From 6854e858a4e32b60bf042eda9a76cd6dc00acf4a Mon Sep 17 00:00:00 2001
From: Christian Nennemann <christian@nennemann.de>
Date: Sat, 4 Apr 2026 09:35:55 +0200
Subject: [PATCH] fix: address v0.7.0 review findings

- Auto-select: fast workflow now maps to pipeline strategy (was falling through to pdca)
- Evidence validation: check for missing evidence markers, not just banned phrases
- Remove sed-based artifact mutation (avoids table row corruption), track downgrades in events only
- Pipeline verify: explicit merge guard prevents merging before tests/re-review pass
---
 skills/run/SKILL.md | 70 +++++++++++++++++++++++++++++++++++++--------
 1 file changed, 58 insertions(+), 12 deletions(-)

diff --git a/skills/run/SKILL.md b/skills/run/SKILL.md
index 3bb724a..8d5ec45 100644
--- a/skills/run/SKILL.md
+++ b/skills/run/SKILL.md
@@ -82,6 +82,8 @@ if [[ "$STRATEGY" == "auto" ]]; then
     STRATEGY="pipeline"
   elif echo "$TASK_LOWER" | grep -qE '(refactor|redesign|review)'; then
     STRATEGY="pdca"
+  elif [[ "$WORKFLOW" == "fast" ]]; then
+    STRATEGY="pipeline"
   elif [[ "$WORKFLOW" == "thorough" ]]; then
     STRATEGY="pdca"
   else
@@ -510,30 +512,59 @@ After each returns, emit `review.verdict` and save artifact.
 
 #### 3c-ii. Evidence Validation
 
-After all reviewers complete, scan their outputs for banned phrases in CRITICAL/WARNING findings. Downgrade unsupported findings before proceeding to Act.
+After all reviewers complete, scan CRITICAL/WARNING findings for two conditions:
+1. **Banned phrases** — hedged language without evidence
+2. **Missing evidence** — no command output, code citation, or reproduction steps
+
+Downgrade unsupported findings to INFO before proceeding to Act.
 
 ```bash
 BANNED_PHRASES=("might be" "could potentially" "appears to" "seems like" "may not")
+EVIDENCE_MARKERS=("exit" "output" "line [0-9]" ":[0-9]" "returned" "FAIL" "PASS" "assert")
 
 for artifact in .archeflow/artifacts/${RUN_ID}/check-*.md; do
   REVIEWER=$(basename "$artifact" .md | sed 's/check-//')
-  while IFS= read -r line; do
+
+  # Read findings table rows (CRITICAL and WARNING only)
+  grep -E '\| (CRITICAL|WARNING) \|' "$artifact" 2>/dev/null | while IFS= read -r line; do
     SEVERITY=$(echo "$line" | grep -oE '(CRITICAL|WARNING)' | head -1)
-    [[ -z "$SEVERITY" ]] && continue
+    DOWNGRADE_REASON=""
+
+    # Check 1: banned phrases
     for phrase in "${BANNED_PHRASES[@]}"; do
       if echo "$line" | grep -qi "$phrase"; then
-        echo "EVIDENCE DOWNGRADE: $REVIEWER finding uses '$phrase' — downgrading to INFO"
-        ./lib/archeflow-event.sh "$RUN_ID" decision check "" \
-          '{"what":"evidence_downgrade","from":"'"$SEVERITY"'","to":"INFO","reviewer":"'"$REVIEWER"'","reason":"banned phrase: '"$phrase"'"}'
-        # Replace severity in artifact
-        sed -i "s/$line/$(echo "$line" | sed "s/$SEVERITY/INFO/")/" "$artifact"
+        DOWNGRADE_REASON="banned phrase: $phrase"
         break
       fi
     done
-  done < "$artifact"
+
+    # Check 2: no evidence markers (only if not already flagged)
+    if [[ -z "$DOWNGRADE_REASON" ]]; then
+      HAS_EVIDENCE=false
+      for marker in "${EVIDENCE_MARKERS[@]}"; do
+        if echo "$line" | grep -qiE "$marker"; then
+          HAS_EVIDENCE=true
+          break
+        fi
+      done
+      if [[ "$HAS_EVIDENCE" == "false" ]]; then
+        DOWNGRADE_REASON="no evidence cited"
+      fi
+    fi
+
+    if [[ -n "$DOWNGRADE_REASON" ]]; then
+      echo "EVIDENCE DOWNGRADE: $REVIEWER $SEVERITY finding — $DOWNGRADE_REASON"
+      ./lib/archeflow-event.sh "$RUN_ID" decision check "" \
+        '{"what":"evidence_downgrade","from":"'"$SEVERITY"'","to":"INFO","reviewer":"'"$REVIEWER"'","reason":"'"$DOWNGRADE_REASON"'"}'
+      # Note: the orchestrator tracks downgraded findings separately —
+      # do not modify the artifact file (avoids sed corruption on table rows)
+    fi
+  done
 done
 ```
 
+**Important:** Downgraded findings are tracked in events, NOT by modifying artifact files. The Act phase reads the decision events to know which findings were downgraded and excludes them from CRITICAL tallies.
+
 #### 3d. Phase Transition: Check to Act
 
 Collect all verdict seq numbers for the parent array.
@@ -822,9 +853,24 @@ Run the project's test suite. If tests pass and no CRITICAL findings exist:
 
 If CRITICAL findings exist:
 
-1. Spawn Maker for a **single targeted fix** — provide only the CRITICAL findings as context
-2. Re-run tests
-3. If still failing, report to user (do not cycle back)
+1. **Do NOT merge yet** — the branch remains separate
+2. Spawn Maker for a **single targeted fix** — provide only the CRITICAL findings as context
+3. Re-run the reviewer(s) that raised the CRITICAL finding(s) on just the fixed files
+4. Re-run test suite
+5. If tests pass and re-review approves: merge
+6. If still failing after this one fix attempt: **abort** — do NOT merge, report to user with the branch name for manual resolution
+
+```bash
+# Pipeline verify: explicit merge guard
+if [[ "$VERIFY_PASS" == "true" ]]; then
+  ./lib/archeflow-git.sh merge "$RUN_ID" --no-ff
+  ./lib/archeflow-rollback.sh "$RUN_ID"  # post-merge test validation
+else
+  echo "Pipeline aborted: CRITICAL findings not resolved after 1 fix attempt."
+  echo "Branch: archeflow/$RUN_ID (not merged)"
+  # Emit run.complete with status: aborted
+fi
+```
 
 WARNINGs are logged in the run event but do not block the merge.