prizmkit 1.1.67 → 1.1.68

package/bundled/VERSION.json

@@ -1,5 +1,5 @@
 {
-  "frameworkVersion": "1.1.67",
-  "bundledAt": "2026-06-09T02:37:28.761Z",
-  "bundledFrom": "d4b8c30"
+  "frameworkVersion": "1.1.68",
+  "bundledAt": "2026-06-09T14:36:58.835Z",
+  "bundledFrom": "82060fd"
 }

package/bundled/dev-pipeline/lib/common.sh

@@ -418,6 +418,46 @@ prizm_start_ai_session() {
     PRIZM_AI_PID=$!
 }
 
+# Detect AI CLI/provider infrastructure failures that are outside the
+# generated code's control. These should be retried without consuming the
+# item's code retry budget.
+prizm_detect_infra_error() {
+    local session_log="${1:-}"
+    local progress_json="${2:-}"
+
+    local haystack=""
+    if [[ -n "$session_log" && -f "$session_log" ]]; then
+        haystack="$(tail -c 65536 "$session_log" 2>/dev/null || true)"
+    fi
+    if [[ -n "$progress_json" && -f "$progress_json" ]]; then
+        haystack+=$'\n'
+        haystack+="$(cat "$progress_json" 2>/dev/null || true)"
+    fi
+
+    [[ -n "$haystack" ]] || return 1
+
+    if printf '%s' "$haystack" | grep -Eiq \
+        'auth_unavailable|no auth available|502 Bad Gateway|503 Service Unavailable|504 Gateway Timeout|gateway timeout|upstream (connect )?error|connection reset|ECONNRESET|ETIMEDOUT|ENOTFOUND|EAI_AGAIN|rate limit|rate_limit|temporarily unavailable|overloaded'; then
+        return 0
+    fi
+
+    return 1
+}
+
+prizm_extract_update_new_status() {
+    python3 -c "
+import json, sys
+raw = sys.stdin.read()
+try:
+    data = json.loads(raw)
+except Exception:
+    sys.exit(0)
+value = data.get('new_status')
+if value:
+    print(value)
+"
+}
+
 # Run an AI CLI session synchronously.
 # Usage: prizm_run_ai_session <prompt_path> <log_path> <model>
 prizm_run_ai_session() {

package/bundled/dev-pipeline/run-bugfix.sh

@@ -145,6 +145,11 @@ spawn_and_wait_session() {
         log_warn "Session was stale-killed by heartbeat monitor (no progress for too long)"
     fi
 
+    local was_infra_error=false
+    if [[ $exit_code -ne 0 ]] && prizm_detect_infra_error "$session_log" "$progress_json"; then
+        was_infra_error=true
+    fi
+
     # Session summary
     if [[ -f "$session_log" ]]; then
         local final_size=$(wc -c < "$session_log" 2>/dev/null | tr -d ' ')
@@ -162,6 +167,10 @@ spawn_and_wait_session() {
     if [[ $exit_code -eq 124 ]]; then
         log_warn "Session timed out after ${SESSION_TIMEOUT}s"
         session_status="timed_out"
+    elif [[ "$was_infra_error" == true ]]; then
+        log_warn "Session failed due to AI CLI/provider infrastructure error"
+        log_warn "Infrastructure errors are retried without consuming code retry budget"
+        session_status="infra_error"
     elif [[ "$was_stale_killed" == true ]]; then
         log_warn "Session stale-killed (no progress for ${STALE_KILL_THRESHOLD}s)"
         log_warn "Stale-killed sessions are treated as failed; dev branch is preserved for inspection"
@@ -259,14 +268,20 @@ sys.exit(0)
     prizm_detect_subagents "$session_log"
 
     # Update bug status (do NOT commit on dev branch — commit happens after merge)
-    python3 "$SCRIPTS_DIR/update-bug-status.py" \
+    local update_output
+    update_output=$(python3 "$SCRIPTS_DIR/update-bug-status.py" \
         --bug-list "$bug_list" \
         --state-dir "$STATE_DIR" \
         --bug-id "$bug_id" \
         --session-status "$session_status" \
         --session-id "$session_id" \
         --max-retries "$max_retries" \
-        --action update >/dev/null 2>&1 || true
+        --action update 2>&1) || {
+        log_error "Failed to update bug status: $update_output"
+        update_output=""
+    }
+
+    _SPAWN_ITEM_STATUS="$(printf '%s' "$update_output" | prizm_extract_update_new_status)"
 
