diff --git a/fpga-goldenref-flow/SKILL.md b/fpga-goldenref-flow/SKILL.md
new file mode 100644
index 0000000..9a16b6b
--- /dev/null
+++ b/fpga-goldenref-flow/SKILL.md
@@ -0,0 +1,219 @@
+---
+name: fpga-goldenref-flow
+description: >
+  Run the fpga-goldenref-flow LangGraph design-and-execution workflow for the
+  project at E:\LangGraph_Design\fpga-goldenref-flow. Drives the compiled graph
+  in-process (NO langgraph dev server) via a persistent SQLite checkpointer:
+  submits a run, surfaces the human-review interrupt (plans are summarised in the
+  Claude conversation for the user to approve/reject), resumes execution, and
+  displays the final summary — all within the Claude session.
+
+  Trigger whenever the user says any of: "run FPGA flow", "start FPGA workflow",
+  "invoke fpga-goldenref-flow", "run goldenref flow", "启动 FPGA 工作流",
+  "运行 FPGA 设计流程", "跑一下 FPGA flow", "run the FPGA agent",
+  "execute the FPGA design pipeline", or any request to interact with the
+  LangGraph agent inside this project. Also trigger when the user wants to approve
+  or reject the generated plan, or resume a paused fpga-goldenref-flow run.
+---
+
+## 驱动方式：进程内驱动（无 dev server）
+
+工作流是一张 LangGraph 图，由 `scripts\run_fpga_local.py` **在本进程内**驱动
+（已移除 langgraph dev server 路径）。直接 `build_graph()` + **SqliteSaver 持久化**
+驱动编译好的图，状态存在 `<output_dir>\.fpga_flow_local.sqlite`，按 `thread_id`
+持久化，`start`/`resume`/`continue` 各自独立进程调用都能接续。
+
+```powershell
+conda run -n langgraph python `
+  "C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
+  start --input-dir "E:\<proj>\Notes" --output-dir "E:\<proj>\fpga_runs"
+```
+
+为什么是进程内驱动：`langgraph dev` 是**内存存储的开发服务器**，对本项目这种长耗时、
+多模块、反复中断续跑的执行不可靠——重启丢线程、run 队列被 cancel 残留堵成永久
+`pending`、watchfiles `--reload` 自激。进程内驱动没有这些问题（无队列、无内存丢失、
+无 reload），状态全部落在 SQLite。
+
+---
+
+## Project info
+
+| Item | Value |
+|---|---|
+| Root | `E:\LangGraph_Design\fpga-goldenref-flow` |
+| Conda env | `langgraph` (`C:\Users\bowei\.conda\envs\langgraph`) |
+| Graph name | `fpga_goldenref_flow` (在 `langgraph.json` 里声明；进程内驱动直接 `build_graph()`) |
+| Default input dir | `Notes/` (contains PR00.md, Task00.md) |
+| Helper script | `C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py` |
+
+---
+
+## Full workflow
+
+> **入口约束**：下面每一步都通过 helper 脚本 `run_fpga_local.py` 在 `langgraph`
+> conda 环境里执行。不要直接 `import` `app.*` 在别处运行，统一走 helper 脚本以保证
+> SQLite 持久化与退出码一致。
+
+### Step 1 — Submit a new run
+
+**Before calling the script, determine the two key paths:**
+- `--input-dir` — the directory that holds the project's requirement files (e.g. `Notes/`). Use an absolute path or a path relative to the current shell's CWD.
+- `--output-dir` — the directory where all generated files (task folders, plan.md, summary.md) and the run's checkpoint DB + session file will be written. **This must be inside the caller's project directory, not inside the workflow development directory.** Use the absolute path to the project being worked on, e.g. `E:\MyProject\fpga_runs`.
+
+Run the helper script using the `langgraph` conda environment:
+```powershell
+conda run -n langgraph python `
+  "C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
+  start `
+  --input-dir "E:\<project-path>\Notes" `
+  --output-dir "E:\<project-path>\fpga_runs"
+```
+
+Optional flag: `--prompt "additional context"` if the user supplied extra requirements.
+
+> **Rule:** always pass `--output-dir` as an absolute path pointing into the calling project.
+> If omitted, files fall back to `<input-dir-parent>/runs` which may or may not be in the project directory.
+
+The script prints `[INFO] Thread : <id>` and `[INFO] Output dir : <path>` (note them
+for resume), then node-level progress (`-> node_name`) as the graph runs.
+
+**Exit codes:**
+| Code | Meaning |
+|---|---|
+| 0 | Workflow completed — jump to Step 4 |
+| 1 | Error — read the output, diagnose, report to user |
+| 2 | An interrupt fired — read the `[INTERRUPT]` payload's `action` and branch (see below) |
+| 3 | Codex unavailable — workflow stopped (no downgrade). Resume from checkpoint later with `continue`. |
+
+**Two interrupts fire in order — branch on `action` in the `[INTERRUPT]` payload:**
+1. `"action": "select_plan_model"` — first, right after decomposition → **Step 1.5**.
+2. `"action": "confirm_plan"` — later, after plans are generated → **Step 2**.
+
+### Step 1.5 — Select plan model (first interrupt)
+
+When the `[INTERRUPT]` payload has `"action": "select_plan_model"`, the workflow has
+finished decomposition and is waiting for the user to pick the Claude model used to
+**author/revise** the plans (review stays on Codex). The payload includes `default`
+(Opus 4.8) and the decomposition overview.
+
+Ask the user which model (use AskUserQuestion), offering **Opus 4.8 (default/recommended)**,
+**Fable 5**, **Sonnet 4.6**. Then resume with the choice:
+```powershell
+conda run -n langgraph python `
+  "C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
+  resume --output-dir "E:\<project-path>\fpga_runs" `
+  --plan-model opus    # or: fable | sonnet | a full id like claude-opus-4-8
+```
+The workflow then generates plans with that model and stops again at the
+`confirm_plan` interrupt (exit 2) → go to Step 2.
+
+### Step 2 — Human review (Claude reads plans, asks user)
+
+When the script exits with code 2 (`confirm_plan`) it prints:
+- `[INTERRUPT]` — the raw interrupt payload (may include a message)
+- `[PLAN] <task_id>: <path>` — absolute paths to generated plan files
+- `[REQ]  <task_id>: <path>` — absolute paths to requirement files
+
+For each plan path, read the file:
+```powershell
+Get-Content "<plan_path>" -Encoding utf8
+```
+
+Then **summarise the plan for the user** in 3–5 bullet points per task and ask:
+
+> "FPGA 工作流已生成以下设计计划，请确认是否批准继续执行：
+> …bullet points…
+> **批准（继续执行）还是拒绝（请说明需要修改的地方）？**"
+
+Wait for the user's answer before proceeding to Step 3.
+
+### Step 3 — Resume the workflow
+
+> **并发安全(MANDATORY)**：`resume` 必须绑定到本次运行的工程，绝不能依赖全局会话文件。
+> **总是带上 `--output-dir`**（与 `start` 时完全相同的绝对路径），这样多个工程并发时
+> 各自的会话文件与 SQLite 互不串。等价地，也可以用 `--thread-id "<start 打印的 Thread id>"`
+> 直接指定线程，完全绕过会话文件（最稳）。省略两者只在「同一时间只有一个工程在跑」时才安全。
+
+**If the user approves:**
+```powershell
+conda run -n langgraph python `
+  "C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
+  resume --output-dir "E:\<project-path>\fpga_runs"
+```
+(Default behaviour is approved — no extra flag needed.)
+
+**If the user rejects:**
+```powershell
+conda run -n langgraph python `
+  "C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
+  resume --output-dir "E:\<project-path>\fpga_runs" `
+  --rejected --feedback "<user feedback verbatim>"
+```
+
+> Use the **same `--output-dir`** you passed at `start` (it is printed on the
+> `[INFO] Output dir :` line). Alternatively pass `--thread-id "<id>"` from the
+> `[INFO] Thread :` line at start.
+
+After rejection the workflow loops back to plan generation; you will likely hit
