prizmkit 1.1.92 → 1.1.93

package/bundled/skills/bugfix-pipeline-launcher/references/configuration.md

@@ -12,7 +12,6 @@ Translating user responses to env vars:
 | Verbose: On | `VERBOSE=1` |
 | Max retries: N | `MAX_RETRIES=N` |
 | Critic: On | `ENABLE_CRITIC=1` |
-| Timeout: value | `SESSION_TIMEOUT=<seconds>` |
 | Stop on failure: On | `STOP_ON_FAILURE=1` |
 | Deploy: Yes | `ENABLE_DEPLOY=1` |
 | Effort: value | `PRIZMKIT_EFFORT=<value>` |
@@ -28,9 +27,6 @@ Not exposed in interactive menu, pass via `--env`:
 | `DEV_BRANCH` | auto-generated | Custom dev branch name (default: `bugfix/pipeline-{run_id}`) |
 | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
 | `HEARTBEAT_STALE_THRESHOLD` | `600` | Max seconds without heartbeat before marking stale |
-| `LOG_CLEANUP_ENABLED` | `1` | Run periodic log cleanup (`0` to disable) |
-| `LOG_RETENTION_DAYS` | `14` | Delete logs older than N days |
-| `LOG_MAX_TOTAL_MB` | `1024` | Keep total logs under N MB via oldest-first cleanup |
 
 ## Interactive Configuration Options
 
@@ -52,28 +48,22 @@ Present these via `AskUserQuestion` in step 5. Round 1 is one `AskUserQuestion`
 - On — Enable adversarial critic review (`ENABLE_CRITIC=1`): an independent AI agent reviews the diagnosis/plan for completeness and the fix for defects, edge cases, and regression risks. Adds ~5-10 min per bug.
 
 **Question 4 — Advanced config?** (multiSelect: false):
-- No (default) — Use defaults for session timeout and failure behavior
-- Yes — Configure session timeout, stop-on-failure, deploy, and reasoning effort options
+- No (default) — Use defaults for failure behavior
+- Yes — Configure stop-on-failure, deploy, and reasoning effort options
 
 Note: Bug filter defaults to all bugs (by severity order). Default Critic to Off unless bugs have `severity: "critical"` or `severity: "high"` (in which case default to On). If the user selects "Other" on any option, handle their custom input.
 
 ### Round 2 (only if Advanced config = Yes)
 
-**Question 1 — Session timeout** (multiSelect: false):
-- None (default) — No timeout
-- 30 min — `SESSION_TIMEOUT=1800`
-- 1 hour — `SESSION_TIMEOUT=3600`
-- 2 hours — `SESSION_TIMEOUT=7200`
-
-**Question 2 — Stop on failure** (multiSelect: false):
+**Question 1 — Stop on failure** (multiSelect: false):
 - Off (default) — Pipeline continues to next task after failure
 - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
-**Question 3 — Deploy after completion?** (multiSelect: false):
+**Question 2 — Deploy after completion?** (multiSelect: false):
 - No (default) — Skip deployment after pipeline completes
 - Yes — Run /prizmkit-deploy automatically after all bugs fixed successfully (`ENABLE_DEPLOY=1`). Deployment is blocked if any bug was not fixed (status not 'completed', 'skipped', or 'needs_info').
 
-**Question 4 — Reasoning effort** (multiSelect: false):
+**Question 3 — Reasoning effort** (multiSelect: false):
 - Default (none) — Use CLI default
 - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
 - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)

package/bundled/skills/feature-pipeline-launcher/SKILL.md

@@ -150,12 +150,12 @@ Detect user intent from their message, then follow the corresponding workflow:
    - 5
 
    **Question 4 — Advanced config?** (multiSelect: false):
-   - No (default) — Use defaults for session timeout and failure behavior
-   - Yes — Configure session timeout, stop-on-failure, deploy-after-completion, and reasoning effort options
+   - No (default) — Use defaults for failure behavior
+   - Yes — Configure stop-on-failure, deploy-after-completion, and reasoning effort options
 
    Default Critic to Off unless features have `estimated_complexity: "high"` or above (in which case default to On).
 
