@ai-dev-methodologies/rlp-desk 0.2.2 → 0.2.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-dev-methodologies/rlp-desk",
-  "version": "0.2.2",
+  "version": "0.2.4",
   "description": "Fresh-context iterative loops for Claude Code — autonomous task completion with independent verification",
   "scripts": {
     "postinstall": "node scripts/postinstall.js",

package/src/commands/rlp-desk.md

@@ -97,7 +97,7 @@ Options (parse from `$ARGUMENTS`):
 - `--consensus-scope all|final-only` — when consensus runs (default: `all`)
   - `all`: consensus runs on every verify (current behavior)
   - `final-only`: consensus only on final ALL verify
-- `--debug` — enable debug logging (tmux mode only, writes to logs/<slug>/debug.log)
+- `--debug` — enable debug logging (writes to logs/<slug>/debug.log)
 
 ### Mode Selection
 
@@ -144,11 +144,14 @@ DEBUG=<1 if --debug, else 0> \
 1. Validate scaffold: `.claude/ralph-desk/prompts/<slug>.worker.prompt.md` etc.
 2. Check sentinels (complete/blocked). Found → tell user `/rlp-desk clean <slug>`.
 3. Clean previous `done-claim.json`, `verify-verdict.json`.
+4. If `--debug`: create/clear `logs/<slug>/debug.log`. Define a helper: to "debug_log" means append a timestamped line to this file via `Bash("echo \"[$(date '+%Y-%m-%d %H:%M:%S')] $msg\" >> .claude/ralph-desk/logs/<slug>/debug.log")`.
 
 ### Leader Loop
 
 **CRITICAL: DO NOT STOP between iterations.** You MUST continue the loop automatically until a sentinel is written (COMPLETE or BLOCKED) or max_iter is reached. Do NOT pause to ask the user. Do NOT wait for confirmation. The loop is fully autonomous — just report each iteration result briefly and immediately proceed to the next iteration.
 
+If `--debug`, at loop start debug_log: `[PLAN] slug=<slug> max_iter=<N> worker_engine=<engine> worker_model=<model> verifier_engine=<engine> verifier_model=<model> verify_mode=<mode> consensus=<0|1> consensus_scope=<scope>`
+
 For each iteration (1 to max_iter):
 
 **① Check sentinels**
@@ -166,11 +169,13 @@ rm -f .claude/ralph-desk/memos/<slug>-verify-verdict.json
 **② Read memory.md** → Stop Status, Next Iteration Contract
 - Also read **Completed Stories** → verified work so far
 - Also read **Key Decisions** → settled architectural choices
+- If `--debug`: debug_log `[EXEC] iter=N phase=read_memory stop_status=<status> contract="<summary>"`
 
 **③ Decide model** (§4 of governance.md)
 - Previous iteration failed → upgrade model
 - Simple task → downgrade
 - User specified → use that
+- If `--debug`: debug_log `[EXEC] iter=N phase=model_select worker_model=<model> reason=<reason>`
 
 **④ Build worker prompt**
 - Read `.claude/ralph-desk/prompts/<slug>.worker.prompt.md`
@@ -178,6 +183,7 @@ rm -f .claude/ralph-desk/memos/<slug>-verify-verdict.json
 - Write to `.claude/ralph-desk/logs/<slug>/iter-NNN.worker-prompt.md` (audit trail)
 
 **⑤ Execute Worker**
+- If `--debug`: debug_log `[EXEC] iter=N phase=worker engine=<engine> model=<model> dispatched=true`
 
 If `--worker-engine claude` (default):
 ```
@@ -199,11 +205,14 @@ Bash("codex exec --model <worker_codex_model> --reasoning-effort <worker_codex_r
 - Codex runs as a subprocess via Bash(), not Agent().
 - Each Bash() call = fresh context for codex.
 
+- If `--debug`: debug_log `[EXEC] iter=N phase=worker_done engine=<engine>`
+
 **⑥ Read memory.md again** (Worker updated it)
 - `stop=continue` → go to ⑧
 - `stop=verify` → go to ⑦
 - `stop=blocked` → write BLOCKED sentinel, stop
 - Also read `iter-signal.json` for `us_id` field (which US was just completed)
+- If `--debug`: debug_log `[EXEC] iter=N phase=worker_signal status=<stop_status> us_id=<us_id>`
 
 **⑦ Execute Verifier**
 
@@ -225,6 +234,7 @@ Bash("codex exec --model <worker_codex_model> --reasoning-effort <worker_codex_r
 - Verifier checks all AC at once
 
 **⑦a Dispatch Verifier**
+- If `--debug`: debug_log `[EXEC] iter=N phase=verifier engine=<engine> model=<model> scope=<us_id> dispatched=true`
 
 If `--verifier-engine claude` (default):
 ```
@@ -263,6 +273,8 @@ After the primary verifier runs, run a second verifier with the OTHER engine:
     5. Go to ⑧ with fix contract as next Worker contract
   - `request_info` → Leader reads Verifier's questions, decides outcome (or relays to Worker in next contract) → go to ⑧
   - `blocked` → write BLOCKED sentinel, stop
+- If `--debug`: debug_log `[EXEC] iter=N phase=verdict engine=<engine> verdict=<pass|fail|request_info> us_id=<us_id>`
+- If `--debug` and consensus: debug_log `[EXEC] iter=N phase=consensus claude=<verdict> codex=<verdict> round=<N>`
 
 **⑧ Write result log and report to user, continue loop**
 - Write `logs/<slug>/iter-NNN.result.md`:
@@ -271,6 +283,10 @@ After the primary verifier runs, run a second verifier with the OTHER engine:
   - Verifier verdict `[leader-measured]`
 - Write `status.json`
 - Report: iteration N, phase, model used, result
+- If `--debug`: debug_log `[EXEC] iter=N phase=result status=<result> consecutive_failures=<N> verified_us=<list>`
+
+At loop end (COMPLETE, BLOCKED, or TIMEOUT):
+- If `--debug`: debug_log `[VALIDATE] result=<COMPLETE|BLOCKED|TIMEOUT> iterations=<N> verified_us=<list>`
 
 ### Circuit Breaker
 - context-latest.md unchanged 3 iterations → BLOCKED
@@ -342,7 +358,7 @@ Run options:
   --verify-mode per-us|batch Verification strategy (default: per-us)
   --verify-consensus         Cross-engine consensus verification
   --consensus-scope SCOPE    When consensus runs: all|final-only (default: all)
-  --debug                    Debug logging (tmux mode only)
+  --debug                    Debug logging (logs/<slug>/debug.log)
 ```
 
 ## Architecture

package/src/scripts/run_ralph_desk.zsh

@@ -1411,7 +1411,56 @@ run_consensus_verification() {
     # Consensus disagreement
     log_debug "[EXEC] iter=$iter phase=consensus_disagreement round=$CONSENSUS_ROUND claude=$CLAUDE_VERDICT codex=$CODEX_VERDICT action=fix_contract"
 
-    # Either fails → build combined fix contract
+    # --- Pre-existing failure detection ---
+    # Get files changed by Worker in this iteration
+    local worker_changed_files=""
+    worker_changed_files=$(cd "$ROOT" && git diff --name-only HEAD~1 HEAD 2>/dev/null || echo "")
+    log_debug "[EXEC] iter=$iter worker_changed_files=\"$worker_changed_files\""
+
+    # Check if ALL failing issues reference files NOT touched by the worker
+    local has_worker_caused_issues=0
+    local failing_verdict_file=""
+    if [[ "$CLAUDE_VERDICT" = "fail" ]]; then failing_verdict_file="$claude_verdict_file"
+    elif [[ "$CODEX_VERDICT" = "fail" ]]; then failing_verdict_file="$codex_verdict_file"
+    fi
+
+    if [[ -n "$failing_verdict_file" && -n "$worker_changed_files" ]]; then
+      # Extract file paths mentioned in issues and check against worker changes
+      local issue_files
+      issue_files=$(jq -r '.issues[]? | .description // ""' "$failing_verdict_file" 2>/dev/null)
+      for changed_file in $(echo "$worker_changed_files"); do
+        if echo "$issue_files" | grep -q "$changed_file" 2>/dev/null; then
+          has_worker_caused_issues=1
+          break
+        fi
+      done
+
+      if (( ! has_worker_caused_issues )); then
+        # None of the failing issues reference files the worker changed
+        log "  Pre-existing failure detected: failing tests are NOT in files changed by Worker."
+        log_debug "[EXEC] iter=$iter pre_existing_failure=true failing_engine=$([ \"$CLAUDE_VERDICT\" = 'fail' ] && echo claude || echo codex)"
+
+        # Treat as pass — the other engine passed, and failures are pre-existing
+        {
+          echo '{'
+          echo '  "verdict": "pass",'
+          echo '  "verified_at_utc": "'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'",'
+          echo '  "summary": "Consensus PASS (pre-existing failure filtered): claude='"$CLAUDE_VERDICT"' codex='"$CODEX_VERDICT"'. Failing tests not in worker-changed files.",'
+          echo '  "recommended_state_transition": "complete",'
+          echo '  "pre_existing_failure": true,'
+          echo '  "worker_changed_files": "'"$(echo $worker_changed_files | tr '\n' ',')"'",'
+          echo '  "consensus": {'
+          echo '    "claude": { "verdict": "'"$CLAUDE_VERDICT"'" },'
+          echo '    "codex": { "verdict": "'"$CODEX_VERDICT"'" },'
+          echo '    "round": '"$CONSENSUS_ROUND"
+          echo '  }'
+          echo '}'
+        } | atomic_write "$VERDICT_FILE"
+        return 0
+      fi
+    fi
+
+    # --- Worker-caused failure: build fix contract as before ---
     local fix_contract="$LOGS_DIR/iter-$(printf '%03d' $iter).fix-contract.md"
     {
       echo "# Fix Contract (Consensus Round $CONSENSUS_ROUND, iteration $iter)"
@@ -1577,9 +1626,13 @@ main() {
   PREV_CONTEXT_HASH=$(compute_context_hash)
 
   # --- governance.md s7: Leader Loop ---
+  local HARD_CEILING=$(( ITER_TIMEOUT * 3 ))  # absolute max per iteration (no extensions beyond this)
+
   for (( ITERATION = 1; ITERATION <= MAX_ITER; ITERATION++ )); do
     log ""
     log "========== Iteration $ITERATION / $MAX_ITER =========="
+    local ITER_START_TIME
+    ITER_START_TIME=$(date +%s)
     local _iter_contract=""
     _iter_contract=$(sed -n '/^## Next Iteration Contract$/,/^## /{ /^## Next/d; /^## [^N]/d; p; }' "$MEMORY_FILE" 2>/dev/null | head -1 | tr '\n' ' ')
     log_debug "[EXEC] iter=$ITERATION start contract=\"${_iter_contract:-none}\""
@@ -1692,8 +1745,20 @@ main() {
         local worker_cmd
         worker_cmd=$(tmux display-message -p -t "$WORKER_PANE" '#{pane_current_command}' 2>/dev/null)
         if [[ "$worker_cmd" == "node" || "$worker_cmd" == "claude" || "$worker_cmd" == "codex" ]]; then
-          log "  Worker timed out but still active ($worker_cmd). Extending poll..."
-          log_debug "[EXEC] iter=$ITERATION timeout_active=true process=$worker_cmd"
+          # Check hard ceiling before extending
+          local iter_elapsed=$(( $(date +%s) - ITER_START_TIME ))
+          if (( iter_elapsed >= HARD_CEILING )); then
+            log_error "Worker hit hard ceiling (${HARD_CEILING}s = 3x iter_timeout). Killing iteration."
+            log_debug "[EXEC] iter=$ITERATION hard_ceiling_hit=true elapsed=${iter_elapsed}s ceiling=${HARD_CEILING}s process=$worker_cmd"
+            tmux send-keys -t "$WORKER_PANE" C-c 2>/dev/null
+            sleep 1
+            WORKER_PANE=$(replace_worker_pane "$WORKER_PANE" "worker")
+            update_status "worker" "hard_timeout"
+            worker_poll_done=1
+            break
+          fi
+          log "  Worker timed out but still active ($worker_cmd). Extending poll... (${iter_elapsed}s/${HARD_CEILING}s)"
+          log_debug "[EXEC] iter=$ITERATION timeout_active=true process=$worker_cmd elapsed=${iter_elapsed}s ceiling=${HARD_CEILING}s"
           log_debug "[EXEC] iter=$ITERATION poll_extended=true worker_cmd=$worker_cmd"
           update_status "worker" "slow"
           # Loop continues — re-poll same iteration