@gobing-ai/spur 0.4.2 → 0.4.3

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
     "plugins": [
         {
             "name": "sp",
-            "version": "0.4.2",
+            "version": "0.4.3",
             "source": "./plugins/sp"
         }
     ]

package/config/decisions/maker-liveness.yaml

@@ -0,0 +1,39 @@
+$schema: "@gobing-ai/spur/schemas/decision-catalog.schema.json"
+# Liveness probe catalog (feature P11, docs/design/decision-observability-and-adoption.md §3.4).
+#
+# `maker-liveness` is served by exactly one caller: `spur decision status --probe`,
+# which asks it once per distinct registered effective maker to prove the maker
+# answers *now* rather than inferring health from configuration. No workflow may
+# reference this id — a decision whose answer classifies nothing real has no place
+# in a run, and `spur decision status --reliability` would otherwise count probe
+# runs as adoption evidence.
+#
+# The probe writes no `decision_logs` row and emits no `decision.*` event, so these
+# runs never enter the recorded evidence the same report displays next to them.
+#
+# Resolution: this file ships in the shared layer (the installed package's
+# config/decisions/). A project can override it per basename through
+# .spur/decisions/ or decisions.paths (first layer wins, ADR-113 style). Replacing it
+# with a catalog that omits the id makes `--probe` fail loudly before any maker call.
+version: 1
+
+defaults:
+    # Deliberately not the 0.7 upstream / 0.8 catalog floor. minConfidence gates
+    # whether an *answer* is accepted; the probe asks whether the *maker* answered.
+    # Under a 0.8 floor a live maker reporting 0.6 would fall back and the probe would
+    # report "not working" for a backend that is working. A maker that never answered
+    # (no-backend, timeout, error) falls back regardless of this value.
+    minConfidence: 0
+
+decisions:
+    maker-liveness:
+        type: choice
+        # Rendered as the question when the caller passes no `instructions`: the probe
+        # always does pass one, so this description is the fallback wording, not the
+        # probe prompt.
+        description: >
+            Liveness probe. Answer `ok` if this maker can serve a decision right now.
+        criteria:
+            ok: The maker answered the question it was asked.
+            unclear: The maker could not answer.
+        fallback: unclear

package/config/plugin-scripts.json

@@ -22,10 +22,6 @@
             "contract": "standard",
             "twin": "daily-summary/daily-summary.mjs"
         },
-        {
-            "rel": "daily-summary/logger.ts",
-            "contract": "repo-only"
-        },
         {
             "rel": "dogfood-testing/detect-pipeline-driving.ts",
             "contract": "standard",

package/config/rules/README.md

@@ -17,6 +17,7 @@ install or to ts-libs.
 | `surface` | `surface/` | CLI surface consistency (registerXxxCommand wiring, --json serialization) |
 | `migration` | `migration/` | Transitional helpers for the regex → `rg` evaluator move (`rg-dialect`) |
 | `ui` | `ui/` | Web UI seam boundaries (import seam, daisyUI class leak) |
+| `docs` | `docs/` | Sourced API/library claims in markdown — citation anchor + HIGH/MEDIUM/LOW level. Advisory (`info`), and deliberately **not** in a preset: see the file header for its calibration audit and the one-line promotion step. |
 
