fix: fix: standardize logging across all agents — capture errors, log exit codes, consistent format (#367)

lib/agent-sdk.sh

@@ -52,12 +52,16 @@ agent_run() {
   log "agent_run: starting (resume=${resume_id:-(new)}, dir=${run_dir})"
   output=$(cd "$run_dir" && flock -w 600 "$lock_file" timeout "${CLAUDE_TIMEOUT:-7200}" claude "${args[@]}" 2>>"$LOGFILE") && rc=0 || rc=$?
   if [ "$rc" -eq 124 ]; then
-    log "agent_run: timeout after ${CLAUDE_TIMEOUT:-7200}s"
+    log "agent_run: timeout after ${CLAUDE_TIMEOUT:-7200}s (exit code $rc)"
   elif [ "$rc" -ne 0 ]; then
     log "agent_run: claude exited with code $rc"
+    # Log last 3 lines of output for diagnostics
+    if [ -n "$output" ]; then
+      log "agent_run: last output lines: $(echo "$output" | tail -3)"
+    fi
   fi
   if [ -z "$output" ]; then
-    log "agent_run: empty output (claude may have crashed or failed)"
+    log "agent_run: empty output (claude may have crashed or failed, exit code: $rc)"
   fi
 
   # Extract and persist session_id
@@ -89,9 +93,13 @@ agent_run() {
         local nudge_rc
         output=$(cd "$run_dir" && flock -w 600 "$lock_file" timeout "${CLAUDE_TIMEOUT:-7200}" claude -p "$nudge" --resume "$_AGENT_SESSION_ID" --output-format json --dangerously-skip-permissions --max-turns 50 ${CLAUDE_MODEL:+--model "$CLAUDE_MODEL"} 2>>"$LOGFILE") && nudge_rc=0 || nudge_rc=$?
         if [ "$nudge_rc" -eq 124 ]; then
-          log "agent_run: nudge timeout after ${CLAUDE_TIMEOUT:-7200}s"
+          log "agent_run: nudge timeout after ${CLAUDE_TIMEOUT:-7200}s (exit code $nudge_rc)"
         elif [ "$nudge_rc" -ne 0 ]; then
           log "agent_run: nudge claude exited with code $nudge_rc"
+          # Log last 3 lines of output for diagnostics
+          if [ -n "$output" ]; then
+            log "agent_run: nudge last output lines: $(echo "$output" | tail -3)"
+          fi
         fi
         new_sid=$(printf '%s' "$output" | jq -r '.session_id // empty' 2>/dev/null) || true
         if [ -n "$new_sid" ]; then

lib/env.sh

@@ -13,7 +13,7 @@ FACTORY_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 if [ "${DISINTO_CONTAINER:-}" = "1" ]; then
   DISINTO_DATA_DIR="${HOME}/data"
   DISINTO_LOG_DIR="${DISINTO_DATA_DIR}/logs"
-  mkdir -p "${DISINTO_DATA_DIR}" "${DISINTO_LOG_DIR}"/{dev,action,review,supervisor,vault,site,metrics,gardener}
+  mkdir -p "${DISINTO_DATA_DIR}" "${DISINTO_LOG_DIR}"/{dev,action,review,supervisor,vault,site,metrics,gardener,planner,predictor,architect,dispatcher}
 else
   DISINTO_LOG_DIR="${FACTORY_ROOT}"
 fi
@@ -138,8 +138,12 @@ unset CLAWHUB_TOKEN 2>/dev/null || true
 export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
 
 # Shared log helper
+# Usage: log "message"
+# Output: [2026-04-03T14:00:00Z] agent: message
+# Where agent is set via LOG_AGENT variable (defaults to caller's context)
 log() {
-  printf '[%s] %s\n' "$(date -u '+%Y-%m-%d %H:%M:%S UTC')" "$*"
+  local agent="${LOG_AGENT:-agent}"
+  printf '[%s] %s: %s\n' "$(date -u '+%Y-%m-%dT%H:%M:%SZ')" "$agent" "$*"
 }
 
 # =============================================================================

lib/pr-lifecycle.sh

@@ -357,11 +357,18 @@ pr_close() {
   local pr_num="$1"
 
   _prl_log "closing PR #${pr_num}"
-  curl -sf -X PATCH \
+  local resp http_code
+  resp=$(curl -sf -w "\n%{http_code}" -X PATCH \
     -H "Authorization: token ${FORGE_TOKEN}" \
     -H "Content-Type: application/json" \
     "${FORGE_API}/pulls/${pr_num}" \
-    -d '{"state":"closed"}' >/dev/null 2>&1 || true
+    -d '{"state":"closed"}' 2>/dev/null) || true
+  http_code=$(printf '%s\n' "$resp" | tail -1)
+  if [ "$http_code" != "200" ] && [ "$http_code" != "204" ]; then
+    _prl_log "pr_close FAILED: HTTP ${http_code} for PR #${pr_num}"
+    return 1
+  fi
+  _prl_log "PR #${pr_num} closed"
 }
 
 # ---------------------------------------------------------------------------
@@ -398,11 +405,18 @@ pr_walk_to_merge() {
       if [ "${_PR_CI_FAILURE_TYPE:-}" = "infra" ] && [ "$ci_retry_count" -lt 1 ]; then
         ci_retry_count=$((ci_retry_count + 1))
         _prl_log "infra failure — retriggering CI (retry ${ci_retry_count})"
+        local rebase_output rebase_rc
         ( cd "$worktree" && \
           git commit --allow-empty -m "ci: retrigger after infra failure" --no-verify && \
           git fetch "$remote" "${PRIMARY_BRANCH}" 2>/dev/null && \
           git rebase "${remote}/${PRIMARY_BRANCH}" && \
-          git push --force-with-lease "$remote" HEAD ) 2>&1 | tail -5 || true
+          git push --force-with-lease "$remote" HEAD ) > /tmp/rebase-output-$$ 2>&1
+        rebase_rc=$?
+        rebase_output=$(cat /tmp/rebase-output-$$)
+        rm -f /tmp/rebase-output-$$
+        if [ "$rebase_rc" -ne 0 ]; then
+          _prl_log "rebase/push failed (exit code $rebase_rc): $(echo "$rebase_output" | tail -5)"
+        fi
         continue
       fi