@gobing-ai/spur 0.3.73 → 0.3.74

package/config/workflows/wrapup-pipeline.yaml

@@ -17,7 +17,10 @@
 #          -> feature-transition (conditional: if vars.feature set)
 #          -> branch-cleanup (conditional: if vars.merge=true)
 #          -> done
-#        (task-resolve with empty list short-circuits to `skipped`).
+#        task-resolve with a VALIDATED empty list short-circuits to `skipped`;
+#        invalid wrap input, an unresolved/non-completed task, a failed metrics
+#        capture, a failed required sync, or a failed feature gate routes to
+#        `failed` (0770) instead of being absorbed by an always-defensive skip.
 #
 # Vars (passed as a JSON object via `--vars`):
 # tasks    — JSON array of WBS strings, passed as a JSON-encoded STRING value
@@ -39,21 +42,33 @@
 # a
 # single model query that both repairs doc drift (sp:doc-evolve) and captures
 #     working learnings (task 0607 R2 — one query answers both; count 2 -> 1).
-# - feature-transition is a soft shell (always exit 0) so a blocked feature sync
-#     does not abort wrap-up after learnings/metrics already landed.
+# - feature-transition is a soft shell (always exit 0); a failed required sync
+#     or feature gate records FAIL and routes to `failed` instead of claiming
+#     success (0770).
+# - 0770 truthful outcomes: vars.tasks is parsed and validated ONCE at
+#     task-resolve (JSON array of non-empty WBS strings, every member resolved
+#     via `task show` to a completed status); siblings consume the normalized
+#     run-scoped artifact and never re-parse raw input (malformed input can no
+#     longer be silently re-interpreted as an empty list). All captures are
+#     run-scoped under .spur/run/<runId>-wrapup-*; a lookup failure is
+#     recorded, never silently omitted as success.
 # - branch-cleanup HITL is exhaustive (yes/no/cancel → done; missing answer
-# defense).
+# defense) and consent-only: it records the decision, performs no git op.
 #   - Wrap-up never mutates task status (consumes completed work only).
 
 "$schema": "@gobing-ai/spur/schemas/state-machine-workflow.schema.json"
 kind: state-machine
 name: wrapup-pipeline
+version: "1"
 description: "Post-execution wrap-up: doc-sync (doc drift + learning capture), metrics, feature-transition, branch-cleanup"
 iterationBound: 10
 initialState: start
 terminalStates:
   - done
   - skipped
+  - failed
+failureStates:
+  - failed
 vars:
   tasks: "[]"
   feature: ""
@@ -64,22 +79,11 @@ vars:
   __runId: ""
   mode: ""
   stepTimeoutMs: "1800000"
-  # Corpus-aware quality gate for the feature-transition hop (R1, task 0625).
-  # The per-task gate (`spur-check`) deliberately excludes corpus-check — the
-  # only
-  # sweep that observes feature-level findings — so a transition that arms one
-  # would go green. This gate is therefore the CORPUS SWEEP ALONE (~29 s), not
-  # `spur-check-new`: every task in the feature already paid a full `spur-check`
-  # in its own pipeline, and the states that run before this hop (`doc-sync`,
-  # `metrics-record`) write only markdown and task sections, which Biome skips
-  # (`ignoreUnknown: true`). Re-running the ~105 s per-task gate here
-  # re-verifies
-  # unchanged code and measures nothing new. Soft by design: the gate reports
-  # PASS/FAIL and lets the operator decide; it never hard-fails the wrap-up
-  # shell.
+  # Recheck the affected feature after sync (D61 / ADR-108), not the corpus
+  # or full code suite. Explicit caller overrides remain supported.
   # TRUSTED CONFIG ONLY — this string is executed via `sh -c` (same surface as
   # task-pipeline's qualityGateCmd). Never interpolate untrusted input into it.
-  featureGateCmd: "bun run corpus-check"
+  featureGateCmd: '$spurBin feature check "$feature"'
   __hitlAnswer: ""
 
 states:
@@ -94,10 +98,17 @@ states:
 
