@event4u/agent-config 14.12.0 → 14.14.0

package/src/config/evaluator-budgets.json

@@ -1,5 +1,5 @@
 {
-  "_comment": "Outside-in evaluator budgets (road-to-credible-install Phase 6). VALUES ARE FROZEN FROM MEASURED ACCEPTANCE NUMBERS of Phases 0-3 (2026-07-27, packed tarball @ 9.8.0 tree, --omit=dev consumer install), never invented. The umbrella harness (src/scripts/evaluator_umbrella.sh) measures the packed artifact and check_evaluator_budgets.ts enforces: absolute budget AND >regression_pct growth vs last_measured fails even under budget. Owner + review date are lint-enforced (lint_budget_ownership). Timing metrics carry a per-entry regression_pct override (200) \u2014 wall-clock noise would flap a 10% creep rule; their absolute max is the binding gate. Sizes/counts keep the tight 10% creep.",
+  "_comment": "Outside-in evaluator budgets (road-to-credible-install Phase 6). VALUES ARE FROZEN FROM MEASURED ACCEPTANCE NUMBERS of Phases 0-3 (2026-07-27, packed tarball @ 9.8.0 tree, --omit=dev consumer install), never invented. The umbrella harness (src/scripts/evaluator_umbrella.sh) measures the packed artifact and check_evaluator_budgets.ts enforces: absolute budget AND >regression_pct growth vs last_measured fails even under budget. Owner + review date are lint-enforced (lint_budget_ownership). Timing metrics carry a per-entry regression_pct override (200) — wall-clock noise would flap a 10% creep rule; their absolute max is the binding gate. Sizes/counts keep the tight 10% creep.",
   "schema_version": 1,
   "owner": "maintainer",
   "review_by": "2027-07-27",
@@ -11,23 +11,23 @@
     "always_blocking": [
       "a metric with no measurement supplied"
     ],
-    "rationale": "road-to-gates-that-can-fail Phase 5. A hard fail on main turns every legitimate command addition into a blocked merge, which is how budgets get quietly raised with a cushion instead of consciously \u2014 so budget / regression / drift findings are ADVISORY on main, the nightly and ordinary PRs, and BLOCKING on a release ref. Not a weakening: before the Phase-4 path triggers, this gate ran on release PRs and the nightly only, so the surfaces that now warn never saw it at all. A LOCAL run (no CI env) is strict, because a maintainer running it by hand \u2014 including release.ts \u2014 wants the strict answer and blocks nobody. A metric with NO measurement is always blocking in either posture: that is a broken harness reporting green on nothing. Implemented in src/scripts/check_evaluator_budgets.ts::detectPosture; override with --posture warn|fail.",
-    "delivery": "This posture IS the nightly-visibility route (council 2026-08-02, blocker nightly-visibility-owner), not a second mechanism beside it: the nightly publishes measurement_record below, a later run re-measures and compares, and the contradiction warns on main / fails on release. No notification channel, no auto-managed issue \u2014 a one-maintainer channel producing routine noise gets muted, and a muted channel reproduces the original failure."
+    "rationale": "road-to-gates-that-can-fail Phase 5. A hard fail on main turns every legitimate command addition into a blocked merge, which is how budgets get quietly raised with a cushion instead of consciously — so budget / regression / drift findings are ADVISORY on main, the nightly and ordinary PRs, and BLOCKING on a release ref. Not a weakening: before the Phase-4 path triggers, this gate ran on release PRs and the nightly only, so the surfaces that now warn never saw it at all. A LOCAL run (no CI env) is strict, because a maintainer running it by hand — including release.ts — wants the strict answer and blocks nobody. A metric with NO measurement is always blocking in either posture: that is a broken harness reporting green on nothing. Implemented in src/scripts/check_evaluator_budgets.ts::detectPosture; override with --posture warn|fail.",
+    "delivery": "This posture IS the nightly-visibility route (council 2026-08-02, blocker nightly-visibility-owner), not a second mechanism beside it: the nightly publishes measurement_record below, a later run re-measures and compares, and the contradiction warns on main / fails on release. No notification channel, no auto-managed issue — a one-maintainer channel producing routine noise gets muted, and a muted channel reproduces the original failure."
