Go to file
kuhyx 5ffd035c21 session-autopsy: measure turn efficiency, the dominant token cost
Cache read is charged per API round-trip on the whole conversation so far, so a
long session's cost is driven by TURN COUNT, not message length. One measured
session spent 267M cache-read against 856k output — a ratio of 290:1. The report
priced tokens but never counted the turns spending them.

Across the 263 stored transcripts this now shows 33,508 tool turns at an 8%
batching rate, of which 4,437 (13%) decided nothing: polling a counter, running
a linter, checking whether a push landed. At 606k average context re-read per
turn that is ~2.7B cache-read tokens on turns a script could have taken.

- turns.py classifies a command as poll / lint_test / vcs_check / substantive,
  deliberately conservative: state-changing commands (git commit, push) count as
  substantive even though they are scriptable, so the reported waste is a floor.
  A turn is only mechanical when EVERY command in it is.
- Batching is grouped by requestId, not by transcript line: one API response can
  span several lines, and counting per line reports every turn as single-tool
  (0% batching where the real rate is 12%).
- records.py gains TurnEfficiency (schema v3, additive — old records read as
  zeros) with derived rates written into to_dict so readers need not recompute.
- report.py gains a "Turn efficiency" section pricing each mechanical kind.
- _TurnTracker owns both the totals and the open turn, after pylint flagged
  _Accumulator over its attribute budget; _Accumulator.turns is now a property,
  so every existing caller is unchanged.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-26 19:29:25 +02:00
.github Run all 14 shell tests in CI 2026-07-19 19:39:28 +02:00
.hippo style: prettier format .hippo memory files 2026-05-28 07:05:24 +02:00
.vscode chore: archive 41 unmaintained directories to testsAndMisc-archive 2026-05-14 20:21:05 +02:00
bucket_catch bucket_catch: introduce a real design-token system, fix reversed gradients 2026-07-22 19:18:12 +02:00
docs session-autopsy: measure turn efficiency, the dominant token cost 2026-07-26 19:29:25 +02:00
kcd2_dice_solver kcd2_dice_solver: Balatro's joker replaces the one, confirmed 2026-07-25 16:33:08 +02:00
linux_configuration Fix: stop the Flutter SDK reading your own repo as itself inside git hooks 2026-07-26 15:39:33 +02:00
meta Make the hook tests' non-vacuity re-verifiable, and gate it 2026-07-25 17:37:34 +02:00
phone_focus_mode Add overnight power-save to night-lockdown; harden dnsmasq with a watchdog 2026-07-23 11:58:37 +02:00
python_pkg session-autopsy: measure turn efficiency, the dominant token cost 2026-07-26 19:29:25 +02:00
third_party/agent-skills style(prettier): apply markdown/json formatting updates 2026-05-07 22:08:00 +02:00
.copilotignore chore: archive 41 unmaintained directories to testsAndMisc-archive 2026-05-14 20:21:05 +02:00
.fvmrc chore: consolidate root configs into meta/, drop unused C dir + split/pdfCentered/geo_data 2026-05-14 20:40:12 +02:00
.gitignore linux_configuration: self-hosted dufs cloud storage + KeePass WebDAV auto-sync 2026-07-12 03:40:54 +02:00
.pre-commit-config.yaml Make the hook tests' non-vacuity re-verifiable, and gate it 2026-07-25 17:37:34 +02:00
.prettierignore cloud_gallery: React media-gallery SPA served by dufs (Phase 3) 2026-07-12 06:05:52 +02:00
CLAUDE.md remove(digital-wellbeing): delete unusable focus-mode daemon entirely 2026-07-19 13:15:04 +02:00
DESIGN_AUDIT_TODO.md Format the design-audit report with prettier 2026-07-21 15:38:08 +02:00
lint_python.sh chore: consolidate root configs into meta/, drop unused C dir + split/pdfCentered/geo_data 2026-05-14 20:40:12 +02:00
pyproject.toml chore: consolidate root configs into meta/, drop unused C dir + split/pdfCentered/geo_data 2026-05-14 20:40:12 +02:00
README.md chore: consolidate root configs into meta/, drop unused C dir + split/pdfCentered/geo_data 2026-05-14 20:40:12 +02:00
requirements.txt chore: consolidate root configs into meta/, drop unused C dir + split/pdfCentered/geo_data 2026-05-14 20:40:12 +02:00
run.sh chore: consolidate root configs into meta/, drop unused C dir + split/pdfCentered/geo_data 2026-05-14 20:40:12 +02:00

testsAndMisc

A collection of personal projects, scripts, and experiments — from a GPS-based phone focus tool to Linux/Arch automation, with CI, linting, and pre-commit hooks across the board.

Highlights

Phone Focus Mode

Location-based app restriction for rooted Android. Automatically disables non-whitelisted apps within 500 m of home using ADB + Magisk. Features Haversine distance calculation, hysteresis to prevent toggling, fail-safe unlock, and state persistence. Bash, Android ADB.

Linux Configuration

Automated Arch Linux setup: fresh-install scripts, i3 window manager config, LaTeX environment, and system tests. Includes documentation and test result logging.

Scripts

Utility scripts for development workflows — build file validation, secret detection, and custom makepkg helpers.

Repository Layout

Path Description
python_pkg/ Python packages (each maintained subpackage lives here)
linux_configuration/ Arch Linux setup, i3 config, system maintenance scripts
phone_focus_mode/ GPS-based Android focus enforcer
scripts/ Workspace-level helper scripts and pre-commit hooks
docs/ Reference docs and historical reports
third_party/ Vendored upstream skills/agents
meta/ Repo-wide tooling: pyproject.toml, requirements.txt, .pre-commit-config.yaml, run.sh, lint_python.sh, .fvmrc. Symlinked into the repo root so tools that auto-discover from root keep working.

Archived / unmaintained projects live in the sibling repository testsAndMisc-archive.

Tooling

  • Python linting: Ruff with all rules enabled (see meta/pyproject.toml)
  • Dependencies: pip install -r meta/requirements.txt (combined runtime + dev)
  • CI: GitHub Actions — lint, build, and test on push
  • Testing: pytest (Python), custom shell-based test harness for scripts