-   **If user chose "Yes" to Advanced config**, ask a second round of `AskUserQuestion` — see the advanced config questions (session timeout, stop-on-failure, deploy-after-completion, reasoning effort) in `${SKILL_DIR}/references/configuration.md`.
+   **If user chose "Yes" to Advanced config**, ask a second round of `AskUserQuestion` — see the advanced config questions (stop-on-failure, deploy-after-completion, reasoning effort) in `${SKILL_DIR}/references/configuration.md`.
 
    **Environment variable mapping** and **advanced environment variables** tables — read `${SKILL_DIR}/references/configuration.md` for the full translation tables (8 config→env mappings + 9 advanced variables).
 
@@ -168,7 +168,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```bash
-   VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high \
+   VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high \
      .prizmkit/dev-pipeline/run-feature.sh run .prizmkit/plans/feature-list.json --features F-001:F-005
    ```
 

package/bundled/skills/feature-pipeline-launcher/references/configuration.md

@@ -6,21 +6,15 @@ Environment variable mappings for the feature launcher.
 
 Asked only when the user chose "Yes" to Advanced config in step 6.
 
-**Question 1 — Session timeout** (multiSelect: false):
-- None (default) — No timeout
-- 30 min — `SESSION_TIMEOUT=1800`
-- 1 hour — `SESSION_TIMEOUT=3600`
-- 2 hours — `SESSION_TIMEOUT=7200`
-
-**Question 2 — Stop on failure** (multiSelect: false):
+**Question 1 — Stop on failure** (multiSelect: false):
 - Off (default) — Pipeline continues to next task after failure
 - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
-**Question 3 — Deploy after completion?** (multiSelect: false):
+**Question 2 — Deploy after completion?** (multiSelect: false):
 - No (default) — Skip deployment after pipeline completes
 - Yes — Run /prizmkit-deploy automatically after all features complete successfully (`ENABLE_DEPLOY=1`). Deployment is blocked if any feature did not complete successfully (status not 'completed' or manually 'skipped').
 
-**Question 4 — Reasoning effort** (multiSelect: false):
+**Question 3 — Reasoning effort** (multiSelect: false):
 - Default (none) — Use CLI default
 - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
 - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
@@ -38,7 +32,6 @@ Translating user responses to env vars:
 | Verbose: Off | `VERBOSE=0` |
 | Verbose: On | `VERBOSE=1` |
 | Max retries: N | `MAX_RETRIES=N` |
-| Timeout: value | `SESSION_TIMEOUT=<seconds>` |
 | Stop on failure: On | `STOP_ON_FAILURE=1` |
 | Deploy: Yes | `ENABLE_DEPLOY=1` |
 | Effort: value | `PRIZMKIT_EFFORT=<value>` |
@@ -55,9 +48,6 @@ Not exposed in interactive menu, pass via `--env`:
 | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
 | `HEARTBEAT_STALE_THRESHOLD` | `600` | Max seconds without heartbeat before marking stale |
 | `PIPELINE_MODE` | (none) | Override mode for all features: `lite`\|`standard`\|`full` |
-| `LOG_CLEANUP_ENABLED` | `1` | Run periodic log cleanup (`0` to disable) |
-| `LOG_RETENTION_DAYS` | `14` | Delete logs older than N days |
-| `LOG_MAX_TOTAL_MB` | `1024` | Keep total logs under N MB via oldest-first cleanup |
 
 ## Error Handling
 

package/bundled/skills/refactor-pipeline-launcher/SKILL.md

@@ -154,8 +154,8 @@ Detect user intent from their message, then follow the corresponding workflow:
    - Off — Skip post-task test verification (faster but riskier)
 
    **Question 4 — Advanced config?** (multiSelect: false):
-   - No (default) — Use defaults for critic review, session timeout, and failure behavior
-   - Yes — Configure critic review, session timeout, stop-on-failure, and reasoning effort options
+   - No (default) — Use defaults for critic review and failure behavior
+   - Yes — Configure critic review, stop-on-failure, and reasoning effort options
 
    Note: Refactor filter defaults to all refactor items (by priority order). If the user selects "Other" on any option, handle their custom input.
 
