Skip to content

feat(method): call-floor — 5 call-count levers, compound ticks, skill orient split (supersedes #147)#149

Merged
pilotspacex-byte merged 5 commits into
mainfrom
feat/call-floor
Jul 14, 2026
Merged

feat(method): call-floor — 5 call-count levers, compound ticks, skill orient split (supersedes #147)#149
pilotspacex-byte merged 5 commits into
mainfrom
feat/call-floor

Conversation

@pilotspacex-byte

Copy link
Copy Markdown
Contributor

Supersedes #147 — GitHub auto-closed it when base branch feat/ceremony-to-effort was deleted at the #146 squash-merge; branch rebased onto main (identical 5 commits, conflict-free).

Stacked on #146 (feat/ceremony-to-effort). Five levers targeting the WM1 re-measure residuals (mean 18.7 calls vs the ≤12 bar), all fast-lane, all gate PASS, fence 3508/3508.

Tasks

  1. init-resume-pointer (a2df502) — the already initialised refusal names add.py status; kills the observed +2 double-init calls/rep.
  2. milestone-lane-nudge (a2df502) — new-milestone prints a lane: advisory naming the oneshot lane (rep r1 lost 9-10 calls to milestone bait). v2 prefix after the persona-nudge marker fence.
  3. scope-coverage-hint (a2df502) — the freeze scope echo also notes §3 Touches paths OUTSIDE the declared scope (the too-narrow class behind the re-cross repairs).
  4. compound-ticks (d8e1718) — OPT-IN freeze --cross (stamp → land in tests) + completing gate accepted at build (auto-cross → record); oneshot lane 8-9 → 6 calls; defaults byte-identical; recipe advertises the compressed lane. Self-proved: tasks 4 and 5 shipped through their own compound ticks.
  5. skill-orient-split (2d10b2a) — SKILL.md 12819 → 9498B (-26%); the Beyond-the-bundle routing prose moves to on-demand beyond.md; every structural pin held; core pool rebaselined +211B net per the documented method.

State

author: Tin Dang tindang.ht97@gmail.com

…al levers

Extends ceremony-to-effort's open meter criteria; every task maps to a
measured residual in the WM1 re-measure (double-init, milestone bait,
too-narrow scope, pure ticks, SKILL.md read weight). Human 'fix all'
2026-07-13.

author: Tin Dang <tindang.ht97@gmail.com>
… nudge · scope coverage hint

Three small levers from the WM1 re-measure's residual anatomy, batched
under one fence (3496/3496 OK, +8 new tests):

- init-resume-pointer: the `already initialised` refusal ends with
  `resume: add.py status` — the observed double-init (+2 calls/rep)
  dead-ends in one call; still a refusal, zero tree writes
- milestone-lane-nudge: new-milestone prints `lane: single task? the
  oneshot lane is cheaper...` at the bait point that cost rep r1
  ~10 calls; v2 change request re-prefixed from note: after three
  persona-nudge suites pinned that marker class one-per-invocation
- scope-coverage-hint: the freeze echo notes §3 Touches paths that
  exist but sit OUTSIDE the resolved scope — the too-narrow class
  behind the measured re-cross repairs; propose-not-impose, never
  speculative

ENGINE_MD5 -> 6f4e791f, engine synced x3, SEAMS _declared_scope pin
re-aimed 5581->5595. Gate PASS x3.

refs: milestone call-floor (1-3/5), stacked on PR #146
author: Tin Dang <tindang.ht97@gmail.com>
…d (call-floor 4/5)

The oneshot lane's 8-9 engine calls include two PURE ticks with no work
between them: freeze->tests and build->verify->gate. Two opt-in
compressions remove them, worth ~2 calls/task at the WM1 meter:

- `freeze --by X --cross`: after a plan-phase freeze STAMPS, the task
  lands in tests in the same call (state first, marker mirrored). A
  refused/already-frozen freeze never crosses; a change-request
  re-freeze at a non-plan phase gets an advisory note instead.
- `gate PASS|RISK-ACCEPTED` at the BUILD phase auto-crosses
  build->verify then runs every completion check unchanged (tamper,
  scope, high-risk, consumer-stale, green-bar). Phases before build
  keep their refusals verbatim; HARD-STOP is untouched.
- the new-task recipe advertises the compressed lane; the
  test_kickoff_truth RecipeTest pin updates to the new recipe truth
  (declared in-scope doc-truth ripple, flow-honesty precedent).

