Commit Graph
6 Commits
Author SHA1 Message Date
ekcSchianoandClaude Opus 5.5 3b5c655d51 Refresh to 8,748 spreadsheet runs; squad answers ignore case; rebuild checks the runs first
CI / test (pull_request) Successful in 1m59s
- spreadsheet 8,132 -> 8,748 rows (about 600 new; the sheet's keeper fixed 'Sqaudmate' in 72 answers,
  corrected 15 attempt numbers to 'First Attempt' and re-pasted the daily bulk logs); register 288 -> 292
- form.yaml squad_any_case: a typed 'second' is Second (it stopped the build)
- collection rebuild: the runs are built and checked first, so a failed check stops it before the model,
  plan, reports and statistics are rebuilt from stale runs
- route model, plan, Black evidence, screen tree, statistics, graph and metadata rebuilt (9,473 runs)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ
2026-11-16 17:13:23 +00:00
ekcSchianoandClaude Opus 5.5 93bdfcd4da One rebuild list for the refresh, the bot cycle and the daily workflows; graph.json rebuilt
CI / test (pull_request) Canceled after 0s
- python -m collection rebuild: graph, route model, experiment plan, the Black evidence, the screen
  tree, statistics, build. refresh, cycle and both update-sources workflows use it, so the morning
  update also rebuilds the reports the tests check (it rebuilt only graph, model and stats before)
- graph.json had not been rebuilt since the played-steps fix (no Node on the Mac)
- docs: the branch is pushed; README mentions rebuild

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ
2026-11-16 16:27:20 +00:00
ekcSchianoandClaude Fable 5.2 f8e4f575f4 Screen tree, register rows in the master list, and bot runs coded from the picks that were played
CI / test (pull_request) Canceled after 0s
- analysis/tree/build_tree.py -> data/public/tree.json, analysis/reports/TREE.md: every screen the bot has seen,
  every option, where each led (fixed or dice, with ranges), best known picks per colour chosen cautiously, where
  any picks end, and the untested options. solver.js screenPick(): least-tried and Thompson picks from the tree.
- The bot logs a pick it then overrode as a step: 37 runs were coded with choices they never made. Importer and
  graph.js now use the played steps only.
- runs_clean.csv: the Unofficial Dragon Register's 288 bonded dragons are in the master list as outcome-only
  rows, flagged (no analysis uses them).
- Cycle, refresh and the bot kit rebuild and carry the tree; tests check every generated report is current.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014jqCC2LZ4x1WHQ1V57nTsv
2026-11-16 15:50:12 +00:00
ekcSchianoandClaude Fable 5.2 d01ec46fcc The Black is not dice: developer statements, evidence report, and a plan that looks for the rule
- planner/knowledge.yaml: what the game's developer has said (paraphrased, dated, graded), what the Atlas does
  with each statement, and the open questions with the experiment that tests each.
- analysis/black/evidence.py -> analysis/reports/BLACK.md: counts from the runs. On the same recorded route the
  shadow shows on 21 of 79 first attempts and 1 of 80 later ones; no single route; Blue then Black after the shadow.
- game.yaml: the shadow is a guard (not a roll); what follows it is the Blue, then the Black; on-screen text for
  the squad's direction screen.
- planner/experiments.yaml v2: one exact path on every fresh account (fresh-replicate), then one choice changed
  at a time (fresh-ablate); shadow-again, second-attempt-same-path, veteran-repeat, veteran-variety; what the bot
  records about the account; the sequence to follow once the shadow shows.
- solver.js: assign() takes account facts, account offsets and cycled arms; recommendOption() answers the
  squad screen (stay + direction) in one pick.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014jqCC2LZ4x1WHQ1V57nTsv
2026-11-16 15:24:03 +00:00
ekcSchianoandClaude Fable 5.2 ab3664f369 Route model: first attempts are their own shadow roll; experiment plan and automated bot cycle
- game.yaml: `givens` (first or later attempt) and `distinct` levels that are not pooled; the shadow roll
  depends on the attempt first. Form submissions show the shadow on 9% of first attempts and 0.3% of later ones.
- Reporting bias: a roll whose bias cannot be measured can borrow another roll's (`borrow: {shadow: meadow}`),
  so form submissions inform the shadow again. An assumption, stated in planner/policy.yaml.
- policy.json: targets.<colour>.firstAttempt (this attempt, eventually). Black: about 1.4% on a first attempt,
  0.07% on a later one.
- solver.js: advisor options `attempt`, `fix`, sampling "uniform"; assign() and armFor() for the plan.
- planner/experiments.yaml + build_experiments.py -> data/public/experiments.json (progress and status per
  experiment, rebuilt from the bot's runs).
- python -m collection cycle: import bot runs, refit, re-plan, deliver the kit; .gitea/workflows/bot-cycle.yml.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014jqCC2LZ4x1WHQ1V57nTsv
2026-11-12 03:31:33 +00:00
ekcSchianoandClaude Opus 5.5 5c49591dae Hand-offs without GitHub: bot kit zip, bot zip import, local refresh
- python -m collection export-bot-kit: policy.json, solver.js, graph.js and a
  README with checksums, zipped for the bot
- the bot import takes a folder or a zip (files may sit under any top folder)
- python -m collection refresh: the daily workflow, run locally
- trajectories files are named by date and raw checksum, so two imports on
  one day never overwrite each other

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ
2026-11-10 01:50:12 +00:00