Human ruling on the needs-human-review allocator swap (+4.6%, CI
[+3.3%,+5.8%]): accepted as a real win for the measured comrak CLI
single-stream markdown-render workload, explicitly not a blanket
mimalloc mandate. Ledger row stays needs-human-review (append-only);
the ruling is documented in results/rulings/phase0-comrak-002.md and
reflected in the case study.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
Two defects found and fixed in a hostile review of the whole package:
1. The ROI report generator trusted the ledger verdict field and would
mint a clean $16,886/year report for phase2-comrak-010 — the
memory-leaking patch the audit overturned (immutably 'accepted' in the
append-only ledger, sanitizers_clean:false). report_row now exposes
sanitizers_clean and the report treats accepted-but-not-sanitizer-clean
as NOT shippable, printing a warning before any dollar figure. Legit
wins (sanitizers_clean:true) still render clean.
2. bench-runner service --rate 0 / --count 0 could panic via
from_secs_f64(1/0); run_session now guards finite/positive rate and
non-zero count/workers.
Attacks correctly refused (verified, no change): ledger UPDATE/DELETE,
propose_patch ../ + .git escapes, read_target_source traversal. All 10
accepted rows satisfy the green-gates + CI>=1.02 invariant. Findings
recorded in results/adversarial-review.md.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
phase4-cjson-service (ledger): the accepted batch win phase3-cjson-002
measured under a 150 rps coordinated-omission-correct replay (20 rounds,
40k requests, 0 drops). p50 latency +6.2%, 95% CI [+5.8%, +7.2%] —
accepted; p99 CI [0.07, 4.97] too noisy (single-worker loopback tail),
harness correctly rejected. ROI (500-core fleet, $0.04/core-hr): 27.5
cores / $9,621/year at the CI lower bound, report generated mechanically
(results/phase4/cjson-service-roi.md).
- results/phase4/: case study + README + the generated ROI report.
- CLAUDE.md: Phase 4 complete; Phases 0-4 all done.
All SPEC §5 exit criteria met across every phase; zero shipped false
accepts across the whole project.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
- bench-runner service mode (SPEC §3.1 mode c): a coordinated-omission-
correct, open-loop, fixed-rate load generator; latency measured from
the intended send time so queueing is counted, not hidden. Interleaved
A/B of two server binaries, exact percentiles (bounded sample, no HDR
bucketing error), bootstrap p50/p99 CIs via the existing ratio-CI
machine. service-calibrate: A/A false-positive + injected latency-
regression detection (calibration in progress).
- targets/cjson/service.c: minimal single-threaded HTTP server wrapping
the patched cJSON.c (trust-layer, outside the workspace allowlist);
env-toggled per-request busy-wait for the injection calibration only.
- report generator (crates/report bin): reads a ledger row +
optional service-latency JSON, renders throughput→cores→dollars and/or
latency percentiles, every figure with its CI, pricing source, and the
methodology printed inline (SPEC §9); flags any non-accepted row so a
rejected change never reads as a committed saving.
- ledger::report_row; justfile service/service-calibrate/report.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
phase3-cjson-002 (class 5+3): stack-buffer number parsing + strtod
round-trip replacing sscanf. +8.85% median, 95% CI [+7.5%, +10.0%] on
the C target, banked. 100% audit: byte-identical golden replay,
independent ASan+UBSan clean, 10k-input differential fuzz 0 divergences,
patch bounds/free-gating verified by eye.
- verdict: an infrastructure sanitizer-BUILD failure (missing runtime,
broken toolchain) now caps the accept at needs-human-review and logs
it, instead of crashing the verdict and losing a measured bench.
- results/phase3/: four public case studies (tokei class-5 wins; build
flags + allocators; the comrak caught false-accept; the cJSON
cross-language proof) + README. Compound-speedup claim stated as an
approximation, not a measured figure (CIs don't multiply).
- .gitignore: cjson build-artifact dirs.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
- coz wired (harness -DHOTPATH_COZ hook, scripts, just coz) + installed,
but the apt coz runtime aborts in its own init_coz/pthread_create
interposition on this glibc (known coz bug, reproduces on the pristine
binary). Documented in results/cjson/coz/README.md; callgrind cache-sim
is the working profiler.
- cjson no-op verdict smoke: full C pipeline flows (clang {out} baseline
rebuild, Unity/CTest + golden gates, interleaved bench) to a correct
null result (median 0.9995).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
~22% of Ir in glibc float serialization (__printf_fp, cJSON print_number)
and parsing (strtod/str_to_mpn, cJSON parse_number), plus parse_value/
parse_string and malloc/free churn. Ample headroom (SPEC §6).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
20/20 sessions: A/A false-positive rate 0.000 (<0.05 required),
injected-5%-slowdown detection 1.000 (>=0.95 required). The C workload
is a trusted measurement anchor; verdict benches on cjson are now valid.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
diff-test standalone (just gates / CI target-gates) passed the now-
templated build.binary into golden replay verbatim — literal {out}.
It now builds the current tree to targets/<t>/gates-build and tests
that, with a --binary override. CI's target-gates-no-net job gains
clang/cmake, fetches+gates the cjson C target (clang build -> Unity/
CTest -> golden replay) alongside tokei.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
20 audited attempts, 0 shipped false accepts, 3 verified auto-accepted
wins (tokei class-5: +10.7%, +3.7%, +9.9%; ~1.25x vs upstream with
Phase-0 wins). Independent 20-way adversarial re-audit (phase2-final-audit
workflow) confirmed every verdict follows its evidence, correct
equivalence tier, no harness-gaming, ledger append-only intact.
Closeout changes:
- case study: full 20-row attempt table, scoreboard, corrected
comrak-010 CI upper bound (+12.1%, was +12.2%), exit-criteria section
flipped to ALL MET, OS-isolation gap marked closed.
- CLAUDE.md Current-phase line: Phase 2 complete, next Phase 3.
- verdict: derive the ledger 'phase' column from the run_id namespace
(phaseN-*) instead of the hardcoded 1 the re-audit flagged; historical
rows are immutable and stay as written (run_id prefix is authoritative).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
The pipeline auto-accepted an LSan-flagged teardown patch (+10.7%
median) because ASan/LSan were per-attempt manual; the 100% audit
overturned it (black_box liveness ends at scope close, process::exit
runs after — 384-byte arena chunk unreachable at exit). verdict now
builds the patched tree with ASan+LSan and runs the pinned workload on
every would-be accept, capping flagged wins at needs-human-review per
SPEC §8. Shipped false accepts remain 0; the win was not banked; case
study carries the corrective record.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
comrak-010's patch added an unresolvable dependency version; the
candidate build failed before the verdict binary ran, no ledger row was
ever written, and the agent polled read_verdict into its turn cap. The
detached pipeline now traps any failure into a log marker, and
read_verdict reports status=failed with the log tail instead of
'running' forever. Attempt relaunched.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
Class 5 on tokei: forward-only all-whitespace break test replaces
trim().is_empty() (drops the redundant rposition scan per processed
byte). Median 1.0367, 95% CI [1.027, 1.052]. Equivalence eyeball done
(same AsciiExt::is_whitespace predicate, empty-window case identical);
diff-fuzz + ASan running before the win is counted.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
- propose_patch allows the /dev/null headers git emits for new/deleted
files (previously every new-file diff was refused as an absolute path).
- read_target_source serves HEAD (pristine) content instead of the
working tree, matching propose_patch's standalone-vs-pristine base so
post-proposal reads can't drift a later diff's context lines.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
A stale socket file survived a container idle window while the daemon
died; the [ -S ] check skipped the restart and the nested agent's MCP
server crashed at connect. The agent refused cleanly (no ledger row, no
fabrication). Liveness now means answering read_playbook, not existing.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
The agent's parse_context skip-scan passed upstream tests but broke
byte-identical golden replay on the pinned corpus; bench correctly never
ran. First rejected-gate of the grind: the equivalence stack blocking a
wrong-output patch that a green test suite would have shipped.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
- Standalone-proposal semantics: workspace resets to pristine before
every apply, so probe patches can't accumulate into a tested tree the
ledger's patch field doesn't describe.
- Friendly errors: explicit trailing-newline check, and git apply's
stderr relayed on refusal instead of a generic message.
- Tool docs + task prompt updated to match.
- phase2-comrak-004 audited: honest rejected-bench (median 1.0124,
CI [1.0011, 1.0267] — real but under the 2% bar), Mutex pre-flagged
for human review, cumulative-probe state disclosed in the hypothesis.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
Ledger row: class 5 (algorithmic) on tokei, first-byte gate table for
the per-byte token matchers in perform_multi_line_analysis.
Speedup median 1.107, 95% CI [1.084, 1.131] vs the banked-wins baseline,
workload: 221 MB / 4360 files, single rayon thread, pinned core.
Manual audit gates (pipeline covers tests+golden+bench only):
- Differential fuzz, 10k mutated inputs across 200 batched runs:
0 divergences after canonicalizing tokei's benign parallel-walker
output ordering (present in pristine baseline; counts identical).
Fuzzer added as scripts/diff-fuzz-tokei.py.
- ASan run recorded in the case study (next commit).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
Mechanically re-checks a ledger row against the accept rule (CI lower
bound vs threshold, gate greenness, patch path allowlist) and prints
the full evidence for the human part of the 100% Phase 2 audit.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
- Profiles regenerated with callgrind --cache-sim --branch-sim for both
targets: per-function D1/LL miss and branch-mispredict columns unlock
playbook class-4 preconditions (comrak: syntect write_highlighted owns
31% of D1 read misses; tokei: parse_lines owns 56% of Ir).
- tokei workspace: accepted Phase 0 wins banked as a local commit so
stash-based baseline rebuilds attribute only the marginal patch to new
attempts (false-accept trap closed before grinding).
- read_ledger now returns per-attempt history (class, hotspot,
hypothesis, verdict): a class may be re-entered with a materially new
hypothesis, never a duplicate one. Task prompt updated to match.
- read_verdict long-polls the ledger up to 45s server-side (under the
60s MCP cap), cutting the agent's polling turn burn ~15x.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
harnessd gains --socket mode (Unix socket, trusted uid, mutating ops
serialized); the harness client speaks socket when
HOTPATH_HARNESS_SOCKET is set. scripts/agent-isolated.sh launches an
attempt with the agent tree confined — mountns mode (repo bind-mounted
read-only, CAP_SYS_ADMIN/CAP_SYS_PTRACE dropped; no credential copying)
or user mode (unprivileged hpagent, bench-metal shape).
scripts/isolation-check.sh + just isolation-check verify the boundary
from the agent's side: 19 checks, both modes, all passing — repo
writes, forged ledger INSERTs, trust-binary replacement, rw remounts,
and userns re-entry all refused; the harnessd socket door works.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
The Claude Agent SDK loop (agent/hotpath_agent/loop.py, model
claude-fable-5) drives the seven harness tools over a standalone stdio
MCP server (mcp_server.py) and runs the full profile -> hypothesize ->
patch -> gated-verdict cycle on comrak with no human in the loop.
Three audited attempts, all honest rejections, ZERO false accepts:
- phase2-comrak-001 class 3: syntect buffer with_capacity, [0.971,1.007]
- phase2-comrak-002 class 5: gate dead VecDeque build, [0.982,1.026]
- phase2-comrak-003 class 6: hoist find_special_char check, [0.970,1.007]
The agent picked the cheapest untried class each time (3->5->6) and
TWICE refused to fabricate a verdict it couldn't read back, verifying
ledger integrity instead — the anti-reward-hacking behavior SPEC §10
targets.
Harness changes surfaced by the loop:
- run_verdict is now async: launches the multi-minute build+bench
detached (past the 60s MCP transport cap) and returns immediately;
new read_verdict op polls the append-only ledger row (ledger
verdict_summary). Fixes attempt 001's unreadable-verdict gap.
- read_target_source takes offset/limit line windows so 100KB+ files
page instead of overflowing — removes the agent's reason to reach for
a shell (attempt 003 paged a 2400-line file cleanly, no shell).
Honest boundary note (case study + code comments): in THIS dev
container the SDK tool allow/deny layer is defense-in-depth, not the
trust boundary — a nested CLI as root under a parent session doesn't
reliably gate built-ins. SPEC §10's boundary is OS process/user
isolation; that hardening is the remaining Phase 2 exit item
(docs/infra.md). What holds regardless: propose_patch is the only
mediated write path (path-allowlist + git apply) and the ledger is
append-only.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
Claude
benbrownandGitHub