- (c): cnt's slot is spill_stack_slot[23] (evicted from $s7), so the phantom @0x8 must be an initial-loop no-traffic slot; every producer refuted on dump facts (leaf: no save area; LO spilled after GR and products alternate to GR_REGS — C3 measured; no unallocated single-block equiv pseudo; expand-time locals precede; 13 lh single-use, no lb). Rows 49/50 = two move_movables hoists in body order.
- row (d) read only (rtu DIFF 13 re-verified); brief + step 0 (§501-N banked-sibling search on its symbol set) in the checkpoint
- no src/ change in this commit; fleet R22 owed at the T4b close (last check-all 218/218 before the (b) bank)
- main:func_80032A74 (422 ins, closeness 1): the residual is ONE reload-time slot at sp+0x48 (u16 draft = 422/422 code, DIFF 22 frame
rows; s16 draft = DIFF 1 at idx 244 lh vs lhu). Every post-parameter slot producer enumerated from gcc-2.7.2 (reload1.c:658 ghost
alter_reg / caller-save.c:249 area / reload1.c:879 invalid-equiv / reload1.c:3499 spill_stack_slot) and refuted on the bytes: combine's
newi2pat ghosts re-derive a narrow load and the site is lhu (no lb, no double load); a save area without sw/lw needs sched.c:4962
staleness and no register-only insn shares a block with a call; $t0 holds no pseudo; LO mult results retry into GR_REGS. Verdict
PROVED at 1 (pin kept with the verdict; ledger WALL-PROVED).
- NEW mechanism measured: local-alloc.c optimize_reg_copy_2 (tmp = x; tmp op= c; x = tmp) mints a ghost with stale refs, but after
regclass -> GR_REGS, allocated, no slot (P13/P14). 18 isolated reproducers, 0 draft variants; cookbook §501-M; accelerators (12).
- tools/ghost_census.py (new): ghosts in a .lreg dump with their class (ST_REGS => slot). tools/cc1_dumps.sh: prints the .frame line,
ins count, spill lines and the census; the under-counting standalone-(use) grep is gone. SETUP rows (R21).
- tools/backlog.py: load_best kept the EARLIEST record at equal closeness (docstring said latest) — the S84 row never rendered; fixed.
- CURRENT_PHASE.md: S84 log + refreshed 🛑 checkpoint (rows (b)(c)(d) next, then T5). No src/config/carve change; fleet check-all
218/218 rc 0 at the S84 preflight.
- 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)
- CURRENT_PHASE.md: T3 row DONE with the close numbers; the S83 steps 8–9 log entry; the 🛑 SESSION CHECKPOINT rewritten
(T3 CLOSED, T4 NEXT; the 15-row census with draft paths and mechanisms; the T4 procedure incl. the §376 re-probe of the
three CC1-FAIL walls before any verdict; T5 carry)
- step 8 tail: func_8001BC6C BANKED (commit:3948); func_800CD674 plateau ledgered; func_800CF3E8 Opus second look 27 HOLDS —
§500-D1's mechanism corrected to cse.c find_best_addr (fold_rtx MEM, COST pseudo 0 vs hard reg 1), the alias lever refuted
5/5, a new zero-byte pinned-pointer launder found (79 @ 470) — cookbook §500-H, backlog row with cost (245k tokens / 29 min)
- make report: fleet instr 13,484,739 / 13,488,497 = 100.0% · distinct 5,812,831 / 5,816,589 = 99.9% (90,975 / 90,984 unique)
· fn-count 363,199 / 363,214 = 100.00% · INCLUDE_ASM 15; main REAL 783 · LINKED 1,256 · VERBATIM 3 · stubs 6 ·
byte-identical 2,085 / 2,091 = 99.71% · 143dbb89; census .run/P32/frontier_t3_close.json; twin_rescan 0 free
- R22 (clean + extract-all + check-all) after the Makefile guard + the main bank: 218 passed / 0 failed, exits 0/0/0
(.run/P32/t3s3/r22c_full.log) — the third green fleet sweep of the session (10:46, 11:09, 12:00)
- docs/accelerators.md (5)–(7): the build is the batch verdict / read a waypoint's diff both ways / a live probe in src/ is
build input; docs/backlog.md 14 open; verdicts.jsonl 50 rows; the s83 Opus draft + report kept (R20)
- kill gate: 29 banks + 3 new verdicts this session, the three bounded tail attempts spent — T3 closes on the evidence
- 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)
- phase-ends/DIGEST.md (NEW, Drew-directed 2026-09-05): every phase's synopsis (P1–P32), every rule R1–R64 in full, the
corrections that supersede parts of PROJECT_CONTEXT.md (P8→R19, commit cadence→R42, H1→R1, headless Ghidra, roadmap v2,
effort doctrine, the pinned triple), and the doc map. Maintained at every PhaseEnd (CLAUDE.md Phase Boundary step 3b, P7).