+exit code 2 again with new plans — repeat Step 2.
+
+> **Codex 不可用 (exit 3)**：若任一 resume/start 以 exit 3 退出，说明 codex(gpt-5.5)
+> 额度被占满，工作流已停在断点（状态已存 SQLite，不降级）。等 codex 空出来后从断点续跑：
+> ```powershell
+> conda run -n langgraph python `
+>   "C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
+>   continue --output-dir "E:\<project-path>\fpga_runs"
+> ```
+
+### Step 4 — Show results
+
+When the script exits with code 0 it prints `[SUMMARY]` followed by the contents
+of `<output-dir>\summary.md`. Present this to the user.
+
+If the user wants to inspect a specific task's plan or requirement:
+```
+<output-dir>\<task_id>\plan.md
+<output-dir>\<task_id>\requirement.md
+```
+
+The `output-dir` is the value passed to `--output-dir` at start time (printed in the
+`[INFO] Output dir :` line) and is also stored in the session file.
+
+---
+
+## Session state (per-project — concurrency safe)
+
+Between `start` and `resume` the helper writes a small session file **inside the
+run's own `output_dir`**, so concurrent projects never share it:
+```
+<output_dir>\.fpga_flow_session.json
+```
+It holds `thread_id` and `output_dir`. `resume`/`continue` locate it via the
+`--output-dir` you pass (hence Step 3 requires it). It is deleted automatically when
+the run completes successfully.
+
+**Isolation guarantees for concurrent projects:**
+- Graph state (`MainState`/`FpgaState`, checkpoints) is isolated by `thread_id`
+  inside that run's own `<output_dir>\.fpga_flow_local.sqlite` — different projects
+  use different output dirs and different DBs, and cannot see each other's state.
+- Generated files are isolated by `output_dir`.
+- The session pointer is isolated by living inside each `output_dir`. **Always
+  pass `--output-dir` (or `--thread-id`) to `resume`** so it never reads another
+  project's session.
+
+To abandon a paused run and start fresh, delete that project's
+`<output_dir>\.fpga_flow_session.json` (and, if you want a clean checkpoint,
+`<output_dir>\.fpga_flow_local.sqlite`) before calling `start`.
+
+---
+
+## Troubleshooting
+
+| Symptom | Fix |
+|---|---|
+| `ModuleNotFoundError` | `conda run -n langgraph pip install langgraph langgraph-checkpoint-sqlite` |
+| `No session file found` | Must call `start` before `resume` (or pass `--thread-id`) |
+| Empty `[PLAN]` lines | Look in `<output_dir>\` for `plan.md` files under each `<task_id>` folder |
+| `interrupted` never advances | Make sure `--rejected` flag is accompanied by `--feedback` text |
+| exit 3 (Codex 不可用) | Wait for codex quota, then `continue --output-dir <same path>` from the checkpoint |
+| Stale state after editing `app\*` | In-process driver imports fresh each run; just re-run `start`/`continue`. To reset a thread, delete that run's `.fpga_flow_local.sqlite`. |
diff --git a/fpga-goldenref-flow/scripts/__pycache__/run_fpga_local.cpython-311.pyc b/fpga-goldenref-flow/scripts/__pycache__/run_fpga_local.cpython-311.pyc
new file mode 100644
index 0000000..106e44b
Binary files /dev/null and b/fpga-goldenref-flow/scripts/__pycache__/run_fpga_local.cpython-311.pyc differ
diff --git a/fpga-goldenref-flow/scripts/run_fpga_local.py b/fpga-goldenref-flow/scripts/run_fpga_local.py
new file mode 100644
index 0000000..c825ade
--- /dev/null
+++ b/fpga-goldenref-flow/scripts/run_fpga_local.py
@@ -0,0 +1,260 @@
+#!/usr/bin/env python3
+"""
+fpga-goldenref-flow workflow runner — IN-PROCESS driver (NO langgraph dev server).
+
+Drives the compiled LangGraph graph directly in this Python process with a
+persistent SQLite checkpointer. This avoids the langgraph dev server entirely:
+no REST, no in-memory store, no background run-queue / enqueue jams, no
+watchfiles reload loop. State persists across start/resume/continue invocations
+in <output_dir>/.fpga_flow_local.sqlite, keyed by thread_id.
+
+This is the sole driver for the graph (the langgraph dev server path has been
+removed). CLI + exit codes:
+
+  start     submit a new run; exits 2 at an interrupt
+  resume    answer an interrupt (--plan-model OR approve/--rejected --feedback)
+  continue  continue a thread paused at a normal node boundary (input=None)
+
+Exit codes: 0 complete · 1 error · 2 interrupted (human action needed)
+"""
+import os
+import sys
+import json
+import uuid
+import argparse
+import sqlite3
+
+# Drive the graph in-process: import the app package.
+FPGA_FLOW_ROOT = r"E:\LangGraph_Design\fpga-goldenref-flow"
+if FPGA_FLOW_ROOT not in sys.path:
+    sys.path.insert(0, FPGA_FLOW_ROOT)
+
+RECURSION_LIMIT = int(os.getenv("FPGA_FLOW_RECURSION_LIMIT", "300"))
+
+
+def _session_file(output_dir: str = "") -> str:
+    base = (output_dir or "").strip() or FPGA_FLOW_ROOT
+    return os.path.join(base, ".fpga_flow_session.json")
+
+
+def _db_path(output_dir: str) -> str:
+    base = (output_dir or "").strip() or FPGA_FLOW_ROOT
+    return os.path.join(base, ".fpga_flow_local.sqlite")
+
+
+def save_session(thread_id, output_dir):
+    with open(_session_file(output_dir), "w", encoding="utf-8") as f:
+        json.dump({"thread_id": thread_id, "output_dir": output_dir, "driver": "local"}, f)
+
+
+def load_session(output_dir=""):
+    path = _session_file(output_dir)
+    if not os.path.exists(path):
+        print(f"[FAIL] No session file at {path}. Run 'start' first (or pass --thread-id).", flush=True)
+        sys.exit(1)
+    with open(path, encoding="utf-8") as f:
+        return json.load(f)
+
+
+# ── graph + checkpointer ──────────────────────────────────────────────────────
+
+def _build(output_dir):
+    """Compile the graph with a persistent SQLite checkpointer (keeps the conn)."""
+    from langgraph.checkpoint.sqlite import SqliteSaver
+    from app.main_graph import build_graph
+    conn = sqlite3.connect(_db_path(output_dir), check_same_thread=False)
+    saver = SqliteSaver(conn)
+    try:
+        saver.setup()  # create checkpoint tables if not present
+    except Exception:
+        pass
+    return build_graph(checkpointer=saver), conn
+
+
+def _config(thread_id):
+    return {"configurable": {"thread_id": thread_id}, "recursion_limit": RECURSION_LIMIT}
+
+
+def _stream(graph, config, payload):
+    """Run the graph to its next pause, printing node-level progress."""
+    for chunk in graph.stream(payload, config, stream_mode="updates"):
+        if isinstance(chunk, dict):
+            for node in chunk:
+                if node and not str(node).startswith("__"):
+                    print(f"  -> {node}", flush=True)
+
+
+def _pending_interrupts(graph, config):
+    """Return list of interrupt payload values currently pending (if any)."""
+    snap = graph.get_state(config)
+    vals = []
+    for task in (snap.tasks or ()):
+        for it in (getattr(task, "interrupts", None) or ()):
+            v = getattr(it, "value", it)
+            vals.append(v)
+    return vals, snap
+
+
+def _print_interrupt(graph, config):
+    vals, snap = _pending_interrupts(graph, config)