   },
   "measurement_record": {
     "path": "agents/evidence/metrics/evaluator-measurements.json",
-    "written_by": "src/scripts/evaluator_umbrella.sh (UMBRELLA_RECORD=1 \u2014 the nightly sets it)",
+    "written_by": "src/scripts/evaluator_umbrella.sh (UMBRELLA_RECORD=1 — the nightly sets it)",
     "compared_by": "src/scripts/check_evaluator_budgets.ts --recorded",
     "note": "Only entries WITHOUT `deterministic: false` participate in the drift comparison. The council's recorded objection was that a non-deterministic comparison produces noise and gets ignored; determinism is therefore a precondition, verified per metric, not an assumption."
   },
   "remeasurement_2026_08_02": {
     "verified_against_a_fresh_run": {
-      "cli_help_command_count": "80 \u2014 three consecutive runs of the pinned method on an unchanged tree returned 80/80/80. Matches last_measured; deterministic confirmed.",
-      "mcp_public_tool_count": "19 \u2014 two consecutive tools/list runs on a freshly built dist/mcp/server.mjs returned 19/19. Matches last_measured; deterministic confirmed."
+      "cli_help_command_count": "80 — three consecutive runs of the pinned method on an unchanged tree returned 80/80/80. Matches last_measured; deterministic confirmed.",
+      "mcp_public_tool_count": "19 — two consecutive tools/list runs on a freshly built dist/mcp/server.mjs returned 19/19. Matches last_measured; deterministic confirmed."
     },
-    "not_re_measured": "unpacked_size_mb, node_modules_mb, runtime_dep_count, cli_version_cold_ms, mcp_boot_to_initialize_ms. All five require the packed-tarball harness (npm pack of a fully built tree, then a clean `npm install --omit=dev <tarball>` into a scratch project) that evaluator_umbrella.sh runs in CI. They were NOT re-measured in this pass and their values remain the 2026-07-27 acceptance numbers \u2014 stated rather than invented. The next nightly writes the real numbers into measurement_record, and the drift check then reports any contradiction with last_measured on the PR that carries it."
+    "not_re_measured": "unpacked_size_mb, node_modules_mb, runtime_dep_count, cli_version_cold_ms, mcp_boot_to_initialize_ms. All five require the packed-tarball harness (npm pack of a fully built tree, then a clean `npm install --omit=dev <tarball>` into a scratch project) that evaluator_umbrella.sh runs in CI. They were NOT re-measured in this pass and their values remain the 2026-07-27 acceptance numbers — stated rather than invented. The next nightly writes the real numbers into measurement_record, and the drift check then reports any contradiction with last_measured on the PR that carries it."