     _SPAWN_RESULT="$session_status"
 }
@@ -693,6 +708,7 @@ else:
     trap cleanup_single_bug SIGINT SIGTERM
 
     _SPAWN_RESULT=""
+    _SPAWN_ITEM_STATUS=""
 
     # Branch lifecycle: create and checkout bugfix branch
     local _proj_root
@@ -1078,12 +1094,14 @@ DEPLOY_PROMPT_EOF
         # Spawn session
         log_info "Spawning AI CLI session: $session_id"
         _SPAWN_RESULT=""
+        _SPAWN_ITEM_STATUS=""
 
         spawn_and_wait_session \
             "$bug_id" "$bug_list" "$session_id" \
             "$bootstrap_prompt" "$session_dir" "$MAX_RETRIES" "$bug_model" "$_ORIGINAL_BRANCH"
 
         local session_status="$_SPAWN_RESULT"
+        local item_status_after_session="${_SPAWN_ITEM_STATUS:-}"
 
         # Merge per-bug dev branch back to original on success
         if [[ "$session_status" == "success" && -n "$_DEV_BRANCH_NAME" ]]; then
@@ -1112,15 +1130,18 @@ DEPLOY_PROMPT_EOF
         session_count=$((session_count + 1))
         total_subagent_calls=$((total_subagent_calls + _SUBAGENT_COUNT))
 
-        # Stop-on-failure: abort pipeline if task failed and STOP_ON_FAILURE is enabled
-        if [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" ]]; then
+        # Stop-on-failure: abort only after the task is actually marked failed.
+        # Pending retry outcomes, including infrastructure errors, keep running.
+        if [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" && "$item_status_after_session" == "failed" ]]; then
             echo ""
             log_error "════════════════════════════════════════════════════"
-            log_error "  STOP_ON_FAILURE: Pipeline halted after $bug_id failed."
+            log_error "  STOP_ON_FAILURE: Pipeline halted after $bug_id exhausted retries."
             log_error "  Total sessions completed: $session_count"
             log_error "  Set STOP_ON_FAILURE=0 to continue past failures."
             log_error "════════════════════════════════════════════════════"
             break
+        elif [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" ]]; then
+            log_info "STOP_ON_FAILURE: $bug_id is ${item_status_after_session:-unknown}; retry budget not exhausted, continuing."
         fi
 
         # Stuck detection

package/bundled/dev-pipeline/run-feature.sh

@@ -153,6 +153,11 @@ spawn_and_wait_session() {
         log_warn "Session was stale-killed by heartbeat monitor (no progress for too long)"
     fi
 
+    local was_infra_error=false
+    if [[ $exit_code -ne 0 ]] && prizm_detect_infra_error "$session_log" "$progress_json"; then
+        was_infra_error=true
+    fi
+
     # Show final session summary
     if [[ -f "$session_log" ]]; then
         local final_size=$(wc -c < "$session_log" 2>/dev/null | tr -d ' ')
@@ -172,6 +177,10 @@ spawn_and_wait_session() {
     if [[ $exit_code -eq 124 ]]; then
         log_warn "Session timed out after ${SESSION_TIMEOUT}s"
         session_status="timed_out"
+    elif [[ "$was_infra_error" == true ]]; then
+        log_warn "Session failed due to AI CLI/provider infrastructure error"
+        log_warn "Infrastructure errors are retried without consuming code retry budget"
+        session_status="infra_error"
     elif [[ "$was_stale_killed" == true ]]; then
         log_warn "Session stale-killed (no progress for ${STALE_KILL_THRESHOLD}s)"
         log_warn "Stale-killed sessions are treated as failed; dev branch is preserved for inspection"
@@ -347,6 +356,8 @@ sys.exit(0)
         log_error ".prizmkit/plans/feature-list.json may be out of sync. Manual intervention needed."
     }
 
+    _SPAWN_ITEM_STATUS="$(printf '%s' "$update_output" | prizm_extract_update_new_status)"
+
     # Return status via global variable (avoids $() swallowing stdout)
     _SPAWN_RESULT="$session_status"
 }
@@ -848,6 +859,7 @@ else:
     trap cleanup_single_feature SIGINT SIGTERM
 
     _SPAWN_RESULT=""
+    _SPAWN_ITEM_STATUS=""
 