+    for v in vals:
+        print(f"\n[INTERRUPT] {json.dumps(v, indent=2, default=str, ensure_ascii=False)}", flush=True)
+    # plan/requirement paths from state
+    values = snap.values or {}
+    for serial in values.get("serial_tasks", []):
+        for pt in serial.get("parallel_tasks", []):
+            tid = pt.get("task_id", "?")
+            if pt.get("plan_path"):
+                print(f"[PLAN] {tid}: {pt['plan_path']}", flush=True)
+            if pt.get("req_path"):
+                print(f"[REQ]  {tid}: {pt['req_path']}", flush=True)
+    print("\n[ACTION REQUIRED] Claude will read these plans and ask for your approval.", flush=True)
+
+
+def _show_summary(output_dir):
+    summary = os.path.join(output_dir, "summary.md")
+    if os.path.exists(summary):
+        with open(summary, encoding="utf-8") as f:
+            print(f"\n[SUMMARY]\n{f.read()}", flush=True)
+    else:
+        print(f"[DONE] Workflow completed. (summary not found at {summary})", flush=True)
+
+
+def _finish(graph, config, output_dir):
+    """After a stream returns, classify: interrupted (2) / done (0)."""
+    vals, snap = _pending_interrupts(graph, config)
+    if vals:
+        print("\n[STATUS] interrupted", flush=True)
+        _print_interrupt(graph, config)
+        sys.exit(2)
+    if snap.next:
+        # paused without an interrupt (rare) — treat as needing continue
+        print(f"\n[STATUS] paused (next={list(snap.next)})", flush=True)
+        sys.exit(2)
+    print("\n[STATUS] success", flush=True)
+    _show_summary(output_dir)
+    sf = _session_file(output_dir)
+    if os.path.exists(sf):
+        os.remove(sf)
+    sys.exit(0)
+
+
+# ── commands ──────────────────────────────────────────────────────────────────
+
+def cmd_start(args):
+    raw_out = (args.output_dir or "").strip()
+    output_dir = os.path.abspath(raw_out) if raw_out else os.path.join(
+        os.path.dirname(os.path.abspath(args.input_dir)), "runs")
+    os.makedirs(output_dir, exist_ok=True)
+    thread_id = str(uuid.uuid4())
+    print(f"[INFO] Driver : in-process (no dev server)", flush=True)
+    print(f"[INFO] Thread : {thread_id}", flush=True)
+    print(f"[INFO] Output dir : {output_dir}", flush=True)
+    print(f"[INFO] Checkpoints : {_db_path(output_dir)}", flush=True)
+
+    graph, conn = _build(output_dir)
+    try:
+        inp = {"input_dir": args.input_dir, "output_dir": output_dir}
+        if args.prompt:
+            inp["user_prompt"] = args.prompt
+        print("[INFO] Running fpga_flow graph ...\n", flush=True)
+        save_session(thread_id, output_dir)
+        _stream(graph, _config(thread_id), inp)
+        _finish(graph, _config(thread_id), output_dir)
+    finally:
+        conn.close()
+
+
+def _resolve_thread(args):
+    output_dir = (args.output_dir or "").strip()
+    thread_id = (getattr(args, "thread_id", "") or "").strip()
+    if not thread_id:
+        sess = load_session(output_dir)
+        thread_id = sess["thread_id"]
+        output_dir = sess.get("output_dir", output_dir)
+    return thread_id, output_dir
+
+
+def cmd_resume(args):
+    from langgraph.types import Command
+    thread_id, output_dir = _resolve_thread(args)
+    graph, conn = _build(output_dir)
+    try:
+        plan_model = (getattr(args, "plan_model", "") or "").strip()
+        if plan_model:
+            resume_val = {"plan_model": plan_model}
+            print(f"[INFO] Resuming {thread_id}  plan_model={plan_model}", flush=True)
+        else:
+            resume_val = {"approved": not args.rejected, "feedback": args.feedback or ""}
+            print(f"[INFO] Resuming {thread_id}  approved={not args.rejected}", flush=True)
+        print("", flush=True)
+        _stream(graph, _config(thread_id), Command(resume=resume_val))
+        _finish(graph, _config(thread_id), output_dir)
+    finally:
+        conn.close()
+
+
+def cmd_continue(args):
+    thread_id, output_dir = _resolve_thread(args)
+    graph, conn = _build(output_dir)
+    try:
+        print(f"[INFO] Continuing {thread_id} from checkpoint ...\n", flush=True)
+        _stream(graph, _config(thread_id), None)
+        _finish(graph, _config(thread_id), output_dir)
+    finally:
+        conn.close()
+
+
+def main():
+    p = argparse.ArgumentParser(description="fpga-goldenref-flow IN-PROCESS runner (no dev server)")
+    sub = p.add_subparsers(dest="cmd")
+
+    ps = sub.add_parser("start")
+    ps.add_argument("--input-dir", default="Notes/")
+    ps.add_argument("--output-dir", default="")
+    ps.add_argument("--prompt", default="")
+
+    pr = sub.add_parser("resume")
+    pr.add_argument("--plan-model", default="")
+    pr.add_argument("--rejected", action="store_true", default=False)
+    pr.add_argument("--feedback", default="")
+    pr.add_argument("--output-dir", default="")
+    pr.add_argument("--thread-id", default="")
+
+    pc = sub.add_parser("continue")
+    pc.add_argument("--output-dir", default="")
+    pc.add_argument("--thread-id", default="")
+
+    args = p.parse_args()
+    if not args.cmd:
+        p.print_help(); sys.exit(1)
+
+    try:
+        from app.nodes_design import CodexUnavailable
+    except Exception:
+        CodexUnavailable = ()  # type: ignore
+
+    try:
+        if args.cmd == "start":
+            cmd_start(args)
+        elif args.cmd == "resume":
+            cmd_resume(args)
+        elif args.cmd == "continue":
+            cmd_continue(args)
+    except SystemExit:
+        raise
+    except CodexUnavailable as exc:
+        out = getattr(args, "output_dir", "") or ""
+        bar = "=" * 64
+        print(f"\n{bar}", flush=True)
+        print("[ALARM] CODEX 不可用 —— 工作流已停止（不降级）", flush=True)
+        print(f"原因：{exc}", flush=True)
+        print("codex(gpt-5.5) 与你其它工作共享额度。请等 codex 空出来后,从断点续跑：", flush=True)
+        print(f'  run_fpga_local.py continue --output-dir "{out}"', flush=True)
+        print("状态已保存到 SQLite,不会丢失;不会回退到 Claude 或更弱模型。", flush=True)
+        print(bar, flush=True)
+        sys.exit(3)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/fpga-imx6-flow/SKILL.md b/fpga-imx6-flow/SKILL.md
new file mode 100644
index 0000000..94053db
--- /dev/null
+++ b/fpga-imx6-flow/SKILL.md
@@ -0,0 +1,177 @@
+---
+name: fpga-imx6-flow
+description: >
+  Run the fpga-imx6-flow LangGraph workflow at E:\LangGraph_Design\FPGA-imx6-flow —
+  the closed-loop SMOD (FPGA + i.MX6) hardware-in-the-loop design/debug pipeline:
+  power on the board, connect JTAG, program bitstream/flash, restart the imx6 app,
+  analyze (ILA + COM6 serial), judge against design requirements, and iterate by
+  modifying RTL/imx6 code. It drives the graph in-process (no langgraph dev) and
+  hands the 5 interrupts (analyze / meets-requirement / propose / modify-FPGA /
+  modify-imx6) back to this Claude session to execute.
+
+  ALWAYS use this skill whenever the user wants to run, start, drive, resume, or