 ## Presets
 

package/config/rules/docs/sourced-api-claims.yaml

@@ -9,22 +9,43 @@ $schema: "@gobing-ai/spur/schemas/rule-file.schema.json"
 # gate runs --fail-on warning, so this rule surfaces findings for review without
 # reddening gates — changed-file enforcement happens in SECUA review).
 #
+# Calibration audit (2026-10-12, `spur rule run --file … --json`, unsuppressed):
+# the category was pulled from `recommended-pre-check` on 2026-10-08 for "finding
+# noise" — 593 findings. The audit split them 580 `cited-version-strings` /
+# 13 `cited-api-claims`, and 579 of the 580 were false positives on two shapes
+# that are not external claims at all: a document's own version
+# (`docs/00_ADR.md:5` → `version: 1.69.0`), a section number in a heading
+# (`docs/04_DESIGN.md:116` → `### 1.0.1 Shared option registry`) and a
+# `§`-numbered cross-reference (`docs/00_ADR.md:1118` → `§1.2.1`). All three are
+# excluded by the pattern below — the first two on the line's shape, the third on
+# the token itself. The remaining source was a stale exclude list that stopped at
+# `docs/tasks4/` while the active corpus folder is `docs/tasks5/`, which alone
+# produced 226 findings; it is now one `docs/tasks*/**` glob. 593 → 330 after those
+# two fixes, then 277 once the `§` shape was excluded too — the residual are
+# version-pinned package claims that genuinely lack a same-line anchor, and they
+# stay visible rather than suppressed.
+#
 # The semantic contract — every external API/library claim carries a source
 # citation (URL or path:line) AND a confidence level (HIGH/MEDIUM/LOW) — is
 # owned by the sp-source-driven-development skill and verified in SECUA review
-# (code-verification secu-review checklist). Generic "supports/requires" prose
-# is deliberately out of scope here: in this corpus it is structural writing,
-# not external API assertion, and would drown the signal.
+# (code-verification secu-review checklist). These rules are its deterministic
+# backstop: the two `cited-*` rules cover the citation half, and
+# `cited-api-claims-confidence` covers the level half. All are severity `info`,
+# and the category is deliberately NOT in `recommended-pre-check` — it surfaces
+# findings for review without reddening gates. To promote it to a gate, add
+# `- docs` to that preset's `extends` once the residual list is triaged.
 include:
   - "docs/**/*.md"
   - "plugins/sp/skills/**/references/**/*.md"
 exclude:
   # Legacy task archives are historical records — retro-citing ~900 closed
-  # lines is make-work; the tripwire targets active authoring surfaces.
-  - "docs/tasks/"
-  - "docs/tasks2/"
-  - "docs/tasks3/"
-  - "docs/tasks4/"
+  # lines is make-work; the tripwire targets active authoring surfaces. One glob
+  # rather than the literal tasks/…tasks4/ list that let the active folder through.
+  # The trailing `/**` is load-bearing: `docs/tasks*/` ends as a pattern segment
+  # tested against `x.md`, so the anchored matcher binds nothing and the fragment
+  # fallback strips the `*` down to `docs/tasks/` — which is why that form
+  # silently excluded nothing (measured 2026-10-12).
+  - "docs/tasks*/**"
   - "drizzle/**"
   - "**/node_modules/**"
 rules:
@@ -41,10 +62,15 @@ rules:
       config:
         mode: forbid
         # Fire when the line has NO citation anchor (no URL, no path:line) AND
-        # contains a semver-ish token. Lookarounds exclude IPs (127.0.0.1) and
-        # longer dotted numerics; fenced-code lines are out of regex reach —
-        # that residual noise is why this is warning, not error.
-        pattern: "^(?!.*(?:https?://|(?:[\\w.-]+/)+[\\w.-]+:\\d+)).*(?<![\\d.])\\d+\\.\\d+\\.\\d+(?!\\.\\d)"
+        # contains a semver-ish token. Lookarounds exclude IPs (127.0.0.1),
+        # longer dotted numerics, a heading's section number (`### 1.0.1 Title`),
+        # a document-version metadata line (`version: 1.69.0`) and a `§`-numbered
+        # section reference (`§7.3.1`) — none of which is an external claim;
+        # fenced-code lines are out of regex reach — that residual noise is why
+        # this is info, not warning. The `§` guard sits on the token itself, not on
+        # the line, so a line carrying both a section reference and a real version
+        # still fires on the version.
+        pattern: "^(?!.*(?:https?://|(?:[\\w.-]+/)+[\\w.-]+:\\d+))(?!\\s*#{1,6}\\s+\\d+\\.\\d+\\.\\d+)(?!\\s*[\\w-]+:\\s*\\d+\\.\\d+\\.\\d+\\s*$).*(?<![\\d.§])\\d+\\.\\d+\\.\\d+(?!\\.\\d)"
   - id: cited-api-claims
     description: >
       A markdown line making a time- or version-anchored external API claim
@@ -58,3 +84,21 @@ rules:
       config:
         mode: forbid
         pattern: "^(?!.*(?:https?://|(?:[\\w.-]+/)+[\\w.-]+:\\d+)).*\\b(?:deprecated (?:since|in|as of)|introduced in|added in|available since|stable since)\\b"
+  - id: cited-api-claims-confidence
+    description: >
+      A markdown line making a time- or version-anchored external API claim
+      ("deprecated since 1.2", "introduced in v3", "available since 0.9") must
+      also state its confidence level — HIGH, MEDIUM or LOW — so a reader can
+      tell a checked fact from model memory; contract in
+      sp-source-driven-development. Pairs with `cited-api-claims`, which covers
+      the citation half: a line missing both halves reports once per rule,
+      deliberately, because each missing half is its own defect.
+    severity: info
+    evaluator:
+      type: regex
+      config:
+        mode: forbid
+        # Fires on a claim line carrying no uppercase level token. The verbs match
+        # `cited-api-claims` exactly, so the two rules never disagree about which
+        # lines are claims.
+        pattern: "^(?!.*\\b(?:HIGH|MEDIUM|LOW)\\b).*\\b(?:deprecated (?:since|in|as of)|introduced in|added in|available since|stable since)\\b"