@@ -172,7 +172,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```bash
-   VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high \
+   VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high \
      .prizmkit/dev-pipeline/run-refactor.sh run .prizmkit/plans/refactor-list.json
    ```
 

package/bundled/skills/refactor-pipeline-launcher/references/configuration.md

@@ -14,7 +14,6 @@ Translating user responses to env vars:
 | Strict behavior: On | `STRICT_BEHAVIOR_CHECK=1` |
 | Strict behavior: Off | `STRICT_BEHAVIOR_CHECK=0` |
 | Critic: On | `ENABLE_CRITIC=true` |
-| Timeout: value | `SESSION_TIMEOUT=<seconds>` |
 | Stop on failure: On | `STOP_ON_FAILURE=1` |
 | Deploy: Yes | `ENABLE_DEPLOY=1` |
 | Effort: value | `PRIZMKIT_EFFORT=<value>` |
@@ -30,9 +29,6 @@ Not exposed in interactive menu, pass via `--env`:
 | `DEV_BRANCH` | auto-generated | Custom dev branch name (default: `refactor/pipeline-{run_id}`) |
 | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
 | `HEARTBEAT_STALE_THRESHOLD` | `600` | Max seconds without heartbeat before marking stale |
-| `LOG_CLEANUP_ENABLED` | `1` | Run periodic log cleanup (`0` to disable) |
-| `LOG_RETENTION_DAYS` | `14` | Delete logs older than N days |
-| `LOG_MAX_TOTAL_MB` | `1024` | Keep total logs under N MB via oldest-first cleanup |
 
 ## Error Handling
 
@@ -57,23 +53,17 @@ Not exposed in interactive menu, pass via `--env`:
 
 Only run this when the user answered "Yes" to the **Advanced config?** question in step 6. It applies to a minority of sessions.
 
-Ask a second round of `AskUserQuestion` with these 4 questions:
+Ask a second round of `AskUserQuestion` with these 3 questions:
 
-**Question 1 — Session timeout** (multiSelect: false):
-- None (default) — No timeout
-- 30 min — `SESSION_TIMEOUT=1800`
-- 1 hour — `SESSION_TIMEOUT=3600`
-- 2 hours — `SESSION_TIMEOUT=7200`
-
-**Question 2 — Stop on failure** (multiSelect: false):
+**Question 1 — Stop on failure** (multiSelect: false):
 - Off (default) — Pipeline continues to next task after failure
 - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
-**Question 3 — Critic review** (multiSelect: false):
+**Question 2 — Critic review** (multiSelect: false):
 - Off (default) — Skip adversarial review
 - On — Enable adversarial critic review: an independent AI agent reviews the refactor plan for completeness and the implementation for regressions, missed edge cases, and behavior violations. Adds ~5-10 min per refactor task.
 
-**Question 4 — Deploy after completion?** (multiSelect: false):
+**Question 3 — Deploy after completion?** (multiSelect: false):
 - No (default) — Skip deployment after pipeline completes
 - Yes — Run /prizmkit-deploy automatically after all refactors complete successfully (`ENABLE_DEPLOY=1`). Deployment is blocked if any refactor did not complete successfully (status not 'completed' or manually 'skipped').
 

package/bundled/skills-windows/bugfix-pipeline-launcher/SKILL.md

@@ -155,7 +155,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```powershell
-   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"; $env:PRIZMKIT_EFFORT = "high"
+   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:PRIZMKIT_EFFORT = "high"
    .\.prizmkit\dev-pipeline\run-bugfix.ps1 run .prizmkit/plans/bug-fix-list.json
    ```
 

package/bundled/skills-windows/bugfix-pipeline-launcher/references/configuration.md