+  continue the fpga-imx6-flow workflow / SMOD FPGA+imx6 design loop, or says things
+  like "启动 fpga-imx6-flow", "跑 imx6 设计流程", "run the imx6 FPGA flow", "执行
+  SMOD 设计任务", "继续 imx6 工作流", "resume the imx6 design loop", even if they
+  don't name the project path. Before driving the workflow this skill first confirms
+  the langgraph conda environment from /langgraph-vivado-install is in place.
+---
+
+## What this skill does
+
+Drives the **fpga-imx6-flow** graph (24 nodes / 34 flow-edges, 1:1 with
+`Notes/fpga-imx6-flow.excalidraw`). The graph's deterministic hardware/check nodes
+(power, JTAG, program, restart) run in-process; its **5 interrupt nodes** pause and
+hand control to **this Claude session**, which performs the real work (analysis,
+judgment, RTL/app edits) and resumes the same thread. Persistence is a SqliteSaver
+file, so `start`/`resume` survive across separate process calls.
+
+| Item | Value |
+|---|---|
+| Project root | `E:\LangGraph_Design\FPGA-imx6-flow` |
+| Conda env | `langgraph` (`C:\Users\bowei\.conda\envs\langgraph`) |
+| Graph | `app.main_graph:build_graph` (in-process; no langgraph dev) |
+| Driver | `C:\Users\bowei\.claude\skills\fpga-imx6-flow\scripts\run_imx6_flow.py` |
+| Checkpoint | `<project>\runs\skill_checkpoint.sqlite` (keyed by `--thread-id`) |
+| Design source | `Notes/fpga-imx6-flow.excalidraw`, plan `Notes/Task00.md` |
+
+## ⚠️ 硬件时序铁律（上电 / USB-Blast / 烧写，务必遵守）
+
+**每次给 SMOD 上电之前，USB-Blast 必须先断开；上电完成之后再重新连接。** 绝不在
+USB-Blast 处于连接状态时给板卡上电或断电（保护 JTAG 适配器与板卡）。
+
+标准时序（图拓扑已按此实现，手动操作或写 `tools_*` / 真机脚本时也必须遵守）：
+
+```
+断电(COM8 power_off) → 确认已断电 → 断开USB-Blast(COM4 blast_off) → 确认已断开
+  → 上电(COM8 power_on) → 确认已上电 → 连接USB-Blast(COM4 blast_on) → 连接JTAG/烧写/抓ILA
+```
+
+**烧写 flash 的完整闭环**（固化后必须断电重启从 flash 加载再验证）：
+
+```
+断电 → 断开USB-Blast → 上电 → 连接USB-Blast → 用 /fpga_flash 烧写flash
+  → 断电 → 断开USB-Blast → 上电 → 连接USB-Blast → 通过ILA验证flash内容正确
+```
+
+- 在 LangGraph 图里：`power_off → check_power_off →(是) blast_off_a → check_blast_off
+  →(是) power_on → check_power →(是) blast_on → check_hw`。`flash_burn` 烧写后回到
+  `power_off` 做整机断电重启，再次走完上述上电时序后才 `analyze`(抓ILA验证)。
+- **强化确认**：`power_on` 节点在上电前调用 `_ensure_blast_off_before_power()` 兜底确认
+  USB-Blast 已断开；若发现仍连接会强制断开并在 `history` 标记 `rule_violation=True`。
+- vivado-mcp 工具：`power_on`/`power_off`(COM8 继电器)、`USB_Blast_on`/`USB_Blast_off`(COM4)。
+
+> **Run via the env python directly** (not bare `conda run`): on this Windows GBK
+> console, `conda run` re-prints the child's UTF-8 stdout through a GBK codec and
+> **crashes on the Chinese interrupt payloads**. Use the env `python.exe`, or
+> `conda run --no-capture-output`. The driver also re-configures its stdout to UTF-8.
+
+```
+PY = C:\Users\bowei\.conda\envs\langgraph\python.exe
+RUN = C:\Users\bowei\.claude\skills\fpga-imx6-flow\scripts\run_imx6_flow.py
+```
+
+## Step 0 — Confirm the environment (REQUIRED before driving)
+
+The workflow runs in the `langgraph` conda env created by **`/langgraph-vivado-install`**.
+Verify it before starting, so a missing env surfaces as a clear instruction rather
+than a cryptic import error mid-run:
+
+```powershell
+$py = "C:\Users\bowei\.conda\envs\langgraph\python.exe"
+if (-not (Test-Path $py)) { Write-Host "[MISSING] langgraph env" } else {
+  & $py -c "import langgraph; from langgraph.checkpoint.sqlite import SqliteSaver; from langgraph.types import Command; print('[OK] langgraph + checkpoint-sqlite')"
+}
+```
+
+- **If `[OK]`** → proceed to Step 1.
+- **If missing / import fails** → tell the user the env isn't ready and to run
+  **`/langgraph-vivado-install`** first (it creates the `langgraph` env with
+  `langgraph` + `langgraph-checkpoint-sqlite` and the Vivado link). Do not proceed
+  until it succeeds.
+
+**For a real-hardware run** (`--real`), additionally confirm: `env_config.json`'s
+`VIVADO_BIN_PATH` is valid; the vivado-mcp `power_on`/`USB_Blast_on` tools are
+available; COM4/COM6/COM8 are present (`[System.IO.Ports.SerialPort]::GetPortNames()`).
+**Default runs are MOCK** (dry-run of the design loop with no hardware), because the
+workflow's `tools_*` real-hardware paths are still TODO — see "Mock vs real" below.
+
+## Step 1 — Start the workflow
+
+Ask the user (or infer) the first-pass program mode (`bitstream` default, or `flash`)
+and any `--bit-path`/`--flash-path`. Then start:
+
+```powershell
+& $py $RUN start --project-dir "E:\LangGraph_Design\FPGA-imx6-flow" `
+  --thread-id "imx6-<short-task-name>" --program-mode bitstream
+# add --real only when hardware tools are wired and the board is connected
+```
+
+The driver prints **one JSON line** and exits:
+
+| Exit | `status` | Meaning |
+|---|---|---|
+| 0 | `done` | Workflow finished (符合设计要求 / 迭代到上限) → Step 3 |
+| 1 | `error` | Read `error`, diagnose, report to user |
+| 2 | `interrupt` | An interrupt fired → read `interrupt.action` → Step 2 |
+
+## Step 2 — Handle the interrupt, then resume
+
+On exit 2, the JSON's `interrupt.action` tells you what the session must do. Perform
+it, then resume the **same `--thread-id`** with a JSON payload. Repeat until exit 0.
+
+| `action` | excalidraw node | What you (the session) do | Resume JSON |
+|---|---|---|---|
+| `analyze` | 通过ila/串口分析 | Grab COM6 serial log + pull ILA waveform (vivado-mcp); summarize | `{"analysis_log":"<摘要/路径>"}` |
+| `meets_requirement` | 符合设计要求? | Judge the analysis against the design requirement | `{"meets": true}` or `{"meets": false}` |
+| `propose` | 分析原因，提出修改方案 | Diagnose root cause; decide what to change + next program mode | `{"reason":"...","need_fpga": true/false,"need_imx6": true/false,"program_mode":"bitstream"或"flash"}` |
+| `modify_fpga` | 改 RTL→综合→出 bit/flash | Edit RTL, run Vivado synth/impl, produce bit + flash files | `{"bit_path":"...","flash_path":"...","program_mode":"flash"}` |
+| `modify_imx6` | VM 改 app→交叉编译 | In the Ubuntu VM (`bowei@192.168.223.128`) edit app + cross-compile | `{"app_path":"..."}` |
+
+Resume command:
+
+```powershell
+& $py $RUN resume --project-dir "E:\LangGraph_Design\FPGA-imx6-flow" `
+  --thread-id "imx6-<short-task-name>" --resume-json '{"meets": false}'
+```
+
+Notes:
+- Always pass the **same `--thread-id`** used at `start` — that's how the sqlite
+  checkpoint reattaches to the run (concurrency-safe: different tasks → different
+  thread ids → isolated state).
+- `propose` fans out to BOTH `decide_fpga` and `decide_imx6`; with `need_fpga:false`
+  and `need_imx6:false` the loop goes straight to `round_done` → re-program. Setting
+  either true fires the corresponding `modify_*` interrupt next.
+- After `round_done` the graph re-asks the program-mode decision; `program_mode` you
+  set in `propose`/`modify_fpga` chooses bitstream (download bit) vs flash (re-burn +
+  full power/connect re-sequence). This is the big closed loop.
+
+## Step 3 — Finish
+
+On exit 0 (`status: done`), report to the user: iterations completed and that the