     # Branch lifecycle: create and checkout feature branch
     local _proj_root
@@ -1300,11 +1312,13 @@ DEPLOY_PROMPT_EOF
             log_info "Feature model: $feature_model"
         fi
         _SPAWN_RESULT=""
+        _SPAWN_ITEM_STATUS=""
 
         spawn_and_wait_session \
             "$feature_id" "$feature_list" "$session_id" \
             "$bootstrap_prompt" "$session_dir" "$MAX_RETRIES" "$feature_model" "$_ORIGINAL_BRANCH"
         local session_status="$_SPAWN_RESULT"
+        local item_status_after_session="${_SPAWN_ITEM_STATUS:-}"
 
         # Merge per-feature dev branch back to original on success
         if [[ "$session_status" == "success" && -n "$_DEV_BRANCH_NAME" ]]; then
@@ -1333,15 +1347,18 @@ DEPLOY_PROMPT_EOF
         session_count=$((session_count + 1))
         total_subagent_calls=$((total_subagent_calls + _SUBAGENT_COUNT))
 
-        # Stop-on-failure: abort pipeline if task failed and STOP_ON_FAILURE is enabled
-        if [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" ]]; then
+        # Stop-on-failure: abort only after the task is actually marked failed.
+        # Pending retry outcomes, including infrastructure errors, keep running.
+        if [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" && "$item_status_after_session" == "failed" ]]; then
             echo ""
             log_error "════════════════════════════════════════════════════"
-            log_error "  STOP_ON_FAILURE: Pipeline halted after $feature_id failed."
+            log_error "  STOP_ON_FAILURE: Pipeline halted after $feature_id exhausted retries."
             log_error "  Total sessions completed: $session_count"
             log_error "  Set STOP_ON_FAILURE=0 to continue past failures."
             log_error "════════════════════════════════════════════════════"
             break
+        elif [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" ]]; then
+            log_info "STOP_ON_FAILURE: $feature_id is ${item_status_after_session:-unknown}; retry budget not exhausted, continuing."
         fi
 
         # Brief pause before next iteration

package/bundled/dev-pipeline/run-refactor.sh

@@ -147,6 +147,11 @@ spawn_and_wait_session() {
         log_warn "Session was stale-killed by heartbeat monitor (no progress for too long)"
     fi
 
+    local was_infra_error=false
+    if [[ $exit_code -ne 0 ]] && prizm_detect_infra_error "$session_log" "$progress_json"; then
+        was_infra_error=true
+    fi
+
     # Session summary
     if [[ -f "$session_log" ]]; then
         local final_size=$(wc -c < "$session_log" 2>/dev/null | tr -d ' ')
@@ -164,6 +169,10 @@ spawn_and_wait_session() {
     if [[ $exit_code -eq 124 ]]; then
         log_warn "Session timed out after ${SESSION_TIMEOUT}s"
         session_status="timed_out"
+    elif [[ "$was_infra_error" == true ]]; then
+        log_warn "Session failed due to AI CLI/provider infrastructure error"
+        log_warn "Infrastructure errors are retried without consuming code retry budget"
+        session_status="infra_error"
     elif [[ "$was_stale_killed" == true ]]; then
         log_warn "Session stale-killed (no progress for ${STALE_KILL_THRESHOLD}s)"
         log_warn "Stale-killed sessions are treated as failed; dev branch is preserved for inspection"
@@ -286,14 +295,20 @@ sys.exit(0)
     fi
 
     # Update refactor status (do NOT commit on dev branch — commit happens after merge)
-    python3 "$SCRIPTS_DIR/update-refactor-status.py" \
+    local update_output
+    update_output=$(python3 "$SCRIPTS_DIR/update-refactor-status.py" \
         --refactor-list "$refactor_list" \
         --state-dir "$STATE_DIR" \
         --refactor-id "$refactor_id" \
         --session-status "$session_status" \
         --session-id "$session_id" \
         --max-retries "$max_retries" \
-        --action update >/dev/null 2>&1 || true
+        --action update 2>&1) || {
+        log_error "Failed to update refactor status: $update_output"
+        update_output=""
+    }
+
+    _SPAWN_ITEM_STATUS="$(printf '%s' "$update_output" | prizm_extract_update_new_status)"
 
     _SPAWN_RESULT="$session_status"
 }
@@ -723,6 +738,7 @@ else:
     trap cleanup_single_refactor SIGINT SIGTERM
 