@@ -12,7 +12,6 @@ Translating user responses to env vars:
 | Verbose: On | `VERBOSE=1` |
 | Max retries: N | `MAX_RETRIES=N` |
 | Critic: On | `ENABLE_CRITIC=1` |
-| Timeout: value | `SESSION_TIMEOUT=<seconds>` |
 | Stop on failure: On | `STOP_ON_FAILURE=1` |
 | Deploy: Yes | `ENABLE_DEPLOY=1` |
 | Effort: value | `PRIZMKIT_EFFORT=<value>` |
@@ -28,9 +27,6 @@ Not exposed in interactive menu, pass via `--env`:
 | `DEV_BRANCH` | auto-generated | Custom dev branch name (default: `bugfix/pipeline-{run_id}`) |
 | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
 | `HEARTBEAT_STALE_THRESHOLD` | `600` | Max seconds without heartbeat before marking stale |
-| `LOG_CLEANUP_ENABLED` | `1` | Run periodic log cleanup (`0` to disable) |
-| `LOG_RETENTION_DAYS` | `14` | Delete logs older than N days |
-| `LOG_MAX_TOTAL_MB` | `1024` | Keep total logs under N MB via oldest-first cleanup |
 
 ## Interactive Configuration Options
 
@@ -52,24 +48,18 @@ Present these via `AskUserQuestion` in step 5. Round 1 is one `AskUserQuestion`
 - On — Enable adversarial critic review (`ENABLE_CRITIC=1`): an independent AI agent reviews the diagnosis/plan for completeness and the fix for defects, edge cases, and regression risks. Adds ~5-10 min per bug.
 
 **Question 4 — Advanced config?** (multiSelect: false):
-- No (default) — Use defaults for session timeout and failure behavior
-- Yes — Configure session timeout, stop-on-failure, and reasoning effort options
+- No (default) — Use defaults for failure behavior
+- Yes — Configure stop-on-failure, and reasoning effort options
 
 Note: Bug filter defaults to all bugs (by severity order). Default Critic to Off unless bugs have `severity: "critical"` or `severity: "high"` (in which case default to On). If the user selects "Other" on any option, handle their custom input.
 
 ### Round 2 (only if Advanced config = Yes)
 
-**Question 1 — Session timeout** (multiSelect: false):
-- None (default) — No timeout
-- 30 min — `SESSION_TIMEOUT=1800`
-- 1 hour — `SESSION_TIMEOUT=3600`
-- 2 hours — `SESSION_TIMEOUT=7200`
-
-**Question 2 — Stop on failure** (multiSelect: false):
+**Question 1 — Stop on failure** (multiSelect: false):
 - Off (default) — Pipeline continues to next task after failure
 - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
-**Question 3 — Reasoning effort** (multiSelect: false):
+**Question 2 — Reasoning effort** (multiSelect: false):
 - Default (none) — Use CLI default
 - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
 - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)

package/bundled/skills-windows/feature-pipeline-launcher/SKILL.md

@@ -176,12 +176,12 @@ Detect user intent from their message, then follow the corresponding workflow:
    - 5
 
    **Question 4 — Advanced config?** (multiSelect: false):
-   - No (default) — Use defaults for session timeout and failure behavior
-   - Yes — Configure session timeout, stop-on-failure, and reasoning effort options
+   - No (default) — Use defaults for failure behavior
+   - Yes — Configure stop-on-failure, and reasoning effort options
 
    Default Critic to Off unless features have `estimated_complexity: "high"` or above (in which case default to On).
 
-   **If user chose "Yes" to Advanced config**, ask a second round of `AskUserQuestion` — see the advanced config questions (session timeout, stop-on-failure, reasoning effort) in `${SKILL_DIR}/references/configuration.md`.
+   **If user chose "Yes" to Advanced config**, ask a second round of `AskUserQuestion` — see the advanced config questions (stop-on-failure, reasoning effort) in `${SKILL_DIR}/references/configuration.md`.
 
    **Environment variable mapping** and **advanced environment variables** tables — read `${SKILL_DIR}/references/configuration.md` for the full translation tables (8 config→env mappings + 9 advanced variables).
 