+design met requirements (or hit the iteration cap). Offer to inspect
+`<project>\runs\` artifacts or the per-step `history`.
+
+To abandon a paused run and start clean, delete `<project>\runs\skill_checkpoint.sqlite`
+(or use a fresh `--thread-id`).
+
+## Mock vs real
+
+- **MOCK (default)** — `FPGA_IMX6_MOCK=1`; hardware/check nodes return success
+  immediately. Use this to dry-run the *design-loop logic* and the 5 interrupts with
+  no board attached. Great for demonstrating/validating the flow.
+- **Real (`--real`)** — drives actual hardware. Requires the project's
+  `app/tools_hw.py` / `tools_vivado.py` / `tools_imx6.py` real paths to be implemented
+  (they currently raise `NotImplementedError` as TODO — they will reuse the proven
+  vivado-mcp serial/Vivado logic). Until then, `--real` fails at the first hardware
+  node; tell the user to wire the tools first (see `Notes/Task00.md` §7).
+
+## Troubleshooting
+
+| Symptom | Fix |
+|---|---|
+| `UnicodeEncodeError: 'gbk' ...` | Don't use bare `conda run`; use the env `python.exe` or `conda run --no-capture-output`. |
+| `import failed ... Run /langgraph-vivado-install` | The `langgraph` env is missing/incomplete → run `/langgraph-vivado-install`. |
+| Exit 1 `NotImplementedError ... tools_*` | A `--real` run hit an unwired hardware tool. Run without `--real` (mock), or implement `tools_*`. |
+| `resume` seems to start over | You passed a different `--thread-id` than `start`. Use the same one. |
+| Need to see the graph visually | Optional: `langgraph dev` via the project's `langgraph.json` opens Studio — not required to run. |
diff --git a/fpga-imx6-flow/scripts/run_imx6_flow.py b/fpga-imx6-flow/scripts/run_imx6_flow.py
new file mode 100644
index 0000000..ef3da1e
--- /dev/null
+++ b/fpga-imx6-flow/scripts/run_imx6_flow.py
@@ -0,0 +1,123 @@
+"""In-process driver for the fpga-imx6-flow LangGraph workflow.
+
+Builds the compiled graph from the project's app package and drives it with a
+persistent SqliteSaver — no `langgraph dev` server. Mirrors the fpga-flow helper
+convention: exit code 0 = done, 1 = error, 2 = interrupt fired.
+
+Commands:
+    start   --project-dir <dir> [--program-mode bitstream|flash] [--bit-path ..]
+            [--flash-path ..] [--thread-id ..] [--real] [--max-iterations N]
+    resume  --project-dir <dir> --resume-json '<json>' [--thread-id ..] [--real]
+    status  --project-dir <dir> [--thread-id ..]
+
+Output: one JSON line on stdout describing status + the pending interrupt (if any).
+Run via the env python directly or `conda run --no-capture-output` to avoid the
+Windows GBK console re-encode crash on Chinese interrupt payloads.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import sys
+from pathlib import Path
+
+try:
+    sys.stdout.reconfigure(encoding="utf-8")  # emit UTF-8 even on a GBK console
+except Exception:
+    pass
+
+DEFAULT_PROJECT = r"E:\LangGraph_Design\FPGA-imx6-flow"
+
+
+def _emit(obj: dict, code: int) -> None:
+    print(json.dumps(obj, ensure_ascii=False))
+    sys.exit(code)
+
+
+def _pending_interrupt(snap):
+    for task in snap.tasks:
+        if task.interrupts:
+            return task.interrupts[0].value
+    return None
+
+
+def main() -> None:
+    ap = argparse.ArgumentParser(description="Drive the fpga-imx6-flow graph in-process.")
+    ap.add_argument("command", choices=["start", "resume", "status"])
+    ap.add_argument("--project-dir", default=DEFAULT_PROJECT)
+    ap.add_argument("--thread-id", default="imx6-skill-1")
+    ap.add_argument("--resume-json", default="")
+    ap.add_argument("--program-mode", default="bitstream", choices=["bitstream", "flash"])
+    ap.add_argument("--bit-path", default="")
+    ap.add_argument("--flash-path", default="")
+    ap.add_argument("--real", action="store_true",
+                    help="drive real hardware (workflow tools_* must be wired; default is MOCK dry-run)")
+    ap.add_argument("--max-iterations", type=int, default=8)
+    ap.add_argument("--max-hw-retry", type=int, default=3)
+    args = ap.parse_args()
+
+    project = Path(args.project_dir)
+    if not (project / "app" / "main_graph.py").exists():
+        _emit({"status": "error",
+               "error": f"app/main_graph.py not found under {project}; check --project-dir"}, 1)
+
+    # MOCK by default so the design loop can be dry-run with no hardware attached.
+    os.environ["FPGA_IMX6_MOCK"] = "0" if args.real else "1"
+    sys.path.insert(0, str(project))
+
+    try:
+        from langgraph.checkpoint.sqlite import SqliteSaver
+        from langgraph.types import Command
+        from app.main_graph import build_graph
+    except Exception as exc:  # noqa: BLE001
+        _emit({"status": "error",
+               "error": f"import failed: {exc}. Run /langgraph-vivado-install to set up the env."}, 1)
+
+    runs = project / "runs"
+    runs.mkdir(exist_ok=True)
+    db = str(runs / "skill_checkpoint.sqlite")
+    cfg = {"configurable": {"thread_id": args.thread_id}}
+
+    with SqliteSaver.from_conn_string(db) as cp:
+        graph = build_graph(checkpointer=cp)
+        try:
+            if args.command == "start":
+                init = {
+                    "iteration": 0,
+                    "program_mode": args.program_mode,
+                    "bit_path": args.bit_path,
+                    "flash_path": args.flash_path,
+                    "max_hw_retry": args.max_hw_retry,
+                    "max_iterations": args.max_iterations,
+                    "history": [],
+                }
+                graph.invoke(init, cfg)
+            elif args.command == "resume":
+                payload = json.loads(args.resume_json) if args.resume_json else {}
+                graph.invoke(Command(resume=payload), cfg)
+            # status: no invoke, just snapshot
+            snap = graph.get_state(cfg)
+        except Exception as exc:  # noqa: BLE001
+            _emit({"status": "error", "error": str(exc)}, 1)
+
+        if snap.next:
+            _emit({
+                "status": "interrupt",
+                "thread_id": args.thread_id,
+                "mock": not args.real,
+                "next": list(snap.next),
+                "iteration": snap.values.get("iteration"),
+                "interrupt": _pending_interrupt(snap),
+            }, 2)
+        else:
+            _emit({
+                "status": "done",
+                "thread_id": args.thread_id,
+                "iteration": snap.values.get("iteration"),
+                "steps": len(snap.values.get("history", [])),
+            }, 0)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/fpga_flash/SKILL.md b/fpga_flash/SKILL.md
index e39ce0d..9f80834 100644
--- a/fpga_flash/SKILL.md
+++ b/fpga_flash/SKILL.md
@@ -118,11 +118,18 @@ python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/program_flash.py" \
 - `--mcs-file`：第三步生成的 .mcs 路径
 - `--ltx-file`：若设计无 ILA，省略此参数（脚本自动跳过 PROBES.FILE 配置）
 