     _SPAWN_RESULT=""
+    _SPAWN_ITEM_STATUS=""
 
     # Branch lifecycle: create and checkout refactor branch
     local _proj_root
@@ -1114,6 +1130,7 @@ DEPLOY_PROMPT_EOF
         # Spawn session
         log_info "Spawning AI CLI session: $session_id"
         _SPAWN_RESULT=""
+        _SPAWN_ITEM_STATUS=""
 
         spawn_and_wait_session \
             "$refactor_id" "$refactor_list" "$session_id" \
@@ -1130,6 +1147,7 @@ DEPLOY_PROMPT_EOF
         fi
 
         local session_status="$_SPAWN_RESULT"
+        local item_status_after_session="${_SPAWN_ITEM_STATUS:-}"
 
         # Merge per-refactor dev branch back to original on success
         if [[ "$session_status" == "success" && -n "$_DEV_BRANCH_NAME" ]]; then
@@ -1168,15 +1186,18 @@ DEPLOY_PROMPT_EOF
         session_count=$((session_count + 1))
         total_subagent_calls=$((total_subagent_calls + _SUBAGENT_COUNT))
 
-        # Stop-on-failure: abort pipeline if task failed and STOP_ON_FAILURE is enabled
-        if [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" ]]; then
+        # Stop-on-failure: abort only after the task is actually marked failed.
+        # Pending retry outcomes, including infrastructure errors, keep running.
+        if [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" && "$item_status_after_session" == "failed" ]]; then
             echo ""
             log_error "════════════════════════════════════════════════════"
-            log_error "  STOP_ON_FAILURE: Pipeline halted after $refactor_id failed."
+            log_error "  STOP_ON_FAILURE: Pipeline halted after $refactor_id exhausted retries."
             log_error "  Total sessions completed: $session_count"
             log_error "  Set STOP_ON_FAILURE=0 to continue past failures."
             log_error "════════════════════════════════════════════════════"
             break
+        elif [[ "$session_status" != "success" && "$STOP_ON_FAILURE" == "1" ]]; then
+            log_info "STOP_ON_FAILURE: $refactor_id is ${item_status_after_session:-unknown}; retry budget not exhausted, continuing."
         fi
 
         log_info "Pausing 5s before next refactor..."

package/bundled/dev-pipeline/scripts/update-bug-status.py

@@ -41,6 +41,7 @@ SESSION_STATUS_VALUES = [
     "failed",
     "crashed",
     "timed_out",
+    "infra_error",
     "commit_missing",
     "docs_missing",
     "merge_conflict",
@@ -280,6 +281,16 @@ def action_update(args, bug_list_path, state_dir):
         bs["sessions"] = []
         bs["last_session_id"] = None
 
+        err = update_bug_in_list(bug_list_path, bug_id, new_status)
+        if err:
+            error_out("Failed to update .prizmkit/plans/bug-fix-list.json: {}".format(err))
+            return
+    elif session_status == "infra_error":
+        new_status = "pending"
+        bs["infra_error_count"] = bs.get("infra_error_count", 0) + 1
+        bs["last_infra_error_session_id"] = session_id
+        bs["resume_from_phase"] = None
+
         err = update_bug_in_list(bug_list_path, bug_id, new_status)
         if err:
             error_out("Failed to update .prizmkit/plans/bug-fix-list.json: {}".format(err))
@@ -333,6 +344,10 @@ def action_update(args, bug_list_path, state_dir):
     if session_status in ("commit_missing", "docs_missing", "merge_conflict"):
         summary["degraded_reason"] = session_status
         summary["restart_policy"] = "finalization_retry"
+    elif session_status == "infra_error":
+        summary["restart_policy"] = "infra_retry"
+        summary["infra_error_count"] = bs.get("infra_error_count", 0)
+        summary["artifacts_preserved"] = True
     elif session_status != "success":
         summary["restart_policy"] = "full_restart"
         summary["cleanup_performed"] = cleaned

package/bundled/dev-pipeline/scripts/update-feature-status.py

@@ -45,6 +45,7 @@ SESSION_STATUS_VALUES = [
     "failed",
     "crashed",
     "timed_out",
+    "infra_error",
     "commit_missing",
     "docs_missing",
     "merge_conflict",
@@ -645,6 +646,19 @@ def action_update(args, feature_list_path, state_dir):
         fs["sessions"] = []
         fs["last_session_id"] = None
 
