Makefile

@@ -24,7 +24,7 @@ TOOLS := $(REPO)/tools
 # Every cargo recipe runs at the repo root; the shell does not persist cd.
 IN_REPO := cd $(REPO) &&
 
-.PHONY: check test sim bench bench-test coverage dep-weight cost cost-test cost-pin cost-budget shape-budget cost-mix loop-lint self-tests env-test task-done status facts-check facts-gen mutation-check size-metrics runtime-metrics build-time am6 replay-test loc all
+.PHONY: check test sim bench bench-test coverage dep-weight cost cost-test cost-pin cost-budget cost-mix loop-lint self-tests env-test task-done status facts-check facts-gen mutation-check size-metrics runtime-metrics build-time am6 replay-test loc all
 
 ## fmt + clippy (deny warnings) + HashMap deny-lint
 check:
@@ -140,13 +140,6 @@ task-done:
 	@test -n "$(T)" || { echo "usage: make task-done T=CB-WP-0004-T02" >&2; exit 2; }
 	$(PY) $(TOOLS)/task-done.py $(T) $(ARGS)
 
-# CB-WP-0007 T03 / InnerLoop v1.5: session shape for the window since the
-# last commit. Deliberately NOT in `make all` — failing the build on
-# context would block committing, and committing is the natural point to
-# compact. A gate that blocks the remedy is a trap.
-shape-budget: cost-test
-	$(PY) $(TOOLS)/cb-cost.py --shape-budget
-
 # CB-01/CB-02: live spend since the last commit.
 cost-budget: cost-test
 	$(PY) $(TOOLS)/cb-cost.py --budget

specs/InnerLoop.md

@@ -1,31 +1,6 @@
 # The Inner Loop — Assimilate and Surpass
 
-Status: **v1.5** — corrected from CB-WP-0007 (session shape) on
+Status: **v1.4** — corrected from CB-WP-0005 (assertion coverage) on
-2026-08-01. Change from v1.4: a **soft 25% meta budget** (below), after a
-spend review found the project 38% product / 62% loop-meta with cost per
-response degraded 2.9x from its best window.
-
-> **Meta budget — soft, 25% of spend per pass.** Work on the loop's own
-> instruments and process is capped at a quarter of a pass. Measured by
-> `make status` from each workplan's `kind:` frontmatter
-> (`product` | `meta` | `mixed`).
->
-> **Soft on purpose.** A task already started may be finished — stopping
-> mid-task to satisfy a ratio wastes the work and leaves the tree in a
-> worse state than either finishing or never starting. What the budget
-> forbids is *opening* new meta work above the line.
->
-> A pass that exceeds it **says so in its evidence file and names the
-> product work displaced**. That is the whole enforcement: this is a
-> reporting budget, not a gate, for the same reason the session-shape
-> budget is (CB-RES-0005 §4) — it constrains judgment, not artifacts.
->
-> *(v1.5, from the CB-WP-0007 spend review: CB-WP-0005 and CB-WP-0006 cost
-> ~$74, 31% of all spend, for zero measured efficiency gain. Their return
-> was correctness of claims, which is real and is not optimization. The
-> budget exists so that distinction has to be made out loud.)*
-
-v1.4 — corrected from CB-WP-0005 (assertion coverage) on
 2026-07-31. Change from v1.3: where a claim rests on numbers, the
 adversarial reviewer must read the assertion behind each quoted number and
 **mutate it** — re-running the command that prints a number is not

tools/cb-cost.py

@@ -396,8 +396,7 @@ def collect(slug, pin_ref=None, since_ref=None):
     for r in responses:
         r["cost"] = price_of(prices, r["model"], r["toks"], r["timestamp"])
 
-    commits = commit_index(pin)
+    attribute(responses, commit_index(pin))
-    attribute(responses, commits)
 
     by_task = collections.defaultdict(float)
     # T02: per-task token detail, so a task close can report *measured*
@@ -455,28 +454,9 @@ def collect(slug, pin_ref=None, since_ref=None):
     mech = [r for r in responses
             if set(r.get("categories") or []) & MECHANICAL]
 