-此脚本在同一个 Vivado batch 会话中完成：硬件连接 → cfgmem 器件创建 → 擦除/编程/验证。
+此脚本在同一个 Vivado batch 会话中完成：硬件连接 → cfgmem 器件创建 → **载入 flash-loader 比特流（关键步骤）** → 擦除/编程/验证 → 回载用户 bit。
 
-**验证成功的标志：** 输出包含 `End of startup status: HIGH` 且无 `ERROR` 行。
+**验证成功的标志（真正写入 flash）：** 输出必须包含
+`Performing Erase Operation... Erase Operation successful`、
+`Program/Verify Operation successful`、`Flash programming completed successfully`，
+并能读到非零的 `Mfg ID`（如 Winbond=`ef`、Micron=`20`）。
+> ⚠️ 仅有 `End of startup status: HIGH` **不代表写了 flash**——那只是把 bit 载入 FPGA
+> 易失配置。若看到 `Mfg ID : 0 / Unable to read device properties`，说明 flash-loader
+> 没接管 SPI 总线（本 tcl 已用 `create_hw_bitstream`+`program_hw_devices` 载入
+> `spi_<part>_pullnone.bit` 修复此问题）。
 
-ILA core 的 `Dropping logic core` WARNING 是正常现象（golden 镜像不含 ILA core），不影响烧写结果。
+ILA core 的 `Dropping logic core` WARNING 是正常现象（载入 loader/golden 镜像时不含 ILA core），不影响烧写结果。
 