+        err = update_feature_in_list(feature_list_path, feature_id, new_status)
+        if err:
+            error_out("Failed to update .prizmkit/plans/feature-list.json: {}".format(err))
+            return
+    elif session_status == "infra_error":
+        # AI CLI/provider outage, auth failure, gateway error, etc.
+        # This is outside the code's control, so keep the item pending without
+        # consuming the task's retry budget.
+        new_status = "pending"
+        fs["infra_error_count"] = fs.get("infra_error_count", 0) + 1
+        fs["last_infra_error_session_id"] = session_id
+        fs["resume_from_phase"] = None
+
         err = update_feature_in_list(feature_list_path, feature_id, new_status)
         if err:
             error_out("Failed to update .prizmkit/plans/feature-list.json: {}".format(err))
@@ -701,6 +715,10 @@ def action_update(args, feature_list_path, state_dir):
     if session_status in ("commit_missing", "docs_missing", "merge_conflict"):
         summary["degraded_reason"] = session_status
         summary["restart_policy"] = "finalization_retry"
+    elif session_status == "infra_error":
+        summary["restart_policy"] = "infra_retry"
+        summary["infra_error_count"] = fs.get("infra_error_count", 0)
+        summary["artifacts_preserved"] = True
     elif session_status != "success":
         summary["restart_policy"] = "preserve_and_retry"
         summary["artifacts_preserved"] = True

package/bundled/dev-pipeline/scripts/update-refactor-status.py

@@ -42,6 +42,7 @@ SESSION_STATUS_VALUES = [
     "failed",
     "crashed",
     "timed_out",
+    "infra_error",
     "commit_missing",
     "docs_missing",
     "merge_conflict",
@@ -314,6 +315,16 @@ def action_update(args, refactor_list_path, state_dir):
         rs["sessions"] = []
         rs["last_session_id"] = None
 
+        err = update_refactor_in_list(refactor_list_path, refactor_id, new_status)
+        if err:
+            error_out("Failed to update .prizmkit/plans/refactor-list.json: {}".format(err))
+            return
+    elif session_status == "infra_error":
+        new_status = "pending"
+        rs["infra_error_count"] = rs.get("infra_error_count", 0) + 1
+        rs["last_infra_error_session_id"] = session_id
+        rs["resume_from_phase"] = None
+
         err = update_refactor_in_list(refactor_list_path, refactor_id, new_status)
         if err:
             error_out("Failed to update .prizmkit/plans/refactor-list.json: {}".format(err))
@@ -376,6 +387,10 @@ def action_update(args, refactor_list_path, state_dir):
     if session_status in ("commit_missing", "docs_missing", "merge_conflict"):
         summary["degraded_reason"] = session_status
         summary["restart_policy"] = "finalization_retry"
+    elif session_status == "infra_error":
+        summary["restart_policy"] = "infra_retry"
+        summary["infra_error_count"] = rs.get("infra_error_count", 0)
+        summary["artifacts_preserved"] = True
     elif session_status != "success":
         summary["restart_policy"] = "full_restart"
         summary["cleanup_performed"] = cleaned

package/bundled/dev-pipeline/tests/test_auto_skip.py

@@ -303,6 +303,45 @@ def _run_get_next(fl_path, state_dir):
     return result.stdout.strip()
 
 
+def _run_update(fl_path, state_dir, feature_id, session_status, session_id="session-1", max_retries=3):
+    cmd = [
+        "python3", _SCRIPT,
+        "--feature-list", fl_path,
+        "--state-dir", state_dir,
+        "--feature-id", feature_id,
+        "--session-status", session_status,
+        "--session-id", session_id,
+        "--max-retries", str(max_retries),
+        "--action", "update",
+    ]
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    assert result.returncode == 0, result.stderr
+    return json.loads(result.stdout)
+
+
+class TestInfraErrorUpdate:
+    def test_infra_error_keeps_pending_without_consuming_retry(self, tmp_path):
+        features = [_make_feature("F-001", "Root", status="in_progress")]
+        fl_path = _write_fl(tmp_path, features)
+        state_dir = _init_state(tmp_path, ["F-001"])
+        status_path = os.path.join(state_dir, "features", "F-001", "status.json")
+        fs = load_feature_status(state_dir, "F-001")
+        fs["retry_count"] = 2
+        write_json_file(status_path, fs)
+
+        result = _run_update(fl_path, state_dir, "F-001", "infra_error", "session-infra", max_retries=3)
+
+        assert result["new_status"] == "pending"
+        assert result["retry_count"] == 2
+        assert result["restart_policy"] == "infra_retry"
+        assert _read_statuses(fl_path)["F-001"] == "pending"
+
+        fs = load_feature_status(state_dir, "F-001")
+        assert fs["retry_count"] == 2
+        assert fs["infra_error_count"] == 1
+        assert fs["last_infra_error_session_id"] == "session-infra"
+
+
 class TestUnskipByFeatureId:
     """Unskip with --feature-id targets a specific failed feature + downstream."""
 