   },
-  "removed_2026_08_04": "unpacked_size_mb (max 28) \u2014 removed by maintainer decision at the 9.17.0 release: the gate turned every legitimate payload addition into a blocked release (measured 28.22 vs max 28 with all functional gates green), and the maintainer judged tarball size not worth gating. evaluator_umbrella.sh still MEASURES and records unpacked_size_mb as evidence; only the budget enforcement is gone. ADR-204 review_trigger (a) fired and was resolved this way.",
+  "removed_2026_08_04": "unpacked_size_mb (max 28) — removed by maintainer decision at the 9.17.0 release: the gate turned every legitimate payload addition into a blocked release (measured 28.22 vs max 28 with all functional gates green), and the maintainer judged tarball size not worth gating. evaluator_umbrella.sh still MEASURES and records unpacked_size_mb as evidence; only the budget enforcement is gone. ADR-204 review_trigger (a) fired and was resolved this way.",
   "budgets": {
     "node_modules_mb": {
       "max": 140,
@@ -58,18 +58,18 @@
       "deterministic": false
     },
     "cli_help_command_count": {
-      "max": 107,
-      "last_measured": 107,
-      "last_measured_at": "2026-08-23",
-      "method": "registry enumeration \u2014 count of `{ name: '...', disposition` entries in src/cli/registry.ts (NOT --help prose parsing; methods historically disagreed 74 vs 76 vs 79)",
-      "baseline_note": "80 \u2192 81 on 2026-08-03 (release 9.15.0 gate). This RECORDS growth that already shipped through its own reviewed PR; it does not authorize new surface. The +1 is f02db54c2 (fix(cli): register routing:doctor in the CLI registry) \u2014 the command existed, only its registry entry was missing, and the registering PR did not move this budget. The gate did its job again: breach WARNS on main and BLOCKS on release, which is the conscious-decision point rather than a silently raised cap. Re-measured 2026-08-03 via the pinned method: 81. Headroom stays zero by design \u2014 the next registry addition must move this number in its own PR. 81 \u2192 82 on 2026-08-04: the `handoff` subcommand (road-to-agent-handoff-resume Phase 4) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 82. 82 \u2192 84 on 2026-08-04: the `route:explain` + `route:audit` verbs (routing-correctness validation surface) register in the same PR that adds the surface. Re-measured via the pinned method: 84. 84 \u2192 85 on 2026-08-05: the `settings:set` verb (road-to-zero-ceremony-settings Phase 2 \u2014 the one agent-reachable settings writer) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 85. 85 \u2192 86 on 2026-08-06: the `conformance:behavior` verb (road-to-agent-behavior-conformance Phase 5 \u2014 replays the local transcript store through the four mechanised conformance checks) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 86. 86 \u2192 88 on 2026-08-07: the `sessions:list` + `sessions:claim` verbs (road-to-parallel-session-coordination \u2014 the shell surface of the shared session register, needed because /roadmap:next is command markdown and can only reach the register through a shell call) register in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 88. 88 \u2192 89 on 2026-08-08: the `council:status` verb registers in the same PR that adds the surface, per this record's own contract. It exists because an agent in a consumer project announced \"kein Council konfiguriert (keine .agent-settings.yml)\" and substituted a weaker path while the council was configured user-globally the whole time \u2014 there was no verb that answered availability, so the only route was an inference from a filename, and the intuitive filename is the one location ADR-104 guarantees is never consulted. Re-measured via the pinned method: 89. 89 \u2192 91 on 2026-08-08: the `self-repair:status` + `self-repair:release` verbs (the queued-defect reader and the single Hard-Floor-gated outward step of the self-repair loop \u2014 the loop is deliberately unable to publish unless a human runs the release command) register in the same PR that adds the surface, per this record's own contract. Landed alongside the +1 council:status move in the same branch. Re-measured via the pinned method: 91. 91 \u2192 94 on 2026-08-08: the `packs:active`, `settings:get` and `mcp:available` verbs (road-to-capability-answerability Phase 2 \u2014 the three capability probes for the gaps that had none) register in the same PR that adds the surface, per this record's own contract. Each answers a question that was previously only inferable from a filename: which packs are active and from which file, what a setting resolves to and which file set it, and what is declared in mcp.json versus what can actually launch. 