@@ -195,7 +195,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```powershell
-   $env:VERBOSE = "1"; $env:ENABLE_CRITIC = "true"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"; $env:PRIZMKIT_EFFORT = "high"
+   $env:VERBOSE = "1"; $env:ENABLE_CRITIC = "true"; $env:MAX_RETRIES = "5"; $env:PRIZMKIT_EFFORT = "high"
    .\.prizmkit\dev-pipeline\run-feature.ps1 run .prizmkit/plans/feature-list.json --features F-001:F-005
    ```
 

package/bundled/skills-windows/feature-pipeline-launcher/references/configuration.md

@@ -6,17 +6,11 @@ Environment variable mappings for the feature launcher.
 
 Asked only when the user chose "Yes" to Advanced config in step 6.
 
-**Question 1 — Session timeout** (multiSelect: false):
-- None (default) — No timeout
-- 30 min — `SESSION_TIMEOUT=1800`
-- 1 hour — `SESSION_TIMEOUT=3600`
-- 2 hours — `SESSION_TIMEOUT=7200`
-
-**Question 2 — Stop on failure** (multiSelect: false):
+**Question 1 — Stop on failure** (multiSelect: false):
 - Off (default) — Pipeline continues to next task after failure
 - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
-**Question 3 — Reasoning effort** (multiSelect: false):
+**Question 2 — Reasoning effort** (multiSelect: false):
 - Default (none) — Use CLI default
 - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
 - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
@@ -34,7 +28,6 @@ Translating user responses to env vars:
 | Verbose: Off | `VERBOSE=0` |
 | Verbose: On | `VERBOSE=1` |
 | Max retries: N | `MAX_RETRIES=N` |
-| Timeout: value | `SESSION_TIMEOUT=<seconds>` |
 | Stop on failure: On | `STOP_ON_FAILURE=1` |
 | Deploy: Yes | `ENABLE_DEPLOY=1` |
 | Effort: value | `PRIZMKIT_EFFORT=<value>` |
@@ -51,9 +44,6 @@ Not exposed in interactive menu, pass via `--env`:
 | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
 | `HEARTBEAT_STALE_THRESHOLD` | `600` | Max seconds without heartbeat before marking stale |
 | `PIPELINE_MODE` | (none) | Override mode for all features: `lite`\|`standard`\|`full` |
-| `LOG_CLEANUP_ENABLED` | `1` | Run periodic log cleanup (`0` to disable) |
-| `LOG_RETENTION_DAYS` | `14` | Delete logs older than N days |
-| `LOG_MAX_TOTAL_MB` | `1024` | Keep total logs under N MB via oldest-first cleanup |
 
 ## Error Handling
 

package/bundled/skills-windows/refactor-pipeline-launcher/SKILL.md

@@ -176,8 +176,8 @@ Detect user intent from their message, then follow the corresponding workflow:
    - 5
 
    **Question 3 — Advanced config?** (multiSelect: false):
-   - No (default) — Use defaults for critic review, session timeout, and failure behavior
-   - Yes — Configure critic review, session timeout, stop-on-failure, and reasoning effort options
+   - No (default) — Use defaults for critic review and failure behavior
+   - Yes — Configure critic review, stop-on-failure, and reasoning effort options
 
    Note: Refactor filter defaults to all refactor items (by priority order). If the user selects "Other" on any option, handle their custom input.
 
@@ -195,7 +195,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```powershell
-   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"; $env:PRIZMKIT_EFFORT = "high"
+   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:PRIZMKIT_EFFORT = "high"
    .\.prizmkit\dev-pipeline\run-refactor.ps1 run .prizmkit/plans/refactor-list.json
    ```
 

package/bundled/skills-windows/refactor-pipeline-launcher/references/configuration.md

@@ -14,7 +14,6 @@ Translating user responses to env vars:
 | Strict behavior: On | `STRICT_BEHAVIOR_CHECK=1` |
 | Strict behavior: Off | `STRICT_BEHAVIOR_CHECK=0` |
 | Critic: On | `ENABLE_CRITIC=true` |
-| Timeout: value | `SESSION_TIMEOUT=<seconds>` |
 | Stop on failure: On | `STOP_ON_FAILURE=1` |
 | Deploy: Yes | `ENABLE_DEPLOY=1` |
 | Effort: value | `PRIZMKIT_EFFORT=<value>` |
@@ -30,9 +29,6 @@ Not exposed in interactive menu, pass via `--env`:
 | `DEV_BRANCH` | auto-generated | Custom dev branch name (default: `refactor/pipeline-{run_id}`) |
 | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
 | `HEARTBEAT_STALE_THRESHOLD` | `600` | Max seconds without heartbeat before marking stale |
-| `LOG_CLEANUP_ENABLED` | `1` | Run periodic log cleanup (`0` to disable) |
-| `LOG_RETENTION_DAYS` | `14` | Delete logs older than N days |
-| `LOG_MAX_TOTAL_MB` | `1024` | Keep total logs under N MB via oldest-first cleanup |
 