-    # The window the SH-* targets compare against: responses since the
-    # last commit when unpinned, or the whole pinned range when pinned
-    # (a pin is already a window someone chose deliberately).
-    if pin or since:
-        window_responses, window_label = responses, "the pinned/--since range"
-    else:
-        last = commits[-1][0] if commits else ""
-        window_responses = [r for r in responses if last and r["timestamp"] > last]
-        window_label = "since the last commit"
-
     sub = sum(r["cost"] or 0 for r in responses if r["subagent"])
     return {
         "session_shape": session_shape(responses),
-        # CB-WP-0007 T01. SH-1/SH-2 as a cumulative mean over every
-        # response ever recorded cannot detect a worsening trend: the
-        # history outvotes the present. CB-WP-0006 ran at 503,464 mean
-        # context and the cumulative figure still printed 206,952.
-        # Both are reported; only the window is the metric.
-        "session_shape_window": session_shape(window_responses)
-        if window_responses else None,
-        "window_responses": len(window_responses),
-        "window_label": window_label,
         "tool_mix": {
             "turns": dict(mix_turns),
             "cost": dict(mix_cost),
@@ -570,33 +550,16 @@ def render(rep, by_task=False, composition=False):
               f"{mix['mechanical_turns']:>5} turns  ${mix['mechanical_cost']:>8,.2f}"
               f"  = {100*mix['mechanical_cost']/(rep['total'] or 1):.0f}% of pass")
 
-    def _shape_lines(sh, indent="    "):
-        print(f"{indent}SH-1 mean context   {sh['SH-1_mean_context']:>12,.0f} tok  "
-              f"[{'ok ' if sh['SH-1_mean_context']<=200_000 else 'FAIL'} target 200,000]")
-        print(f"{indent}SH-2 p90 context    {sh['SH-2_p90_context']:>12,.0f} tok  "
-              f"[{'ok ' if sh['SH-2_p90_context']<=300_000 else 'FAIL'} target 300,000]")
-        print(f"{indent}SH-3 batching rate  {100*sh['SH-3_batching_rate']:>11.1f}%   "
-              f"[{'ok ' if sh['SH-3_batching_rate']>=0.20 else 'FAIL'} target 20.0%]")
-        print(f"{indent}     {sh['tool_calls']} tool calls in "
-              f"{sh['responses_with_tools']} responses; "
-              f"{sh['calls_in_batched_turns']} in batched turns")
-
-    win = rep.get("session_shape_window")
-    print(f"\n  session shape (specs/SessionShape.md) — window: "
-          f"{rep.get('window_label', '?')}")
-    if win:
-        print(f"    THE METRIC — {rep['window_responses']} response(s)")
-        _shape_lines(win)
-    else:
-        print("    THE METRIC — no responses in the window "
-              "(nothing since the last commit)")
-
     sh = rep["session_shape"]
-    print(f"\n    history, {rep['responses']} responses — context only, NOT the "
+    print("\n  session shape (specs/SessionShape.md)")
-          f"metric.")
+    print(f"    SH-1 mean context   {sh['SH-1_mean_context']:>12,.0f} tok  "
-    print("    A cumulative mean cannot detect a worsening trend; the history")
+          f"[{'ok ' if sh['SH-1_mean_context']<=200_000 else 'FAIL'} target 200,000]")
-    print("    outvotes the present (CB-RES-0005 §1).")
+    print(f"    SH-2 p90 context    {sh['SH-2_p90_context']:>12,.0f} tok  "
-    _shape_lines(sh)
+          f"[{'ok ' if sh['SH-2_p90_context']<=300_000 else 'FAIL'} target 300,000]")
+    print(f"    SH-3 batching rate  {100*sh['SH-3_batching_rate']:>11.1f}%   "
+          f"[{'ok ' if sh['SH-3_batching_rate']>=0.20 else 'FAIL'} target 20.0%]")
+    print(f"         {sh['tool_calls']} tool calls in {sh['responses_with_tools']} responses; "
+          f"{sh['calls_in_batched_turns']} in batched turns")
 
     if rep["unpriced"]:
         print(f"\n  UNPRICED ({len(rep['unpriced'])} responses, model not in sheet):")
@@ -727,63 +690,6 @@ def self_test():
     return 0 if ok else 1
 