94 -> 95 in the same PR: `brand:status` (Phase 2.4 \u2014 brand-layer presence, which the rule depended on and no surface could answer). Re-measured twice via the pinned method on the unchanged tree: 95/95. 95 \u2192 96 on 2026-08-10: the `session:recycle` verb (road-to-token-economy-recycling Phase 2.2 \u2014 the deterministic producer of the main-session recycle envelope; the recycle advisory names this exact verb, so it must exist as a shell surface) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 96. 96 -> 97 on 2026-08-10: the `gates` verb registers in the same PR that adds the surface, per this record's own contract. It exists because the blocker fields the dashboard already parses (Owner, What to do, Resolved when \u2014 CI-enforced by lint_roadmap_blockers) had no owner-filtered reader: the dashboard counts the open blockers across a 600-line file and links each to a per-roadmap anchor, so \"which of these are mine\" was a manual read of every anchor. The same inference-from-a-filename shape as the council:status entry above, one layer up. This branch and the session:recycle branch each measured 96 independently and landed on the same number for different verbs; the merge makes it 97, re-measured twice via the pinned method on the merged tree: 97/97. 97 -> 98 on 2026-08-15: the `workspace:doctor` verb (road-to-inbox-harvest-2026-08-c-workspace-identity Phase 3 \u2014 the read-only report over the new `workspaceIdentity()` resolver) registers in the same PR that adds the surface, per this record's own contract. It exists for the same inference-from-a-filename shape as the council:status and gates entries above, one layer down: the tree answered \"where am I\" in eight ad-hoc places across six files, and the 12.0.0 span shipped the same worktree misclassification twice, so no verb could be asked which checkout is the main one. Read-only by construction \u2014 the roadmap's Non-goals put worktree disposal out of scope and its Risk 3 names \"the pressure read becomes a disposal path by accident\" as the failure to design against, so the command carries no --fix and no --prune. Re-measured twice via the pinned method on the unchanged tree: 98/98. 98 -> 99 on 2026-08-17: the `council:quota` verb (road-to-council-quota-accounting-truth Phase 2) registers in the same PR that adds the surface, per this record's own contract. Exactly the inference-from-a-filename shape as the council:status entry above, one layer down: `cmd_quota` had existed in council_cli.ts and been reachable only via `scripts-run`, so the documented recovery path for an exhausted shared counter -- read the usage, reset one provider -- did not resolve through `agent-config`, and an operator debugging a quota failure met `unknown command`. The verb is read-only apart from the pre-existing `--reset <provider>`, which already required `--confirm`. Re-measured twice via the pinned method on the unchanged tree: 99/99. 99 -> 100 on 2026-08-19: the `decision:memo` verb (road-to-long-horizon-execution Phase 2.2, sequencing UOTL Phase 4.3 -- the decision-memo channel) registers in the same PR that adds the surface, per this record's own contract. It exists because the question ladder gained a rung between \"halt and ask\" and \"decide silently\": a resolution the run makes without contacting the operator is only legitimate if it is reviewable afterwards, and there was no surface that wrote such a record with a fixed shape. Write-and-list only, local-only (agents/runtime/ is gitignored), and it gates nothing -- the locked decision classes are refused at the config schema, never in the ledger. 100 -> 101 in the same PR: `run:supervise` (Phase 3.1 -- the out-of-process watcher for runs whose session died with open steps left). It is the operator-facing half of session continuity: nothing anywhere had the job of noticing that a claimed run stopped moving, so a roadmap 40% done and a roadmap finished looked identical from outside the dead session. Report-only by default and it NEVER merges, pushes or closes -- the auto-merge the reference design carries is a named rejection in the roadmap's harvest section, not an unbuilt feature. Re-measured twice via the pinned method on the unchanged tree: 101/101. 101 \u2192 102 on 2026-08-22: the `adr:effective` verb (road-to-evidence-based-adr-governance step 2.2 \u2014 the effective-state projection over one decision record) registers in the same PR that adds the surface, per this record's own contract. It exists because current truth about an ADR was only reconstructable from linear prose: an agent had to read the body, then every amendment, and decide for itself which clauses still stand. The verb reports status, the Decision verbatim, clauses the record's own amendments superseded, active amendments, the three descriptive axes and the review-trigger state. It AUTHORIZES NOTHING \u2014 Phase 2 of that roadmap is titled \"surfacing only; no authority\" and its AC-7 forbids any authority consequence, so the verb reports an absent axis as absent (`\u2014 (no provenance axis)`, `\u2014 (ungraded)`, `absent \u2192 evidence`) and an unresolvable trigger as `indeterminate` rather than inferring one. Re-measured twice via the pinned method on the unchanged tree: 102/102. 102 \u2192 104 on 2026-08-22: the `council:grant-billing` + `council:revoke-billing` verbs (road-to-billing-cliff-gate Phase 2 \u2014 the run-scoped billing grant that lets `ai_council.fallback.api_on_quota: 'ask'` be answered once per run instead of once per seat) register in the same PR that adds the surface, per this record's own contract. The two are a pair by construction rather than by convenience: a grant that can be issued and not revoked would outlive its run, which is the failure the run-scoped TTL exists to prevent. Re-measured via the pinned method: 104. 104 -> 106 on 2026-08-23: the `ui:audit` + `ui:render` verbs (road-to-frontend-power E2.1 and E3.1 -- the two Class-A commands that give the frontend obligations an artefact a gate can read and a render a verdict can cite) register in the same PR that adds the surface, per this record's own contract. The two are a pair by construction rather than by convenience: `ui-audit-gate`'s enforced_by moved from `none` to a carrier in the same change, and that carrier reports `verification: degraded` whenever the render artefact is absent -- so an audit verb without a render verb would ship a gate that can never reach `verified`. Both are Class A under ADR-124: they terminate, their whole state is a rebuildable directory under agents/runtime/state/, and ui:render closes chromium in a `finally` on every path with no --serve, watch or cache for a resident browser to hide in. Re-measured via the pinned method on the unchanged tree: 106. 106 \u2192 107 on 2026-08-23: the `roadmap:context` verb (road-to-roadmap-situational-awareness \u2014 the single live probe that answers what else is in flight before a roadmap is picked) registers in the same PR that adds the surface, per this record's own contract. Its branch measured 105 against a base of 104 and this branch measured 106 against the same base for `ui:audit` + `ui:render`; the merge makes it 107, re-measured on the merged tree via the pinned method (registry enumeration): 107."
+      "max": 109,
+      "last_measured": 109,
+      "last_measured_at": "2026-08-26",
+      "method": "registry enumeration — count of `{ name: '...', disposition` entries in src/cli/registry.ts (NOT --help prose parsing; methods historically disagreed 74 vs 76 vs 79)",
+      "baseline_note": "80 → 81 on 2026-08-03 (release 9.15.0 gate). This RECORDS growth that already shipped through its own reviewed PR; it does not authorize new surface. The +1 is f02db54c2 (fix(cli): register routing:doctor in the CLI registry) — the command existed, only its registry entry was missing, and the registering PR did not move this budget. The gate did its job again: breach WARNS on main and BLOCKS on release, which is the conscious-decision point rather than a silently raised cap. Re-measured 2026-08-03 via the pinned method: 81. Headroom stays zero by design — the next registry addition must move this number in its own PR. 81 → 82 on 2026-08-04: the `handoff` subcommand (road-to-agent-handoff-resume Phase 4) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 82. 82 → 84 on 2026-08-04: the `route:explain` + `route:audit` verbs (routing-correctness validation surface) register in the same PR that adds the surface. Re-measured via the pinned method: 84. 84 → 85 on 2026-08-05: the `settings:set` verb (road-to-zero-ceremony-settings Phase 2 — the one agent-reachable settings writer) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 85. 85 → 86 on 2026-08-06: the `conformance:behavior` verb (road-to-agent-behavior-conformance Phase 5 — replays the local transcript store through the four mechanised conformance checks) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 86. 86 → 88 on 2026-08-07: the `sessions:list` + `sessions:claim` verbs (road-to-parallel-session-coordination — the shell surface of the shared session register, needed because /roadmap:next is command markdown and can only reach the register through a shell call) register in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 88. 88 → 89 on 2026-08-08: the `council:status` verb registers in the same PR that adds the surface, per this record's own contract. It exists because an agent in a consumer project announced \"kein Council konfiguriert (keine .agent-settings.yml)\" and substituted a weaker path while the council was configured user-globally the whole time — there was no verb that answered availability, so the only route was an inference from a filename, and the intuitive filename is the one location ADR-104 guarantees is never consulted. Re-measured via the pinned method: 89. 89 → 91 on 2026-08-08: the `self-repair:status` + `self-repair:release` verbs (the queued-defect reader and the single Hard-Floor-gated outward step of the self-repair loop — the loop is deliberately unable to publish unless a human runs the release command) register in the same PR that adds the surface, per this record's own contract. Landed alongside the +1 council:status move in the same branch. Re-measured via the pinned method: 91. 91 → 94 on 2026-08-08: the `packs:active`, `settings:get` and `mcp:available` verbs (road-to-capability-answerability Phase 2 — the three capability probes for the gaps that had none) register in the same PR that adds the surface, per this record's own contract. Each answers a question that was previously only inferable from a filename: which packs are active and from which file, what a setting resolves to and which file set it, and what is declared in mcp.json versus what can actually launch. 94 -> 95 in the same PR: `brand:status` (Phase 2.4 — brand-layer presence, which the rule depended on and no surface could answer). Re-measured twice via the pinned method on the unchanged tree: 95/95. 95 → 96 on 2026-08-10: the `session:recycle` verb (road-to-token-economy-recycling Phase 2.2 — the deterministic producer of the main-session recycle envelope; the recycle advisory names this exact verb, so it must exist as a shell surface) registers in the same PR that adds the surface, per this record's own contract. Re-measured via the pinned method: 96. 96 -> 97 on 2026-08-10: the `gates` verb registers in the same PR that adds the surface, per this record's own contract. It exists because the blocker fields the dashboard already parses (Owner, What to do, Resolved when — CI-enforced by lint_roadmap_blockers) had no owner-filtered reader: the dashboard counts the open blockers across a 600-line file and links each to a per-roadmap anchor, so \"which of these are mine\" was a manual read of every anchor. The same inference-from-a-filename shape as the council:status entry above, one layer up. This branch and the session:recycle branch each measured 96 independently and landed on the same number for different verbs; the merge makes it 97, re-measured twice via the pinned method on the merged tree: 97/97. 97 -> 98 on 2026-08-15: the `workspace:doctor` verb (road-to-inbox-harvest-2026-08-c-workspace-identity Phase 3 — the read-only report over the new `workspaceIdentity()` resolver) registers in the same PR that adds the surface, per this record's own contract. It exists for the same inference-from-a-filename shape as the council:status and gates entries above, one layer down: the tree answered \"where am I\" in eight ad-hoc places across six files, and the 12.0.0 span shipped the same worktree misclassification twice, so no verb could be asked which checkout is the main one. Read-only by construction — the roadmap's Non-goals put worktree disposal out of scope and its Risk 3 names \"the pressure read becomes a disposal path by accident\" as the failure to design against, so the command carries no --fix and no --prune. Re-measured twice via the pinned method on the unchanged tree: 98/98. 98 -> 99 on 2026-08-17: the `council:quota` verb (road-to-council-quota-accounting-truth Phase 2) registers in the same PR that adds the surface, per this record's own contract. Exactly the inference-from-a-filename shape as the council:status entry above, one layer down: `cmd_quota` had existed in council_cli.ts and been reachable only via `scripts-run`, so the documented recovery path for an exhausted shared counter -- read the usage, reset one provider -- did not resolve through `agent-config`, and an operator debugging a quota failure met `unknown command`. The verb is read-only apart from the pre-existing `--reset <provider>`, which already required `--confirm`. Re-measured twice via the pinned method on the unchanged tree: 99/99. 99 -> 100 on 2026-08-19: the `decision:memo` verb (road-to-long-horizon-execution Phase 2.2, sequencing UOTL Phase 4.3 -- the decision-memo channel) registers in the same PR that adds the surface, per this record's own contract. It exists because the question ladder gained a rung between \"halt and ask\" and \"decide silently\": a resolution the run makes without contacting the operator is only legitimate if it is reviewable afterwards, and there was no surface that wrote such a record with a fixed shape. Write-and-list only, local-only (agents/runtime/ is gitignored), and it gates nothing -- the locked decision classes are refused at the config schema, never in the ledger. 100 -> 101 in the same PR: `run:supervise` (Phase 3.1 -- the out-of-process watcher for runs whose session died with open steps left). It is the operator-facing half of session continuity: nothing anywhere had the job of noticing that a claimed run stopped moving, so a roadmap 40% done and a roadmap finished looked identical from outside the dead session. Report-only by default and it NEVER merges, pushes or closes -- the auto-merge the reference design carries is a named rejection in the roadmap's harvest section, not an unbuilt feature. Re-measured twice via the pinned method on the unchanged tree: 101/101. 101 → 102 on 2026-08-22: the `adr:effective` verb (road-to-evidence-based-adr-governance step 2.2 — the effective-state projection over one decision record) registers in the same PR that adds the surface, per this record's own contract. It exists because current truth about an ADR was only reconstructable from linear prose: an agent had to read the body, then every amendment, and decide for itself which clauses still stand. The verb reports status, the Decision verbatim, clauses the record's own amendments superseded, active amendments, the three descriptive axes and the review-trigger state. It AUTHORIZES NOTHING — Phase 2 of that roadmap is titled \"surfacing only; no authority\" and its AC-7 forbids any authority consequence, so the verb reports an absent axis as absent (`— (no provenance axis)`, `— (ungraded)`, `absent → evidence`) and an unresolvable trigger as `indeterminate` rather than inferring one. Re-measured twice via the pinned method on the unchanged tree: 102/102. 102 → 104 on 2026-08-22: the `council:grant-billing` + `council:revoke-billing` verbs (road-to-billing-cliff-gate Phase 2 — the run-scoped billing grant that lets `ai_council.fallback.api_on_quota: 'ask'` be answered once per run instead of once per seat) register in the same PR that adds the surface, per this record's own contract. The two are a pair by construction rather than by convenience: a grant that can be issued and not revoked would outlive its run, which is the failure the run-scoped TTL exists to prevent. Re-measured via the pinned method: 104. 104 -> 106 on 2026-08-23: the `ui:audit` + `ui:render` verbs (road-to-frontend-power E2.1 and E3.1 -- the two Class-A commands that give the frontend obligations an artefact a gate can read and a render a verdict can cite) register in the same PR that adds the surface, per this record's own contract. The two are a pair by construction rather than by convenience: `ui-audit-gate`'s enforced_by moved from `none` to a carrier in the same change, and that carrier reports `verification: degraded` whenever the render artefact is absent -- so an audit verb without a render verb would ship a gate that can never reach `verified`. Both are Class A under ADR-124: they terminate, their whole state is a rebuildable directory under agents/runtime/state/, and ui:render closes chromium in a `finally` on every path with no --serve, watch or cache for a resident browser to hide in. Re-measured via the pinned method on the unchanged tree: 106. 106 → 107 on 2026-08-23: the `roadmap:context` verb (road-to-roadmap-situational-awareness — the single live probe that answers what else is in flight before a roadmap is picked) registers in the same PR that adds the surface, per this record's own contract. Its branch measured 105 against a base of 104 and this branch measured 106 against the same base for `ui:audit` + `ui:render`; the merge makes it 107, re-measured on the merged tree via the pinned method (registry enumeration): 107. 107 → 108 on 2026-08-26: the `roadmap:set-step` verb (road-to-skill-ecosystem-runtime-enforcement Phase 6 — the single sanctioned writer of a checkbox glyph) registers in the same PR that adds the surface, per this record's own contract. It exists because the glyph is written today by whatever edits the file, and a concurrent writer destroys work SILENTLY: the loser of an overwrite receives no error. The verb carries an advisory lock, a line-anchored edit that cannot span entries even in principle, a step-count invariant asserted against the LIVE pre-write file rather than an in-memory snapshot, and a post-write survival check. Re-measured via the pinned method (registry enumeration) on the unchanged tree: 108. 108 → 109 on 2026-08-26: the `stubs:due` verb (road-to-inbox-harvest-2026-08-f-owner-decision-queue step 2.1 — the read-only reader over `agents/roadmaps/stubs/` frontmatter) registers in the same PR that adds the surface, per this record's own contract. It exists because step 1.2 backfills a `review_by:` date into 77 parked files, and an AI council (2026-08-26, 2/2) made the ordering a RULE rather than a preference: dates without a reader are strictly worse than no dates, because a stale date certifies attention nobody paid. The verb is read-only by construction — it authors nothing under `agents/roadmaps/stubs/`, so `check_no_stub_inventory_table` stays green and unmodified, and `roadmap:progress` consumes only its two COUNTS for the dashboard header (two integers, no rows, nothing for the deleted index tables to grow back from). Re-measured via the pinned method (registry enumeration) on the unchanged tree: 109."
     },
     "mcp_public_tool_count": {
       "max": 20,
       "last_measured": 20,
       "last_measured_at": "2026-08-17",
       "method": "tools/list length on the stdio server (post-ADR-132: implemented tools only)",
-      "baseline_note": "19 \u2192 20 on 2026-08-17 (release 13.0.0 gate). The +1 is 866bd9861 (feat(mcp): recover what the host dropped \u2014 real ranker tool + a route to it, road-to-inbox-harvest-2026-08-d-runtime-skill-routing Phase 4): `suggest_skill_for_task` was promoted from a discovery STUB to a real ALLOWLIST entry and removed from STUB_TOOLS. Worth stating precisely, because the consumer-visible NAME did not grow \u2014 the stub already published that name and its `task` + `limit` input schema, which the promotion carried over verbatim. What grew is the count of tools tools/list actually returns, which is exactly what this metric measures post-ADR-132: implemented tools only. Same shape as the cli_help_command_count history above \u2014 this RECORDS growth that already shipped through its own reviewed PR (866bd9861 is on main), it does not authorize new surface. The registering PR did not move this budget, so the gate did its job: the breach warned on main and blocked on the release ref, which is the conscious-decision point rather than a silently raised cap. Re-measured twice via the pinned method on a freshly built dist/mcp/server.mjs: 20/20. Headroom stays zero by design \u2014 the next tool that leaves STUB_TOOLS must move this number in its own PR."
+      "baseline_note": "19 → 20 on 2026-08-17 (release 13.0.0 gate). The +1 is 866bd9861 (feat(mcp): recover what the host dropped — real ranker tool + a route to it, road-to-inbox-harvest-2026-08-d-runtime-skill-routing Phase 4): `suggest_skill_for_task` was promoted from a discovery STUB to a real ALLOWLIST entry and removed from STUB_TOOLS. Worth stating precisely, because the consumer-visible NAME did not grow — the stub already published that name and its `task` + `limit` input schema, which the promotion carried over verbatim. What grew is the count of tools tools/list actually returns, which is exactly what this metric measures post-ADR-132: implemented tools only. Same shape as the cli_help_command_count history above — this RECORDS growth that already shipped through its own reviewed PR (866bd9861 is on main), it does not authorize new surface. The registering PR did not move this budget, so the gate did its job: the breach warned on main and blocked on the release ref, which is the conscious-decision point rather than a silently raised cap. Re-measured twice via the pinned method on a freshly built dist/mcp/server.mjs: 20/20. Headroom stays zero by design — the next tool that leaves STUB_TOOLS must move this number in its own PR."
     }
   }
 }