package/config/rules/strict/runtime-boundaries.yaml

@@ -38,6 +38,12 @@ rules:
 
             # Low-level system primitives:
             - "packages/app/src/services/quality-gate.ts" # gate runs `sh -c` with stdout+stderr merged onto ONE fd; ProcessExecutor captures streams separately and cannot reproduce the stream-order contract (task 1006 R1; mirrors the history-anatomy bundling exemptions)
+            # The feature-verification pass runs one long command with stdout+stderr merged onto the
+            # run's single log fd and a 4 h ceiling (the frozen contract from task 0915: `safe argv
+            # spawn, timeout and status handling`). ProcessExecutor captures the two streams separately
+            # and exposes no timeout, so it cannot reproduce either half (task 1176 R2; same class as
+            # the quality-gate exemption above).
+            - "packages/app/src/workflow/feature-verification-run.ts"
 
   - id: no-direct-fs-io
     description: "Prefer ts-runtime's FileSystem seam for fs IO."
@@ -74,6 +80,7 @@ rules:
             - "apps/cli/src/commands/workflow.ts" # FD byte-window tail of the mid-run run log for `workflow trace --follow` streaming (task 0428 / feature D2); readSync at offset over the observability sink's FDs
             - "apps/web/src/modules/discover.ts" # Vite/Astro module scanner fallback under bun test
             - "packages/app/src/services/quality-gate.ts" # gate artifacts (log/findings/receipt) written directly; merged-fd gate log and fsync-free atomic writes must stay byte-stable; bundled standalone for the bare-node plugin twin (task 1006 R1; mirrors history-anatomy.ts)
+            - "packages/app/src/workflow/feature-verification-run.ts" # the pass opens the run's single merged log fd (`openSync(path,'a')`) and mkdirs the run dir beside the receipt writer, exactly as the plugin entry did before the move; the fd cannot be expressed through the FileSystem seam (task 1176 R2; same class as the quality-gate exemption above)
             - "packages/app/src/services/run-storage.ts" # durable-evidence migration core (task 1025 R4): atomic tmp+rename byte copies with digest reread and atomic manifest publish must stay byte-stable (mirrors agent-usage-producer.ts / project-registry.ts exemptions)
 