- CLAUDE.md Session Start Protocol rewritten: PROJECT_CONTEXT → DIGEST → the THREE most recent PhaseEnds → CURRENT_PHASE
(+ cookbook head/newest § + SETUP §5.4 for matching phases); rules transcribed in full from the digest; the 🛑 SESSION
CHECKPOINT block reproduced VERBATIM in chat as the session's only in-phase seed. Measured load order ≈55k tokens
(was ~150k reading all 32 PhaseEnds). phase-ends/README.md + SETUP §7 pointer updated (R21).
- CURRENT_PHASE.md: the T3 🛑 block REFRESHED and SUPERSEDING the 09:30 one — written to be replayed: what happened in the
dead session (times, hashes, the overflow, the swept dir), what the successor did, the 44-stub census with every row's
state/draft path, the 10 banked with hashes+shas, the 9-step resume order with exact invocations, the file/tool
inventory and gotchas, carried context for T4/T5, environment, the plain-English recap; Log entry for the protocol change.
- .run/P32/t3/PROMPT_TEMPLATE.md (tracked): the verbatim agent prompts (Haiku / Haiku+twin / Sonnet escalation / Opus /
Sonnet) for launching the 17 queued rows under the amended output contract.
- memories updated outside the repo: checkpoint-current-phase-before-pause (the verbatim-replay contract; a dead session's
checkpoint is written by the successor from the transcripts) and session-start-list-rules-in-full (the ~100k protocol).
- verdict ledger .run/P32/t3/verdicts.jsonl rebuilt from the 31 T3 transcripts (agent_verdicts.py); every unbanked draft
re-verified with rtu_match in its real TU: 10 MATCH awaiting the gate (main func_80015B6C 120 + func_8002FDE8 73;
md_SC03_054 func_801EF6D8 604 + six jtbls; md_SC03_053 func_801EF734 44 + func_801EF7E4 72; md_MAIN_007
func_800CF148/2BC/EEFC/EF94/068) + func_800CF3B0 leaf-exact behind the TU's void/3-arg decl; 9 NEAR at exact length
(2/6/15/17/27/35/46/49/137), each with its class and inert-lever list
- R48 incident: one agent's `find .run/P32/t3/opus -maxdepth 1 -type f ! -name <mine> -exec mv {} _scratch/` swept 11
sibling deliverables (two MATCHes among them); found in _scratch/, restored to the contract paths, byte-verified;
tools/agent_drafts_restore.py (NEW: transcript replay) as the fallback; .gitignore allowlist for .run/P32/** so the
drafts, ledger and census files are committed (R20)
- harvest (R16/R30): cookbook §500 (10 banked closers, 10 MATCH closers, 9 NEAR classes, two NEW mechanisms — the
pinned-base-vs-pseudo-address alias basin and #line-equalised ASM_OPERANDS for cross_jump — and the wave-process
defects); wave-playbook §S80 addendum-2 (per-function work dirs, JSON-only final message, the 20-agent cap, the
recovery tools); accelerators P32 T3; decision-log P32 S82 (R31); SETUP tooling row (R21); cookbook-index
regenerated; .run/P32/t3/BRIEF.md output contract amended for the 17 queued launches
- CURRENT_PHASE: T3 row IN PROGRESS, Log entry, 🛑 SESSION CHECKPOINT (census 44 stubs / 5,313 ins with every row's
state and draft path, the 9-step resume order, the dead session's read-only T4 pre-read); harness task list rebuilt
- no src/ or config/ change in this commit; no fleet R22 has run since the 10 T3 banks — the resume order starts with one
- md_SC03_056 (TEXT_LO 0x4, 4 stubs / 61 ins): 15/17 pointers cluster inside at 0x801CBB50; one outward call
(0x8018151C) hits a function only 3 overlays have, ov_SC03_002 among them; req_fit 9/9 for ov_SC03_002
- payload_base_evidence.py v2 (controls 7/7 throughout): (a) STRONG = internal jals + fn-ptr-table entries on the
module's own starts >= 2 (SC03/53 STRONG); (b) OUTWARD-EXPLAINED — a pure jal-vote base whose "internal" targets
are function starts of the fleet's overlays is downgraded: SC03/56's 0x80178C8C was two SHARED-engine functions
spaced like two of its five starts (and nobody's DESTPTR), a false STRONG; (c) the requester cross-check is
informational only — shared engine code makes every requester fit (an R39 control caught it scoring: 6/7)
- memory-map §S45 p7 amended: all five rows ONBOARDED + the two instrument findings (the first build is a NULL
oracle for FINE base errors — +8 builds byte-identical, +0x1000 fails the link; outward-explained vote bases);
SETUP row amended. The parked-for-L3 ledger is EMPTY pending `make audit-disc` (T2c).