Defaults byte-identical: the bare freeze and every existing tick
sequence are unchanged (3496 prior fixtures still pass unmodified).

7 red/green tests in test_compound_ticks.py; full fence 3503/3503 OK.
Engine synced x3, ENGINE_MD5 re-aimed 26f78f04, SEAMS _declared_scope
pin 5595->5619. The feature proved itself: this task's own gate ran
from the build phase via the new compound tick.

refs: milestone call-floor (WM1 residual: pure ticks), task compound-ticks frozen @ v1
author: Tin Dang <tindang.ht97@gmail.com>
…ond.md (call-floor 5/5)

SKILL.md is read on EVERY task but carried ~3.4KB of on-demand routing
prose ("Beyond the bundle" verbose bullets) most tasks never take:

- the prose moves to the NEW on-demand guide skill/add/beyond.md
  (synced x3: canonical + _bundled + .claude/skills)
- SKILL.md keeps a compact one-line-per-trigger index; the always-read
  orient core drops 12819 -> 9498 bytes (-26%), pinned <= 9500 by
  test_skill_orient_split.py
- every structural pin holds: 17 on-demand pointers, phase-guide rows,
  banner-cue sentence, question-summary line, SOUL.md proximity,
  "Depth by stage" + "method rationale" sections, .add/personas/ +
  persona loop, advisor-gate-relax, agent-call-preferred default
  execution mode, retrospective-consolidation keep-term
- core pool absorbs beyond.md; baseline 20666 -> 20906 for the +211B
  net new surface (index + file header) per the documented
  rebaseline-for-human-approved-surface method, contract FROZEN @ v1
- wording-lint surface count pins 31 -> 32 (test_wording_lint +
  test_per_step_hooks), declared doc-truth ripples

5 red/green tests; pin battery 131 green; full fence 3508/3508 OK.
No engine change (ENGINE_MD5 untouched). The task's own freeze ran
`freeze --cross` and its gate ran from build — both call-floor 4/5
compound ticks proved themselves here.

refs: milestone call-floor (read burden toward <=30KB), task skill-orient-split frozen @ v1
author: Tin Dang <tindang.ht97@gmail.com>
…the paid re-measure

All 5 tasks gate PASS with test-pinned evidence (a2df502 tasks 1-3,
d8e1718 compound-ticks, 2d10b2a skill-orient-split); 6/7 exit criteria
checked with evidence. The 7th (paid WM1 re-measure, mean calls <= 12)
is human-gated spend — the goal-gate holds the milestone open until it
runs. skill-orient-split criterion checked PARTIAL-ACCEPTED (9498B vs
~8.5K sketch, read path ~33KB vs 30; remaining levers move to the
phase-restructure milestone).

refs: milestone call-floor
author: Tin Dang <tindang.ht97@gmail.com>
@pilotspacex-byte pilotspacex-byte merged commit e2c75ac into main Jul 14, 2026
9 checks passed
pilotspacex-byte added a commit that referenced this pull request Jul 14, 2026
…als follow-on draft (#150)

Human decisions 2026-07-14: run the paid WM1 re-measure, then "Close + draft
follow-on milestone".

- WM1 re-measure (3 reps, pinned sonnet meter, engine = merged main 8360b06):
  fidelity 0.98 x3 / 0 regressions / oracle 1.0 -> criterion MET; calls 20.7
  mean vs <=12 -> UNMET, HUMAN-ACCEPTED-PARTIAL at close; cost $3.17 mean =
  cheapest honest ADD round (-10% vs ceremony). Full record + waste anatomy:
  benchmark/results/2026-07-sixphase-remeasure.md (runs archived
  benchmark/runs/sixphase-r{1,2,3}).
- six-phase-loop -> done (RETRO.md written; 21 open deltas left for the
  human fold review).
- NEW milestone draft call-residuals (--await-confirm, tasks gated): the four
  message-layer levers the anatomy named — init-idempotent-nudge ·
  scope-first-draft · status-orientation-diet · help-habit-kill — targeting
  the ~11-12 call landing with zero enforcement-path changes.

refs: six-phase-loop close, PRs #146/#149/#148 merged
author: Tin Dang <tindang.ht97@gmail.com>

Co-authored-by: Tin Dang <tindang.ht97@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants