi-line-typedef-blocked (24,332 ins incl. the 275-member 0x80128c98) /
9 jr (§53 carve path) / 47 remap-REFUSED.
- R14 PREMISE CORRECTION: the "every sweep passed --source ov_SC01_077" mechanism in the
post-wave checkpoint is wrong (that IS the default and overrides nothing). The real gate
was --band substantial: only 13 of 181 non-jr families are substantial. --band all is it.
- FINDING: the residue is bimodal — 57 families ALL-banked, 52 ZERO, 8 partial — the shape
of a per-family blocker, not per-member codegen. 8 probed via the new generic
.run/s6_diag.py (one build per family, not 137): 7 of 8 are declaration/carry plumbing.
Two proven family_remap defects located at source (D1 comment-line {-guard truncating the
preamble carry; D2 _def_head_at accepting a wrapped multi-line DECLARATION as a def head).
- 9 banked heads propagated: 1,096 non-jr member-matches (family_sweep --hseq --band all, 0 failed)
+ 137 (func_80159A20, jr) + 137 (func_801549F8, jr)
- func_80176734 (371 ins, the largest single item in the frontier) banked + propagated
- FLEET 93.81% fn / 90.9% instr / 83.9% distinct; dedup 1905/0; 0 NON_MATCHING (G4)
- cookbook §132b (--span-rel: the already-matched owner that is ITSELF multi-switch) and §133
(the DEFAULT-FILTER class — three times in one session a tool silently answered a narrower
question than the one asked: my own >=80-ins cut, worklist's h_exact pricing, --band substantial)
Drew T