 ## Error Handling
 
@@ -57,23 +53,17 @@ Not exposed in interactive menu, pass via `--env`:
 
 Only run this when the user answered "Yes" to the **Advanced config?** question in step 6. It applies to a minority of sessions.
 
-Ask a second round of `AskUserQuestion` with these 4 questions:
+Ask a second round of `AskUserQuestion` with these 3 questions:
 
-**Question 1 — Session timeout** (multiSelect: false):
-- None (default) — No timeout
-- 30 min — `SESSION_TIMEOUT=1800`
-- 1 hour — `SESSION_TIMEOUT=3600`
-- 2 hours — `SESSION_TIMEOUT=7200`
-
-**Question 2 — Stop on failure** (multiSelect: false):
+**Question 1 — Stop on failure** (multiSelect: false):
 - Off (default) — Pipeline continues to next task after failure
 - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
-**Question 3 — Critic review** (multiSelect: false):
+**Question 2 — Critic review** (multiSelect: false):
 - Off (default) — Skip adversarial review
 - On — Enable adversarial critic review: an independent AI agent reviews the refactor plan for completeness and the implementation for regressions, missing edge cases, and behavior violations. Adds ~5-10 min per refactor task.
 
-**Question 4 — Reasoning effort** (multiSelect: false):
+**Question 3 — Reasoning effort** (multiSelect: false):
 - Default (none) — Use CLI default
 - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
 - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.92",
+  "version": "1.1.93",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {

package/bundled/dev-pipeline/scripts/cleanup-logs.py

@@ -1,192 +0,0 @@
-#!/usr/bin/env python3
-"""Clean up pipeline session logs by age and total size.
-
-Targets files under any `.../sessions/.../logs/` directory inside a state dir.
-
-Policies:
-1) Remove files older than retention window.
-2) If total remaining size still exceeds max threshold, remove oldest files first
-   until within threshold.
-
-Usage:
-  python3 cleanup-logs.py --state-dir .prizmkit/state/features
-  python3 cleanup-logs.py --state-dir .prizmkit/state/bugfix --retention-days 30 --max-total-mb 2048
-"""
-
-import argparse
-import json
-import os
-import time
-
-from utils import error_out, setup_logging
-
-LOGGER = setup_logging("cleanup-logs")
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(description="Cleanup pipeline logs by age and total size.")
-    parser.add_argument("--state-dir", required=True, help="State directory to scan")
-    parser.add_argument(
-        "--retention-days",
-        type=int,
-        default=14,
-        help="Delete logs older than this many days (default: 14)",
-    )
-    parser.add_argument(
-        "--max-total-mb",
-        type=int,
-        default=1024,
-        help="Target max total log size in MB after cleanup (default: 1024)",
-    )
-    parser.add_argument("--dry-run", action="store_true", help="Report actions without deleting")
-    return parser.parse_args()
-
-
-def iter_log_files(state_dir):
-    """Yield absolute paths of files inside .../sessions/.../logs/ directories."""
-    for root, _dirs, files in os.walk(state_dir):
-        if os.path.basename(root) != "logs":
-            continue
-
-        normalized = root.replace("\\", "/")
-        if "/sessions/" not in normalized:
-            continue
-
-        for name in files:
-            if name == ".DS_Store":
-                continue
-            yield os.path.join(root, name)
-
-
-def file_info(path):
-    """Return file metadata dict with path, size, and mtime."""
-    st = os.stat(path)
-    return {"path": path, "size": st.st_size, "mtime": st.st_mtime}
-
-
-def remove_file(path, dry_run=False):
-    if dry_run:
-        return True
-    try:
-        os.remove(path)
-        return True
-    except OSError:
-        return False
-
-
-def cleanup_empty_dirs(state_dir, dry_run=False):
-    """Remove empty logs directories bottom-up."""
-    removed = 0
-    for root, dirs, _files in os.walk(state_dir, topdown=False):
-        for d in dirs:
-            full = os.path.join(root, d)
-            if os.path.basename(full) != "logs":
-                continue
-            try:
-                if not os.listdir(full):
-                    if not dry_run:
-                        os.rmdir(full)
-                    removed += 1
-            except OSError:
-                continue
-    return removed
-
-
-def main():
-    args = parse_args()
-    state_dir = os.path.abspath(args.state_dir)
-
-    if not os.path.isdir(state_dir):
-        error_out("State directory not found: {}".format(state_dir), code=2)
-
-    if args.retention_days < 0:
-        error_out("retention-days must be >= 0", code=2)
-    if args.max_total_mb < 0:
-        error_out("max-total-mb must be >= 0", code=2)
-
-    now = time.time()
-    retention_cutoff = now - (args.retention_days * 86400)
-    max_total_bytes = args.max_total_mb * 1024 * 1024
-
-    files = []
-    for path in iter_log_files(state_dir):
-        try:
-            files.append(file_info(path))
-        except OSError:
-            continue
-
-    initial_total = sum(f["size"] for f in files)
-
-    deleted_files = []
-    kept_files = []
-
-    # Step 1: age-based cleanup
-    for f in files:
-        if f["mtime"] < retention_cutoff:
-            if remove_file(f["path"], dry_run=args.dry_run):
-                deleted_files.append({**f, "reason": "retention"})
-            else:
-                kept_files.append(f)
-        else:
-            kept_files.append(f)
-
-    # Step 2: size-based cleanup (oldest first)
-    current_total = sum(f["size"] for f in kept_files)
-    if current_total > max_total_bytes:
-        kept_files.sort(key=lambda x: x["mtime"])  # oldest first
-        still_kept = []
-        for f in kept_files:
-            if current_total <= max_total_bytes:
-                still_kept.append(f)
-                continue
-
-            if remove_file(f["path"], dry_run=args.dry_run):
-                deleted_files.append({**f, "reason": "size"})
-                current_total -= f["size"]
-            else:
-                still_kept.append(f)
-
-        kept_files = still_kept
-
-    removed_empty_log_dirs = cleanup_empty_dirs(state_dir, dry_run=args.dry_run)
-
-    final_total = sum(f["size"] for f in kept_files)
-    reclaimed = initial_total - final_total
-
-    report = {
-        "success": True,
-        "state_dir": state_dir,
-        "dry_run": args.dry_run,
-        "retention_days": args.retention_days,
-        "max_total_mb": args.max_total_mb,
-        "initial_files": len(files),
-        "deleted_files": len(deleted_files),
-        "deleted_by_reason": {
-            "retention": sum(1 for f in deleted_files if f["reason"] == "retention"),
-            "size": sum(1 for f in deleted_files if f["reason"] == "size"),
-        },
-        "removed_empty_log_dirs": removed_empty_log_dirs,
-        "initial_total_bytes": initial_total,
-        "final_total_bytes": final_total,
-        "reclaimed_bytes": reclaimed,
-    }
-
-    LOGGER.info(
-        "cleanup complete: deleted=%s reclaimed=%sKB",
-        report["deleted_files"],
-        int(report["reclaimed_bytes"] / 1024),
-    )
-
-    print(json.dumps(report, indent=2, ensure_ascii=False))
-
-
-if __name__ == "__main__":
-    try:
-        main()
-    except KeyboardInterrupt:
-        error_out("cleanup-logs interrupted", code=130)
-    except SystemExit:
-        raise
-    except Exception as exc:
-        LOGGER.exception("Unhandled exception in cleanup-logs")
-        error_out("cleanup-logs failed: {}".format(str(exc)), code=1)