 
-# CB-WP-0007 T03 / CB-RES-0005 D2. Soft = the SessionShape target; hard is
-# 1.5x, set here BEFORE the next measurement per InnerLoop §Step 4.
-# Reported, never in `make all`: failing the build on context would block
-# committing, and committing is what closes the attribution window and is
-# the natural point to compact. A gate that blocks the remedy is a trap.
-SHAPE_SOFT = {"SH-1": 200_000, "SH-2": 300_000}
-SHAPE_HARD = {"SH-1": 300_000, "SH-2": 450_000}
-
-
-def shape_budget(slug):
-    """SH-* for the window since the last commit, with soft/hard verdicts."""
-    try:
-        rep = collect(slug, None)
-    except Abort as e:
-        print(f"ABORT — {e}", file=sys.stderr)
-        return 1
-    win = rep.get("session_shape_window")
-    head = subprocess.run(
-        ["git", "-C", REPO, "log", "-1", "--format=%h %s"],
-        capture_output=True, text=True, check=True).stdout.strip()
-
-    print("session-shape budget — the window since the last commit")
-    print(f"  last commit   {head}")
-    # Positive control: a budget that reports ok because it measured
-    # nothing is the harness-does-nothing shape, in a reporting tool.
-    if not win or rep["window_responses"] == 0:
-        print("  no responses since the last commit — nothing to report",
-              file=sys.stderr)
-        return 1
-    print(f"  window        {rep['window_responses']} response(s)")
-
-    breach = 0
-    for key, label, val in (
-        ("SH-1", "mean context", win["SH-1_mean_context"]),
-        ("SH-2", "p90 context ", win["SH-2_p90_context"]),
-    ):
-        soft, hard = SHAPE_SOFT[key], SHAPE_HARD[key]
-        mark = "ok  " if val <= soft else ("SOFT" if val <= hard else "HARD")
-        print(f"  {key} {label} {val:>10,.0f} tok  [{mark}]  "
-              f"soft {soft:,} / hard {hard:,}")
-        breach = max(breach, 0 if val <= soft else (1 if val <= hard else 2))
-    rate = win["SH-3_batching_rate"]
-    print(f"  SH-3 batching     {100*rate:>9.1f}%   "
-          f"[{'ok  ' if rate >= 0.20 else 'SOFT'}]  floor 20.0%")
-
-    if breach >= 2:
-        print("\n  HARD — compact before continuing. Context this size costs "
-              "~10x per turn\n  against a compacted session "
-              "(specs/SessionShape.md §2).", file=sys.stderr)
-        return 1
-    if breach == 1:
-        print("\n  SOFT — over target. Compaction is the remedy and it is free.")
-    else:
-        print("\n  within budget")
-    return 0
-
-
 def budget(slug, soft, hard):
     """Live cost budget (specs/CostAccounting.md §7).
 
@@ -828,8 +734,6 @@ def main():
     ap.add_argument("--composition", action="store_true")
     ap.add_argument("--session-shape", action="store_true",
                     help="SH-1..SH-3 (always shown in the default report)")
-    ap.add_argument("--shape-budget", action="store_true",
-                    help="SH-1/SH-2/SH-3 for the window since the last commit")
     ap.add_argument("--budget", action="store_true",
                     help="CB-01/CB-02: spend since the last commit, live")
     ap.add_argument("--soft", type=float, default=10.00)
@@ -841,8 +745,6 @@ def main():
     if args.self_test:
         return self_test()
 