package/bundled/dev-pipeline-windows/SCHEMA_ANALYSIS.md

@@ -353,7 +353,7 @@ pending, in_progress, completed, failed, skipped
 | `LOG_CLEANUP_ENABLED` | boolean | 1 | Periodic session log cleanup |
 | `LOG_RETENTION_DAYS` | integer | 14 | Delete session logs older than N days |
 | `LOG_MAX_TOTAL_MB` | integer | 1024 | Keep total logs under N MB |
-| `STOP_ON_FAILURE` | boolean | 0 | Stop after the first failed task |
+| `STOP_ON_FAILURE` | boolean | 0 | Stop after a task exhausts retries |
 | `ENABLE_DEPLOY` | boolean | 0 | Start deploy session after all tasks complete |
 | `DEV_BRANCH` | string | auto-generated | Optional custom dev branch name |
 | `AUTO_PUSH` | boolean | 0 | Push original branch after successful merge |

package/bundled/dev-pipeline-windows/lib/common.ps1

@@ -145,6 +145,25 @@ function Invoke-PrizmPythonText {
   if ($LASTEXITCODE -ne 0) { throw "Python command failed: $($Arguments -join ' ')" }
 }
 
+function Test-PrizmInfraError {
+  param([string]$SessionLog, [string]$ProgressJson)
+  $parts = @()
+  if ($SessionLog -and (Test-Path $SessionLog)) {
+    try {
+      $text = Get-Content $SessionLog -Raw -ErrorAction Stop
+      if ($text.Length -gt 65536) { $text = $text.Substring($text.Length - 65536) }
+      $parts += $text
+    } catch {}
+  }
+  if ($ProgressJson -and (Test-Path $ProgressJson)) {
+    try { $parts += (Get-Content $ProgressJson -Raw -ErrorAction Stop) } catch {}
+  }
+  if ($parts.Count -eq 0) { return $false }
+
+  $haystack = $parts -join "`n"
+  return ($haystack -match '(?i)auth_unavailable|no auth available|502 Bad Gateway|503 Service Unavailable|504 Gateway Timeout|gateway timeout|upstream (connect )?error|connection reset|ECONNRESET|ETIMEDOUT|ENOTFOUND|EAI_AGAIN|rate limit|rate_limit|temporarily unavailable|overloaded')
+}
+
 function Get-PrizmConfigValue {
   param([string]$ConfigPath, [string]$Key)
   if (-not (Test-Path $ConfigPath)) { return $null }

package/bundled/dev-pipeline-windows/lib/pipeline.ps1

@@ -618,10 +618,16 @@ function Invoke-PrizmPipeline {
     }
     Stop-PrizmProgressParser $parserProcess
 
+    $wasInfraError = ($exitCode -ne 0 -and (Test-PrizmInfraError -SessionLog $sessionLog -ProgressJson $progressJson))
+
     $status = 'crashed'
     if ($wasTimedOut) {
       $status = 'timed_out'
       Write-PrizmWarn "AI session timed out after $timeoutSeconds seconds"
+    } elseif ($wasInfraError) {
+      $status = 'infra_error'
+      Write-PrizmWarn "AI session failed due to AI CLI/provider infrastructure error"
+      Write-PrizmWarn "Infrastructure errors are retried without consuming code retry budget"
     } elseif ($wasStaleKilled -or (Test-Path $staleKillMarker)) {
       Write-PrizmWarn "Session was stale-killed by heartbeat monitor (no progress for too long)"
       Write-PrizmWarn "Stale-killed sessions are treated as failed; dev branch is preserved for inspection"
@@ -645,8 +651,12 @@ function Invoke-PrizmPipeline {
     }
 
     $mergeSucceeded = $true
+    $itemListStatus = ''
     if ($status -eq 'success') {
-      Invoke-PrizmPythonText $python (@((Join-Path $paths.ScriptsDir $updateScript), $listOption, $listPath, '--state-dir', $stateDir, '--action', 'update', $idOption, $CurrentItemId, '--session-id', $sessionId, '--session-status', $status) + $maxRetryArgs)
+      $updateResult = Invoke-PrizmPythonJson $python (@((Join-Path $paths.ScriptsDir $updateScript), $listOption, $listPath, '--state-dir', $stateDir, '--action', 'update', $idOption, $CurrentItemId, '--session-id', $sessionId, '--session-status', $status) + $maxRetryArgs)
+      if ($updateResult -and $updateResult.PSObject.Properties['new_status']) {
+        $itemListStatus = [string]$updateResult.new_status
+      }
 
       if (Test-PrizmGitDirty $paths.ProjectRoot) {
         if ($hadDirtyBaseline) {
@@ -676,7 +686,10 @@ function Invoke-PrizmPipeline {
     }
 
     if ($status -ne 'success') {
-      Invoke-PrizmPythonText $python (@((Join-Path $paths.ScriptsDir $updateScript), $listOption, $listPath, '--state-dir', $stateDir, '--action', 'update', $idOption, $CurrentItemId, '--session-id', $sessionId, '--session-status', $status) + $maxRetryArgs)
+      $updateResult = Invoke-PrizmPythonJson $python (@((Join-Path $paths.ScriptsDir $updateScript), $listOption, $listPath, '--state-dir', $stateDir, '--action', 'update', $idOption, $CurrentItemId, '--session-id', $sessionId, '--session-status', $status) + $maxRetryArgs)
+      if ($updateResult -and $updateResult.PSObject.Properties['new_status']) {
+        $itemListStatus = [string]$updateResult.new_status
+      }
       if ($isGitRepository) {
         Invoke-PrizmGitCommitPath $paths.ProjectRoot $listPath "chore($CurrentItemId): update $idName status" | Out-Null
       }
@@ -687,6 +700,7 @@ function Invoke-PrizmPipeline {
     } else {
       Write-PrizmError "$Kind item failed: $CurrentItemId. Log: $sessionLog"
     }
+    $script:PRIZM_ITEM_LIST_STATUS = $itemListStatus
     $script:PRIZM_ITEM_EXIT_CODE = if ($status -eq 'success' -and $mergeSucceeded) { 0 } else { 1 }
     return
   }
@@ -748,9 +762,11 @@ function Invoke-PrizmPipeline {
       $global:PRIZM_EXIT_CODE = $lastExitCode
       return
     }
-    if ($lastExitCode -ne 0 -and $stopOnFailure) {
+    if ($lastExitCode -ne 0 -and $stopOnFailure -and $script:PRIZM_ITEM_LIST_STATUS -eq 'failed') {
       $global:PRIZM_EXIT_CODE = $lastExitCode
       return
+    } elseif ($lastExitCode -ne 0 -and $stopOnFailure) {
+      Write-PrizmInfo "STOP_ON_FAILURE: $nextItemId is $($script:PRIZM_ITEM_LIST_STATUS); retry budget not exhausted, continuing."
     }
   }
 }

package/bundled/dev-pipeline-windows/scripts/update-bug-status.py

@@ -41,6 +41,7 @@ SESSION_STATUS_VALUES = [
     "failed",
     "crashed",
     "timed_out",
+    "infra_error",
     "commit_missing",
     "docs_missing",
     "merge_conflict",
@@ -280,6 +281,16 @@ def action_update(args, bug_list_path, state_dir):
         bs["sessions"] = []
         bs["last_session_id"] = None
 
+        err = update_bug_in_list(bug_list_path, bug_id, new_status)
+        if err:
+            error_out("Failed to update .prizmkit/plans/bug-fix-list.json: {}".format(err))
+            return
+    elif session_status == "infra_error":
+        new_status = "pending"
+        bs["infra_error_count"] = bs.get("infra_error_count", 0) + 1
+        bs["last_infra_error_session_id"] = session_id
+        bs["resume_from_phase"] = None
+
         err = update_bug_in_list(bug_list_path, bug_id, new_status)
         if err:
             error_out("Failed to update .prizmkit/plans/bug-fix-list.json: {}".format(err))
@@ -333,6 +344,10 @@ def action_update(args, bug_list_path, state_dir):
     if session_status in ("commit_missing", "docs_missing", "merge_conflict"):
         summary["degraded_reason"] = session_status
         summary["restart_policy"] = "finalization_retry"
+    elif session_status == "infra_error":
+        summary["restart_policy"] = "infra_retry"
+        summary["infra_error_count"] = bs.get("infra_error_count", 0)
+        summary["artifacts_preserved"] = True
     elif session_status != "success":
         summary["restart_policy"] = "full_restart"
         summary["cleanup_performed"] = cleaned

package/bundled/dev-pipeline-windows/scripts/update-feature-status.py

@@ -45,6 +45,7 @@ SESSION_STATUS_VALUES = [
     "failed",
     "crashed",
     "timed_out",
+    "infra_error",
     "commit_missing",
     "docs_missing",
     "merge_conflict",
@@ -645,6 +646,19 @@ def action_update(args, feature_list_path, state_dir):
         fs["sessions"] = []
         fs["last_session_id"] = None
 
+        err = update_feature_in_list(feature_list_path, feature_id, new_status)
+        if err:
+            error_out("Failed to update .prizmkit/plans/feature-list.json: {}".format(err))
+            return
+    elif session_status == "infra_error":
+        # AI CLI/provider outage, auth failure, gateway error, etc.
+        # This is outside the code's control, so keep the item pending without
+        # consuming the task's retry budget.
+        new_status = "pending"
+        fs["infra_error_count"] = fs.get("infra_error_count", 0) + 1
+        fs["last_infra_error_session_id"] = session_id
+        fs["resume_from_phase"] = None
+
         err = update_feature_in_list(feature_list_path, feature_id, new_status)
         if err:
             error_out("Failed to update .prizmkit/plans/feature-list.json: {}".format(err))
@@ -701,6 +715,10 @@ def action_update(args, feature_list_path, state_dir):
     if session_status in ("commit_missing", "docs_missing", "merge_conflict"):
         summary["degraded_reason"] = session_status
         summary["restart_policy"] = "finalization_retry"
+    elif session_status == "infra_error":
+        summary["restart_policy"] = "infra_retry"
+        summary["infra_error_count"] = fs.get("infra_error_count", 0)
+        summary["artifacts_preserved"] = True
     elif session_status != "success":
         summary["restart_policy"] = "preserve_and_retry"
         summary["artifacts_preserved"] = True

package/bundled/dev-pipeline-windows/scripts/update-refactor-status.py

@@ -42,6 +42,7 @@ SESSION_STATUS_VALUES = [
     "failed",
     "crashed",
     "timed_out",
+    "infra_error",
     "commit_missing",
     "docs_missing",
     "merge_conflict",
@@ -314,6 +315,16 @@ def action_update(args, refactor_list_path, state_dir):
         rs["sessions"] = []
         rs["last_session_id"] = None
 
+        err = update_refactor_in_list(refactor_list_path, refactor_id, new_status)
+        if err:
+            error_out("Failed to update .prizmkit/plans/refactor-list.json: {}".format(err))
+            return
+    elif session_status == "infra_error":
+        new_status = "pending"
+        rs["infra_error_count"] = rs.get("infra_error_count", 0) + 1
+        rs["last_infra_error_session_id"] = session_id
+        rs["resume_from_phase"] = None
+
         err = update_refactor_in_list(refactor_list_path, refactor_id, new_status)
         if err:
             error_out("Failed to update .prizmkit/plans/refactor-list.json: {}".format(err))
@@ -376,6 +387,10 @@ def action_update(args, refactor_list_path, state_dir):
     if session_status in ("commit_missing", "docs_missing", "merge_conflict"):
         summary["degraded_reason"] = session_status
         summary["restart_policy"] = "finalization_retry"
+    elif session_status == "infra_error":
+        summary["restart_policy"] = "infra_retry"
+        summary["infra_error_count"] = rs.get("infra_error_count", 0)
+        summary["artifacts_preserved"] = True
     elif session_status != "success":
         summary["restart_policy"] = "full_restart"
         summary["cleanup_performed"] = cleaned

package/bundled/skills/_metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.67",
+  "version": "1.1.68",
   "skills": {
     "prizm-kit": {
       "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.67",
+  "version": "1.1.68",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {