benbrown/peltier.io
2
1
Fork 0
mirror of https://github.com/bdbrown4/peltier.io.git synced 2026-11-07 10:58:28 +00:00
Code Issues Packages Projects Releases Wiki Activity
45 Commits 12 Branches 0 Tags
3637883c9adeae318a5540429b0b8f0e55174774
Commit Graph
4 Commits
Author SHA1 Message Date
Claude 82eaeceffb agent: bank + verify phase2-tokei-003, refresh tokei profile 
Second verified auto-accepted win: +3.67% median, CI [+2.7%, +5.2%].
diff-fuzz 10k/0 divergences, ASan/LSan clean. Profile regenerated
against the two-win baseline.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
 2026-07-10 20:50:21 +00:00
Claude 393ca7117f agent: case study — phase2-tokei-001 verified win + audit methodology finding 
Also refreshes tokei's cache-sim profile against the new banked-wins
baseline (parse_lines share drops after the first-byte gate landed).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
 2026-07-10 05:11:22 +00:00
Claude 017491010b bench: cache+branch-sim profiles, hypothesis-granular ledger memory, long-poll read_verdict 
- 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
 2026-07-10 04:49:19 +00:00
Claude 7c3c59f5f8 phase0: dry run — comrak & tokei vendored, 3 attempts in ledger 
Target selection (SPEC §6): comrak 0.53.0 (45c1995, BSD-2-Clause) and
tokei 14.0.0 (fa44e51, MIT/Apache-2.0); both CPU-bound with pinned
corpora (progit book 11MB; 8x replicated pinned trees, 221MB) and
committed MANIFEST.sha256 + golden-output pins + regen scripts.

Calibration: A/A null verdicts on both real workloads; taskset -c 2
pinning tightens the A/A CI from [0.938, 1.008] to [0.993, 1.008],
making the 2% accept threshold meaningful in this container.

Profiles (callgrind; perf unavailable): comrak allocator symbols 26.7%
of Ir; tokei perform_multi_line_analysis 31.7%.

Attempts (ledger + results/phase0/):
- comrak class-1 target-cpu=native: null [0.983, 1.011], rejected-bench
- comrak class-2 mimalloc swap: +4.6% [1.033, 1.058], 848 upstream
  tests green, golden byte-identical, ASan-proper clean; LSan flags
  484B in onig (reachability false-positive analysis in case study) ->
  needs-human-review per SPEC §8
- tokei class-1 fat LTO+cgu=1: +1.6% [1.003, 1.026], real but under
  the 2% bar, rejected-bench

Also: ledger-cli for manual rows, targets/ excluded from trust-layer
workspace, corpora/build artifacts gitignored, case study written.
Phase 0 exit criteria (>=10% verified win) not yet met; next
hypotheses logged in results/phase0/attempts.md.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
 2026-07-06 19:28:50 +00:00