-    if args.shape_budget:
-        return shape_budget(args.slug)
     if args.budget:
         return budget(args.slug, args.soft, args.hard)
 

tools/status.py

@@ -48,7 +48,6 @@ def parse_workplan(path):
         m = re.search(rf'^{key}:\s*"?(.*?)"?\s*$', text, re.M)
         return m.group(1) if m else None
 
-    kind = fm("kind") or "untagged"
     tasks = []
     for m in re.finditer(r"```task\n(.*?)```", text, re.S):
         body = m.group(1)
@@ -58,7 +57,7 @@ def parse_workplan(path):
             return mm.group(1) if mm else None
 
         tasks.append((f("id"), f("status"), f("priority")))
-    return fm("id"), fm("title"), fm("status"), tasks, kind
+    return fm("id"), fm("title"), fm("status"), tasks
 
 
 def workplans():
@@ -70,7 +69,7 @@ def workplans():
 
 def next_task(plans):
     """First todo task of the first non-done workplan, with its heading."""
-    for wid, _title, status, tasks, _kind in plans:
+    for wid, _title, status, tasks in plans:
         if status == "done":
             continue
         for tid, tstatus, prio in tasks:
@@ -131,7 +130,7 @@ def report():
           + (f"  ({len(dirty)} uncommitted)" if dirty else "  (clean)"))
 
     print("\n  workplans")
-    for wid, title, status, tasks, _kind in plans:
+    for wid, title, status, tasks in plans:
         done = sum(1 for _, s, _ in tasks if s == "done")
         if status == "done" and done == len(tasks):
             print(f"    {wid}  {status:<12} {done}/{len(tasks)}")
@@ -162,34 +161,6 @@ def report():
     except Exception as e:
         print(f"    UNAVAILABLE — {e}")
 
-    # InnerLoop v1.5 — soft 25% meta budget. Reported, never gated.
-    try:
-        _, _, mod = cost_lines()
-        rep = mod.collect("-home-worsch-clay-borg", None)
-        detail = rep["by_task_detail"]
-        by_kind = {"product": 0.0, "meta": 0.0, "mixed": 0.0}
-        attributed = 0.0
-        for wid, _t, _s, tasks, kind in plans:
-            for tid, _ts, _p in tasks:
-                d = detail.get(tid)
-                if d and kind in by_kind:
-                    by_kind[kind] += d["cost"]
-                    attributed += d["cost"]
-        if attributed > 0:
-            # `mixed` splits evenly; stated rather than hidden.
-            meta = by_kind["meta"] + by_kind["mixed"] / 2
-            share = 100 * meta / attributed
-            mark = "ok  " if share <= 25 else "OVER"
-            print(f"\n  meta budget  [{mark}] {share:.0f}% of "
-                  f"${attributed:,.2f} attributed  (soft 25%, InnerLoop v1.5)")
-            print(f"    product ${by_kind['product']:,.2f}  "
-                  f"meta ${by_kind['meta']:,.2f}  "
-                  f"mixed ${by_kind['mixed']:,.2f} (split 50/50)")
-            print("    NOTE: attributed tasks only — early workplans used bare")
-            print("          T## ids that collide across passes and are excluded.")
-    except Exception as e:
-        print(f"\n  meta budget  UNAVAILABLE — {e}")
-
     print("\n  fast gates")
     code, out = run_tool("loop-lint.py")
     last = out.splitlines()[-1] if out else "?"
@@ -238,18 +209,18 @@ def self_test():
         fh.write(sample)
         tmp = fh.name
     try:
-        wid, title, status, tasks, _kind = parse_workplan(tmp)
+        wid, title, status, tasks = parse_workplan(tmp)
         check("workplan frontmatter parses", (wid, title, status)
               == ("CB-WP-0009", "Sample", "in_progress"), f"{wid} {status}")
         check("both task blocks parse with status and priority",
               tasks == [("CB-WP-0009-T01", "done", "high"),
                         ("CB-WP-0009-T02", "todo", "medium")])
         check("next task is the first todo, not the first task",
-              next_task([(wid, title, status, tasks, "meta")])
+              next_task([(wid, title, status, tasks)])
               == ("CB-WP-0009", "CB-WP-0009-T02", "medium"))
         check("a fully-done workplan yields no next task",
               next_task([("X", "t", "done",
-                          [("X-T01", "done", "high")], "meta")]) is None)
+                          [("X-T01", "done", "high")])]) is None)
     finally:
         os.unlink(tmp)
 
@@ -261,14 +232,9 @@ def self_test():
           sum(len(t) for *_, t in plans) >= 20,
           f"{sum(len(t) for *_, t in plans)} task(s)")
     check("every real workplan has an id and a status",
-          all(w and s for w, _, s, _, _ in plans))
+          all(w and s for w, _, s, _ in plans))
-    # InnerLoop v1.5: the meta budget needs every workplan classified, or
-    # the ratio is computed over an unknown denominator.
-    check("every workplan declares kind: product|meta|mixed",
-          all(k in ("product", "meta", "mixed") for *_, k in plans),
-          ", ".join(f"{w}={k}" for w, *_, k in plans))
     check("every real task has an id and a status",
-          all(i and s for _, _, _, ts, _ in plans for i, s, _ in ts))
+          all(i and s for *_, ts in plans for i, s, _ in ts))
 
     # A heading must be one line. The first version used a dot-all match
     # and returned the prose of the preceding task as the heading.

workplans/CB-WP-0001-inner-loop.md

@@ -1,6 +1,5 @@
 ---
 id: CB-WP-0001
-kind: product
 title: "Establish the assimilate-and-surpass inner loop via the GROUND game kernel"
 status: done
 state_hub_workstream_id: "a1b434dc-b1c6-46b5-bbd9-80a4e6b7620f"

workplans/CB-WP-0002-cost-accounting.md

@@ -1,6 +1,5 @@
 ---
 id: CB-WP-0002
-kind: meta
 title: "Make agentic cost measurable, so D2 claims are falsifiable"
 status: done
 state_hub_workstream_id: "b7c22f69-fbe9-48df-9619-007db79ae338"

workplans/CB-WP-0003-loop-hardening.md

@@ -1,6 +1,5 @@
 ---
 id: CB-WP-0003
-kind: meta
 title: "Harden the inner loop: executable rules, session economics, dead policy"
 status: done
 state_hub_workstream_id: "39d61dc0-870d-45c1-a595-bcf91f289dce"

workplans/CB-WP-0004-mechanical-work.md

@@ -1,6 +1,5 @@
 ---
 id: CB-WP-0004
-kind: meta
 title: "Move mechanical turns off the token budget, and prove it worked"
 status: done
 state_hub_workstream_id: "6880ac78-d817-41b9-b267-f12ff9deea28"

workplans/CB-WP-0005-assertion-coverage.md

@@ -1,6 +1,5 @@
 ---
 id: CB-WP-0005
-kind: meta
 title: "Make the instruments count assertions, then fix what they expose"
 status: done
 state_hub_workstream_id: "0b95a1e3-7780-43d0-81e9-072ef7978734"

workplans/CB-WP-0006-instrument-the-table.md

@@ -1,6 +1,5 @@
 ---
 id: CB-WP-0006
-kind: mixed
 title: "Instrument the acceptance table, then implement what it exposes"
 status: done
 state_hub_workstream_id: "8a6327cc-fd5c-4e2c-a29b-b437c27d1e71"

workplans/CB-WP-0007-session-shape.md

@@ -1,8 +1,7 @@
 ---
 id: CB-WP-0007
-kind: meta
 title: "Make session shape measurable in the window that matters, then enforce it"
-status: in_progress
+status: proposed
 state_hub_workstream_id: "bee19b76-fb60-4dcf-94d0-9242b43e0e42"
 ---
 
@@ -34,31 +33,13 @@ Per InnerLoop §Step 4, no target moves in the commit that measures it —
 and CB-RES-0005 D3 states that up front, because all three targets are
 currently unmet by wide margins and the temptation is obvious.
 
-## Scope cut, 2026-08-01 (maintainer decision)
-
-A spend review before starting found the project **38% product / 62%
-loop-meta**, with cost per response degraded 2.9× from its best window and
-INTENT stage 0 still missing a CLI player and bots. CB-WP-0005 and
-CB-WP-0006 cost **~$74 — 31% of all spend — for zero measured efficiency
-gain** (their return was correctness of claims, which is real but is not
-optimization).
-
-So this workplan is **cut to T01 and T03**, the two tasks that attack the
-2.9× regression directly. **T02 and T04 are cancelled**, not deferred —
-SH-4 trend reporting and the batching trial are more instrument work, and
-the instrument-failure taxonomy is not converging. T06 becomes the
-project-level retrospective the maintainer asked for.
-
-**A soft 25% meta budget is established here** (T03), because the review's
-finding needs a standing number, not a memory.
-
 ## Phase A — measure the right window
 
 ## Task: window the session-shape metrics
 
 ```task
 id: CB-WP-0007-T01
-status: done
+status: todo
 priority: high
 state_hub_task_id: "7e036db4-d97a-45bd-a70a-20fe68225402"
 ```
@@ -77,16 +58,11 @@ target compares against.
 **Refuted if** it lands within 20% of the cumulative number, in which case
 the aggregation was not the problem and this pass should re-plan.
 
-## Task: SH-4 — a windowed trend the instrument can see (CANCELLED)
+## Task: SH-4 — a windowed trend the instrument can see
-
-> **Cancelled unstarted 2026-08-01.** More instrument work, against a
-> review finding that instrument work has stopped paying. The ceiling T03
-> adds catches a bad pass; a trend line would catch a slow slide, which is
-> a real gap — recorded as open, not built.
 
 ```task
 id: CB-WP-0007-T02
-status: cancel
+status: todo
 priority: medium
 state_hub_task_id: "1d5a32ef-4086-4021-b874-24ed2160c4dd"
 ```
@@ -110,7 +86,7 @@ is not a trend, and the first run has nothing to compare against.
 
 ```task
 id: CB-WP-0007-T03
-status: done
+status: todo
 priority: high
 state_hub_task_id: "126a6313-b1f7-462c-8771-5100d38f9429"
 ```
@@ -143,17 +119,11 @@ Carries `--self-test`. Its positive control is the one this project keeps
 needing: a budget that reports `ok` because it measured nothing must
 abort instead.
 
-## Task: batch deliberately, and report what the rate reaches (CANCELLED)
+## Task: batch deliberately, and report what the rate reaches
-
-> **Cancelled unstarted 2026-08-01.** `SessionShape.md` §4 already puts
-> the ceiling at **$2–4 on a $93 pass** — the cheapest of the three
-> metrics to move and the least valuable. Spending a task on it while
-> stage 0 lacks a CLI player is the misallocation the review found.
-> SH-3 remains measured, unmet at 0.0%, and unfalsified.
 
 ```task
 id: CB-WP-0007-T04
-status: cancel
+status: todo
 priority: medium
 state_hub_task_id: "c284db6f-2e16-40fb-be8b-83ae5391c058"
 ```
@@ -184,10 +154,7 @@ priority: high
 state_hub_task_id: "2f78b272-e1f9-4530-bc8c-3a9d82833546"
 ```
 
-Commit `evidence/CB-EV-0006-session-shape.md`. **Reduced with the scope
+Commit `evidence/CB-EV-0006-session-shape.md`. Four tests, all reported:
-cut** — tests 1, 2 and 4 remain; test 3 (SH-3) is cancelled with T04.
-
-Four tests, all reported:
 
 1. **Does the windowed metric differ from cumulative?** Against T01's
    prediction; refuted if within 20%.