 ---
 
diff --git a/fpga_flash/scripts/step4_5_program.tcl b/fpga_flash/scripts/step4_5_program.tcl
index e247fde..a246568 100644
--- a/fpga_flash/scripts/step4_5_program.tcl
+++ b/fpga_flash/scripts/step4_5_program.tcl
@@ -38,6 +38,21 @@ set_property PROGRAM.FILES [list $mcs_file] \
   [get_property PROGRAM.HW_CFGMEM [lindex [get_hw_devices xc7a200t_0] 0]]
 refresh_hw_device [lindex [get_hw_devices xc7a200t_0] 0]
 
+# --- CRITICAL: load Vivado's flash-loader bitstream into the FPGA FIRST so it
+#     bridges JTAG<->SPI flash and takes over the SPI bus. Without this, the user
+#     design (or boot image) holds the SPI pins and the flash read returns
+#     "Mfg ID : 0 / Unable to read device properties" (program fails silently).
+#     This is exactly what the Vivado GUI "Program Configuration Memory Device"
+#     does under the hood before program_hw_cfgmem. ---
+set loader_bit [get_property PROGRAM.HW_CFGMEM_BITFILE [lindex [get_hw_devices xc7a200t_0] 0]]
+create_hw_bitstream -hw_device [lindex [get_hw_devices xc7a200t_0] 0] $loader_bit
+program_hw_devices [lindex [get_hw_devices xc7a200t_0] 0]
+
+# Erase + program + verify the SPI flash (this is the actual flash write).
+program_hw_cfgmem -hw_cfgmem [get_property PROGRAM.HW_CFGMEM [lindex [get_hw_devices xc7a200t_0] 0]]
+
+# Optionally reload the user bit + probes so the device runs the design (with ILA)
+# after flashing. A power-cycle will boot the same content from flash.
 if {$has_ltx} {
     set_property PROBES.FILE      $ltx_file [get_hw_devices xc7a200t_0]
     set_property FULL_PROBES.FILE $ltx_file [get_hw_devices xc7a200t_0]
diff --git a/langgraph-plan-review/.langgraph_api/.langgraph_ops.pckl b/langgraph-plan-review/.langgraph_api/.langgraph_ops.pckl
new file mode 100644
index 0000000..c3b8e8e
Binary files /dev/null and b/langgraph-plan-review/.langgraph_api/.langgraph_ops.pckl differ
diff --git a/langgraph-plan-review/SKILL.md b/langgraph-plan-review/SKILL.md
index faf0814..d20d285 100644
--- a/langgraph-plan-review/SKILL.md
+++ b/langgraph-plan-review/SKILL.md
@@ -7,6 +7,32 @@ description: Use the LangGraph plan-review workflow from the current Claude Code
 
 Use this skill to run the LangGraph plan-review workflow. All scripts are bundled under the skill's own `scripts\` directory (`C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\`) — no dependency on `E:\LangGraph_Design\lab00`.
 