             # Electron Node adapters cannot load Bun runtime implementations; keep the

package/config/script-placement-baseline.json

@@ -16,32 +16,14 @@
             "reason": "Keep (budget exemption; reviewed W4) (plan \u00a72)",
             "exempt": true
         },
-        "plugins/sp/scripts/feature-verification-steps.ts": {
-            "kinds": ["budget"],
-            "reason": "Keep (ADR-119 receipt writer; budget exemption) (plan \u00a72)",
-            "exempt": true
-        },
         "plugins/sp/scripts/wrapup-drift-probe.ts": {
             "kinds": ["budget", "corpus-parse"],
             "reason": "Keep (glue over capture file; budget exemption) (plan \u00a72)",
             "exempt": true
         },
         "plugins/sp/scripts/daily-summary/daily-summary.ts": {
-            "kinds": ["budget", "db-import"],
-            "reason": "Keep (daily-summary/, plan \u00a72); read-only history-health query via dynamic bun:sqlite import (task 1018)"
-        },
-        "plugins/sp/scripts/dogfood-testing/detect-pipeline-driving.ts": {
             "kinds": ["budget"],
-            "reason": "Keep (dogfood-testing/, plan \u00a72)"
-        },
-        "plugins/sp/scripts/dogfood-testing/validate-report.ts": {
-            "kinds": ["budget"],
-            "reason": "Keep (dogfood-testing/, plan \u00a72)"
-        },
-        "plugins/sp/hooks/context-post-tool.ts": {
-            "kinds": ["budget"],
-            "reason": "Keep: ADR-129 core (budget exemption) (plan \u00a72)",
-            "exempt": true
+            "reason": "Keep (daily-summary/, plan \u00a72); read-only history-health reads via the app service (task 1178)"
         },
         "plugins/sp/hooks/pi/guard-extension.ts": {
             "kinds": ["budget"],

package/config/workflows/feature-lifecycle.yaml

@@ -9,7 +9,7 @@
 "$schema": "@gobing-ai/spur/schemas/state-machine-workflow.schema.json"
 kind: state-machine
 name: feature-lifecycle
-version: "2"
+version: "3"
 description: >
   Feature lifecycle FSM (design §2.3, §5.1, DD-13). States are the canonical
   FeatureStatus vocabulary; transitions encode the §2.3 graph including the
@@ -64,6 +64,11 @@ states:
     description: Completed and verified.
   - id: cancelled
     description: Terminal — abandoned.
+  - id: deprecated
+    description: >
+      Retained and frozen (ADR-136). Non-terminal: the record stays readable and
+      countable, nothing may attach new work to it, and leaving it is explicit —
+      un-deprecate to active, or cancelled once the feature is removed.
 
 transitions:
   # Forward path: backlog → active → verifying → done
@@ -142,3 +147,43 @@ transitions:
     description: Cancel feature
     guard:
       kind: always
+
+  # Deprecate: any non-terminal-or-done state → deprecated (frozen, retained — ADR-136)
+  - from: backlog
+    to: deprecated
+    description: Deprecate feature (frozen, retained)
+    guard:
+      kind: always
+  - from: active
+    to: deprecated
+    description: Deprecate feature (frozen, retained)
+    guard:
+      kind: always
+  - from: verifying
+    to: deprecated
+    description: Deprecate feature (frozen, retained)
+    guard:
+      kind: always
+  - from: blocked
+    to: deprecated
+    description: Deprecate feature (frozen, retained)
+    guard:
+      kind: always
+  - from: done
+    to: deprecated
+    description: Deprecate feature (frozen, retained)
+    guard:
+      kind: always
+
+  # Exits out of deprecated: un-deprecate or remove only. Any other edge is
+  # undeclared and refused by the graph (ADR-135).
+  - from: deprecated
+    to: active
+    description: Un-deprecate (mandatory History entry)
+    guard:
+      kind: always
+  - from: deprecated
+    to: cancelled
+    description: Remove deprecated feature
+    guard:
+      kind: always

package/config/workflows/feature-verification.yaml

@@ -10,6 +10,17 @@
 #
 # Run: spur workflow run feature-verification.yaml --vars '{"featureId":"D63"}'
 #
+# No project-side override is required (task 1185, A33). Since the pass moved into the
+# application (1176 / efd78f058) the bundled definition owns it end to end, so a
+# project-layer copy of this file (plus a rooted port under `.spur/scripts/`) is a
+# leftover — the port was written against an entry export contract that has since
+# changed. Remove the override so this definition applies, or migrate the port to the
+# current app-owned operation `runFeatureVerification` (the generated inline bundle's
+# export). If a stale consumer is still reached, feature-lifecycle's `verifying` entry
+# names it: the override path, the consumer script, the export it requires that the
+# shipped entry no longer provides, and the entry path. Reinstalling or upgrading the
+# plugin cannot supply a retired export — only the two remedies above can.
+#
 # Shape: verify -> done | failed. The onEnter step runs the standard script
 # `feature-verification-steps.ts` (no public CLI verb, D63 task 0915): it
 # resolves this very definition for the verifier identity (name, source path,

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.4.2",
+    "version": "0.4.3",
     "description": "Spur CLI — local-first harness for mainstream coding agents: constraint checking, workflow orchestration, agent health, and history analytics. Bun-native; exposes the `spur` command.",
     "keywords": [
         "spur",
@@ -57,14 +57,14 @@
     },
     "devDependencies": {
         "@commander-js/extra-typings": "^14.0.0",
-        "@gobing-ai/ts-db": "^0.5.22",
-        "@gobing-ai/ts-ai-runner": "^0.5.22",
-        "@gobing-ai/ts-dual-workflow-engine": "^0.5.22",
-        "@gobing-ai/ts-infra": "^0.5.22",
-        "@gobing-ai/ts-llm-jsonl-importer": "^0.5.22",
-        "@gobing-ai/ts-rule-engine": "^0.5.22",
-        "@gobing-ai/ts-runtime": "^0.5.22",
-        "@gobing-ai/ts-utils": "^0.5.22",
+        "@gobing-ai/ts-db": "^0.5.24",
+        "@gobing-ai/ts-ai-runner": "^0.5.24",
+        "@gobing-ai/ts-dual-workflow-engine": "^0.5.24",
+        "@gobing-ai/ts-infra": "^0.5.24",
+        "@gobing-ai/ts-llm-jsonl-importer": "^0.5.24",
+        "@gobing-ai/ts-rule-engine": "^0.5.24",
+        "@gobing-ai/ts-runtime": "^0.5.24",
+        "@gobing-ai/ts-utils": "^0.5.24",
         "@types/bun": "1.3.14",
         "@types/figlet": "^1.7.0",
         "@types/node-notifier": "8.0.5",

package/plugins/sp/README.md

@@ -272,15 +272,18 @@ plugins/sp/
 │   └── wayfinder/                   # Multi-session investigation maps (SKILL.md only)
 ├── commands/                        # Slash-command wrappers — the SSOT (hand-editable thin wrappers; see Commands below)
 ├── agents/                          # 4 specialist subagents (expert-spur, super-coder, super-planner, super-reviewer)
-├── hooks/                           # hooks.json + task-write-guard.{ts,test.ts} + context-{session-start,post-tool,session-stop}.ts
-│                                    # + agent-lifecycle.{ts,test.ts} + fleet-guest-stop.{ts,test.ts} (fleet member/guest hooks)
-│                                    # + careful-guard.{ts,test.ts} + context-hooks.test.ts + token-estimate.test.ts
-│                                    # + shared policy modules: agent-hint.ts, destructive-policy.{ts,test.ts}, task-file-policy.{ts,test.ts}
-│                                    # + pi/guard-extension.{ts,test.ts} (plugin.json `extensions.pi` entry point)
+├── hooks/                           # hooks.json + one thin entry per registered identity
+│                                    # + task-write-guard.ts (compat shim) + careful-guard.ts (opt-in, unwired)
+│                                    # + pi/guard-extension.ts (plugin.json `extensions.pi` entry point)
+│                                    # entries delegate to lib cores (task 1174); hook suites live in tests/hooks/
+├── lib/                             # Handwritten plugin cores — context-{post-tool,session-start,session-stop}.ts,
+│                                    # agent-hint.ts, context-owner.ts, destructive-policy.ts, task-file-policy.ts,
+│                                    # env.ts, plus generated *.generated.mjs|.d.mts bundles over packages/app
 ├── scripts/                         # Executable helpers, split from prompts (ADR-031) — batch-preflight.ts + scripts/<skill>/
-│                                    # (daily-summary: {daily-summary, logger}.ts; dogfood-testing: {detect-pipeline-driving, validate-report}.ts)
-├── tests/                           # Plugin tests — skill-structure.test.ts + batch-preflight.test.ts + per-skill suites (command-contract moved to scripts/commands/)
-├── evals/                           # Skill behavioral eval harness (scenarios + judge + run-eval runner)
+│                                    # (daily-summary: daily-summary.ts; dogfood-testing: {detect-pipeline-driving, validate-report}.ts)
+├── tests/                           # Plugin tests — skill-structure.test.ts + hooks/ (guard, context, Pi suites)
+│                                    # + evals/ (behavioral eval corpus + judge; see tests/evals/README.md,
+│                                    # runner at scripts/commands/skill-eval.ts) + per-skill suites
 ├── plugin.json                      # Marketplace entry
 └── README.md                        # This file
 ```
@@ -512,8 +515,9 @@ hint on first launch, and `context-session-stop` closes out the session record.
 `SPUR_SPEC_ID` is set, so outside a fleet it makes no call. `fleet-guest-stop` delivers pending
 inbox work to a session joined as a fleet guest at turn end; any other session passes through.
 
-**Available but unwired:** `careful-guard.ts` ships in `hooks/` (with tests) as an opt-in
-`PreToolUse` guard that asks before destructive shell commands (`rm -rf`, `DROP TABLE`,
+**Available but unwired:** `careful-guard.ts` ships in `hooks/` (its suite is
+`tests/hooks/careful-guard.test.ts`) as an opt-in `PreToolUse` guard that asks before destructive
+shell commands (`rm -rf`, `DROP TABLE`,
 `git push --force`, …) — it is **not** registered in `hooks.json`. Fail-open by contract; escape
 hatch `SPUR_CAREFUL=off`.
 
@@ -529,19 +533,21 @@ hold `SKILL.md` and prompt-side companions only.
 | Script                                               | Role                                                                                                                                                                                                                                                                                              |
 | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `hooks/task-write-guard.ts`                          | Compatibility shim for older installs that still execute the script path directly. Forwards stdin to the stable PATH command `superskill hook run sp task-write-guard`, mirrors parseable PreToolUse decisions, and fails open if the runtime is unavailable. Performs no source-tree CLI lookup. |
-| `hooks/context-*.ts`                                 | Runtime for the three registered context hooks (session-start, post-tool, session-stop) — token-cost estimation + ledger append for `sp:indexed-context`                                                                                                                                          |
+| `hooks/context-*.ts`                                 | argv/stdin entries for the three registered context hooks; the capture, ledger and session logic is the `lib/context-*.ts` core (task 1174)                                                                                                                                                        |
 | `hooks/{agent-lifecycle,fleet-guest-stop}.ts`       | Fleet hooks (1080/1081): member lifecycle reports via `spur agent report`; turn-end inbox delivery to joined guests |
-| `hooks/careful-guard.ts`                             | Opt-in destructive-command guard (unwired — see Hooks above)                                                                                                                                                                                                                                      |
+| `hooks/careful-guard.ts`                             | Opt-in destructive-command guard (unwired — see Hooks above); policy is `lib/destructive-policy.ts`                                                                                                                                                                                                |
+| `lib/context-{post-tool,session-start,session-stop}.ts` | Redaction-capped ledger append, session open/ownership and owner-gated teardown for `sp:indexed-context`                                                                                                                                                                                       |
+| `lib/{agent-hint,context-owner,destructive-policy,task-file-policy}.ts` | Shared hook cores — agent/model hint resolution, host-native session owner derivation, destructive-command classification, task-file matching                                                                                                                              |
 | `scripts/batch-preflight.ts`                         | Pure TABLE A STOP evaluation for `super-planner` — skip doomed pipeline launches without spawning a Skill subprocess; recovery hints map stuck statuses to a single `/sp:dev-*` hop                                                                                                               |
 | `scripts/workflow-step-profile.ts`                   | Thin glue over the generated lib bundle (`lib/step-profile.generated.mjs` from `packages/app/src/workflow/step-profile.ts`) — read-only step profile from `spur workflow trace`: per node and action-kind durations, idle gaps, session mode and `cacheHit` coverage, plus the ADR-115 cache-window flags `sp:spur-doctor` turns into workflow-optimization proposals |
-| `scripts/dogfood-testing/detect-pipeline-driving.ts` | Word-boundary detector for pipeline-driving testees (leading-space invariant)                                                                                                                                                                                                                     |
-| `scripts/dogfood-testing/validate-report.ts`         | Pure `validateReport(md)` — footer-mandatory + 7-check finalize-or-abort contract with stable error codes                                                                                                                                                                                         |
-| `scripts/daily-summary/{daily-summary,logger}.ts`    | ccusage + git-history orchestration helpers for `sp:daily-summary`                                                                                                                                                                                                                                |
+| `scripts/dogfood-testing/detect-pipeline-driving.ts` | Live Phase 1.0 CLI gate over `lib/dogfood-pipeline.ts` — word-boundary detector for pipeline-driving testees (leading-space invariant)                                                                                                                                  |
+| `scripts/dogfood-testing/validate-report.ts`         | CLI entry over `lib/dogfood-report.ts` — pure `validateReport(md)`, footer-mandatory + 7-check finalize-or-abort contract with stable error codes                                                                                                                |
+| `scripts/daily-summary/daily-summary.ts`               | ccusage + git-history orchestration helpers for `sp:daily-summary`, with its own console toggle                                                                                                                                                                                                  |
 | `scripts/task-diffstat.ts`                           | 0943 triage-lane diffstat producer — numstat + untracked scan vs the run base; writes `<wbs>-diffstat.json` with the sensitive-path flag; fails safe (sensitive)                                                       |
 | `scripts/run-summary.ts`                             | Measured execution summary `/sp:dev-run` / `/sp:dev-runall` print by default (`--no-summary` skips) — windows the host transcript by `spur workflow progress` attempt timestamps; per stage/run time, wait, tool calls, total / non-cached tokens; `n/a` for subprocess windows |
 | `scripts/session-timeline.ts`                        | Measured Time/Wait/Token evidence for `sp:session-review` — reads the active Claude Code transcript read-only, one segment per operator prompt, usage deduplicated by message id, tokens split total / non-cached; `{available:false}` exit 0 when no transcript |
 | `scripts/commands/validate-flag-contracts.ts`        | Mechanical consistency gate — compares flag claims across command files, flag-glossary, cross-cutting, dev-operations, and ADR; reports disagreements                                                                                    |
-| `*.test.ts`                                          | Unit suites — in `hooks/` for guards, in `tests/<skill>/` per ADR-031 pairing                                                                                                                                                                                                                     |
+| `*.test.ts`                                          | Unit suites — `tests/hooks/` for the hook entries and their lib cores, `tests/<skill>/` per ADR-031 pairing                                                                                                                                                                                        |
 
 **Design principle:** Scripts are **deterministic enforcement**. Unlike skills (which are advisory
 knowledge consumed by the LLM), scripts run as code and make binary allow/deny decisions. They are

package/plugins/sp/agents/super-reviewer.md

@@ -200,6 +200,7 @@ shallower.
 **Scope:** <wbs diff | path glob>
 **Dimensions:** functional, security, efficiency, correctness, usability, architecture
 **Verdict:** PASS | PARTIAL | FAIL
+**Confidence:** HIGH | MEDIUM | LOW
 ##### Findings (ranked)
 
 | # | Priority | Dimension | Finding | Location | Disposition |
@@ -225,6 +226,48 @@ FAIL, PARTIAL, a missing line, a line split across two lines — routes the run
 `review-fail-triage` and its bounded repair hop. Keep it on one line, in that shape, in every
 review answer; never restate it as prose only.
 
+**The Confidence line is machine-read too (one confidence contract, 2026-10-12).** Every review
+report carries exactly one `Confidence: HIGH | MEDIUM | LOW` line, stated at the level the review can
+actually defend — the same enum and the same earning rule the verify answer uses
+([verdict-schema.md](../skills/code-verification/references/verdict-schema.md) § Confidence level):
+
+- `HIGH` — every requirement row is `MET`, every finding carries a disposition, and the report cites
+  its evidence. `HIGH` says the evidence needs no re-check.
+- `MEDIUM` — the verdict holds but evidence gaps remain; name them.
+- `LOW` — the verdict rests on unverified assumptions that could plausibly flip it; name them.
+
+A missing line, a level outside the enum, or a `HIGH` the rows do not earn turns an otherwise usable
+PASS into a refused one: consumer repositories gate the review answer artifact and every level it
+claims, exactly as they gate the verify answer. This is a contract change — review answers written
+before it were never asked for a level, so pre-adoption artifacts read as debt, not defects.
+
+**Machine-checked at the gate.** The pipeline's own review PASS edges enforce the line before verify:
+`residual-scan review-gate` reads the recorded `### Review` body, and a missing, duplicated or
+out-of-enum level becomes a **blocking** `review-contract` item — `review → verify` stops and the run
+enters `review-fail-triage` with the bounded repair hop, exactly as an open P1–P3 row does. The gate
+checks presence and vocabulary only: whether a level is *earned* stays a judgement call (see the
+earning rule above), so the report must still argue it.
+
+**Source citations for external claims (one claim contract, 2026-10-12).** A Finding cell or a
+Functional Traceability `Evidence` cell that asserts an external API/library claim carries a
+verifiable citation in the SAME cell — a repo `path:line(-end)`, the external named-origin form
+(@origin `path` line N, line number outside the backticks), or an http(s) URL. It is the verify
+answer's rule verbatim, owned by
+[verdict-schema.md](../skills/code-verification/references/verdict-schema.md) § Source citations
+for external claims — claim markers and accepted forms are defined once there and are not restated
+here. The findings table's `Location` column does not stand in for it: `Location` anchors the
+finding's subject, not the claim's source. Cell-free receipts (test counts, reviewed-log notes)
+assert no external claim and need no citation. An uncited external claim is an assumption, so it
+caps the level the report can defend (above).
+
+**Machine-checked at the gate (findings table).** `residual-scan review-gate` applies the same two
+predicates to every finding row: a Finding cell carrying one of the verify lint's claim markers with
+no citation form becomes a **blocking** `review-contract` item, so `review → verify` stops and the
+run enters `review-fail-triage`. The `Location` column is deliberately not consulted as a citation —
+that is the rule stated above, and a gate that accepted it would pass every row that has an anchor.
+Functional Traceability `Evidence` cells stay reviewer-enforced (SECUA review): they are free prose
+in a table the gate does not parse.
+
 **No findings.** Never invent a defect to populate the table. Emit one substantive `P4 (advisory)`
 row that states what was reviewed and what was found — placeholder cells (empty, `—`, `n/a`) are
 rejected by the checker, and so they should be:

package/plugins/sp/bunfig.toml

@@ -1,8 +1,11 @@
 # Workspace-local test config (task 1127 R8/AC7, mirroring apps/cli's 0699 R3 precedent): without
-# it, `cd plugins/sp && bun test` — the run AGENTS.md prescribes — skipped the root preload and
-# resolved the operator's real ~/.config/spur/run/full-gate.lock. These suites then waited silently
-# behind any live host-wide gate holder (their holder line is swallowed by `silenceStdout`), which
-# is the dispatch-budget burn this task exists to remove. Coverage stays gated by the root bunfig
-# (bun run test).
+# it, `cd plugins/sp && bun test` — the run AGENTS.md prescribes — skipped the root preload, so these
+# suites lost the shared test setup (logger muting, the util shims, and the hermeticity env that keeps
+# tests off the operator's real ~/.config/spur/ config, projects registry and slash-command catalog).
+# Coverage stays gated by the root bunfig (bun run test).
+#
+# Historical: this comment once justified the preload by a host-wide `full-gate.lock` wait. That lock
+# was deleted in `refactor(gate): remove gate-lock mechanism and simplify quality-gate`; the preload
+# is still required, for the reasons above (task 1173 R5).
 [test]
 preload = ["../../tests/setup.ts"]

package/plugins/sp/hooks/careful-guard.ts

@@ -22,8 +22,8 @@
  * adapter. This file owns the Claude Code payload/decision shape only.
  */
 
+import { classifyCommand } from '../lib/destructive-policy';
 import { getEnvVar } from '../lib/env';
-import { classifyCommand } from './destructive-policy';
 
 interface ToolPayload {
     tool_name?: string;