- the instrument: module-id word, TEXT_LO estimate, absolute-pointer set, lui hi-half histogram, and a
jal->function-start VOTE (starts = prologues ∪ the word after every `jr $ra`+delay — leaf functions have no
prologue, the recall killer of S45's vote_base 4/12); scores a BOUNDED candidate list (5 §S44 slots ∪ 134
IDXTAB DESTPTRs ∪ vote bases): STRONG / CONSISTENT / INCONSISTENT / NO-EVIDENCE; AMBIGUOUS tie sets are
printed, never picked; a payload with no self-reference is REFUSED as base-independent (R43)
- R39 controls run before any emission: md_MAIN_008/011/013/042, md_SC03_073, md_SC02_009, md_SC07_004
re-derive their byte-proven bases top-ranked from their payloads alone (7/7); TEXT_LO estimates == yaml
(incl. the header-table modules 0x7C/0x14/0x158). The first draft of the scorer FAILED 5/7 (prologue-only
starts; a top-rank assertion on modules the bytes cannot discriminate) — fixed by the controls, not shipped
- the five (G5 static-derived, US): MAIN/7 STRONG 0x800CEDF8 (9/9 jals, 14/16 ptrs on starts); MAIN/9 STRONG
0x800CD348 (6/6, 9/9); SC03/53 + SC03/54 CONSISTENT with 0x801EF468 top of a 12-way tie; SC03/56 SPLIT
(jal vote 0x80178C8C vs pointers/lui ~0x801CBB50). T2b probes each with new_binary.sh — the byte gate decides
- SETUP row (R21); evidence rows .run/P32/t2a/evidence.json
- 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)
- BANK: the stored S71 closeness-0 draft spliced into src/resident/resident_jr_800D128C.c; jtbl_carve --func
carved jtbl_80113FB8 (119 entries, 1 pad word trimmed) + jtbl_80114198 into [0x451c0, .rodata,
resident_jr_800D128C] + [0x453c4, data, tail3]; JTBL_PADS 0,4; make extract + make build BINARY=resident -j8
rc 0, sha 8e17e02ff8954d07c979449198f7e1645046b353 == check (R53). pads_audit ok/ok; interleave_check
ALIGNED n=5; verbatim_check --strict 5==5. Resident stubs 2 -> 1 (func_800D06E8 remains).
- WHY THE GATE SAID DIFF (parallel_gate banked 0/DIFF on an rtu_match MATCH): jtbl_carve.set_overlays_var
regenerated resident_JTBL_INTERLEAVE from the carve set and DROPPED the resident's `--pre hdr.rodata.o`
(§8f leading-rodata sandwich); make extract refused (ld_interleave: hdr.rodata.o would be parked with
.text), the build linked the STALE script (249,252 differing bytes from file offset 0x4), and
harvest_verify._jtbl_prep_one never read the post-carve extract's exit code (R49/R61).
- FIXES (R35/R40/R57): jtbl_carve._merge_pre carries an existing --pre forward (idempotent; overlays
unchanged, 4-shape unit control); harvest_verify refuses loudly on a failed post-carve extract and
restores the snapshot (CARVE refusal, NOT a draft verdict); interleave_check's anchor accepts a leading
--pre (was a false DRIFT n=0 on the resident; control ov_SC02_017 ALIGNED n=44 unchanged).
- cookbook §498 (+ the stale-asm-after-a-failed-extract sequencing law); SETUP rows for all three
- _type_names returned the TAG for `typedef struct Rec801806C8_s Rec801806C8;`, so the typedef block and the
tag's own packed struct definition collided under one key with different bodies and the R43 "CONFLICTING
bodies — a rename is needed" refusal fired on legal C. Now keyed by the alias (_TYPEDEF_TAG_ALIAS); the
`carried` set learns the alias; `typedef struct X X;` (alias == tag) keeps the old key so a second one
still dedupes/refuses. Unit control on 7 block shapes PASS; ov_SC02_017 --only func_80186C64 --dry-run:
2 region files, no carve repoints. cookbook §497; SETUP row.
- jr_isolate_all resident --only func_800D128C: [0x4 c resident] [0x12ec c resident_jr_800D00E4]
[0x2494 c resident_jr_800D128C]; the banked jr func_800D00E4's .rodata carve + JTBL_PADS + --order
repointed to resident_jr_800D00E4.o (config/overlays.mk resident block only, R60); make extract +
make build BINARY=resident -j8 rc 0, sha 8e17e02ff8954d07c979449198f7e1645046b353 == check (R53)
- TOOL FIX (R43/R33): the carried-type test consulted _engine_types() (engine_types.h + common.h) for
every TU, assuming each region includes engine_core.h; the resident includes only common.h, so its
file-local `typedef struct {...} CdFileLoc;` (a name engine_types.h also defines) was silently NOT
carried -> `parse error before cdFileLocTable` in both region TUs, build rc 2 while the stale binary
on disk read green. Now _provided_types(header) derives the set from the TU's own #include lines
(engine_core.h => engine_types.h + common.h, never engine_core's macro-internal typedefs; common.h
=> common.h) and _file_scope_decls(items, provided) uses it at both decision points. R39 controls:
overlay header == legacy set (1,197 names); resident set lacks CdFileLoc. cookbook §496; SETUP row
- rtu_match func_800D128C --split resident_jr_800D128C: MATCH (243 ins) on the stored S71 draft;
the gate is the next commit
Drew T