   - id: task-resolve
     description: >
-      Validate the task list and evaluate closed proportional routing (0758 R1-R4).
-      Empty list -> skipped; tasks > 0 && mode == fast -> fast-path (metrics-record,
-      bypassing doc-sync); missing/unknown/conflict -> doc-sync (safety-path).
-      Writes bounded machine-readable reason to reasonFile.
+      Validate the task list ONCE and evaluate closed proportional routing (0758
+      R1-R4). Validation (0770): vars.tasks must be a JSON array of non-empty
+      WBS strings, deduplicated in first-seen order, and every member must
+      resolve via `spur task show` to a completed status (done/cancelled).
+      Invalid input or an unresolved/non-completed task records FAIL (reason
+      into the run-scoped reason file) and routes to `failed`; siblings consume
+      the normalized run-scoped artifact .spur/run/<runId>-wrapup-tasks.json
+      and never re-parse raw input. A validated empty list -> skipped;
+      tasks > 0 && mode == fast -> fast-path (metrics-record, bypassing
+      doc-sync); missing/unknown/conflict -> doc-sync (safety-path). Writes
+      bounded machine-readable reason to reasonFile.
     onEnter:
       - kind: note
         options:
@@ -130,6 +141,49 @@ states:
             printf '%s %s\n' "$RUN_ID" "$(cat "$REASON_FILE")"
             >> .spur/memory/wrapup-routes.log &&
             exit 0
+      # 0770 truthful input: parse and validate vars.tasks exactly once, here.
+      # Malformed JSON, a non-array, a non-string or empty entry, an unresolved
+      # task, or a task not at a completed status records FAIL (routed to
+      # `failed` by the first declared edge) and is never re-interpreted as an
+      # empty list by a later sibling guard. The normalized, deduplicated list
+      # is persisted run-scoped; metrics/doc siblings only ever read it.
+      - kind: shell
+        options:
+          command: >-
+            mkdir -p .spur/run &&
+            RUN_ID="$__runId" &&
+            if [ -z "$RUN_ID" ]; then
+              echo "task-resolve: __runId is empty — refusing the legacy fixed-path fallback" >&2;
+              exit 1;
+            fi &&
+            REASON_FILE=".spur/run/$RUN_ID-route-reason.txt" &&
+            STATUS_FILE=".spur/run/$RUN_ID-wrapup-resolve.status" &&
+            TASKS_FILE=".spur/run/$RUN_ID-wrapup-tasks.json" &&
+            if ! printf '%s' "$tasks" | jq -e 'type == "array" and all(.[]; type == "string" and length > 0)' > /dev/null 2>&1; then
+              echo "task-resolve: tasks must be a JSON array of non-empty WBS strings" >&2;
+              echo "failed:tasks is not a JSON array of non-empty WBS strings" > "$REASON_FILE";
+              printf 'FAIL\n' > "$STATUS_FILE";
+            else
+              printf '%s' "$tasks" | jq -c 'reduce .[] as $w ([]; if any(.[]; . == $w) then . else . + [$w] end)' > "$TASKS_FILE";
+              RESOLVE_RC=0;
+              for wbs in $(jq -r '.[]' "$TASKS_FILE"); do
+                TASK_JSON=$($spurBin task show "$wbs" --json 2>/dev/null || true);
+                TASK_STATUS=$(printf '%s' "$TASK_JSON" | jq -r '.frontmatter.status // .status // empty' 2>/dev/null || true);
+                if [ "$TASK_STATUS" != "done" ] && [ "$TASK_STATUS" != "cancelled" ]; then
+                  STATUS_DISPLAY="$TASK_STATUS";
+                  if [ -z "$STATUS_DISPLAY" ]; then STATUS_DISPLAY=unresolved; fi;
+                  echo "task-resolve: task $wbs did not resolve to a completed status (status=$STATUS_DISPLAY)" >&2;
+                  RESOLVE_RC=1;
+                fi;
+              done;
+              if [ "$RESOLVE_RC" -eq 0 ]; then
+                printf 'PASS\n' > "$STATUS_FILE";
+              else
+                echo "failed:unresolved or non-completed task (see $TASKS_FILE)" > "$REASON_FILE";
+                printf 'FAIL\n' > "$STATUS_FILE";
+              fi;
+            fi;
+            exit 0
 
   - id: doc-sync
     description: >
@@ -150,59 +204,72 @@ states:
             docs/00_ADR.md, docs/03_ARCHITECTURE.md, docs/04_DESIGN.md, docs/design/* per constitution edit
             rules; do not write task/feature corpus. THEN extract working learnings from tasks ${vars.tasks} —
             conventions, errors fixed, patterns, gotchas, grouped by date and task WBS — as raw markdown
-            (no fences) and END your final message with that markdown (it is captured to .spur/run/wrapup-learnings.md).
+            (no fences) and END your final message with that markdown (it is captured to the
+            run-scoped .spur/run/${vars.__runId}-wrapup-learnings.md).
           # Declared Layer-1 role (0538 R2): routing reason beside the agent:
           # pin.
           role: coder
-          answerFile: .spur/run/wrapup-learnings.md
-          expectFile: .spur/run/wrapup-learnings.md
+          answerFile: .spur/run/${vars.__runId}-wrapup-learnings.md
+          expectFile: .spur/run/${vars.__runId}-wrapup-learnings.md
           timeoutMs: ${vars.stepTimeoutMs}
       - kind: shell
         options:
           command: >-
-            mkdir -p .spur/memory &&
-            if test -s .spur/run/wrapup-learnings.md; then
-              cat .spur/run/wrapup-learnings.md >> .spur/memory/learnings.md &&
+            mkdir -p .spur/run .spur/memory &&
+            LEARNINGS_FILE=".spur/run/$__runId-wrapup-learnings.md" &&
+            if test -s "$LEARNINGS_FILE"; then
+              cat "$LEARNINGS_FILE" >> .spur/memory/learnings.md &&
               printf '\n' >> .spur/memory/learnings.md;
             else
-              echo "wrapup: learning capture missing or empty at $PWD/.spur/run/wrapup-learnings.md - append skipped" >&2;
+              echo "wrapup: learning capture missing or empty at $PWD/$LEARNINGS_FILE - append skipped" >&2;
             fi &&
             exit 0
 
   - id: metrics-record
     description: >
       Append one JSONL row per task to .spur/memory/wrapup-metrics.jsonl deterministically.
+      Reads ONLY the normalized run-scoped task list written by task-resolve (0770):
+      a lookup failure for any member records FAIL and routes to `failed` — a
+      missing metrics row is never silently absorbed as success.
     onEnter:
       - kind: shell
         options:
           command: >-
-            mkdir -p .spur/memory &&
-            printf '%s' "$tasks" | jq -r '(if type == "string" then (try fromjson catch .) else . end) | if type == "array" then .[] else empty end' |
-            while IFS= read -r wbs; do
-              if [ -n "$wbs" ]; then
-                task_json=$($spurBin task show "$wbs" --json 2>/dev/null || true);
-                if [ -n "$task_json" ]; then
-                  feat=$(printf '%s' "$task_json" | jq -r '.frontmatter.feature_id // .feature_id // empty' 2>/dev/null || true);
-                  stat=$(printf '%s' "$task_json" | jq -r '.frontmatter.status // .status // "unknown"' 2>/dev/null || true);
-                  verdict="UNKNOWN";
-                  if [ -f ".spur/run/$wbs-verdict.json" ]; then
-                    v=$(jq -r '.verdict // "UNKNOWN"' ".spur/run/$wbs-verdict.json" 2>/dev/null || true);
-                    if [ -n "$v" ]; then verdict="$v"; fi;
-                  fi;
-                  ts=$(date -u +"%Y-%m-%dT%H:%M:%SZ");
-                  printf '{"wbs":"%s","feature_id":"%s","status":"%s","verdict":"%s","timestamp":"%s"}\n' "$wbs" "$feat" "$stat" "$verdict" "$ts" >> .spur/memory/wrapup-metrics.jsonl;
+            mkdir -p .spur/run .spur/memory &&
+            STATUS_FILE=".spur/run/$__runId-wrapup-metrics.status" &&
+            TASKS_FILE=".spur/run/$__runId-wrapup-tasks.json" &&
+            METRICS_RC=0 &&
+            for wbs in $(jq -r '.[]' "$TASKS_FILE" 2>/dev/null); do
+              task_json=$($spurBin task show "$wbs" --json 2>/dev/null || true);
+              if [ -n "$task_json" ]; then
+                feat=$(printf '%s' "$task_json" | jq -r '.frontmatter.feature_id // .feature_id // empty' 2>/dev/null || true);
+                stat=$(printf '%s' "$task_json" | jq -r '.frontmatter.status // .status // "unknown"' 2>/dev/null || true);
+                verdict="UNKNOWN";
+                if [ -f ".spur/run/$wbs-verdict.json" ]; then
+                  v=$(jq -r '.verdict // "UNKNOWN"' ".spur/run/$wbs-verdict.json" 2>/dev/null || true);
+                  if [ -n "$v" ]; then verdict="$v"; fi;
                 fi;
+                ts=$(date -u +"%Y-%m-%dT%H:%M:%SZ");
+                printf '{"wbs":"%s","feature_id":"%s","status":"%s","verdict":"%s","timestamp":"%s"}\n' "$wbs" "$feat" "$stat" "$verdict" "$ts" >> .spur/memory/wrapup-metrics.jsonl;
+              else
+                echo "metrics-record: task $wbs did not resolve — recording FAIL instead of silently omitting its metrics row" >&2;
+                METRICS_RC=1;
               fi;
-            done &&
+            done;
+            if [ "$METRICS_RC" -eq 0 ]; then printf 'PASS\n' > "$STATUS_FILE"; else printf 'FAIL\n' > "$STATUS_FILE"; fi;
             exit 0
 
   - id: feature-transition
     description: >
       If vars.feature is set, sync feature status via bounded feature-sync-bounded
-      (0411). Soft shell — blocked/failed sync must not abort wrap-up after metrics.
-      Empty vars.feature is NOT a blocked sync but a mis-invocation (the engine only
-      enters this state when vars.feature is set) and fails loud (dogfood 2026-08-15,
-      feature I3: a silent exit 0 made the wrap look complete with no transition).
+      (0411). Soft shell — the run is never aborted after learnings/metrics
+      landed; instead (0770) a failed required sync or a failed feature gate
+      records FAIL in the run-scoped sync status and routes to `failed`, and a
+      successful sync that applied no transition is reported as an explicit
+      no-change. Empty vars.feature is NOT a blocked sync but a mis-invocation
+      (the engine only enters this state when vars.feature is set) and fails
+      loud (dogfood 2026-08-15, feature I3: a silent exit 0 made the wrap look
+      complete with no transition).
     onEnter:
       # Genuinely soft: the terminating `exit 0` must be reached on BOTH
       # branches, so
@@ -217,11 +284,12 @@ states:
       # path (`spur init` does not scaffold `plugins/sp/`), so seeded projects
       # fall
       # back to the plain `spur feature sync` verb.
-      # R1 (0625): a feature transition that changed state may have armed a
-      # feature-level finding the per-task fast gate (spur-check) never sees.
-      # Run the corpus-aware gate after an applied sync OR a non-zero exit that
-      # may follow a partial multi-hop transition, then report PASS/FAIL. Soft
-      # by design: the operator decides, and wrap-up never hard-fails here.
+      # R1 (0625): a feature transition that changed state may have left
+      # cross-task fallout the per-task fast gates never see. Run the
+      # affected-feature gate (featureGateCmd) after an
+      # applied sync OR a non-zero exit that may follow a partial multi-hop
+      # transition, then report PASS/FAIL. Soft by design: the operator
+      # decides, and wrap-up never hard-fails here.
       # NOTE: do not add
       # `#` comments INSIDE the folded shell string — YAML `>-` folds them onto
       # the following statement line and comments it out.
@@ -241,24 +309,41 @@ states:
             fi);
             SYNC_RC=$?;
             printf '%s\n' "$SYNC_OUTPUT";
-            APPLIED=$(printf '%s' "$SYNC_OUTPUT" | jq -r '.applied // false' 2>/dev/null || echo false);
+            if printf '%s' "$SYNC_OUTPUT" | jq -e 'has("applied")' > /dev/null 2>&1; then
+              APPLIED=$(printf '%s' "$SYNC_OUTPUT" | jq -r '.applied // false' 2>/dev/null || echo false);
+            else
+              APPLIED="invalid";
+            fi;
+            GATE="skipped";
             if [ "$APPLIED" = "true" ] || [ "$SYNC_RC" -ne 0 ]; then
-              echo "feature-transition: sync applied or failed after a possible partial transition for $feature — running corpus-aware gate: $featureGateCmd";
+              echo "feature-transition: sync applied or failed after a possible partial transition for $feature — running feature gate: $featureGateCmd";
               if sh -c "$featureGateCmd"; then
-                echo "feature-transition: corpus-aware gate PASS for feature $feature";
+                GATE="PASS";
+                echo "feature-transition: feature gate PASS for feature $feature";
               else
-                echo "feature-transition: corpus-aware gate FAIL for feature $feature — inspect findings before reporting the transition complete" >&2;
+                GATE="FAIL";
+                echo "feature-transition: feature gate FAIL for feature $feature — inspect findings before reporting the transition complete" >&2;
               fi;
             else
-              echo "feature-transition: sync did not apply a transition (rc=$SYNC_RC, applied=$APPLIED) — corpus-aware gate skipped";
+              echo "feature-transition: sync did not apply a transition (rc=$SYNC_RC, applied=$APPLIED) — feature gate skipped (explicit no-change)";
+            fi;
+            SYNC_STATUS="PASS";
+            if [ "$SYNC_RC" -ne 0 ] || [ "$GATE" = "FAIL" ] || [ "$APPLIED" = "invalid" ]; then SYNC_STATUS="FAIL"; fi;
+            if [ "$SYNC_STATUS" = "PASS" ]; then
+              printf 'PASS\n' > ".spur/run/$__runId-wrapup-sync.status";
+            else
+              printf 'FAIL\n' > ".spur/run/$__runId-wrapup-sync.status";
             fi;
             exit 0
 
   - id: branch-cleanup
     description: >
-      Irreversible HITL gate. If vars.merge=true, dispatch branch cleanup (merge or
-      delete). This gate ALWAYS pauses — even under --auto — because branch operations
-      are irreversible (Auto-Decision Principle #6). The operator must explicitly confirm.
+      Irreversible-operation HITL gate, consent-only (0770). If vars.merge=true,
+      branch cleanup (merge or delete) is a candidate — but this gate records
+      the operator decision and performs NO git operation itself; an operator
+      or a separate approved surface executes any actual merge/delete. This
+      gate ALWAYS pauses — even under --auto — because branch operations are
+      irreversible (Auto-Decision Principle #6).
     pause: true
     onEnter:
       - kind: hitl.confirm
@@ -267,12 +352,13 @@ states:
 
   - id: done
     description: >
-      Terminal — wrap-up complete. Output summary: tasks wrapped, learnings captured,
-      metrics recorded, feature advanced (if applicable), branch cleaned (if applicable).
+      Terminal — wrap-up complete. Summary: tasks wrapped, learnings captured,
+      metrics recorded, feature advanced or explicitly no-change (if applicable),
+      branch-cleanup decision recorded (consent-only; no git operation performed).
     onEnter:
       - kind: note
         options:
-          message: "Wrap-up pipeline complete for tasks: ${vars.tasks}. Learnings at .spur/memory/learnings.md, metrics at .spur/memory/wrapup-metrics.jsonl."
+          message: "Wrap-up pipeline complete for tasks: ${vars.tasks}. Learnings at .spur/memory/learnings.md, metrics at .spur/memory/wrapup-metrics.jsonl. Branch cleanup: consent recorded only (merge=${vars.merge}); no git operation performed by wrap-up."
       # Checkpoint write: record session state for resume (Phase 4, task 0171
       # R3)
       - kind: shell
@@ -282,6 +368,13 @@ states:
   - id: skipped
     description: Terminal — wrap-up skipped (empty task list or operator abort).
 
+  - id: failed
+    description: >
+      Terminal — wrap-up failed (0770): invalid wrap input, an unresolved or
+      non-completed task, a failed metrics capture, a failed required sync, or
+      a failed feature gate. Already-written artifacts (learnings, metrics
+      rows, route reason) are preserved; nothing is rolled back.
+
 transitions:
   # ── start -> task-resolve ──
   - from: start
@@ -290,7 +383,17 @@ transitions:
     guard:
       kind: always
 
-  # ── task-resolve: proportional route table (task 0758 R1-R4) ──
+  # ── task-resolve: validation fail + proportional route table (0758 R1-R4, 0770) ──
+  - from: task-resolve
+    to: failed
+    description: >
+      Validation FAIL (0770): malformed wrap input, a non-string/empty entry, an
+      unresolved or non-completed task, or an empty __runId. Declared before the
+      route edges so invalid input can never be absorbed by the empty-list skip.
+    guard:
+      kind: shell
+      options:
+        command: 'test "$(cat .spur/run/$__runId-wrapup-resolve.status 2>/dev/null)" = FAIL'
   - from: task-resolve
     to: skipped
     description: Task list is empty — skip wrap-up.
@@ -313,8 +416,10 @@ transitions:
       options:
         command: 'test "$(echo "$tasks" | jq length 2>/dev/null || echo 0)" -gt 0 && test "$mode" != fast'
   - from: task-resolve
-    to: skipped
-    description: Defense — task list unparseable; skip rather than fail with no-passing-transition.
+    to: failed
+    description: >
+      Defense (0770) — no PASS/FAIL resolve status (shell crashed or never ran):
+      route to `failed` rather than claiming a skip.
     guard:
       kind: always
 
@@ -325,47 +430,67 @@ transitions:
     guard:
       kind: always
 
-  # ── metrics-record: conditional routing based on feature and merge ──
-  # Declaration order matters: feature-transition is tried first (if feature is
-  # set),
-  # then branch-cleanup (if merge=true but no feature), then done (neither).
+  # ── metrics-record: fail edge, then conditional routing (feature → merge → done) ──
+  # Declaration order matters: the FAIL edge is tried first (0770), then
+  # feature-transition (if feature is set), then branch-cleanup (if merge=true
+  # but no feature), then done (neither). Routing edges additionally require
+  # the metrics status PASS so a missing status can never claim success.
+  - from: metrics-record
+    to: failed
+    description: >
+      Metrics capture failed for at least one task — a missing metrics row is
+      recorded as failure, never silently omitted as success (0770).
+    guard:
+      kind: shell
+      options:
+        command: 'test "$(cat .spur/run/$__runId-wrapup-metrics.status 2>/dev/null)" = FAIL'
   - from: metrics-record
     to: feature-transition
-    description: Feature id is set — advance feature through legal lifecycle edges.
+    description: Metrics PASS and feature id is set — advance feature through legal lifecycle edges.
     guard:
       kind: shell
       options:
-        command: 'test -n "$feature"'
+        command: 'test "$(cat .spur/run/$__runId-wrapup-metrics.status 2>/dev/null)" = PASS && test -n "$feature"'
   - from: metrics-record
     to: branch-cleanup
-    description: No feature id, but merge is requested — go to branch cleanup.
+    description: Metrics PASS, no feature id, but merge is requested — go to branch cleanup.
     guard:
       kind: shell
       options:
-        command: 'test -z "$feature" && test "$merge" = true'
+        command: 'test "$(cat .spur/run/$__runId-wrapup-metrics.status 2>/dev/null)" = PASS && test -z "$feature" && test "$merge" = true'
   - from: metrics-record
     to: done
-    description: No feature id and no merge — wrap-up is done.
+    description: Metrics PASS, no feature id and no merge — wrap-up is done.
     guard:
       kind: shell
       options:
-        command: 'test -z "$feature" && test "$merge" != true'
+        command: 'test "$(cat .spur/run/$__runId-wrapup-metrics.status 2>/dev/null)" = PASS && test -z "$feature" && test "$merge" != true'
 
-  # ── feature-transition: -> branch-cleanup (if merge) or done ──
+  # ── feature-transition: fail edge, then branch-cleanup (if merge) or done ──
+  - from: feature-transition
+    to: failed
+    description: >
+      Required synchronization failed (0770): non-zero sync exit, an invalid
+      sync result, or a failed feature gate. The failed status carries the
+      actual reason; already-written learnings/metrics stay on disk.
+    guard:
+      kind: shell
+      options:
+        command: 'test "$(cat .spur/run/$__runId-wrapup-sync.status 2>/dev/null)" = FAIL'
   - from: feature-transition
     to: branch-cleanup
-    description: Feature advanced — merge is requested.
+    description: Sync PASS — merge is requested.
     guard:
       kind: shell
       options:
-        command: 'test "$merge" = true'
+        command: 'test "$(cat .spur/run/$__runId-wrapup-sync.status 2>/dev/null)" = PASS && test "$merge" = true'
   - from: feature-transition
     to: done
-    description: Feature advanced — no merge requested.
+    description: Sync PASS — no merge requested.
     guard:
       kind: shell
       options:
-        command: 'test "$merge" != true'
+        command: 'test "$(cat .spur/run/$__runId-wrapup-sync.status 2>/dev/null)" = PASS && test "$merge" != true'
 
   # ── branch-cleanup: HITL exhaustive routing (yes / no / cancel → done) ──
   # No irreversible git op is wired yet; confirmation is recorded, then wrap

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.3.73",
+    "version": "0.3.74",
     "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",

package/plugins/sp/plugin.json

@@ -1,6 +1,6 @@
 {
     "name": "sp",
-    "version": "0.3.73",
+    "version": "0.3.74",
     "description": "Spur — a local-first harness engineering toolkit that wraps mainstream coding agents with constraint checking, workflow orchestration, and history analytics.",
     "extensions": {
         "pi": ["./hooks/pi/guard-extension.ts"]

package/plugins/sp/scripts/history-anatomy-cache.mjs

@@ -198,6 +198,7 @@ function parseProvenance(reportMarkdown) {
       contractDigest: String(obj.contractDigest ?? ""),
       skillDigest: String(obj.skillDigest ?? ""),
       workflowDigest: String(obj.workflowDigest ?? ""),
+      helperDigest: String(obj.helperDigest ?? ""),
       coverage: coverage.map((c) => ({
         source: String(c.source ?? ""),
         status: String(c.status ?? ""),
@@ -244,6 +245,8 @@ function decideCache(cached, current, opts) {
     reasons.push("logic-changed:skill");
   if (cached.workflowDigest !== current.workflowDigest)
     reasons.push("logic-changed:workflow");
+  if (cached.helperDigest !== current.helperDigest)
+    reasons.push("logic-changed:helper");
   const currentSources = new Set(current.coverage.map((c) => c.source));
   if (cached.coverage.some((c) => !currentSources.has(c.source)))
     reasons.push("coverage-degraded");
@@ -473,6 +476,7 @@ function buildProvenance(opts) {
     contractDigest: logicDigest(opts.contractFile),
     skillDigest: logicDigest(opts.skillDir),
     workflowDigest: logicDigest(opts.workflowFile),
+    helperDigest: logicDigest(opts.helperFile),
     coverage,
     runId: opts.runId,
     currentArtifactPath: opts.artifact,
@@ -503,6 +507,7 @@ var YAML_KEYS = [
   "contractDigest",
   "skillDigest",
   "workflowDigest",
+  "helperDigest",
   "runId",
   "currentArtifactPath",
   "baselineArtifactPath",
@@ -595,7 +600,7 @@ function diffPorcelain(before, now, expects) {
   return [...porcelainPaths(now)].filter((p) => !beforePaths.has(p) && !expects.has(p)).sort();
 }
 var VALID_COMMANDS = "digest, check, paths, assert-clean, probe, stamp, refresh, publish";
-var PROBE_USAGE = "<script> probe --artifact <a.json> --target <report.md> [--baseline <b.json>] [--mode daily|ad-hoc] " + "[--date <YYYY-MM-DD>] [--recompute true] [--out <prov.json>] [--skill-dir <d>] [--contract <f>] [--workflow <f>]";
+var PROBE_USAGE = "<script> probe --artifact <a.json> --target <report.md> [--baseline <b.json>] [--mode daily|ad-hoc] " + "[--date <YYYY-MM-DD>] [--recompute true] [--out <prov.json>] [--skill-dir <d>] [--contract <f>] [--workflow <f>] [--helper <f>]";
 function parseFlags(args) {
   const out = {};
   for (let i = 0;i < args.length; i++) {
@@ -729,6 +734,7 @@ ${result.problems.map((p) => `- ${p}
           skillDir: f["skill-dir"],
           contractFile: f.contract,
           workflowFile: f.workflow,
+          helperFile: f.helper,
           contractVersion: f["contract-version"],
           runId: f["run-id"],
           spurVersion: f["spur-version"]

package/plugins/sp/scripts/history-anatomy-cache.ts

@@ -4,7 +4,8 @@
  *
  * ADR-079 makes cache validity a *derived* fact, not a stored claim: a cached report is reusable
  * only for its model-authored half, and only when a freshly derived semantic digest of the analyze
- * artifact plus the contract/skill/workflow logic digests all match what the cache recorded.
+ * artifact plus the contract/skill/workflow/helper logic digests all match what the cache
+ * recorded (helper digest: task 0771 — the deterministic half is part of cache identity).
  *
  * This script performs deterministic file, hash, and schema work only — no finding, remediation,
  * severity, or ranking logic (that is judgment, owned by the sp:history-anatomy skill). Jobs:
@@ -68,6 +69,8 @@ export interface CacheProvenance {
     contractDigest: string;
     skillDigest: string;
     workflowDigest: string;
+    /** Digest of the executing helper twin itself (0771): a changed deterministic half invalidates. */
+    helperDigest: string;
     coverage: Array<{ source: string; status: string; lastImportedAt: string | null }>;
     // 0660 R7 audit fields. Recorded in the published frontmatter for provenance; deliberately
     // NOT part of the invalidation matrix — a changed run id or executor is not stale evidence.
@@ -243,6 +246,7 @@ export function parseProvenance(reportMarkdown: string): CacheProvenance | null
             contractDigest: String(obj.contractDigest ?? ''),
             skillDigest: String(obj.skillDigest ?? ''),
             workflowDigest: String(obj.workflowDigest ?? ''),
+            helperDigest: String(obj.helperDigest ?? ''),
             coverage: coverage.map((c) => ({
                 source: String(c.source ?? ''),
                 status: String(c.status ?? ''),
@@ -300,6 +304,7 @@ export function decideCache(
     if (cached.contractDigest !== current.contractDigest) reasons.push('logic-changed:contract');
     if (cached.skillDigest !== current.skillDigest) reasons.push('logic-changed:skill');
     if (cached.workflowDigest !== current.workflowDigest) reasons.push('logic-changed:workflow');
+    if (cached.helperDigest !== current.helperDigest) reasons.push('logic-changed:helper');
 
     // Coverage cannot degrade: the cache must not claim broader coverage than the current
     // analyze covers. If the cached report covered a source the current analyze no longer does,
@@ -601,6 +606,7 @@ export interface ProbeOptions {
     skillDir?: string;
     contractFile?: string;
     workflowFile?: string;
+    helperFile?: string;
     contractVersion?: string;
     runId?: string;
     spurVersion?: string;
@@ -660,6 +666,7 @@ export function buildProvenance(opts: ProbeOptions): CacheProvenance {
         contractDigest: logicDigest(opts.contractFile),
         skillDigest: logicDigest(opts.skillDir),
         workflowDigest: logicDigest(opts.workflowFile),
+        helperDigest: logicDigest(opts.helperFile),
         coverage,
         runId: opts.runId,
         currentArtifactPath: opts.artifact,
@@ -697,6 +704,7 @@ const YAML_KEYS: Array<keyof CacheProvenance> = [
     'contractDigest',
     'skillDigest',
     'workflowDigest',
+    'helperDigest',
     'runId',
     'currentArtifactPath',
     'baselineArtifactPath',
@@ -823,7 +831,7 @@ export function diffPorcelain(before: string, now: string, expects: Set<string>)
 const VALID_COMMANDS = 'digest, check, paths, assert-clean, probe, stamp, refresh, publish';
 const PROBE_USAGE =
     '<script> probe --artifact <a.json> --target <report.md> [--baseline <b.json>] [--mode daily|ad-hoc] ' +
-    '[--date <YYYY-MM-DD>] [--recompute true] [--out <prov.json>] [--skill-dir <d>] [--contract <f>] [--workflow <f>]';
+    '[--date <YYYY-MM-DD>] [--recompute true] [--out <prov.json>] [--skill-dir <d>] [--contract <f>] [--workflow <f>] [--helper <f>]';
 
 /** `--key value` / `--flag` → record. Bare flags become `"true"` so `--recompute` needs no value. */
 function parseFlags(args: string[]): Record<string, string | undefined> {
@@ -956,6 +964,7 @@ export function runCacheCli(argv: string[]): CacheCliResult {
                     skillDir: f['skill-dir'],
                     contractFile: f.contract,
                     workflowFile: f.workflow,
+                    helperFile: f.helper,
                     contractVersion: f['contract-version'],
                     runId: f['run-id'],
                     spurVersion: f['spur-version'],

package/plugins/sp/scripts/pr-reviewing.mjs

@@ -325,7 +325,11 @@ function hasPendingRequest(comments, head, login) {
 }
 function requireExpectedHead(args, pr) {
   const expected = args.flags.get("--head");
-  if (expected && expected !== pr.headRefOid) {
+  if (!expected) {
+    writeStatus(args, "FAIL");
+    fail(args, "--head <sha> is required and must match the reviewed request HEAD", 2);
+  }
+  if (expected !== pr.headRefOid) {
     writeStatus(args, "FAIL");
     fail(args, `PR HEAD moved from ${expected.slice(0, 7)} to ${pr.headRefOid.slice(0, 7)} \u2014 request a new review`, 2);
   }

package/plugins/sp/scripts/pr-reviewing.ts

@@ -519,8 +519,14 @@ function hasPendingRequest(comments: readonly GhIssueComment[], head: string, lo
 }
 
 function requireExpectedHead(args: ParsedArgs, pr: GhPr): void {
+    // 0771: head pinning only protects when the flag actually carries a SHA — an empty or
+    // missing --head must fail loud instead of silently reviewing whatever HEAD is current.
     const expected = args.flags.get('--head');
-    if (expected && expected !== pr.headRefOid) {
+    if (!expected) {
+        writeStatus(args, 'FAIL');
+        fail(args, '--head <sha> is required and must match the reviewed request HEAD', 2);
+    }
+    if (expected !== pr.headRefOid) {
         writeStatus(args, 'FAIL');
         fail(
             args,