+## ⚠️ 强制执行规则（MANDATORY — read first）
+
+**plan-review 工作流必须、且只能通过 `langgraph dev` 服务器来驱动。**
+
+- ✅ **唯一允许的入口**：`run_langgraph.ps1` → `run_workflow.py`。后者是一个**纯 REST/SDK 客户端**
+  （`langgraph_sdk.get_sync_client(url=http://127.0.0.1:2024)`），每次 start/resume 都把 run
+  投递到 `langgraph dev` 服务器执行。先用 `manage_dev_server.ps1 start` 把服务器拉起。
+  这样 LangGraph Studio 才能实时追踪线程、节点、中断与状态。
+
+- 🚫 **绝对禁止**：直接 `import` / 在进程内运行本 skill 的图定义模块
+  （`scripts\graph.py`、`scripts\workflow.py`、`scripts\agents.py`）来跑工作流。包括但不限于：
+  - `python -c "from graph import ...; graph.invoke(...)"` 或 `.stream(...)`
+  - 写临时脚本 build 编译图后在进程内调用
+  - 任何绕过 `http://127.0.0.1:2024` 的「就地执行」方式
+
+  这类调用在 dev server 进程**之外**运行，Studio 追踪不到状态，**一律不允许**——
+  即使只是想「快速验证一个节点」也不行。
+
+- ℹ️ **例外说明**：`review_task.py`（Codex 评审 shim）会直接调 `codex`，这是**合规的**——
+  它是由运行在 dev server 内的图通过 `codex_review_command` 调起的评审步骤，不是绕过
+  dev server 去驱动工作流本身。区别在于：驱动图 = 必须走 dev server；图内部调用的工具 = 正常。
+
+- 🛠 **改了 `graph.py`/`workflow.py`/`agents.py` 后**：dev server 内存里仍是旧代码。先
+  `manage_dev_server.ps1 stop` 再 `start`（或让 `--reload` 生效），再经 `run_langgraph.ps1`
+  重跑，使改动在被追踪的运行中生效。
+
 ## Pre-flight: Environment Setup
 
 Before running the workflow for the first time (or when unsure the environment is ready), verify that the required packages are installed in the `langgraph` conda env:
@@ -32,6 +58,7 @@ conda run -n langgraph langgraph --version
 
 ## Invariants
 
+- **Drive the graph only through the dev server** (see the mandatory rule above): `run_langgraph.ps1` → `run_workflow.py` → `http://127.0.0.1:2024`. Never import or run `graph.py`/`workflow.py`/`agents.py` in-process to execute the workflow — that bypasses the dev server and LangGraph Studio cannot track it.
 - Use the current Claude Code session for all Claude Code work. Do not launch another `claude` process.
 - Assume the current Claude Code session already has `--dangerously-skip-permissions`.
 - Run Python through the recorded conda environment. `run_langgraph.ps1` resolves conda from `-CondaExe`, `CONDA_EXE`, `conda` on PATH, or the user-profile miniconda fallback:
diff --git a/langgraph-plan-review/scripts/__pycache__/agents.cpython-311.pyc b/langgraph-plan-review/scripts/__pycache__/agents.cpython-311.pyc
new file mode 100644
index 0000000..44ceaa2
Binary files /dev/null and b/langgraph-plan-review/scripts/__pycache__/agents.cpython-311.pyc differ
diff --git a/langgraph-plan-review/scripts/__pycache__/graph.cpython-311.pyc b/langgraph-plan-review/scripts/__pycache__/graph.cpython-311.pyc
new file mode 100644
index 0000000..150b3d2
Binary files /dev/null and b/langgraph-plan-review/scripts/__pycache__/graph.cpython-311.pyc differ
diff --git a/langgraph-plan-review/scripts/__pycache__/workflow.cpython-311.pyc b/langgraph-plan-review/scripts/__pycache__/workflow.cpython-311.pyc
new file mode 100644
index 0000000..e61694a
Binary files /dev/null and b/langgraph-plan-review/scripts/__pycache__/workflow.cpython-311.pyc differ
diff --git a/langgraph-plan-review/scripts/manage_dev_server.ps1 b/langgraph-plan-review/scripts/manage_dev_server.ps1
index 1c55c86..10f7073 100644
--- a/langgraph-plan-review/scripts/manage_dev_server.ps1
+++ b/langgraph-plan-review/scripts/manage_dev_server.ps1
@@ -40,9 +40,9 @@ function Get-StoredPid {
 }
 
 function Test-ServerRunning {
-    $pid = Get-StoredPid
-    if ($pid -eq 0) { return $false }
-    $proc = Get-Process -Id $pid -ErrorAction SilentlyContinue
+    $storedPid = Get-StoredPid
+    if ($storedPid -eq 0) { return $false }
+    $proc = Get-Process -Id $storedPid -ErrorAction SilentlyContinue
     if (-not $proc) { return $false }
     return (Test-HttpOk "$ApiUrl/ok")
 }
@@ -107,8 +107,8 @@ switch ($Command) {
 
     "start" {
         if (Test-ServerRunning) {
-            $pid = Get-StoredPid
-            Write-Host "[dev-server] Already running (PID $pid) at $ApiUrl"
+            $storedPid = Get-StoredPid
+            Write-Host "[dev-server] Already running (PID $storedPid) at $ApiUrl"
             Write-Host "[dev-server] Studio: https://smith.langchain.com/studio/?baseUrl=$ApiUrl"
             exit 0
         }
@@ -122,6 +122,10 @@ switch ($Command) {
         Remove-Item $StdoutLog -ErrorAction SilentlyContinue
         Remove-Item $StderrLog -ErrorAction SilentlyContinue
 
+        # Force UTF-8 to avoid GBK decode errors on Chinese Windows systems
+        $env:PYTHONUTF8 = "1"
+        $env:PYTHONIOENCODING = "utf-8"
+
         $proc = Start-Process -FilePath $lgExe `
             -ArgumentList "dev", "--no-browser" `
             -WorkingDirectory $SkillDir `
@@ -167,9 +171,9 @@ switch ($Command) {
     }
 
     "stop" {
-        $pid = Get-StoredPid
-        if ((Stop-ServerProcess -PidValue $pid)) {
-            Write-Host "[dev-server] Stopped (PID $pid)"
+        $storedPid = Get-StoredPid
+        if ((Stop-ServerProcess -PidValue $storedPid)) {
+            Write-Host "[dev-server] Stopped (PID $storedPid)"
         } else {
             Write-Host "[dev-server] Not running (nothing to stop)"
         }
@@ -178,8 +182,8 @@ switch ($Command) {
 
     "status" {
         if (Test-ServerRunning) {
-            $pid = Get-StoredPid
-            Write-Host "[dev-server] Running (PID $pid) at $ApiUrl"
+            $storedPid = Get-StoredPid
+            Write-Host "[dev-server] Running (PID $storedPid) at $ApiUrl"
             Write-Host "[dev-server] Studio: https://smith.langchain.com/studio/?baseUrl=$ApiUrl"
         } else {
             Write-Host "[dev-server] Not running"