v0.8.2: build fixes, WebUI security and correctness

Build: <fcntl.h> in tui.c, format-truncation in http_srv.c and /web.

WebUI:
- refuse cross-site requests (Origin must be the page itself) in the
  default no-token mode: any page could POST approval=yolo and a prompt
- session/workspace/undo/compact/attach/model changes are 409 while a
  turn runs (use-after-free, messages landing in the wrong session)
- ask_user returned "dismissed" at once instead of waiting
- cancel and shutdown wake a turn parked on a permission or question;
  SIGTERM mid-turn no longer hangs or crashes
- a page opened while a question is pending still gets it;
  Last-Event-ID resumes the stream; event seq matches the SSE id
- token mode: page assets load without the token, images via cookie
- --web-open works, --web-port/--web-token are validated
- frontend: gate keys ignored while typing, clear-images button,
  reasoning no longer wiped while streaming

HTTP server: auth and size cap before reading the body, strict
Content-Length, NUL in url_decode, 413 on keep-alive, idle timeout,
absolute-form only without a leading '/', case-insensitive Connection,
header deadline, 400 for long request lines, unlink before close,
poll() instead of select(), SO_EXCLUSIVEADDRUSE on Windows.

Markdown sanitizer escapes quotes in attribute values.

/web: passes this session's provider/model/base/effort/approval (key
via the environment), keeps output off the TUI, shows the real URL and
keeps CURRENT on the TUI's session.

Tests: scripts/e2e_webui_ask.py, scripts/e2e_webui_http.py (run from
e2e_webui.sh), sanitizer quote test.

README.md

@@ -212,10 +212,10 @@ Gitea Release `vVERSION`（同名资源会被替换）；仓库可设 `RELEASE_T
 | `CST_MAX_STEPS` / `--max-steps` | 每个用户回合最多调用模型几次（30） |
 | `CST_TOOL_OUT_CAP` | 单个工具输出发给模型的字节上限（16384，保留头 60% + 尾 40%） |
 | `CST_CTX_WINDOW` | 发给模型的最近非 system 消息条数（80） |
-| `CST_CTX_TOKENS` / `CST_AUTO_COMPACT=0` | 覆盖模型上下文窗口大小 / 关闭自动压缩（用到 80% 时自动 `/compact`） |
+| `CST_CTX_TOKENS` / `CST_AUTO_COMPACT=0` | 覆盖模型上下文窗口大小 / 关闭自动压缩（用到 75% 时自动 `/compact`） |
 | `CST_NO_PROJECT_NOTES=1` | 不把工作区的 `AGENTS.md` 注入 system prompt |
 | `NO_COLOR` / `CST_ASCII=1` | 关闭颜色 / 强制 ASCII 图形（非 UTF-8 终端自动退化） |
-| `CST_SHELL_TIMEOUT` | `run_shell` 超时秒数（120），超时整组进程被杀，exit=124 |
+| `CST_SHELL_TIMEOUT` | `run_shell` 超时秒数（默认不限），设了才在超时后整组杀进程，exit=124 |
 | `CST_METRICS=0` / `CST_METRICS_PATH` | 关闭 / 指定计时埋点 JSONL（默认 `.agent/metrics/<session>.jsonl`） |
 | `CST_RECORD_SSE=DIR` / `CST_REPLAY_SSE=DIR` | 录制 / 回放原始 SSE 流（`NNNN.sse` + `NNNN.req.json`） |
 | `CST_APPROVAL=ask\|auto\|yolo` / `CST_SANDBOX=off\|landlock\|seccomp` | 审批模式 / 关闭沙箱（回落到只读白名单规则）或只用指定沙箱 |
@@ -319,7 +319,7 @@ TUI 中 `/tools off NAME`、`/tools on NAME` 可临时开关单个工具。
   `sudo`、`rm`、解释器（`python3 -c …`）等危险前缀不会被建议成规则。
 - **撤销**：每轮写文件前自动快照到 `.agent/undo/`，`/undo` 恢复上一轮改动的全部文件（新建的文件会被删除）。
 - **AGENTS.md**：工作区根目录的 `AGENTS.md` 会注入 system prompt；`/init` 让 agent 自己生成一份。
-- **自动压缩**：上一轮 prompt 用到模型上下文 80% 时，下一轮开始前自动总结历史（`CST_AUTO_COMPACT=0` 关闭）。
+- **自动压缩**：上一轮 prompt 用到模型上下文 75% 时，下一轮开始前自动总结历史（`CST_AUTO_COMPACT=0` 关闭）。
 
 ### 扩展：Skills、插件、MCP、子 agent
 
@@ -408,6 +408,7 @@ Thought（推理过程）默认折叠成一行“Thought · 3.2s”，生成中
 | `/diff [path]` * | `git status` + `git diff` |
 | `/compact` | 手动压缩上下文 |
 | `/export [file]` *、`/copy` * | 导出 Markdown 记录；复制上一条回复（OSC 52，需终端支持） |
+| `/web` * | 后台起一个 WebUI 进程（同 workspace、新会话，日志写到 `.agent/webui.log`） |
 | `/init` | 让 agent 写 `AGENTS.md` |
 | `/details` *、`/thinking [on\|off]`、`/keys` * | 展开全部 tool 输出；Thought 默认展开/折叠；快捷键列表 |
 | `/skills [reload\|list]`、`/skill <name> [任务]` | 浏览 skills；带着某个 skill 开始一轮 |

docs/env_openai.md

@@ -73,7 +73,7 @@ export OPENAI_MODEL='your-model'
 | `CST_MAX_STEPS` | 每个用户回合最多调用模型几次（默认 30） |
 | `CST_TOOL_OUT_CAP` | 单个工具输出发给模型的字节上限（默认 16384） |
 | `CST_CTX_WINDOW` | 发给模型的最近非 system 消息条数（默认 80） |
-| `CST_SHELL_TIMEOUT` | `run_shell` 超时秒数（默认 120） |
+| `CST_SHELL_TIMEOUT` | `run_shell` 超时秒数（默认不限，Ctrl+C / 停止按钮仍可随时中断） |
 | `CST_METRICS=0` / `CST_METRICS_PATH` | 关闭 / 指定计时埋点 JSONL |
 | `CST_RECORD_SSE` / `CST_REPLAY_SSE` | 录制 / 回放原始 SSE 流目录；`CST_REPLAY_CHUNK` 控制回放分块字节数 |
 | `CST_MODELS` | `/model` 可选列表，`:` 或 `,` 分隔 |

docs/webui.md

@@ -47,7 +47,9 @@ webui: token 3f9a…  (append #token=3f9a… to the URL)
 
 | 场景 | 行为 |
 |---|---|
-| 默认 `127.0.0.1` | 不需要 token；`Host` 必须是 loopback（防 DNS rebinding） |
+| 默认 `127.0.0.1` | 不需要 token；`Host` 必须是 loopback（防 DNS rebinding）；带 `Origin` 的请求必须来自本页面自己（`http://<Host>`），否则 401 —— 防止任意网页跨站 POST 驱动 agent |
+| 静态资源 | 页面本身与 `app.js`/`style.css` 不需要 token；`/api/attach/<rel>` 图片仍要（页面会把 token 写进 `SameSite=Strict` cookie） |
+| 请求解析 | 鉴权与大小检查在读请求体**之前**完成；`Content-Length` 必须是纯数字且只有一个值；请求头整体 15 s 内收完 |
 | `--web-host 0.0.0.0` | 没给 `--web-token` 时自动生成随机 token 并打印；所有 `/api/*` 都要 token |
 | token 传递 | `Authorization: Bearer <t>`、`Cookie: cst_token=<t>` 或 `?token=<t>`（`EventSource` 不能设 header，所以查询参数是必需的一条路） |
 | 资源 | 只有白名单路由；路径里的 `..`/编码 NUL 一律 400；静态资源来自二进制内嵌（或 `--web-dev DIR`） |
@@ -70,7 +72,10 @@ GET /api/events?since=<seq>      →  text/event-stream (chunked)
 
 * 每条事件都有 `id: <seq>`（单调递增）与 `data: {"type":…,"seq":…, …}`。
 * 断线重连带上 `since=<最后收到的 seq>`（浏览器用 `Last-Event-ID` 也行），
-  服务端保留最近 2000 条，超出后从可用的最老一条开始。
+  服务端保留最近 2000 条，超出后从可用的最老一条开始；比当前 seq 还大（服务端重启过）
+  就当作新连接。
+* 新连接（不带 `since`）只收之后的事件；但若有尚未回答的 `permission`/`ask_user`，
+  会从那条事件开始补发，刷新页面不会丢掉正在等的问题。
 * 心跳是 SSE 注释 `: ping`（每秒一次，客户端忽略）。
 * `state` 事件在状态变化时整份重发，客户端可以直接替换本地状态。
 
@@ -95,7 +100,8 @@ GET /api/events?since=<seq>      →  text/event-stream (chunked)
 `state` 字段：`workspace` `session` `provider` `model` `effort` `approval`
 (`ask|auto|yolo`) `plan_mode` `protocol_tools` `status_busy` `todo`
 `context_tokens` `undo_available` `pending_images[]` `usage{requests,prompt_tokens,
-completion_tokens,cost,priced,currency}`。
+completion_tokens,cached_tokens,cache_miss_tokens,cost,priced,currency}`。
+`cached_tokens` / `cache_miss_tokens` 来自上游的 prompt cache 统计，前端用它算命中率。
 
 ### 请求
 
@@ -106,19 +112,23 @@ completion_tokens,cost,priced,currency}`。
 | GET | `/api/sessions` | `{current, sessions:[{id,title,messages,mtime}]}` |
 | POST | `/api/sessions/new` | `{}` → `{id}` |
 | POST | `/api/sessions/switch` | `{"id":"…"}` |
+| POST | `/api/workspace` | `{"path":"/abs/dir"}` —— 换工作目录（权限规则/埋点/AGENTS.md 跟着换），并**在新目录里开一个新会话**（会话是按目录存的）；返回 `{id}`，坏路径 → 400 |
 | POST | `/api/turn` | `{"text":"…"}` → 202 `{ok:true}`；已有轮次在跑时 **409** |
-| POST | `/api/cancel` | `{}` —— 取消当前轮（不会杀进程） |
+| POST | `/api/cancel` | `{}` —— 取消当前轮（不会杀进程）；挂起的权限问题按拒绝、提问按忽略处理 |
 | POST | `/api/permission` | `{"id":N,"answer":0\|1\|2\|3}` → deny / once / always-tool / always-prefix |
 | POST | `/api/ask_user` | `{"id":N,"text":"…"}` 或 `{"id":N,"dismiss":true}` |
 | POST | `/api/config` | `{model?,provider?,effort?,approval?,plan_mode?}` |
 | POST | `/api/undo` | 回滚最近一轮的文件改动，回 200 + 报告文本 |
 | POST | `/api/compact` | 手动压缩上下文 |
-| POST | `/api/attach?name=x.png` | 请求体是图片原始字节（≤16 MiB），进入"待发送"列表 |
+| POST | `/api/attach?name=x.png` | 请求体是图片原始字节（≤32 MiB），进入"待发送"列表 |
 | DELETE | `/api/attach` | 清空待发送图片 |
 | GET | `/api/attach/<rel>` | 读回已存进会话的图片（`rel` 由消息的 `attach[].rel` 给出） |
 | POST | `/api/quit` | 关闭进程 |
 
 未命中路由 → `404 {"error":"not found"}`；需要 token 而没给 → `401`。
+轮次运行中（或另一个修改正在进行）时，`sessions/new`、`sessions/switch`、`workspace`、
+`undo`、`compact`、`attach`（上传/清空）以及改 `model/provider/effort` 的 `config`
+一律 **409**；`approval`/`plan_mode` 可以中途改。
 
 ### 客户端接入示例（10 行）
 
@@ -149,6 +159,18 @@ api("/api/turn", {"text": "hello"})           # 之后读 /api/events 收流
 Markdown 在**服务端**渲染（复用 TUI 用的 sashidown 流式 API），客户端只贴 HTML；
 因此不需要引入任何 JS 依赖，也顺带保证了"只发送已确认的 HTML"。
 
+界面本身：左栏可收（顶栏按钮 / `?side=0`），右栏可收（`?panel=0`），主题 `?theme=dark|light`；
+三个开关都会记进 `localStorage`，带查询参数时以参数为准。空状态只留一句提示，第一轮
+对话开始后自动隐去；右栏只给三件事——任务清单、本轮文件改动行数（`+N −M`）、上下文
+占用与 prompt cache 命中率。布局类在页面脚本之前就写进 `<body>`，避免首帧闪一下再收起。
+
+TUI 里打 `/web` 会另起一个 WebUI 进程（`--web --workspace <当前目录> --new`），
+日志在 `<workspace>/.agent/webui.log`：TUI 不能被 `cst_webui_run()` 的阻塞循环占住，
+而且两个进程同时写一个会话文件会把它写坏，所以子进程总是开新会话。
+
+自动压缩的门槛是模型上下文窗口的 **75%**（`CST_CTX_BUDGET` 可覆盖）；到点后下一轮
+开始前先总结历史，而不是等到塞满。
+
 ## 测试
 
 ```bash

include/cst_agent.h

@@ -321,6 +321,12 @@ cst_agent_config_t *cst_agent_config_mut(cst_agent_t *a);
 void cst_agent_request_cancel(cst_agent_t *a);
 int cst_agent_new_session(cst_agent_t *a, char *id_out, size_t id_sz);
 int cst_agent_switch_session(cst_agent_t *a, const char *id);
+/* Re-root the agent at another directory. Per-workspace state (permission
+ * rules, metrics, project notes) follows, the system prompt is rebuilt and the
+ * token budget is re-measured. The session is not touched: the caller decides
+ * whether to keep it or start a new one. */
+int cst_agent_set_workspace(cst_agent_t *a, const char *path, char *err,
+                            size_t err_sz);
 int cst_agent_compact(cst_agent_t *a, char *err, size_t err_sz);
 /* Bare id of the current session (file name without .jsonl). */
 void cst_agent_session_id(const cst_agent_t *a, char *out, size_t out_sz);

include/cst_http.h

@@ -32,6 +32,7 @@ typedef struct {
   const char *host;
   const char *content_type;
   const char *user_agent;
+  const char *last_event_id; /* an EventSource reconnecting */
   int keep_alive;
 } cst_http_req_t;
 
@@ -72,8 +73,10 @@ cst_http_server_t *cst_http_start(const cst_http_opts_t *o, char *err,
 int cst_http_port(const cst_http_server_t *s);
 /* Non-zero once stop() was called: long-lived handlers must return. */
 int cst_http_stopping(const cst_http_server_t *s);
-/* Close the listener and every connection, then wait for the threads. */
+/* Close the listener and every connection, then wait (30 s at most) for the
-void cst_http_stop(cst_http_server_t *s);
+ * handler threads. Returns how many still run: their ud must stay alive. */
+int cst_http_stop(cst_http_server_t *s);
+/* Does nothing while handlers still run on s. */
 void cst_http_free(cst_http_server_t *s);
 
 /* --- inside a handler --- */

include/cst_version.h

@@ -2,8 +2,8 @@
 #define CST_VERSION_H
 
 #define CST_VERSION_MAJOR 0
-#define CST_VERSION_MINOR 7
+#define CST_VERSION_MINOR 8
-#define CST_VERSION_PATCH 8
+#define CST_VERSION_PATCH 2
 
 #define CST_VERSION_STR_(x) #x
 #define CST_VERSION_STR(x) CST_VERSION_STR_(x)

include/cst_webui.h

@@ -17,6 +17,10 @@
 extern "C" {
 #endif
 
+/* What --web listens on when --web-port/CST_WEB_PORT says nothing (the
+ * README and --help quote this number, so keep them in sync). */
+#define CST_WEBUI_DEFAULT_PORT 8787
+
 typedef struct {
   const char *host;  /* NULL = 127.0.0.1; "0.0.0.0" = every interface */
   int port;          /* 0 = pick a free port */

include/os_compat.h

@@ -114,9 +114,10 @@ int os_win_get_label(const char *path, char *out, size_t n);
 int os_clipboard_set(const char *utf8, size_t n);
 #endif
 
-/* Child processes get stdin=/dev/null, their own process group, and are
+/* Child processes get stdin=/dev/null and their own process group. They run
- * killed after the timeout (CST_SHELL_TIMEOUT seconds, default 120) or when
+ * with no time limit unless one is asked for (CST_SHELL_TIMEOUT seconds, or
- * *flag becomes non-zero. Exit code 124 = timeout, 130 = cancelled. */
+ * os_set_run_timeout()); either way a non-zero *flag cancels them.
+ * Exit code 124 = killed by that timeout, 130 = cancelled. */
 void os_set_cancel_flag(volatile int *flag);
 volatile int *os_get_cancel_flag(void);
 void os_set_run_timeout(int seconds); /* this thread; 0 = default */

scripts/e2e_webui.sh

@@ -47,6 +47,19 @@ BASE="http://127.0.0.1:$PORT"
 echo "   port $PORT"
 
 fail() { echo "FAIL: $1"; echo "--- events"; cat "$EVENTS" 2>/dev/null | head -40; exit 1; }
+# SIGTERM must shut the server down cleanly, even mid-turn (128+ = a crash)
+stop_server() {
+  kill "$1" 2>/dev/null || return 0
+  n=0
+  while kill -0 "$1" 2>/dev/null && [ $n -lt 200 ]; do n=$((n + 1)); sleep 0.2; done
+  if kill -0 "$1" 2>/dev/null; then
+    kill -9 "$1" 2>/dev/null || true
+    fail "$2 hung on SIGTERM"
+  fi
+  st=0
+  wait "$1" 2>/dev/null || st=$?
+  [ "$st" -lt 128 ] || fail "$2 died with status $st on SIGTERM"
+}
 
 # 1. the shell page and the state endpoint
 curl -fsS --max-time 5 "$BASE/" | grep -q "<title>CST-Agent" || fail "GET / is not the shell page"
@@ -160,7 +173,7 @@ fi
 # 7. the interactive approval path: a fresh server in ask mode must raise a
 # permission event, and answering it must let the turn continue.
 echo "== permission round trip (-A ask)"
-kill "$SRV_PID" 2>/dev/null || true   # the first server's replay is spent
+stop_server "$SRV_PID" "the first server"   # its replay is spent
 rm -rf "$WORK/pw"; mkdir -p "$WORK/pw"
 P_EVENTS="$WORK/permission-events.txt"
 P_LOG="$WORK/permission-server.log"   # its own log: the port parse must not
@@ -206,7 +219,7 @@ else
     i=$((i + 1)); sleep 0.2
   done
   grep -q "event: permission_done" "$P_EVENTS" || fail "the answer was not acknowledged"
-  kill "$P_PID" 2>/dev/null || true
+  stop_server "$P_PID" "the ask-mode server"
   kill "$P_CURL" 2>/dev/null || true
   echo "   answered request $PID_REQ with 'allow once'"
 fi
@@ -260,4 +273,15 @@ done
 kill -0 "$T_PID" 2> /dev/null && fail "the server ignored /api/quit"
 wait "$T_PID" 2>/dev/null || true
 
+# 9. ask_user waits for the answer, and the HTTP hardening checks (both
+# need a scripted model: python3)
+if command -v python3 > /dev/null; then
+  echo "== ask_user round trip"
+  CST_AGENT="$BIN" python3 "$ROOT/scripts/e2e_webui_ask.py" > "$WORK/ask.txt" 2>&1 ||
+    { cat "$WORK/ask.txt"; fail "the ask_user round trip"; }
+  echo "== HTTP hardening"
+  CST_AGENT="$BIN" python3 "$ROOT/scripts/e2e_webui_http.py" > "$WORK/http.txt" 2>&1 ||
+    { cat "$WORK/http.txt"; fail "the HTTP hardening checks"; }
+fi
+
 echo "== OK: (events: $(grep -c '^event: ' "$EVENTS"))"

scripts/e2e_webui_ask.py

@@ -0,0 +1,164 @@
+"""WebUI ask_user round trip against a fake OpenAI-compatible API.
+
+  python3 scripts/e2e_webui_ask.py      (CST_AGENT= picks the binary)
+
+Checks: the turn really waits for the answer, a page opened while the
+question is open still receives it, and Last-Event-ID resumes the stream.
+"""
+import json, os, shutil, subprocess, sys, tempfile, threading, time, urllib.request
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+
+BIN = os.environ.get("CST_AGENT", os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "cst-agent"))
+REQS = []
+
+
+class H(BaseHTTPRequestHandler):
+    def log_message(self, *a):
+        pass
+
+    def do_GET(self):
+        body = json.dumps({"data": [{"id": "deepseek-flash"}]}).encode()
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        self.wfile.write(body)
+
+    def do_POST(self):
+        n = int(self.headers.get("Content-Length", 0))
+        REQS.append(json.loads(self.rfile.read(n)))
+        self.send_response(200)
+        self.send_header("Content-Type", "text/event-stream")
+        self.end_headers()
+        base = {"id": "x", "object": "chat.completion.chunk", "model": "deepseek-flash"}
+
+        def ev(o):
+            self.wfile.write(b"data: " + json.dumps({**base, **o}).encode() + b"\n\n")
+            self.wfile.flush()
+        if len(REQS) == 1:
+            args = json.dumps({"question": "Pick a colour?", "options": "red\nblue"})
+            ev({"choices": [{"index": 0, "delta": {"role": "assistant", "tool_calls": [
+                {"index": 0, "id": "call_1", "type": "function",
+                 "function": {"name": "ask_user", "arguments": args}}]}}]})
+            ev({"choices": [{"index": 0, "delta": {}, "finish_reason": "tool_calls"}]})
+        else:
+            ev({"choices": [{"index": 0, "delta": {"role": "assistant", "content": "done"}}]})
+            ev({"choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}]})
+        self.wfile.write(b"data: [DONE]\n\n")
+        self.wfile.flush()
+
+
+fails = 0
+
+
+def check(ok, msg):
+    global fails
+    print(("PASS " if ok else "FAIL ") + msg)
+    fails += 0 if ok else 1
+
+
+class Sse:
+    def __init__(self, base, last_id=None):
+        self.lines = []
+        req = urllib.request.Request(base + "/api/events")
+        if last_id is not None:
+            req.add_header("Last-Event-ID", str(last_id))
+        self.r = urllib.request.urlopen(req, timeout=60)
+        threading.Thread(target=self.pump, daemon=True).start()
+
+    def pump(self):
+        try:
+            for raw in self.r:
+                self.lines.append(raw.decode())
+        except Exception:
+            pass
+
+    def events(self, name):
+        out = []
+        for i, l in enumerate(self.lines):
+            if l.strip() == "event: " + name and i + 1 < len(self.lines):
+                out.append(json.loads(self.lines[i + 1][6:]))
+        return out
+
+    def ids(self):
+        return [int(l[4:]) for l in self.lines if l.startswith("id: ")]
+
+    def close(self):
+        try:
+            self.r.close()
+        except Exception:
+            pass
+
+
+def wait(fn, t=15):
+    end = time.time() + t
+    while time.time() < end:
+        v = fn()
+        if v:
+            return v
+        time.sleep(0.1)
+    return None
+
+
+def post(base, path, obj):
+    req = urllib.request.Request(base + path, data=json.dumps(obj).encode(),
+                                 headers={"Content-Type": "application/json"})
+    try:
+        with urllib.request.urlopen(req, timeout=5) as r:
+            return r.status
+    except urllib.error.HTTPError as e:
+        return e.code
+
+
+api = ThreadingHTTPServer(("127.0.0.1", 0), H)
+threading.Thread(target=api.serve_forever, daemon=True).start()
+ws = tempfile.mkdtemp(prefix="cst-ask-")
+log = open(ws + "/server.log", "w+")
+p = subprocess.Popen([BIN, "--web", "--web-port", "0", "--workspace", ws, "--new",
+                      "--api-key", "sk-x", "--provider", "deepseek", "--model", "deepseek-flash",
+                      "--api-base", "http://127.0.0.1:%d/v1" % api.server_address[1],
+                      "--protocol", "native-eos", "--approval", "auto"],
+                     stdout=log, stderr=subprocess.STDOUT)
+try:
+    def port():
+        log.seek(0)
+        for l in log.read().splitlines():
+            if l.startswith("webui: http://127.0.0.1:"):
+                return l.split(":")[3].split("/")[0]
+    pt = wait(port)
+    base = "http://127.0.0.1:%s" % pt
+    a = Sse(base)
+    time.sleep(0.3)
+    check(post(base, "/api/turn", {"text": "ask me"}) == 202, "turn accepted")
+    ask = wait(lambda: a.events("ask_user"))
+    check(bool(ask), "ask_user event raised")
+    time.sleep(1.5)
+    check(len(REQS) == 1, "the turn waits for the answer (requests so far: %d)" % len(REQS))
+    # a page opened now must still see the open question
+    b = Sse(base)
+    check(bool(wait(lambda: b.events("ask_user"), 5)), "a late page gets the open question")
+    # reconnect with Last-Event-ID: nothing before that id is resent
+    last = a.ids()[-1]
+    c = Sse(base, last_id=last - 1)
+    got = wait(lambda: c.ids(), 5)
+    check(bool(got) and got[0] == last, "Last-Event-ID resumes after that id (%s, want %d)" % (got[:1] if got else got, last))
+    if ask:
+        check(post(base, "/api/ask_user", {"id": ask[0]["id"], "text": "blue"}) == 200, "answer accepted")
+    end = wait(lambda: a.events("turn_end"), 20)
+    check(bool(end) and end[0].get("rc") == 0, "turn ended rc=0")
+    tool_msgs = [m for m in (REQS[1]["messages"] if len(REQS) > 1 else []) if m.get("role") == "tool"]
+    check(bool(tool_msgs) and "blue" in json.dumps(tool_msgs), "the answer reached the model: %s" % json.dumps(tool_msgs)[:200])
+    for s in (a, b, c):
+        s.close()
+finally:
+    p.terminate()
+    try:
+        p.wait(20)
+    except subprocess.TimeoutExpired:
+        p.kill()
+        check(False, "server hung on SIGTERM")
+    check(p.returncode is not None and p.returncode < 128 and p.returncode >= 0, "clean exit (%s)" % p.returncode)
+    log.close()
+    shutil.rmtree(ws, ignore_errors=True)
+print("FAILED:", fails)
+sys.exit(1 if fails else 0)

scripts/e2e_webui_http.py

@@ -0,0 +1,234 @@
+"""WebUI HTTP hardening checks over raw sockets, against a scripted model.
+
+  python3 scripts/e2e_webui_http.py      (CST_AGENT= picks the binary)
+
+Cross-site requests, request parsing (Content-Length, NUL, long lines,
+keep-alive), auth before the body, changes refused while a turn runs,
+cancel waking a pending question, token mode and shutdown.
+"""
+import json, os, re, shutil, socket, subprocess, sys, tempfile, threading, time
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+
+BIN = os.environ.get("CST_AGENT", os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "cst-agent"))
+REQS = []
+
+
+class Api(BaseHTTPRequestHandler):
+    """First call: ask_user. Later calls: a plain answer."""
+
+    def log_message(self, *a):
+        pass
+
+    def do_GET(self):
+        body = json.dumps({"data": [{"id": "deepseek-flash"}]}).encode()
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        self.wfile.write(body)
+
+    def do_POST(self):
+        n = int(self.headers.get("Content-Length", 0))
+        REQS.append(json.loads(self.rfile.read(n)))
+        self.send_response(200)
+        self.send_header("Content-Type", "text/event-stream")
+        self.end_headers()
+        base = {"id": "x", "object": "chat.completion.chunk", "model": "deepseek-flash"}
+
+        def ev(o):
+            self.wfile.write(b"data: " + json.dumps({**base, **o}).encode() + b"\n\n")
+            self.wfile.flush()
+        if len(REQS) == 1:
+            args = json.dumps({"question": "Pick?", "options": "a\nb"})
+            ev({"choices": [{"index": 0, "delta": {"role": "assistant", "tool_calls": [
+                {"index": 0, "id": "call_1", "type": "function",
+                 "function": {"name": "ask_user", "arguments": args}}]}}]})
+            ev({"choices": [{"index": 0, "delta": {}, "finish_reason": "tool_calls"}]})
+        else:
+            ev({"choices": [{"index": 0, "delta": {"role": "assistant", "content": "ok"}}]})
+            ev({"choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}]})
+        self.wfile.write(b"data: [DONE]\n\n")
+        self.wfile.flush()
+
+
+fails = 0
+
+
+def check(ok, msg):
+    global fails
+    print(("PASS " if ok else "FAIL ") + msg)
+    fails += 0 if ok else 1
+
+
+def raw(port, data, timeout=5, read_all=True):
+    """Send bytes, return everything read until EOF/timeout."""
+    s = socket.create_connection(("127.0.0.1", port), timeout=timeout)
+    s.sendall(data)
+    out = b""
+    try:
+        while True:
+            b = s.recv(65536)
+            if not b:
+                break
+            out += b
+            if not read_all:
+                break
+    except socket.timeout:
+        pass
+    s.close()
+    return out.decode("latin1")
+
+
+def status(resp):
+    # a pipelined response starts right after the previous body, not on a new line
+    return [int(m) for m in re.findall(r"HTTP/1\.1 (\d{3}) ", resp)]
+
+
+def req(method, path, headers=None, body=b"", host=None):
+    h = {"Host": host or "127.0.0.1:%d" % PORT, "Connection": "close"}
+    h.update(headers or {})
+    if body or method == "POST":
+        h["Content-Length"] = str(len(body))
+    head = "%s %s HTTP/1.1\r\n" % (method, path) + "".join("%s: %s\r\n" % kv for kv in h.items()) + "\r\n"
+    return head.encode() + body
+
+
+def start(ws, *extra):
+    log = open(os.path.join(ws, "server.log"), "w+")
+    p = subprocess.Popen([BIN, "--web", "--web-port", "0", "--workspace", ws, "--new",
+                          "--api-key", "sk-x", "--provider", "deepseek", "--model", "deepseek-flash",
+                          "--api-base", "http://127.0.0.1:%d/v1" % api.server_address[1],
+                          "--protocol", "native-eos", "--approval", "auto", *extra],
+                         stdout=log, stderr=subprocess.STDOUT)
+    end = time.time() + 10
+    while time.time() < end:
+        log.seek(0)
+        for l in log.read().splitlines():
+            if l.startswith("webui: http://127.0.0.1:"):
+                return p, int(l.split(":")[3].split("/")[0]), log
+        time.sleep(0.1)
+    raise SystemExit("server did not start")
+
+
+def stop(p, name):
+    p.terminate()
+    try:
+        p.wait(20)
+    except subprocess.TimeoutExpired:
+        p.kill()
+        check(False, name + " hung on SIGTERM")
+        return
+    check(0 <= p.returncode < 128, "%s exits cleanly (%s)" % (name, p.returncode))
+
+
+api = ThreadingHTTPServer(("127.0.0.1", 0), Api)
+threading.Thread(target=api.serve_forever, daemon=True).start()
+root = tempfile.mkdtemp(prefix="cst-http-")
+try:
+    ws = os.path.join(root, "a")
+    os.makedirs(ws)
+    p, PORT, log = start(ws)
+    me = "http://127.0.0.1:%d" % PORT
+    cfg = b'{"approval":"ask"}'
+    # 1. cross-site requests
+    r = raw(PORT, req("POST", "/api/config", {"Origin": "http://evil.example", "Content-Type": "text/plain"}, cfg))
+    check(status(r)[:1] == [401], "a cross-site POST is refused (%s)" % status(r))
+    r = raw(PORT, req("POST", "/api/config", {"Origin": "null"}, cfg))
+    check(status(r)[:1] == [401], "Origin: null is refused")
+    r = raw(PORT, req("POST", "/api/config", {"Origin": me, "Content-Type": "application/json"}, b'{"approval":"auto"}'))
+    check(status(r)[:1] == [200], "our own page may POST (%s)" % status(r))
+    r = raw(PORT, req("POST", "/api/config", {}, b'{"approval":"auto"}'))
+    check(status(r)[:1] == [200], "a client without Origin (curl) may POST")
+    r = raw(PORT, req("GET", "/api/attach/img-0000.png", host="evil.example"))
+    check(status(r)[:1] == [401], "session images need the Host check too (%s)" % status(r))
+    r = raw(PORT, req("GET", "/app.js"))
+    check(status(r)[:1] == [200], "assets are served")
+    # 2. request parsing
+    r = raw(PORT, req("GET", "/api/state%00x"))
+    check(status(r)[:1] == [400], "an encoded NUL in the path is a 400 (%s)" % status(r))
+    smuggle = b"GET /api/sessions HTTP/1.1\r\nHost: 127.0.0.1\r\n\r\n"
+    r = raw(PORT, ("POST /api/cancel HTTP/1.1\r\nHost: 127.0.0.1:%d\r\nContent-Length: abc\r\n\r\n" % PORT).encode() + smuggle)
+    check(status(r) == [400], "Content-Length: abc is a 400, nothing smuggled (%s)" % status(r))
+    r = raw(PORT, ("POST /api/cancel HTTP/1.1\r\nHost: 127.0.0.1:%d\r\nContent-Length: 0\r\nContent-Length: %d\r\n\r\n"
+                   % (PORT, len(smuggle))).encode() + smuggle)
+    check(status(r) == [400], "two different Content-Lengths are a 400 (%s)" % status(r))
+    r = raw(PORT, ("GET /%s HTTP/1.1\r\nHost: x\r\n\r\n" % ("a" * 9000)).encode())
+    check(status(r)[:1] == [400], "an over-long request line is a 400 (%s)" % status(r))
+    r = raw(PORT, req("GET", "/api/state?x=http://a/b"))
+    check(status(r)[:1] == [200], "'://' in the query leaves the path alone (%s)" % status(r))
+    r = raw(PORT, req("GET", "/api/state", {"Connection": "Close"}), timeout=3)
+    check("Connection: close" in r, "Connection: Close (any case) closes")
+    ka = ("GET /api/state HTTP/1.1\r\nHost: 127.0.0.1:%d\r\n\r\n" % PORT).encode()
+    big = ("POST /api/turn HTTP/1.1\r\nHost: 127.0.0.1:%d\r\nContent-Length: 5000000\r\n\r\n" % PORT).encode()
+    r = raw(PORT, ka + big)
+    check(status(r) == [200, 413], "a 413 after a keep-alive request still arrives (%s)" % status(r))
+    # 3. a pending question: changes are refused, approval may change, cancel wakes it
+    events = []
+
+    def sse():
+        s = socket.create_connection(("127.0.0.1", PORT))
+        s.sendall(("GET /api/events HTTP/1.1\r\nHost: 127.0.0.1:%d\r\n\r\n" % PORT).encode())
+        buf = b""
+        s.settimeout(60)
+        try:
+            while True:
+                b = s.recv(65536)
+                if not b:
+                    break
+                buf += b
+                events[:] = [l[7:] for l in buf.decode("latin1").split("\n") if l.startswith("event: ")]
+        except Exception:
+            pass
+    threading.Thread(target=sse, daemon=True).start()
+    time.sleep(0.4)
+    r = raw(PORT, req("POST", "/api/turn", {"Content-Type": "application/json"}, b'{"text":"go"}'))
+    check(status(r)[:1] == [202], "turn accepted")
+    end = time.time() + 15
+    while time.time() < end and "ask_user" not in events:
+        time.sleep(0.1)
+    check("ask_user" in events, "the question is open")
+    for path, body in (("/api/sessions/new", b""), ("/api/workspace", json.dumps({"path": root}).encode()),
+                       ("/api/compact", b""), ("/api/undo", b""), ("/api/config", b'{"model":"x"}')):
+        r = raw(PORT, req("POST", path, {"Content-Type": "application/json"}, body))
+        check(status(r)[:1] == [409], "%s is refused mid-turn (%s)" % (path, status(r)))
+    r = raw(PORT, req("POST", "/api/config", {"Content-Type": "application/json"}, b'{"approval":"yolo"}'))
+    check(status(r)[:1] == [200], "approval may change mid-turn")
+    r = raw(PORT, req("POST", "/api/cancel", {"Content-Type": "application/json"}, b"{}"))
+    end = time.time() + 10
+    while time.time() < end and "turn_end" not in events:
+        time.sleep(0.1)
+    check("turn_end" in events, "cancel ends a turn parked on a question")
+    r = raw(PORT, req("POST", "/api/sessions/new", {"Content-Type": "application/json"}))
+    check(status(r)[:1] == [200], "after the turn, a new session is fine (%s)" % status(r))
+    stop(p, "the server")
+
+    # 4. token mode: the page loads, the API and images do not without it
+    ws2 = os.path.join(root, "b")
+    os.makedirs(ws2)
+    p, PORT, log = start(ws2, "--web-token", "tok-x")
+    r = raw(PORT, req("GET", "/app.js"))
+    check(status(r)[:1] == [200], "token mode: app.js loads without the token (%s)" % status(r))
+    r = raw(PORT, req("GET", "/api/state"))
+    check(status(r)[:1] == [401], "token mode: the API needs it")
+    r = raw(PORT, req("GET", "/api/attach/img-0000.png"))
+    check(status(r)[:1] == [401], "token mode: images need it")
+    r = raw(PORT, req("GET", "/api/state", {"Cookie": "cst_token=tok-x"}))
+    check(status(r)[:1] == [200], "token mode: the cookie works")
+    t0 = time.time()
+    r = raw(PORT, ("POST /api/attach HTTP/1.1\r\nHost: 127.0.0.1:%d\r\nContent-Length: 33554431\r\n"
+                   "Expect: 100-continue\r\n\r\n" % PORT).encode(), timeout=5)
+    check(status(r) == [401] and time.time() - t0 < 3,
+          "no token, no body read: 401 at once (%s, %.1fs)" % (status(r), time.time() - t0))
+    stop(p, "the token server")
+
+    # 5. option checks
+    rc = subprocess.run([BIN, "--web", "--web-port", "70000", "--workspace", ws2],
+                        capture_output=True, timeout=10).returncode
+    check(rc != 0, "--web-port 70000 is refused")
+    rc = subprocess.run([BIN, "--web", "--web-token", "x" * 80, "--web-port", "0", "--workspace", ws2,
+                         "--api-key", "k"], capture_output=True, timeout=10).returncode
+    check(rc != 0, "an over-long --web-token is refused")
+finally:
+    shutil.rmtree(root, ignore_errors=True)
+print("FAILED:", fails)
+sys.exit(1 if fails else 0)

src/agent_loop.c

@@ -2558,9 +2558,9 @@ static int can_continue(const cst_agent_t *a, const turn_t *t,
   return st->http_status > 0 && st->http_status < 400 && !st->client_stopped;
 }
 
-/* Prompt size at which the session is compacted: CST_CTX_BUDGET, else 60% of
+/* Prompt size at which the session is compacted: CST_CTX_BUDGET, else 75% of
- * the context window capped at 256K tokens. Even a cached prompt is billed
+ * the context window, capped at 256K tokens. Even a cached prompt is billed on
- * on every step, so huge windows are not worth filling. */
+ * every step, so a 1M-token window is not worth filling. */
 static long ctx_budget(const cst_agent_t *a) {
   const char *e = getenv("CST_CTX_BUDGET");
   if (e && atol(e) > 0)
@@ -2568,7 +2568,7 @@ static long ctx_budget(const cst_agent_t *a) {
   long win = cst_model_context_tokens(a->cfg.model);
   if (win <= 0)
     return 0;
-  long b = win / 10 * 6;
+  long b = win / 4 * 3;
   return b > 262144 ? 262144 : b;
 }
 
@@ -2948,6 +2948,42 @@ int cst_agent_new_session(cst_agent_t *a, char *id_out, size_t id_sz) {
   return 0;
 }
 
+int cst_agent_set_workspace(cst_agent_t *a, const char *path, char *err,
+                            size_t err_sz) {
+  char dummy[8];
+  if (!err || !err_sz) {
+    err = dummy;
+    err_sz = sizeof(dummy);
+  }
+  err[0] = 0;
+  if (!a || !path || !path[0]) {
+    snprintf(err, err_sz, "empty path");
+    return -1;
+  }
+  char abs[sizeof(a->cfg.workspace_root)];
+  if (os_realpath(path, abs, sizeof(abs)) != 0) {
+    snprintf(err, err_sz, "no such directory: %s", path);
+    return -1;
+  }
+  /* a file, or a tree we may not write to, fails here instead of halfway
+   * through the next turn */
+  if (cst_agent_store_ensure(abs) != 0) {
+    snprintf(err, err_sz, "cannot use as a workspace: %s", abs);
+    return -1;
+  }
+  snprintf(a->cfg.workspace_root, sizeof(a->cfg.workspace_root), "%s", abs);
+  /* everything that is kept per workspace follows the new root */
+  cst_perms_close(a->perms);
+  a->perms = cst_perms_open(a->cfg.workspace_root);
+  cst_metrics_close(a->metrics);
+  a->metrics = cst_metrics_open(a->cfg.workspace_root,
+                                cst_session_path(a->session));
+  cst_agent_reload_notes(a);
+  ensure_system(a);          /* the prompt names the directory */
+  a->last_prompt_tokens = 0; /* the old budget was measured elsewhere */
+  return 0;
+}
+
 int cst_agent_switch_session(cst_agent_t *a, const char *id) {
   if (!a || !id || !id[0])
     return -1;

src/http_srv.c

@@ -4,8 +4,11 @@
 
 #include "cst_http.h"
 #include "cst_util.h"
+#include "os_compat.h"
 
+#include <errno.h>
 #include <pthread.h>
+#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -44,6 +47,9 @@ struct cst_http_conn {
   int sent;
   int streaming;
   int failed;
+  int nreq;            /* requests served on this connection */
+  int expect_continue; /* the client waits for "100 Continue" */
+  int keep_alive_req;  /* what the client asked for */
   cst_http_conn_t *prev, *next;
 };
 
@@ -72,10 +78,15 @@ static const char *status_text(int code) {
 
 /* --- reading -------------------------------------------------------------- */
 
-static int fill(cst_http_conn_t *c, int timeout_ms) {
+/* deadline: os_now_ms() value; the whole read must be done by then, so a
+ * client trickling one byte at a time cannot hold the thread forever. */
+static int fill(cst_http_conn_t *c, double deadline) {
   if (c->rpos < c->rlen)
     return 1;
-  long r = os_net_recv(c->sock, c->rbuf, sizeof(c->rbuf), timeout_ms);
+  double left = deadline - os_now_ms();
+  if (left <= 0)
+    return -2;
+  long r = os_net_recv(c->sock, c->rbuf, sizeof(c->rbuf), (int)left + 1);
   if (r <= 0)
     return (int)r; /* 0 eof, -1 error, -2 timeout */
   c->rpos = 0;
@@ -83,10 +94,12 @@ static int fill(cst_http_conn_t *c, int timeout_ms) {
   return 1;
 }
 
-static int rd_line(cst_http_conn_t *c, char *out, size_t cap, int timeout_ms) {
+#define RD_TOO_LONG (-3)
+
+static int rd_line(cst_http_conn_t *c, char *out, size_t cap, double deadline) {
   size_t n = 0;
   for (;;) {
-    int rc = fill(c, timeout_ms);
+    int rc = fill(c, deadline);
     if (rc <= 0)
       return rc;
     while (c->rpos < c->rlen) {
@@ -98,7 +111,7 @@ static int rd_line(cst_http_conn_t *c, char *out, size_t cap, int timeout_ms) {
         return 1;
       }
       if (n + 2 >= cap)
-        return -1;
+        return RD_TOO_LONG;
       out[n++] = ch;
     }
   }
@@ -132,7 +145,8 @@ static char *rd_body(cst_http_conn_t *c, size_t n, int timeout_ms) {
   return buf;
 }
 
-static void url_decode(const char *in, char *out, size_t cap, int plus_space) {
+/* -1 when the input encodes a NUL (out then holds what came before it). */
+static int url_decode(const char *in, char *out, size_t cap, int plus_space) {
   size_t o = 0;
   for (const char *p = in; *p && o + 1 < cap; p++) {
     if (*p == '%' && p[1] && p[2]) {
@@ -146,8 +160,10 @@ static void url_decode(const char *in, char *out, size_t cap, int plus_space) {
                                             : -1;
       if (hi >= 0 && lo >= 0) {
         char ch = (char)((hi << 4) | lo);
-        if (ch == 0)
+        if (ch == 0) {
-          return; /* a decoded NUL would truncate the path */
+          out[o] = 0;
+          return -1;
+        }
         out[o++] = ch;
         p += 2;
         continue;
@@ -156,6 +172,23 @@ static void url_decode(const char *in, char *out, size_t cap, int plus_space) {
     out[o++] = (*p == '+' && plus_space) ? ' ' : *p;
   }
   out[o] = 0;
+  return 0;
+}
+
+/* Comma-separated header tokens, compared without case ("Close"). */
+static int has_token(const char *val, const char *tok) {
+  size_t n = strlen(tok);
+  for (const char *p = val; p && *p;) {
+    while (*p == ' ' || *p == '\t' || *p == ',')
+      p++;
+    size_t i = 0;
+    while (i < n && p[i] && (p[i] | 0x20) == (tok[i] | 0x20))
+      i++;
+    if (i == n && (p[i] == 0 || p[i] == ',' || p[i] == ' ' || p[i] == '\t'))
+      return 1;
+    p = strchr(p, ',');
+  }
+  return 0;
 }
 
 static int key_is(const char *line, const char *key) {
@@ -189,12 +222,16 @@ static int read_request(cst_http_conn_t *c, size_t *want_body) {
   cst_http_server_t *s = c->srv;
   char line[HTTP_LINE_MAX];
   cst_http_req_t *r = &c->req;
-  int first = c->rpos >= c->rlen; /* nothing buffered: this is a new client */
+  int first = c->nreq == 0; /* a keep-alive pause gets the idle timeout */
   memset(r, 0, sizeof(*r));
   c->hdrs_used = 0;
+  c->expect_continue = 0;
   *want_body = 0;
   int rc = rd_line(c, line, sizeof(line),
-                   first ? s->o.read_timeout_ms : s->o.idle_timeout_ms);
+                   os_now_ms() + (first ? s->o.read_timeout_ms
+                                        : s->o.idle_timeout_ms));
+  if (rc == RD_TOO_LONG)
+    return -1;
   if (rc <= 0)
     return 0;
   char *sp1 = strchr(line, ' ');
@@ -214,9 +251,10 @@ static int read_request(cst_http_conn_t *c, size_t *want_body) {
   r->keep_alive = strncmp(version, "HTTP/1.", 7) == 0 &&
                   version[7] >= '1' && version[7] <= '9';
   /* absolute-form ("http://host/path") is legal: keep the path */
+  if (target[0] != '/') {
     char *scheme = strstr(target, "://");
-  if (scheme)
+    target = scheme ? strchr(scheme + 3, '/') : NULL;
-    target = strchr(scheme + 3, '/');
+  }
   if (!target || target[0] != '/')
     return -1;
   {
@@ -227,7 +265,8 @@ static int read_request(cst_http_conn_t *c, size_t *want_body) {
       *q = 0;
       snprintf(r->query, sizeof(r->query), "%s", q + 1);
     }
-    url_decode(raw, r->path, sizeof(r->path), 0);
+    if (url_decode(raw, r->path, sizeof(r->path), 0) != 0)
+      return -1;
     size_t plen = strlen(r->path);
     if (plen == 0 || strstr(r->path, ".."))
       return -1;
@@ -235,8 +274,9 @@ static int read_request(cst_http_conn_t *c, size_t *want_body) {
   size_t hdr_bytes = 0;
   size_t content_length = 0;
   int have_length = 0;
+  double deadline = os_now_ms() + s->o.read_timeout_ms;
   for (;;) {
-    rc = rd_line(c, line, sizeof(line), s->o.read_timeout_ms);
+    rc = rd_line(c, line, sizeof(line), deadline);
     if (rc <= 0)
       return -1;
     if (!line[0])
@@ -251,18 +291,29 @@ static int read_request(cst_http_conn_t *c, size_t *want_body) {
     while (*val == ' ' || *val == '\t')
       val++;
     if (key_is(line, "content-length")) {
-      content_length = (size_t)strtoul(val, NULL, 10);
+      /* digits only, and one value: "5x" or two lengths would let the
+       * rest of the body run as a second request behind a proxy */
+      char *end = NULL;
+      errno = 0;
+      unsigned long long v = strtoull(val, &end, 10);
+      while (end && (*end == ' ' || *end == '\t'))
+        end++;
+      if (*val < '0' || *val > '9' || !end || *end || errno == ERANGE ||
+          v > (unsigned long long)SIZE_MAX ||
+          (have_length && content_length != (size_t)v))
+        return -1;
+      content_length = (size_t)v;
       have_length = 1;
     } else if (key_is(line, "transfer-encoding")) {
       return -1; /* chunked request bodies are not supported */
     } else if (key_is(line, "connection")) {
-      if (strstr(val, "close"))
+      if (has_token(val, "close"))
         r->keep_alive = 0;
-      else if (strstr(val, "keep-alive"))
+      else if (has_token(val, "keep-alive"))
         r->keep_alive = 1;
     } else if (key_is(line, "expect")) {
-      const char *cont = "HTTP/1.1 100 Continue\r\n\r\n";
+      /* answered once auth and the size cap have passed */
-      os_net_send_all(c->sock, cont, strlen(cont), 5000);
+      c->expect_continue = has_token(val, "100-continue");
     } else if (key_is(line, "authorization")) {
       r->authorization = store_str(c, val);
     } else if (key_is(line, "cookie")) {
@@ -275,6 +326,8 @@ static int read_request(cst_http_conn_t *c, size_t *want_body) {
       r->content_type = store_str(c, val);
     } else if (key_is(line, "user-agent")) {
       r->user_agent = store_str(c, val);
+    } else if (key_is(line, "last-event-id")) {
+      r->last_event_id = store_str(c, val);
     }
   }
   if (have_length)
@@ -429,24 +482,30 @@ int cst_http_query(const cst_http_req_t *req, const char *key, char *out,
 
 /* --- connections ---------------------------------------------------------- */
 
-static void dispatch(cst_http_server_t *s, cst_http_conn_t *c) {
+static const cst_http_route_t *find_route(const cst_http_server_t *s,
-  const cst_http_route_t *route = NULL;
+                                          const cst_http_req_t *req) {
   const cst_http_route_t *fallback = NULL;
   for (int i = 0; i < s->nroutes; i++) {
     const cst_http_route_t *r = &s->routes[i];
-    if (strcmp(r->method, "*") != 0 && strcmp(r->method, c->req.method) != 0)
+    if (strcmp(r->method, "*") != 0 && strcmp(r->method, req->method) != 0)
       continue;
     if (strcmp(r->path, "*") == 0) {
       fallback = r;
       continue;
     }
-    if (strcmp(r->path, c->req.path) == 0) {
+    if (strcmp(r->path, req->path) == 0)
-      route = r;
+      return r;
-      break;
   }
+  return fallback;
 }
-  if (!route)
+
-    route = fallback;
+/* Route, auth and the size cap are settled before the body is read: an
+ * unauthenticated client must not make us buffer 32 MiB. */
+static void serve(cst_http_server_t *s, cst_http_conn_t *c, size_t want) {
+  const cst_http_route_t *route = find_route(s, &c->req);
+  size_t cap = route && route->max_body ? route->max_body : s->o.max_body;
+  if (want > 0)
+    c->req.keep_alive = 0; /* until the body is read, the stream is ours */
   if (!route) {
     cst_http_send_err(c, 404, "not found");
     return;
@@ -455,6 +514,25 @@ static void dispatch(cst_http_server_t *s, cst_http_conn_t *c) {
     cst_http_send_err(c, 401, "unauthorized");
     return;
   }
+  if (want > cap) {
+    cst_http_send_err(c, 413, "request body too large");
+    return;
+  }
+  if (want > 0) {
+    if (c->expect_continue) {
+      const char *cont = "HTTP/1.1 100 Continue\r\n\r\n";
+      os_net_send_all(c->sock, cont, strlen(cont), 5000);
+    }
+    char *body = rd_body(c, want, s->o.read_timeout_ms);
+    if (!body) {
+      c->failed = 1;
+      return;
+    }
+    c->body = body;
+    c->req.body = body;
+    c->req.body_len = want;
+    c->req.keep_alive = c->keep_alive_req;
+  }
   int rc = route->fn(c, route->ud);
   if (!c->sent)
     cst_http_send_err(c, rc == 0 ? 500 : 404,
@@ -477,32 +555,14 @@ static void *conn_main(void *arg) {
     }
     if (rc == 0)
       break;
-    size_t cap = s->o.max_body;
+    c->nreq++;
-    for (int i = 0; i < s->nroutes; i++) {
-      const cst_http_route_t *r = &s->routes[i];
-      if (r->max_body && strcmp(r->method, c->req.method) == 0 &&
-          strcmp(r->path, c->req.path) == 0)
-        cap = r->max_body;
-    }
-    if (want > cap) {
-      c->req.keep_alive = 0;
-      cst_http_send_err(c, 413, "request body too large");
-      break;
-    }
-    if (want > 0) {
-      char *body = rd_body(c, want, s->o.read_timeout_ms);
-      if (!body)
-        break;
-      c->body = body;
-      c->req.body = body;
-      c->req.body_len = want;
-    }
     c->sent = 0;
     c->streaming = 0;
-    dispatch(s, c);
+    c->keep_alive_req = c->req.keep_alive;
+    serve(s, c, want);
     if (s->o.on_log) {
       char line[512];
-      snprintf(line, sizeof(line), "%s %s -> %d", c->req.method, c->req.path,
+      snprintf(line, sizeof(line), "%s %.480s -> %d", c->req.method, c->req.path,
                c->failed ? 499 : (c->sent ? 200 : 500));
       s->o.on_log(line, s->o.log_ud);
     }
@@ -512,11 +572,12 @@ static void *conn_main(void *arg) {
     c->req.body_len = 0;
     c->req.authorization = c->req.cookie = c->req.origin = NULL;
     c->req.host = c->req.content_type = c->req.user_agent = NULL;
+    c->req.last_event_id = NULL;
     if (!c->req.keep_alive || s->stopping || c->failed)
       break;
   }
-  os_net_shutdown(c->sock);
+  /* unlink first: stop() shuts down every listed socket, and a closed fd
-  os_net_close(c->sock);
+   * number may already belong to someone else */
   pthread_mutex_lock(&s->mu);
   if (c->prev)
     c->prev->next = c->next;
@@ -524,10 +585,14 @@ static void *conn_main(void *arg) {
     s->conns_first = c->next;
   if (c->next)
     c->next->prev = c->prev;
+  pthread_mutex_unlock(&s->mu);
+  os_net_shutdown(c->sock);
+  os_net_close(c->sock);
+  free(c);
+  pthread_mutex_lock(&s->mu);
   s->nconn--;
   pthread_cond_broadcast(&s->cv);
   pthread_mutex_unlock(&s->mu);
-  free(c);
   return NULL;
 }
 
@@ -536,8 +601,22 @@ static void *accept_main(void *arg) {
   while (!s->stopping) {
     int timed_out = 0;
     os_socket_t sock = os_net_accept(s->listener, 500, &timed_out);
-    if (sock == OS_SOCKET_BAD)
+    if (sock == OS_SOCKET_BAD) {
+      if (!timed_out) { /* EMFILE and friends: the listener stays readable */
+        struct timespec ts;
+        clock_gettime(CLOCK_REALTIME, &ts);
+        ts.tv_nsec += 100000000;
+        if (ts.tv_nsec >= 1000000000) {
+          ts.tv_sec++;
+          ts.tv_nsec -= 1000000000;
+        }
+        pthread_mutex_lock(&s->mu);
+        if (!s->stopping)
+          pthread_cond_timedwait(&s->cv, &s->mu, &ts);
+        pthread_mutex_unlock(&s->mu);
+      }
       continue;
+    }
     if (s->stopping) {
       os_net_close(sock);
       break;
@@ -644,9 +723,9 @@ int cst_http_stopping(const cst_http_server_t *s) {
   return s ? s->stopping : 1;
 }
 
-void cst_http_stop(cst_http_server_t *s) {
+int cst_http_stop(cst_http_server_t *s) {
   if (!s)
-    return;
+    return 0;
   pthread_mutex_lock(&s->mu);
   s->stopping = 1;
   for (cst_http_conn_t *c = s->conns_first; c; c = c->next)
@@ -670,13 +749,20 @@ void cst_http_stop(cst_http_server_t *s) {
     }
     pthread_cond_timedwait(&s->cv, &s->mu, &ts);
   }
+  int left = s->nconn;
   pthread_mutex_unlock(&s->mu);
   os_net_close(s->listener);
+  return left;
 }
 
 void cst_http_free(cst_http_server_t *s) {
   if (!s)
     return;
+  pthread_mutex_lock(&s->mu);
+  int left = s->nconn;
+  pthread_mutex_unlock(&s->mu);
+  if (left > 0)
+    return; /* a handler still runs on it (see stop()): leak, not crash */
   pthread_mutex_destroy(&s->mu);
   pthread_cond_destroy(&s->cv);
   free(s->routes);

src/main.c

@@ -43,7 +43,7 @@ static void usage(const char *argv0) {
           "  -n, --max-steps N     model calls per turn (30)\n"
           "  -H, --headless -p TEXT  run one prompt without the TUI\n"
           "      --web             serve the UI over HTTP on 127.0.0.1:8787\n"
-          "      --web-port N      port (0 = pick a free one)\n"
+          "      --web-port N      port (default 8787, 0 = pick a free one)\n"
           "      --web-host ADDR   bind address (default 127.0.0.1; a\n"
           "                        non-loopback address requires a token)\n"
           "      --web-token T     require ?token=T / Authorization: Bearer T\n"
@@ -255,6 +255,16 @@ static int demo_ctl_impl(const char *workspace) {
   return 0;
 }
 
+/* 0..65535, digits only: atoi turned "70000" into port 4464, "abc" into 0. */
+static int parse_port(const char *s, int *out) {
+  char *end = NULL;
+  long v = strtol(s, &end, 10);
+  if (!s[0] || *end || v < 0 || v > 65535)
+    return -1;
+  *out = (int)v;
+  return 0;
+}
+
 int main(int argc, char **argv) {
   if (os_console_init() != 0)
     fprintf(stderr, "warning: the process code page is not UTF-8 (Windows 10 "
@@ -332,9 +342,12 @@ int main(int argc, char **argv) {
   int web_mode = 0;
   cst_webui_opts_t web;
   memset(&web, 0, sizeof(web));
+  web.port = CST_WEBUI_DEFAULT_PORT; /* 0 would mean "pick a free one" */
   const char *env = getenv("CST_WEB_PORT");
-  if (env && env[0])
+  if (env && env[0] && parse_port(env, &web.port) != 0) {
-    web.port = atoi(env);
+    fprintf(stderr, "CST_WEB_PORT=%s is not a port (0-65535)\n", env);
+    return 1;
+  }
   web.host = getenv("CST_WEB_HOST");
   web.token = getenv("CST_WEB_TOKEN");
   web.root = getenv("CST_WEB_ROOT");
@@ -481,7 +494,11 @@ int main(int argc, char **argv) {
       web_mode = 1;
       break;
     case 0x102:
-      web.port = atoi(optarg);
+      if (parse_port(optarg, &web.port) != 0) {
+        fprintf(stderr, "--web-port %s is not a port (0-65535)\n", optarg);
+        curl_global_cleanup();
+        return 1;
+      }
       web_mode = 1;
       break;
     case 0x103:

src/net.c

@@ -12,6 +12,10 @@
 #ifndef WIN32_LEAN_AND_MEAN
 #define WIN32_LEAN_AND_MEAN
 #endif
+#if !defined(_WIN32_WINNT) || _WIN32_WINNT < 0x0600
+#undef _WIN32_WINNT
+#define _WIN32_WINNT 0x0600 /* WSAPoll */
+#endif
 #include <winsock2.h>
 #include <ws2tcpip.h>
 #else
@@ -21,8 +25,8 @@
 #include <netdb.h>
 #include <netinet/in.h>
 #include <netinet/tcp.h>
+#include <poll.h>
 #include <signal.h>
-#include <sys/select.h>
 #include <sys/socket.h>
 #include <unistd.h>
 #endif
@@ -45,7 +49,6 @@ static void set_err_win(char *err, size_t err_sz, const char *what) {
 }
 #define SET_ERR(e, n, w) set_err_win(e, n, w)
 #define NET_FD(s) ((SOCKET)(s))
-#define NET_NFDS(s) (0) /* Winsock ignores nfds */
 static void net_close_raw(os_socket_t s) { closesocket((SOCKET)s); }
 static int net_last_would_block(void) {
   int e = WSAGetLastError();
@@ -58,7 +61,6 @@ static int net_last_conn_reset(void) {
 #else
 #define SET_ERR(e, n, w) set_err(e, n, w)
 #define NET_FD(s) ((int)(s))
-#define NET_NFDS(s) ((int)((s) + 1))
 static void net_close_raw(os_socket_t s) { close(s); }
 static int net_last_would_block(void) { return errno == EINTR; }
 static int net_last_conn_reset(void) {
@@ -84,15 +86,22 @@ void os_net_cleanup(void) {
 #endif
 }
 
+/* poll, not select: FD_SET past FD_SETSIZE writes out of bounds, and a
+ * failed connect shows up as an error event, not as writable, on Windows. */
 static int wait_io(os_socket_t s, int want_write, int timeout_ms) {
-  fd_set fds;
+#ifdef _WIN32
-  FD_ZERO(&fds);
+  WSAPOLLFD p;
-  FD_SET(NET_FD(s), &fds);
+  p.fd = NET_FD(s);
-  struct timeval tv;
+  p.events = want_write ? POLLWRNORM : POLLRDNORM;
-  tv.tv_sec = timeout_ms / 1000;
+  p.revents = 0;
-  tv.tv_usec = (timeout_ms % 1000) * 1000;
+  int rc = WSAPoll(&p, 1, timeout_ms < 0 ? -1 : timeout_ms);
-  int rc = select(NET_NFDS(s), want_write ? NULL : &fds,
+#else
-                  want_write ? &fds : NULL, NULL, timeout_ms < 0 ? NULL : &tv);
+  struct pollfd p;
+  p.fd = NET_FD(s);
+  p.events = want_write ? POLLOUT : POLLIN;
+  p.revents = 0;
+  int rc = poll(&p, 1, timeout_ms < 0 ? -1 : timeout_ms);
+#endif
   if (rc > 0)
     return 1;
   if (rc == 0)
@@ -137,8 +146,15 @@ os_socket_t os_net_listen(const char *host, int port, char *err, size_t err_sz)
     return OS_SOCKET_BAD;
   }
   int one = 1;
+#ifdef _WIN32
+  /* SO_REUSEADDR on Windows lets another process bind the same port and
+   * take over our connections */
+  setsockopt(NET_FD(s), SOL_SOCKET, SO_EXCLUSIVEADDRUSE, (const char *)&one,
+             sizeof(one));
+#else
   setsockopt(NET_FD(s), SOL_SOCKET, SO_REUSEADDR, (const char *)&one,
              sizeof(one));
+#endif
 #ifdef IPV6_V6ONLY
   if (sa.ss_family == AF_INET6)
     setsockopt(NET_FD(s), IPPROTO_IPV6, IPV6_V6ONLY, (const char *)&one,

src/os_compat.c

@@ -519,7 +519,7 @@ int os_run_timeout_effective(void) {
   const char *e = getenv("CST_SHELL_TIMEOUT");
   if (e && atoi(e) > 0)
     return atoi(e);
-  return 120;
+  return 0; /* no limit: a build, a test suite or a long clone must finish */
 }
 
 double os_now_ms(void) {
@@ -662,7 +662,8 @@ int os_run_capture_ex(const char *cwd, const char *const argv[],
   int truncated = 0, killed = 0;
   int status = 0, reaped = 0, bg_killed = 0;
   double reaped_at = 0, killed_at = 0;
-  double deadline = os_now_ms() + os_run_timeout_effective() * 1000.0;
+  int timeout_s = os_run_timeout_effective();
+  double deadline = timeout_s > 0 ? os_now_ms() + timeout_s * 1000.0 : 0;
   for (;;) {
     struct pollfd pfd = {pipefd[0], POLLIN, 0};
     int pr = poll(&pfd, 1, 100);
@@ -692,7 +693,7 @@ int os_run_capture_ex(const char *cwd, const char *const argv[],
     }
     /* Checked on every pass, so a chatty command still stops promptly. */
     if (!reaped && !killed &&
-        ((g_run_cancel && *g_run_cancel) || now > deadline)) {
+        ((g_run_cancel && *g_run_cancel) || (deadline > 0 && now > deadline))) {
       killed = (g_run_cancel && *g_run_cancel) ? 2 : 1;
       killed_at = now;
       kill(-pid, SIGTERM);

src/os_win.c

@@ -601,7 +601,10 @@ int os_run_capture_token(const char *cwd, const char *const argv[],
   buf[0] = 0;
   int truncated = 0, killed = 0, reaped = 0, bg_killed = 0;
   double reaped_at = 0, killed_at = 0;
-  double deadline = os_now_ms() + os_run_timeout_effective() * 1000.0;
+  /* no timeout unless one was asked for: a deadline far in the future keeps
+   * every `now > deadline` check working without a second code path */
+  int timeout_s = os_run_timeout_effective();
+  double deadline = timeout_s > 0 ? os_now_ms() + timeout_s * 1000.0 : 1e18;
   int idle = 0; /* empty polls in a row: wait longer once output stalls */
   for (;;) {
     DWORD avail = 0;

src/tui.c

@@ -5364,6 +5364,151 @@ static void cmd_quit(tui_t *t, char *arg, int *quit) {
   *quit = 1;
 }
 
+/* /web: the WebUI is a second front end for the same engine and is designed to
+ * run as its own process, so this starts one on the same workspace and leaves
+ * the TUI holding the terminal. The child gets a fresh session: two writers on
+ * one session file is the one thing that would corrupt it. */
+#ifndef _WIN32
+#include <fcntl.h>
+#include <sys/wait.h> /* waitpid: collect the WebUI started by the last /web */
+#endif
+#ifndef CST_WEBUI_DEFAULT_PORT
+#define CST_WEBUI_DEFAULT_PORT 8787 /* keep in sync with include/cst_webui.h */
+#endif
+static void cmd_web(tui_t *t, char *arg, int *quit) {
+  (void)arg;
+  (void)quit;
+#ifdef _WIN32
+  push_system_line(t, "open another terminal and run: cst-agent --web");
+#else
+  static pid_t spawned = 0;
+  if (spawned > 0) {          /* collect the one we started last time */
+    waitpid(spawned, NULL, WNOHANG);
+    spawned = 0;
+  }
+  char dir[4096], exe[4096 + 16];
+  if (os_exe_dir(dir, sizeof(dir)) != 0) {
+    push_system_line(t, "cannot locate this binary: run cst-agent --web yourself");
+    return;
+  }
+  snprintf(exe, sizeof(exe), "%s/cst-agent", dir);
+  const cst_agent_config_t *cfg = cst_agent_config(t->agent);
+  const char *ws = (cfg && cfg->workspace_root[0]) ? cfg->workspace_root : ".";
+  char logf[4096 + 32];
+  snprintf(logf, sizeof(logf), "%s/.agent", ws);
+  os_mkdir_p(logf, 0755);
+  snprintf(logf, sizeof(logf), "%s/.agent/webui.log", ws);
+  /* The WebUI talks to what this session talks to (-b, -m, a /provider
+   * switch...). The key goes through the environment, not argv (ps). */
+  const char *argv[20];
+  int na = 0;
+  argv[na++] = "cst-agent";
+  argv[na++] = "--web";
+  argv[na++] = "--workspace";
+  argv[na++] = ws;
+  argv[na++] = "--new";
+  if (cfg && cfg->provider[0])
+    argv[na++] = "--provider", argv[na++] = cfg->provider;
+  if (cfg && cfg->model[0])
+    argv[na++] = "--model", argv[na++] = cfg->model;
+  if (cfg && cfg->api_base[0])
+    argv[na++] = "--api-base", argv[na++] = cfg->api_base;
+  if (cfg && cfg->effort[0])
+    argv[na++] = "--effort", argv[na++] = cfg->effort;
+  if (cfg)
+    argv[na++] = "--approval", argv[na++] = cst_approval_name(cfg->approval);
+  argv[na] = NULL;
+  size_t nenv = 0;
+  while (environ[nenv])
+    nenv++;
+  char **envp = calloc(nenv + 2, sizeof(char *));
+  char keyvar[600] = "";
+  if (!envp) {
+    push_system_line(t, "out of memory");
+    return;
+  }
+  size_t ne = 0;
+  for (size_t i = 0; i < nenv; i++)
+    if (strncmp(environ[i], "CST_API_KEY=", 12) != 0)
+      envp[ne++] = environ[i];
+  if (cfg && cfg->api_key[0]) {
+    snprintf(keyvar, sizeof(keyvar), "CST_API_KEY=%s", cfg->api_key);
+    envp[ne++] = keyvar;
+  }
+  envp[ne] = NULL;
+  pid_t pid = fork();
+  if (pid < 0) {
+    free(envp);
+    push_system_line(t, "cannot start a second process");
+    return;
+  }
+  if (pid == 0) {
+    setsid();
+    /* never inherit the TUI's terminal: its output would land on our screen */
+    int in = open("/dev/null", O_RDONLY);
+    if (in >= 0 && in != STDIN_FILENO) {
+      dup2(in, STDIN_FILENO);
+      close(in);
+    }
+    int fd = open(logf, O_WRONLY | O_CREAT | O_TRUNC, 0600);
+    if (fd < 0)
+      fd = open("/dev/null", O_WRONLY);
+    if (fd >= 0) {
+      dup2(fd, STDOUT_FILENO);
+      dup2(fd, STDERR_FILENO);
+      if (fd > 2)
+        close(fd);
+    }
+    execve(exe, (char *const *)argv, envp);
+    _exit(127);
+  }
+  free(envp);
+  spawned = pid;
+  /* Wait (2 s at most) for the URL it prints once it listens: the port may
+   * come from CST_WEB_PORT, or it may not start at all. */
+  char url[512] = "";
+  int died = 0;
+  for (int i = 0; i < 40 && !url[0] && !died; i++) {
+    usleep(50000);
+    FILE *fp = fopen(logf, "r");
+    char line[512];
+    while (fp && fgets(line, sizeof(line), fp)) {
+      if (strncmp(line, "webui: http", 11) == 0) {
+        line[strcspn(line, "\r\n")] = 0;
+        snprintf(url, sizeof(url), "%s", line + 7);
+        break;
+      }
+    }
+    if (fp)
+      fclose(fp);
+    if (!url[0] && waitpid(pid, NULL, WNOHANG) == pid) {
+      died = 1;
+      spawned = 0;
+    }
+  }
+  /* its --new made the WebUI's session CURRENT; a plain `cst-agent` later
+   * should still resume this one */
+  char sid[128] = "";
+  cst_agent_session_id(t->agent, sid, sizeof(sid));
+  if (sid[0])
+    cst_agent_store_set_current(ws, sid);
+  char msg[4200];
+  if (died)
+    snprintf(msg, sizeof(msg), "the WebUI did not start (port busy?): see %s",
+             logf);
+  else if (url[0])
+    snprintf(msg, sizeof(msg), "WebUI started in the background: %s (new session)",
+             url);
+  else
+    snprintf(msg, sizeof(msg), "WebUI starting in the background "
+                               "(http://127.0.0.1:%d/ unless CST_WEB_PORT says "
+                               "otherwise)", CST_WEBUI_DEFAULT_PORT);
+  push_system_line(t, msg);
+  snprintf(msg, sizeof(msg), "its log: %s", logf);
+  push_system_line(t, msg);
+#endif
+}
+
 static const slash_cmd_t SLASH[] = {
     {"help", "?", "", "list commands and keys", 1, cmd_help},
     {"new", "clear", "", "start a new session", 0, cmd_new},
@@ -5422,6 +5567,8 @@ static const slash_cmd_t SLASH[] = {
      cmd_agents},
     {"skill", "", "<name> [task]", "run a task with a skill loaded", 0,
      cmd_skill},
+    {"web", "", "", "start the WebUI in the background (127.0.0.1:8787)", 1,
+     cmd_web},
     {"quit", "q exit", "", "quit", 1, cmd_quit},
 };
 

src/web_md.c

@@ -64,7 +64,17 @@ static void attr_append(cst_buf_t *b, const char *name, size_t nlen,
   cst_buf_puts(b, " ");
   cst_buf_append(b, name, nlen);
   cst_buf_puts(b, "=\"");
-  cst_buf_append(b, val, vlen);
+  /* a single-quoted or bare value may hold '"': it must not end ours */
+  for (size_t i = 0; i < vlen; i++) {
+    if (val[i] == '"')
+      cst_buf_puts(b, "&quot;");
+    else if (val[i] == '<')
+      cst_buf_puts(b, "&lt;");
+    else if (val[i] == '>')
+      cst_buf_puts(b, "&gt;");
+    else
+      cst_buf_append(b, val + i, 1);
+  }
   cst_buf_puts(b, "\"");
 }
 

src/webui.c

@@ -72,11 +72,14 @@ typedef struct wui {
   wui_sse_t *subs;
 
   int busy;
+  int op_busy;     /* a session/workspace/undo/compact/attach call runs */
+  int turn_live;   /* the turn thread still uses w; cleared as it exits */
   uint64_t req_id; /* permission/ask id counter */
   uint64_t perm_id;
   int perm_active, perm_answer;
   uint64_t ask_id;
-  int ask_active, ask_rc;
+  int ask_active, ask_rc; /* ask_rc: 0 pending, 1 answered, -1 dismissed */
+  uint64_t pending_seq; /* event of the open permission/ask_user, 0 = none */
   char ask_ans[WUI_ASK_MAX];
 
   volatile int stopping;
@@ -88,36 +91,44 @@ static uint64_t wui_first_seq(const wui_t *w) {
   return w->seq > WUI_RING ? w->seq - WUI_RING + 1 : 1;
 }
 
-/* Owns data (a cJSON object). */
+/* Owns data (a cJSON object). Returns the event's seq, 0 when dropped. */
-static void wui_emit(wui_t *w, const char *type, cJSON *data) {
+static uint64_t wui_emit(wui_t *w, const char *type, cJSON *data) {
   if (!data)
     data = cJSON_CreateObject();
   if (!data)
-    return;
+    return 0;
   cJSON_AddStringToObject(data, "type", type);
+  /* the seq in the payload must match the SSE id, so it is taken under mu */
+  pthread_mutex_lock(&w->mu);
   cJSON_AddNumberToObject(data, "seq", (double)(w->seq + 1));
   char *json = cJSON_PrintUnformatted(data);
   cJSON_Delete(data);
-  if (!json)
-    return;
   cst_buf_t f = {0};
+  if (json)
     cst_buf_printf(&f, "event: %s\ndata: %s\n\n", type, json);
   free(json);
   if (!f.buf) {
+    pthread_mutex_unlock(&w->mu);
     cst_buf_free(&f);
-    return;
+    return 0;
   }
-  pthread_mutex_lock(&w->mu);
+  uint64_t seq = ++w->seq;
-  w->seq++;
+  int slot = (int)(seq % WUI_RING);
-  int slot = (int)(w->seq % WUI_RING);
   free(w->ring[slot].frame);
   w->ring[slot].frame = f.buf; /* stolen */
-  w->ring[slot].seq = w->seq;
+  w->ring[slot].seq = seq;
   f.buf = NULL;
   for (wui_sse_t *s = w->subs; s; s = s->next)
     pthread_cond_broadcast(&s->cv);
   pthread_mutex_unlock(&w->mu);
   cst_buf_free(&f);
+  return seq;
+}
+
+static void wui_set_pending(wui_t *w, uint64_t seq) {
+  pthread_mutex_lock(&w->mu);
+  w->pending_seq = seq;
+  pthread_mutex_unlock(&w->mu);
 }
 
 static void wui_emit_str(wui_t *w, const char *type, const char *key,
@@ -181,6 +192,8 @@ static cJSON *wui_state_new(wui_t *w) {
     cJSON_AddNumberToObject(u, "requests", sess.requests);
     cJSON_AddNumberToObject(u, "prompt_tokens", (double)sess.prompt);
     cJSON_AddNumberToObject(u, "completion_tokens", (double)sess.out);
+    cJSON_AddNumberToObject(u, "cached_tokens", (double)sess.cached);
+    cJSON_AddNumberToObject(u, "cache_miss_tokens", (double)sess.miss);
     cJSON_AddNumberToObject(u, "cost", sess.cost);
     cJSON_AddBoolToObject(u, "priced", sess.priced != 0);
     cJSON_AddStringToObject(u, "currency", sess.currency);
@@ -377,7 +390,7 @@ static int wui_wait_permission(wui_t *w, const char *tool, const char *detail,
                                            strncmp(detail, CST_PERM_SANDBOX,
                                                    strlen(CST_PERM_SANDBOX)) ==
                                                0);
-    wui_emit(w, "permission", o);
+    wui_set_pending(w, wui_emit(w, "permission", o));
   }
   int timeout = w->perm_timeout_s > 0 ? w->perm_timeout_s : 600;
   /* Nobody is watching: do not hang the turn for ten minutes. */
@@ -402,6 +415,8 @@ static int wui_wait_permission(wui_t *w, const char *tool, const char *detail,
       break;
     }
   }
+  w->perm_active = 0;
+  w->pending_seq = 0;
   pthread_mutex_unlock(&w->mu);
   cJSON *e = cJSON_CreateObject();
   if (e) {
@@ -425,7 +440,7 @@ static int on_ask_user(const char *question, const char *options, char *ans,
   uint64_t id = w->req_id;
   w->ask_id = id;
   w->ask_active = 1;
-  w->ask_rc = -1;
+  w->ask_rc = 0;
   w->ask_ans[0] = 0;
   int has_client = w->subs != NULL;
   pthread_mutex_unlock(&w->mu);
@@ -447,7 +462,7 @@ static int on_ask_user(const char *question, const char *options, char *ans,
       }
       p = nl ? nl + 1 : NULL;
     }
-    wui_emit(w, "ask_user", o);
+    wui_set_pending(w, wui_emit(w, "ask_user", o));
   }
   int timeout = has_client ? 600 : 3;
   int rc = -1;
@@ -470,6 +485,8 @@ static int on_ask_user(const char *question, const char *options, char *ans,
       break;
     }
   }
+  w->ask_active = 0;
+  w->pending_seq = 0;
   pthread_mutex_unlock(&w->mu);
   return rc;
 }
@@ -542,6 +559,8 @@ static int wui_serve_asset(cst_http_conn_t *c, wui_t *w, const char *path) {
   return -1;
 }
 
+static int wui_auth(const cst_http_req_t *req, void *ud);
+
 static int h_asset(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   const cst_http_req_t *req = cst_http_request(c);
@@ -550,6 +569,9 @@ static int h_asset(cst_http_conn_t *c, void *ud) {
    * reachable. */
   static const char prefix[] = "/api/attach/";
   if (strncmp(req->path, prefix, sizeof(prefix) - 1) == 0) {
+    /* the fallback route is public (the page's own assets); images are not */
+    if (wui_auth(req, w) != 0)
+      return cst_http_send_err(c, 401, "unauthorized");
     const char *rel = req->path + sizeof(prefix) - 1;
     if (!cst_attach_rel_ok(rel))
       return -1;
@@ -567,8 +589,8 @@ static int h_asset(cst_http_conn_t *c, void *ud) {
     size_t n = strlen(rel);
     if (n > 4 && strcmp(rel + n - 4, ".png") == 0)
       ctype = "image/png";
-    else if (n > 4 && (strcmp(rel + n - 4, ".jpg") == 0 ||
+    else if ((n > 4 && strcmp(rel + n - 4, ".jpg") == 0) ||
-                       strcmp(rel + n - 4, ".jpeg") == 0))
+             (n > 5 && strcmp(rel + n - 5, ".jpeg") == 0))
       ctype = "image/jpeg";
     else if (n > 4 && strcmp(rel + n - 4, ".gif") == 0)
       ctype = "image/gif";
@@ -628,11 +650,19 @@ static int h_events(cst_http_conn_t *c, void *ud) {
   char buf[32];
   if (cst_http_query(req, "since", buf, sizeof(buf)) == 0)
     s.cursor = (uint64_t)strtoull(buf, NULL, 10);
+  else if (req->last_event_id)
+    s.cursor = (uint64_t)strtoull(req->last_event_id, NULL, 10);
   pthread_mutex_init(&s.mu, NULL);
   pthread_cond_init(&s.cv, NULL);
   pthread_mutex_lock(&w->mu);
-  if (s.cursor == 0)
+  /* 0 = a fresh client wants new events only; past the head = ids from an
-    s.cursor = w->seq; /* a fresh client wants new events only */
+   * earlier server process */
+  if (s.cursor == 0 || s.cursor > w->seq) {
+    s.cursor = w->seq;
+    /* a page opened while a question waits must still get to answer it */
+    if (w->pending_seq && w->pending_seq <= w->seq)
+      s.cursor = w->pending_seq - 1;
+  }
   if (s.cursor < wui_first_seq(w) - 1)
     s.cursor = wui_first_seq(w) - 1; /* too far behind: resume at the head */
   s.next = w->subs;
@@ -739,14 +769,19 @@ static void *wui_turn_main(void *arg) {
   wui_end_turn(w, rc, err);
   free(t->prompt);
   free(t);
+  pthread_mutex_lock(&w->mu);
+  w->turn_live = 0;
+  pthread_cond_broadcast(&w->cv);
+  pthread_mutex_unlock(&w->mu);
   return NULL;
 }
 
 static int wui_start_turn(wui_t *w, const char *text, char *err, size_t err_sz) {
   pthread_mutex_lock(&w->mu);
-  if (w->busy) {
+  if (w->busy || w->op_busy) {
     pthread_mutex_unlock(&w->mu);
-    snprintf(err, err_sz, "a turn is already running");
+    snprintf(err, err_sz, w->busy ? "a turn is already running"
+                                  : "another change is running");
     return -1;
   }
   w->busy = 1;
@@ -774,11 +809,15 @@ static int wui_start_turn(wui_t *w, const char *text, char *err, size_t err_sz)
     return -1;
   }
   pthread_t th;
+  pthread_mutex_lock(&w->mu);
+  w->turn_live = 1;
+  pthread_mutex_unlock(&w->mu);
   if (pthread_create(&th, NULL, wui_turn_main, t) != 0) {
     free(t->prompt);
     free(t);
     pthread_mutex_lock(&w->mu);
     w->busy = 0;
+    w->turn_live = 0;
     pthread_mutex_unlock(&w->mu);
     snprintf(err, err_sz, "cannot start the turn thread");
     return -1;
@@ -806,9 +845,45 @@ static int h_turn(cst_http_conn_t *c, void *ud) {
                            "{\"ok\":true}");
 }
 
+/* The agent is not locked: switching sessions, the workspace, undo, compact
+ * and the pending images all change what a running turn reads. These run
+ * one at a time and never during a turn. */
+static int wui_claim(wui_t *w) {
+  pthread_mutex_lock(&w->mu);
+  int ok = !w->busy && !w->op_busy;
+  if (ok)
+    w->op_busy = 1;
+  pthread_mutex_unlock(&w->mu);
+  return ok ? 0 : -1;
+}
+
+static void wui_release(wui_t *w) {
+  pthread_mutex_lock(&w->mu);
+  w->op_busy = 0;
+  pthread_mutex_unlock(&w->mu);
+}
+
+#define WUI_EXCLUSIVE(name)                                                    \
+  static int name(cst_http_conn_t *c, void *ud) {                              \
+    wui_t *w = ud;                                                             \
+    if (wui_claim(w) != 0)                                                     \
+      return cst_http_send_err(c, 409, "busy: wait for the running turn");     \
+    int rc = name##_x(c, ud);                                                  \
+    wui_release(w);                                                            \
+    return rc;                                                                 \
+  }
+
 static int h_cancel(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   cst_agent_request_cancel(w->agent);
+  /* a turn parked on the gate or a question would not see the flag */
+  pthread_mutex_lock(&w->mu);
+  if (w->perm_active && w->perm_answer < 0)
+    w->perm_answer = CST_PERM_DENY;
+  if (w->ask_active && w->ask_rc == 0)
+    w->ask_rc = -1;
+  pthread_cond_broadcast(&w->cv);
+  pthread_mutex_unlock(&w->mu);
   return cst_http_send_str(c, 200, "application/json; charset=utf-8",
                            "{\"ok\":true}");
 }
@@ -868,11 +943,15 @@ static int h_ask_user(cst_http_conn_t *c, void *ud) {
 static int h_sessions(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   const cst_agent_config_t *cfg = cst_agent_config(w->agent);
-  static char ids[200][128];
+  char (*ids)[128] = malloc(200 * sizeof(*ids)); /* handlers run in parallel */
+  if (!ids)
+    return cst_http_send_err(c, 500, "out of memory");
   int n = cst_agent_store_list(cfg->workspace_root, ids, 200);
   cJSON *root = cJSON_CreateObject();
-  if (!root)
+  if (!root) {
+    free(ids);
     return cst_http_send_err(c, 500, "out of memory");
+  }
   char cur[128] = "";
   cst_agent_store_get_current(cfg->workspace_root, cur, sizeof(cur));
   cJSON_AddStringToObject(root, "current", cur);
@@ -891,6 +970,7 @@ static int h_sessions(cst_http_conn_t *c, void *ud) {
     cJSON_AddNumberToObject(o, "mtime", (double)in.mtime);
     cJSON_AddItemToArray(arr, o);
   }
+  free(ids);
   char *json = cJSON_PrintUnformatted(root);
   cJSON_Delete(root);
   int rc = cst_http_send_json(c, 200, json);
@@ -898,7 +978,7 @@ static int h_sessions(cst_http_conn_t *c, void *ud) {
   return rc;
 }
 
-static int h_session_new(cst_http_conn_t *c, void *ud) {
+static int h_session_new_x(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   char id[128] = "";
   if (cst_agent_new_session(w->agent, id, sizeof(id)) != 0)
@@ -916,7 +996,39 @@ static int h_session_new(cst_http_conn_t *c, void *ud) {
   return rc;
 }
 
-static int h_session_switch(cst_http_conn_t *c, void *ud) {
+/* POST /api/workspace {"path":"/abs/dir"} - re-root the agent. The session
+ * store is per directory, so this always lands in a fresh session there. */
+static int h_workspace_x(cst_http_conn_t *c, void *ud) {
+  wui_t *w = ud;
+  const cst_http_req_t *req = cst_http_request(c);
+  cJSON *j = req->body_len ? cJSON_Parse(req->body) : NULL;
+  const cJSON *p = j ? cJSON_GetObjectItem(j, "path") : NULL;
+  if (!cJSON_IsString(p) || !p->valuestring[0]) {
+    cJSON_Delete(j);
+    return cst_http_send_err(c, 400, "path is required");
+  }
+  char err[256] = "";
+  int rc = cst_agent_set_workspace(w->agent, p->valuestring, err, sizeof(err));
+  cJSON_Delete(j);
+  if (rc != 0)
+    return cst_http_send_err(c, 400, err[0] ? err : "cannot switch workspace");
+  char id[128] = "";
+  if (cst_agent_new_session(w->agent, id, sizeof(id)) != 0)
+    return cst_http_send_err(c, 500, "cannot start a session there");
+  wui_emit_str(w, "session", "id", id);
+  wui_emit_state(w);
+  cJSON *o = cJSON_CreateObject();
+  if (!o)
+    return cst_http_send_err(c, 500, "out of memory");
+  cJSON_AddStringToObject(o, "id", id);
+  char *json = cJSON_PrintUnformatted(o);
+  cJSON_Delete(o);
+  rc = cst_http_send_json(c, 200, json);
+  free(json);
+  return rc;
+}
+
+static int h_session_switch_x(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   const cst_http_req_t *req = cst_http_request(c);
   cJSON *j = req->body_len ? cJSON_Parse(req->body) : NULL;
@@ -941,6 +1053,15 @@ static int h_config(cst_http_conn_t *c, void *ud) {
     cJSON_Delete(j);
     return cst_http_send_err(c, 400, "expected a JSON object");
   }
+  /* the strings are read by the turn as it builds each request; approval
+   * and plan mode may change mid-turn (say, to yolo at a pending gate) */
+  int claimed = cJSON_GetObjectItem(j, "model") ||
+                cJSON_GetObjectItem(j, "provider") ||
+                cJSON_GetObjectItem(j, "effort");
+  if (claimed && wui_claim(w) != 0) {
+    cJSON_Delete(j);
+    return cst_http_send_err(c, 409, "busy: wait for the running turn");
+  }
   const cJSON *item;
   if ((item = cJSON_GetObjectItem(j, "model")) && cJSON_IsString(item))
     snprintf(cfg->model, sizeof(cfg->model), "%s", item->valuestring);
@@ -961,12 +1082,14 @@ static int h_config(cst_http_conn_t *c, void *ud) {
     cfg->read_only = cfg->plan_mode;
   }
   cJSON_Delete(j);
+  if (claimed)
+    wui_release(w);
   wui_emit_state(w);
   return cst_http_send_str(c, 200, "application/json; charset=utf-8",
                            "{\"ok\":true}");
 }
 
-static int h_undo(cst_http_conn_t *c, void *ud) {
+static int h_undo_x(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   char report[2048] = "";
   if (cst_agent_undo(w->agent, report, sizeof(report)) != 0)
@@ -976,7 +1099,7 @@ static int h_undo(cst_http_conn_t *c, void *ud) {
   return cst_http_send_str(c, 200, "text/plain; charset=utf-8", report);
 }
 
-static int h_compact(cst_http_conn_t *c, void *ud) {
+static int h_compact_x(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   char err[256] = "";
   if (cst_agent_compact(w->agent, err, sizeof(err)) != 0)
@@ -986,7 +1109,7 @@ static int h_compact(cst_http_conn_t *c, void *ud) {
                            "{\"ok\":true}");
 }
 
-static int h_attach_upload(cst_http_conn_t *c, void *ud) {
+static int h_attach_upload_x(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   const cst_http_req_t *req = cst_http_request(c);
   char name[256] = "pasted.png";
@@ -1002,7 +1125,7 @@ static int h_attach_upload(cst_http_conn_t *c, void *ud) {
                            "{\"ok\":true}");
 }
 
-static int h_attach_clear(cst_http_conn_t *c, void *ud) {
+static int h_attach_clear_x(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   cst_agent_pending_clear(w->agent);
   wui_emit_state(w);
@@ -1010,6 +1133,14 @@ static int h_attach_clear(cst_http_conn_t *c, void *ud) {
                            "{\"ok\":true}");
 }
 
+WUI_EXCLUSIVE(h_session_new)
+WUI_EXCLUSIVE(h_workspace)
+WUI_EXCLUSIVE(h_session_switch)
+WUI_EXCLUSIVE(h_undo)
+WUI_EXCLUSIVE(h_compact)
+WUI_EXCLUSIVE(h_attach_upload)
+WUI_EXCLUSIVE(h_attach_clear)
+
 static int h_quit(cst_http_conn_t *c, void *ud) {
   wui_t *w = ud;
   w->stopping = 1;
@@ -1073,10 +1204,51 @@ static int host_is_loopback(const char *host) {
   return 0;
 }
 
+static int strncasecmp_ascii(const char *a, const char *b, size_t n) {
+  for (size_t i = 0; i < n; i++) {
+    char x = a[i], y = b[i];
+    if (x >= 'A' && x <= 'Z')
+      x = (char)(x - 'A' + 'a');
+    if (y >= 'A' && y <= 'Z')
+      y = (char)(y - 'A' + 'a');
+    if (x != y)
+      return x < y ? -1 : 1;
+    if (!x)
+      return 0;
+  }
+  return 0;
+}
+
+/* A browser names the page that sent a request in Origin. Without a token
+ * that is the only thing that tells our own page from any site the user
+ * visits: a no-cors POST with a text/plain body needs no preflight and
+ * carries Host: 127.0.0.1. So it must be this very origin. */
+static int origin_is_self(const char *origin, const char *host) {
+  if (!origin)
+    return 1; /* curl and friends; browsers always send it on POST */
+  while (*origin == ' ')
+    origin++;
+  const char *rest = NULL;
+  if (strncmp(origin, "http://", 7) == 0)
+    rest = origin + 7;
+  else if (strncmp(origin, "https://", 8) == 0)
+    rest = origin + 8;
+  if (!rest || !host)
+    return 0;
+  while (*host == ' ')
+    host++;
+  size_t n = strlen(host);
+  while (n && (host[n - 1] == ' ' || host[n - 1] == '\t'))
+    n--;
+  return strlen(rest) == n && strncasecmp_ascii(rest, host, n) == 0;
+}
+
 static int wui_auth(const cst_http_req_t *req, void *ud) {
   wui_t *w = ud;
   if (!w->need_auth)
-    return host_is_loopback(req->host) ? 0 : -1;
+    return host_is_loopback(req->host) && origin_is_self(req->origin, req->host)
+               ? 0
+               : -1;
   char buf[128];
   if (req->authorization && strncmp(req->authorization, "Bearer ", 7) == 0 &&
       token_matches(w, req->authorization + 7))
@@ -1124,20 +1296,21 @@ static void wui_make_token(char *out, size_t out_sz) {
 }
 
 static void open_browser(const char *url) {
+  char cmd[600];
 #if defined(_WIN32)
-  char cmd[600];
   snprintf(cmd, sizeof(cmd), "start \"\" \"%s\"", url);
-  os_run_shell_c(".", cmd, 0, NULL);
 #elif defined(__APPLE__)
-  char cmd[600];
   snprintf(cmd, sizeof(cmd), "open '%s'", url);
-  os_run_shell_c(".", cmd, 0, NULL);
 #else
-  char cmd[600];
+  /* Termux has no xdg-open; termux-open-url hands the URL to Android. */
-  snprintf(cmd, sizeof(cmd), "xdg-open '%s' >/dev/null 2>&1 &", url);
+  const char *opener =
-  os_run_shell_c(".", cmd, 0, NULL);
+      getenv("TERMUX_VERSION") ? "termux-open-url" : "xdg-open";
+  snprintf(cmd, sizeof(cmd), "%s '%s' >/dev/null 2>&1 &", opener, url);
 #endif
-  (void)url;
+  os_run_result_t r;
+  memset(&r, 0, sizeof(r)); /* a NULL result makes the runner refuse */
+  os_run_shell_c(".", cmd, 0, &r);
+  os_run_result_free(&r);
 }
 
 int cst_webui_run(cst_agent_t *agent, const cst_webui_opts_t *opts) {
@@ -1157,6 +1330,14 @@ int cst_webui_run(cst_agent_t *agent, const cst_webui_opts_t *opts) {
   snprintf(w->host, sizeof(w->host), "%s",
            opts->host && opts->host[0] ? opts->host : "127.0.0.1");
   if (opts->token && opts->token[0]) {
+    if (strlen(opts->token) >= sizeof(w->token)) {
+      fprintf(stderr, "webui: the token is longer than %d characters\n",
+              (int)sizeof(w->token) - 1);
+      pthread_cond_destroy(&w->cv);
+      pthread_mutex_destroy(&w->mu);
+      free(w);
+      return 1;
+    }
     snprintf(w->token, sizeof(w->token), "%s", opts->token);
     w->need_auth = 1;
   } else if (strcmp(w->host, "127.0.0.1") != 0 &&
@@ -1173,6 +1354,7 @@ int cst_webui_run(cst_agent_t *agent, const cst_webui_opts_t *opts) {
       {"GET", "/api/sessions", h_sessions, NULL, 0, 0},
       {"POST", "/api/sessions/new", h_session_new, NULL, 0, 0},
       {"POST", "/api/sessions/switch", h_session_switch, NULL, 0, 0},
+      {"POST", "/api/workspace", h_workspace, NULL, 0, 0},
       {"POST", "/api/turn", h_turn, NULL, 0, 0},
       {"POST", "/api/cancel", h_cancel, NULL, 0, 0},
       {"POST", "/api/permission", h_permission, NULL, 0, 0},
@@ -1189,8 +1371,10 @@ int cst_webui_run(cst_agent_t *agent, const cst_webui_opts_t *opts) {
     routes[i].ud = w;
     routes[i].auth = w->need_auth || strcmp(routes[i].path, "/") != 0;
   }
-  routes[0].auth = 0;  /* the shell page itself sets the cookie */
+  /* the shell page and its assets carry no token (app.js reads it from the
-  routes[sizeof(routes) / sizeof(routes[0]) - 1].auth = w->need_auth;
+   * URL and sets the cookie); h_asset checks /api/attach/ itself */
+  routes[0].auth = 0;
+  routes[sizeof(routes) / sizeof(routes[0]) - 1].auth = 0;
 
   cst_http_opts_t ho;
   memset(&ho, 0, sizeof(ho));
@@ -1224,8 +1408,12 @@ int cst_webui_run(cst_agent_t *agent, const cst_webui_opts_t *opts) {
             w->token);
   fflush(stderr);
   wui_emit_state(w);
-  if (opts->open_browser)
+  if (opts->open_browser) {
-    open_browser(url);
+    char full[sizeof(url) + 80];
+    snprintf(full, sizeof(full), "%s%s%s", url, w->need_auth ? "#token=" : "",
+             w->need_auth ? w->token : "");
+    open_browser(full);
+  }
 
   if (opts->prompt && opts->prompt[0]) {
     char err2[256] = "";
@@ -1243,8 +1431,38 @@ int cst_webui_run(cst_agent_t *agent, const cst_webui_opts_t *opts) {
     nanosleep(&ts, NULL);
   }
   fprintf(stderr, "webui: shutting down\n");
+  /* Wake a turn parked on a permission/ask_user answer, cancel it and wait
+   * for its thread: it emits through w, and the agent is destroyed next. */
+  pthread_mutex_lock(&w->mu);
   w->stopping = 1;
-  cst_http_stop(w->srv);
+  pthread_cond_broadcast(&w->cv);
+  int live = w->turn_live;
+  pthread_mutex_unlock(&w->mu);
+  cst_agent_request_cancel(w->agent); /* also a /api/compact in flight */
+  if (live) {
+    struct timespec deadline;
+    clock_gettime(CLOCK_REALTIME, &deadline);
+    deadline.tv_sec += 30;
+    pthread_mutex_lock(&w->mu);
+    while (w->turn_live &&
+           pthread_cond_timedwait(&w->cv, &w->mu, &deadline) == 0)
+      ;
+    live = w->turn_live;
+    pthread_mutex_unlock(&w->mu);
+  }
+  if (live) {
+    /* still running (a command ignoring cancel): the caller would destroy
+     * the agent under it, so leave without tearing anything down */
+    fprintf(stderr, "webui: the running turn did not stop in 30 s\n");
+    fflush(NULL);
+    _Exit(1);
+  }
+  if (cst_http_stop(w->srv) > 0) {
+    /* a handler still runs and uses w and the agent: same as above */
+    fprintf(stderr, "webui: a request did not finish in 30 s\n");
+    fflush(NULL);
+    _Exit(1);
+  }
   cst_http_free(w->srv);
   for (int i = 0; i < WUI_RING; i++)
     free(w->ring[i].frame);

tests/test_webui.c

@@ -236,6 +236,16 @@ static void test_sanitize(void) {
   CHECK(strstr(html, "<a") == NULL); /* an unusable href drops the tag */
   free(html);
 
+  /* a quote inside a single-quoted or bare value cannot open a new attribute */
+  const char *quoted = "<a href='http://x\" onmouseover=\"alert(1)'>q</a>"
+                       "<a href=http://y\"onmouseover=alert(2)//>r</a>";
+  html = cst_web_md_sanitize(quoted, strlen(quoted));
+  CHECK(html != NULL);
+  CHECK(strstr(html, "\" onmouseover") == NULL);
+  CHECK(strstr(html, "\"onmouseover") == NULL);
+  CHECK(strstr(html, "&quot;") != NULL);
+  free(html);
+
   /* streaming: a javascript: link is dropped, a split tag never leaks */
   {
     cst_buf_free(&g_md_out);

web/index.html

@@ -1,41 +1,230 @@
 <!DOCTYPE html>
-<html lang="zh-CN">
+<html lang="zh-CN" data-theme="dark">
 <head>
 <meta charset="utf-8">
-<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover">
+<meta name="color-scheme" content="dark light">
 <title>CST-Agent</title>
 <link rel="stylesheet" href="style.css">
 </head>
 <body>
-<header id="bar">
+<!-- one icon set, drawn as a sprite so every glyph shares the same 24px grid,
-  <span class="tag" id="planmode">Build</span>
+     stroke weight and round caps: mixed emoji/unicode never looks like a family -->
-  <span class="tag" id="approval">auto</span>
+<svg id="atlas" aria-hidden="true" hidden>
-  <span class="ws" id="ws" title="workspace"></span>
+  <symbol id="i-menu" viewBox="0 0 24 24"><path d="M4 7h16M4 12h16M4 17h16"/></symbol>
-  <span class="model" id="model" title="model">-</span>
+  <symbol id="i-panel-left" viewBox="0 0 24 24"><rect x="3.5" y="5" width="17" height="14" rx="3"/><path d="M9.5 5v14"/></symbol>
-  <span class="muted" id="ctx"></span>
+  <symbol id="i-panel-right" viewBox="0 0 24 24"><rect x="3.5" y="5" width="17" height="14" rx="3"/><path d="M14.5 5v14"/></symbol>
+  <symbol id="i-chevron" viewBox="0 0 24 24"><path d="M6 9.5l6 5 6-5"/></symbol>
+  <symbol id="i-plus" viewBox="0 0 24 24"><path d="M12 5v14M5 12h14"/></symbol>
+  <symbol id="i-refresh" viewBox="0 0 24 24"><path d="M20 12a8 8 0 1 1-2.6-5.9M20 4.5V9h-4.5"/></symbol>
+  <symbol id="i-settings" viewBox="0 0 24 24"><path d="M4 6.5h5M15 6.5h5M4 12h7M17 12h3M4 17.5h5M15 17.5h5"/><circle cx="11.5" cy="6.5" r="2"/><circle cx="15" cy="12" r="2"/><circle cx="11.5" cy="17.5" r="2"/></symbol>
+  <symbol id="i-moon" viewBox="0 0 24 24"><path d="M20 14.6A8.6 8.6 0 0 1 9.4 4 8.6 8.6 0 1 0 20 14.6z"/></symbol>
+  <symbol id="i-sun" viewBox="0 0 24 24"><circle cx="12" cy="12" r="4.2"/><path d="M12 2.5v2.2M12 19.3v2.2M2.5 12h2.2M19.3 12h2.2M5.2 5.2l1.6 1.6M17.2 17.2l1.6 1.6M18.8 5.2l-1.6 1.6M6.8 17.2l-1.6 1.6"/></symbol>
+  <symbol id="i-more" viewBox="0 0 24 24"><circle cx="5.5" cy="12" r="1.6" class="f"/><circle cx="12" cy="12" r="1.6" class="f"/><circle cx="18.5" cy="12" r="1.6" class="f"/></symbol>
+  <symbol id="i-send" viewBox="0 0 24 24"><path d="M12 19.5V5M5.8 11.2 12 5l6.2 6.2"/></symbol>
+  <symbol id="i-stop" viewBox="0 0 24 24"><rect x="7" y="7" width="10" height="10" rx="2.5" class="f"/></symbol>
+  <symbol id="i-image" viewBox="0 0 24 24"><rect x="3.5" y="5" width="17" height="14" rx="3"/><path d="M4 15.5 8.6 11l4 4 2.8-2.8L20.5 16"/><circle cx="9" cy="9.4" r="1.5"/></symbol>
+  <symbol id="i-clipboard" viewBox="0 0 24 24"><rect x="8.5" y="3.5" width="7" height="4" rx="1.6"/><path d="M15.5 5.5h3v15h-13v-15h3M9 12h6M9 15.5h4"/></symbol>
+  <symbol id="i-list" viewBox="0 0 24 24"><path d="M4 6.8h2M4 12h2M4 17.2h2M9 6.8h11M9 12h11M9 17.2h11"/></symbol>
+  <symbol id="i-copy" viewBox="0 0 24 24"><rect x="8.5" y="8.5" width="11" height="11" rx="2.6"/><path d="M15.5 8.5V7a2.5 2.5 0 0 0-2.5-2.5H6.5A2.5 2.5 0 0 0 4 7v6.5A2.5 2.5 0 0 0 6.5 16h1.5"/></symbol>
+  <symbol id="i-compress" viewBox="0 0 24 24"><path d="M8 3.5V9H3M16 20.5V15h5M3 9h4M16 15h5"/></symbol>
+  <symbol id="i-undo" viewBox="0 0 24 24"><path d="M9.5 5.5 4 11l5.5 5.5"/><path d="M4 11h10.2a5.2 5.2 0 0 1 0 10.4H8.5"/></symbol>
+  <symbol id="i-close" viewBox="0 0 24 24"><path d="M6.5 6.5l11 11M17.5 6.5l-11 11"/></symbol>
+  <symbol id="i-check" viewBox="0 0 24 24"><path d="M5 12.6l4.6 4.6L19 7.6"/></symbol>
+  <symbol id="i-shield" viewBox="0 0 24 24"><path d="M12 3.5 5 6.2v5.4c0 4.2 2.9 7.5 7 8.9 4.1-1.4 7-4.7 7-8.9V6.2z"/></symbol>
+  <symbol id="i-bolt" viewBox="0 0 24 24"><path d="M13.4 3 5.5 13.6H11l-.9 7.4L18.5 10H13z"/></symbol>
+  <symbol id="i-alert" viewBox="0 0 24 24"><path d="M12 4 2.8 20h18.4z"/><path d="M12 10v4.4M12 17.2v.2"/></symbol>
+  <symbol id="i-cpu" viewBox="0 0 24 24"><rect x="7" y="7" width="10" height="10" rx="2.6"/><path d="M10 3v4M14 3v4M10 17v4M14 17v4M3 10h4M3 14h4M17 10h4M17 14h4"/></symbol>
+  <symbol id="i-lv1" viewBox="0 0 24 24"><path d="M5 18.5V13h3.4v5.5z" class="f"/></symbol>
+  <symbol id="i-lv2" viewBox="0 0 24 24"><path d="M5 18.5V13h3.4v5.5zM10.3 18.5V9.6h3.4v8.9z" class="f"/></symbol>
+  <symbol id="i-lv3" viewBox="0 0 24 24"><path d="M5 18.5V13h3.4v5.5zM10.3 18.5V9.6h3.4v8.9zM15.6 18.5V6.4h3.4v12.1z" class="f"/></symbol>
+  <symbol id="i-lv4" viewBox="0 0 24 24"><path d="M4 18.5V13h2.6v5.5zM8.7 18.5V10h2.6v8.5zM13.4 18.5V6.8h2.6v11.7zM18.1 18.5V4h2.6v14.5z" class="f"/></symbol>
+  <symbol id="i-file" viewBox="0 0 24 24"><path d="M13.5 3.5H7A2.5 2.5 0 0 0 4.5 6v12A2.5 2.5 0 0 0 7 20.5h10A2.5 2.5 0 0 0 19.5 18V9.5z"/><path d="M13.5 3.5v6h6"/></symbol>
+  <symbol id="i-clock" viewBox="0 0 24 24"><circle cx="12" cy="12" r="8.5"/><path d="M12 7.2V12l3.2 2"/></symbol>
+  <symbol id="i-folder" viewBox="0 0 24 24"><path d="M3.5 6.5A1.5 1.5 0 0 1 5 5h4l2 2.5h8A1.5 1.5 0 0 1 20.5 9v9A1.5 1.5 0 0 1 19 19.5H5A1.5 1.5 0 0 1 3.5 18z"/></symbol>
+</svg>
+
+<div id="app">
+
+  <!-- rail: identity, one primary action, sessions, identity again.
+       Everything else is a popover anchored where it belongs. -->
+  <aside id="side">
+   <div class="side-inner">
+    <div class="side-head">
+      <div class="brand">
+        <span class="brand-name">CST-Agent</span>
+      </div>
+      <button id="btn-collapse" class="icon" title="收起侧栏 (Ctrl+B)">
+        <svg class="i"><use href="#i-panel-left"/></svg>
+      </button>
+    </div>
+
+    <button id="btn-new" class="new-task">
+      <svg class="i"><use href="#i-plus"/></svg><span>新建任务</span>
+    </button>
+
+    <div class="side-sec">
+      <span>最近</span>
+      <button id="btn-refresh-sessions" class="icon tiny" title="刷新">
+        <svg class="i"><use href="#i-refresh"/></svg>
+      </button>
+    </div>
+    <div id="sessions-list" class="sessions"></div>
+
+    <div class="side-foot">
+      <div class="who">
+        <span class="avatar">C</span>
+        <span class="who-text">
+          <b id="foot-ws">workspace</b>
+          <i id="foot-session">-</i>
+        </span>
+      </div>
+      <button id="btn-settings" class="icon" title="设置">
+        <svg class="i"><use href="#i-settings"/></svg>
+      </button>
+    </div>
+   </div>
+  </aside>
+
+  <!-- main column -->
+  <main id="main">
+    <header id="topbar">
+      <button id="btn-side" class="icon" title="展开侧栏 (Ctrl+B)">
+        <svg class="i"><use href="#i-panel-left"/></svg>
+      </button>
+      <button id="btn-drawer" class="icon only-narrow" title="侧栏">
+        <svg class="i"><use href="#i-menu"/></svg>
+      </button>
+      <button id="chip-model" class="chip model" title="模型与推理强度">
+        <svg class="i"><use href="#i-cpu"/></svg><span class="lbl">-</span>
+        <svg class="i chev"><use href="#i-chevron"/></svg>
+      </button>
       <span class="grow"></span>
-  <button id="btn-sessions" title="sessions">会话</button>
+      <div class="seg" id="seg-mode" title="计划模式只读，不改文件">
-  <button id="btn-model" title="model">模型</button>
+        <button data-mode="build">构建</button>
-  <button id="btn-undo" title="undo">撤销</button>
+        <button data-mode="plan">计划</button>
-  <button id="btn-compact" title="compact">压缩</button>
+      </div>
-  <button id="btn-clear" title="clear view">清屏</button>
+      <button id="chip-approval" class="chip quiet" title="审批权限">
+        <svg class="i"><use href="#i-shield"/></svg><span class="lbl">auto</span>
+        <svg class="i chev"><use href="#i-chevron"/></svg>
+      </button>
+      <button id="btn-theme" class="icon" title="明暗切换">
+        <svg class="i only-dark"><use href="#i-moon"/></svg>
+        <svg class="i only-light"><use href="#i-sun"/></svg>
+      </button>
+      <button id="btn-panel" class="icon" title="运行详情 (Ctrl+J)">
+        <svg class="i"><use href="#i-panel-right"/></svg>
+      </button>
+      <button id="btn-menu" class="icon" title="更多">
+        <svg class="i"><use href="#i-more"/></svg>
+      </button>
     </header>
 
-<main id="log"></main>
+    <div id="scroll">
-<aside id="todo" hidden></aside>
+      <section id="empty">
+        <p class="ready">准备好开始构建了吗</p>
+      </section>
+      <div id="log"></div>
+    </div>
+
+    <button id="to-bottom" class="round" hidden title="回到最新">
+      <svg class="i"><use href="#i-chevron"/></svg>
+    </button>
 
     <footer id="composer">
-  <div id="pending" hidden></div>
+      <div id="pending" class="pending" hidden></div>
-  <div class="row">
-    <textarea id="input" rows="1" placeholder="输入消息，Enter 发送，Shift+Enter 换行"></textarea>
-    <button id="btn-send">发送</button>
-    <button id="btn-stop" hidden>停止</button>
-    <label class="att" title="附上图片"><input type="file" id="file" accept="image/*" hidden>+图</label>
-  </div>
-  <div class="hint"><span id="status">就绪</span><span class="grow"></span><span id="usage" class="muted"></span></div>
-</footer>
 
+      <!-- permission gate: inline, the turn really is waiting on it -->
+      <div id="gate" class="gate" hidden>
+        <div class="gate-head">
+          <span class="gate-title" id="gate-title">需要确认</span>
+          <span class="grow"></span>
+          <span class="gate-timer" id="gate-timer"></span>
+        </div>
+        <pre id="gate-detail"></pre>
+        <div class="gate-keys" id="gate-keys"></div>
+        <div class="gate-row" id="gate-buttons"></div>
+      </div>
+
+      <div class="box">
+        <textarea id="input" rows="1" placeholder="给 CST-Agent 派个任务…"></textarea>
+        <div class="box-row">
+          <button id="btn-plus" class="icon att" title="添加图片或计划模式">
+            <svg class="i"><use href="#i-plus"/></svg>
+          </button>
+          <button id="btn-undo" class="chip quiet" title="撤销上一次文件写入">
+            <svg class="i"><use href="#i-undo"/></svg><span>撤销</span>
+          </button>
+          <span class="grow"></span>
+          <button id="cost" class="cost" title="用量详情"></button>
+          <button id="btn-stop" class="icon stop" hidden title="停止">
+            <svg class="i"><use href="#i-stop"/></svg>
+          </button>
+          <button id="btn-send" class="round send" title="发送 (Enter)">
+            <svg class="i"><use href="#i-send"/></svg>
+          </button>
+        </div>
+      </div>
+      <div class="hint-line">
+        <span id="status">就绪</span>
+        <span class="grow"></span>
+        <span id="usage" class="quiet"></span>
+      </div>
+      <input type="file" id="file" accept="image/*" multiple hidden>
+    </footer>
+  </main>
+
+  <!-- right panel: the run, not the chat -->
+  <aside id="panel">
+   <div class="panel-inner">
+    <div class="panel-head">
+      <span>运行详情</span>
+      <span class="grow"></span>
+      <button id="btn-panel-close" class="icon tiny" title="关闭">
+        <svg class="i"><use href="#i-close"/></svg>
+      </button>
+    </div>
+
+    <section class="card" id="card-todo">
+      <h4>任务清单</h4>
+      <div id="todo-body" class="muted">模型还没有给出任务清单。</div>
+    </section>
+
+    <section class="card" id="card-files">
+      <h4>文件改动 <span class="badge" id="files-count">0</span></h4>
+      <div id="files-body" class="muted">本轮还没有改动文件。</div>
+    </section>
+
+    <section class="card">
+      <h4>上下文</h4>
+      <div class="kv"><span>占用</span><b id="kv-ctx">0</b></div>
+      <div class="kv"><span>缓存命中</span><b id="kv-cache">-</b></div>
+    </section>
+   </div>
+  </aside>
+
+</div>
+
+<div id="backdrop"></div>
+<div id="pop" class="pop" hidden></div>
 <div id="modal" hidden><div id="modal-box"></div></div>
+<script>
+/* Layout is decided here, before app.js runs and before the first paint: the
+ * rail must not flash open and then fold, and a broken script further down can
+ * no longer take the layout down with it. */
+(() => {
+  const q = new URLSearchParams(location.search);
+  const pick = (key) => {
+    const v = q.get(key);
+    if (v === '0' || v === '1') return v === '0';
+    return localStorage.getItem('cst.' + key) === '0';
+  };
+  if (pick('side')) document.body.classList.add('no-side');
+  if (pick('panel')) document.body.classList.add('no-panel');
+  const t = q.get('theme') || localStorage.getItem('cst.theme');
+  if (t) document.documentElement.dataset.theme = t;
+})();
+</script>
 <script src="app.js"></script>
 </body>
 </html>

web/style.css

@@ -1,103 +1,647 @@
+/* CST-Agent WebUI - one stylesheet, no build step.
+ *
+ * Design rules
+ *   - one fact, one home: sessions in the rail, model/approval/plan in the
+ *     top bar, the run in the right panel, attachments in the composer;
+ *   - settings open as popovers anchored to the control that owns them,
+ *     with icon + label + one line of explanation + a check on the current
+ *     value (the pattern all three reference apps use);
+ *   - motion is short and eased: 120ms for feedback, 180ms for entrances,
+ *     nothing bounces, and prefers-reduced-motion turns it all off. */
+
+/* Tokens are named the way the reference desktop app names them: four text
+ * levels, three surfaces per zone (main / sidebar / composer), and borders
+ * mixed out of the foreground rather than hard-coded greys - which is what
+ * keeps the dark and the light sheet on the same visual rhythm. */
 :root {
-  --bg: #14161a;
+  color-scheme: dark;
-  --bg2: #1b1e24;
+
-  --fg: #d8dde5;
+  --text-primary: #f2f2f5;
-  --muted: #8b93a1;
+  --text-secondary: #a9a9b4;
-  --line: #2a2f38;
+  --text-tertiary: #7d7d89;
-  --accent: #7fb2ff;
+  --text-quaternary: #5e5e69;
-  --ok: #7ddc8f;
+  --text-error: #f0616d;
-  --warn: #ffcc66;
+  --text-success: #3ecf95;
-  --err: #ff7b72;
+
-  --tool: #b5e3c8;
+  --main-surface-primary: #0d0d0f;
+  --main-surface-secondary: #141417;
+  --main-surface-tertiary: #1d1d22;
+
+  --sidebar-surface-primary: #111114;
+  --sidebar-surface-secondary: #18181c;
+  --sidebar-surface-tertiary: #202026;
+
+  --composer-surface-primary: #16161a;
+  --composer-surface-secondary: #202026;
+
+  --bg-code: #08080a;
+
+  /* every hover/active tint is alpha, so it lands correctly on any surface */
+  --hover: color-mix(in srgb, var(--text-primary) 7%, transparent);
+  --hover-strong: color-mix(in srgb, var(--text-primary) 13%, transparent);
+
+  --accent-primary: #3ecf95;
+  --accent-fg: #04241a;
+  --accent-weak: color-mix(in srgb, var(--accent-primary) 14%, transparent);
+  --accent-line: color-mix(in srgb, var(--accent-primary) 55%, transparent);
+  --link: var(--accent-primary);
+  --violet: #8b7bff;
+  --warn: #e0b341;
+  --selection-bg: color-mix(in srgb, var(--accent-primary) 30%, transparent);
+  --selection-fg: var(--text-primary);
+
+  --border-light: color-mix(in srgb, var(--text-primary) 14%, transparent);
+  --border-medium: color-mix(in srgb, var(--text-primary) 24%, transparent);
+  --border-heavy: color-mix(in srgb, var(--text-primary) 34%, transparent);
+
+  /* short aliases: the rest of the sheet keeps reading the same way */
+  --bg: var(--main-surface-primary);
+  --bg-soft: var(--main-surface-secondary);
+  --bg-lift: var(--main-surface-tertiary);
+  --bg-hover: var(--hover);
+  --fg: var(--text-primary);
+  --fg-dim: var(--text-secondary);
+  --fg-faint: var(--text-tertiary);
+  --fg-quat: var(--text-quaternary);
+  --line: var(--border-light);
+  --line-strong: var(--border-medium);
+  --accent: var(--accent-primary);
+  --danger: var(--text-error);
+
+  --rail: 252px;
+  --panel: 296px;
+  --radius: 12px;
+  --radius-lg: 22px;
+  --shadow: 0 16px 40px rgba(0, 0, 0, .45);
+  --shadow-sm: 0 6px 18px rgba(0, 0, 0, .3);
+  --mono: ui-monospace, SFMono-Regular, "JetBrains Mono", Menlo, Consolas, monospace;
+  --sans: system-ui, -apple-system, "Segoe UI", Roboto, "Noto Sans CJK SC", sans-serif;
+  --ease: cubic-bezier(.22, .61, .36, 1);
+  --ease-pop: cubic-bezier(.2, .9, .3, 1.06);   /* enters with a hint of overshoot */
+  --t-fast: 120ms;
+  --t: 180ms;
 }
+[data-theme="light"] {
+  color-scheme: light;
+
+  --text-primary: #14141a;
+  --text-secondary: #55555f;
+  --text-tertiary: #7c7c86;
+  --text-quaternary: #9c9ca6;
+  --text-error: #c8303f;
+  --text-success: #0f8f66;
+
+  --main-surface-primary: #ffffff;
+  --main-surface-secondary: #f7f7f9;
+  --main-surface-tertiary: #ffffff;
+
+  --sidebar-surface-primary: #fafafb;
+  --sidebar-surface-secondary: #f1f1f4;
+  --sidebar-surface-tertiary: #ffffff;
+
+  --composer-surface-primary: #ffffff;
+  --composer-surface-secondary: #f4f4f6;
+
+  --bg-code: #f5f5f7;
+
+  --accent-primary: #0f9d70;
+  --accent-fg: #ffffff;
+
+  --border-light: color-mix(in srgb, var(--text-primary) 12%, transparent);
+  --border-medium: color-mix(in srgb, var(--text-primary) 20%, transparent);
+  --border-heavy: color-mix(in srgb, var(--text-primary) 30%, transparent);
+
+  --warn: #a9761a;
+  --shadow: 0 16px 40px rgba(20, 20, 35, .14);
+  --shadow-sm: 0 6px 18px rgba(20, 20, 35, .1);
+}
+
 * { box-sizing: border-box; }
-html, body { margin: 0; height: 100%; }
+html, body { height: 100%; margin: 0; }
 body {
   background: var(--bg); color: var(--fg);
-  font: 14px/1.55 ui-monospace, SFMono-Regular, Menlo, Consolas, "Noto Sans Mono CJK SC", monospace;
+  font: 15px/1.62 var(--sans);
-  display: flex; flex-direction: column; height: 100%;
+  -webkit-font-smoothing: antialiased;
+  -webkit-text-size-adjust: 100%;
+  overflow: hidden; /* columns scroll, never the page */
 }
-button {
+button, textarea, input { font: inherit; color: inherit; }
-  background: var(--bg2); color: var(--fg); border: 1px solid var(--line);
+button { cursor: pointer; background: none; border: 0; }
-  border-radius: 6px; padding: 3px 9px; font: inherit; cursor: pointer;
+button:disabled { cursor: default; }
-}
+.grow { flex: 1 1 auto; }
-button:hover { border-color: var(--accent); }
+.quiet, .muted { color: var(--fg-dim); }
-.grow { flex: 1; }
+.tiny { font-size: 12px; }
-.muted { color: var(--muted); }
+[hidden] { display: none !important; }
+::selection { background: var(--selection-bg); color: var(--selection-fg); }
 
-#bar {
+/* one icon system: everything is drawn on the same 24px grid, stroked with
-  display: flex; align-items: center; gap: 8px; padding: 6px 10px;
+ * the current text colour, so header, rail, popovers and composer match */
-  border-bottom: 1px solid var(--line); background: var(--bg2);
+svg.i {
-  position: sticky; top: 0; z-index: 3; flex-wrap: wrap;
+  width: 18px; height: 18px; flex: 0 0 auto; display: block;
+  fill: none; stroke: currentColor; stroke-width: 1.7;
+  stroke-linecap: round; stroke-linejoin: round;
 }
-.tag { border: 1px solid var(--line); border-radius: 999px; padding: 0 8px; color: var(--muted); }
+svg.i .f { fill: currentColor; stroke: none; }
-.tag.on { color: var(--bg); background: var(--accent); border-color: var(--accent); }
+.icon svg.i { width: 18px; height: 18px; }
-.ws { color: var(--muted); overflow: hidden; text-overflow: ellipsis; max-width: 40vw; white-space: nowrap; }
+.icon.tiny svg.i { width: 15px; height: 15px; }
-.model { color: var(--accent); }
+.chip svg.i { width: 15px; height: 15px; }
+.chip .chev { width: 13px; height: 13px; opacity: .6; }
+.new-task svg.i { width: 17px; height: 17px; }
+.send svg.i { width: 19px; height: 19px; stroke-width: 2; }
+svg.i.only-light { display: none; }
+[data-theme="light"] svg.i.only-dark { display: none; }
+[data-theme="light"] svg.i.only-light { display: block; }
 
-#log { flex: 1; overflow: auto; padding: 12px 14px 20px; }
+/* the changed-file rows in the run panel: path, then +added / -removed */
-#log .msg { margin: 0 0 14px; }
+.fstat { display: flex; align-items: center; gap: 8px; padding: 5px 0; font-size: 13px; animation: fade-in var(--t) var(--ease) both; }
-#log .who { color: var(--muted); font-size: 12px; margin-bottom: 2px; }
+.fstat .fimg { width: 15px; height: 15px; color: var(--text-quaternary); }
-#log .body { white-space: pre-wrap; word-break: break-word; }
+.fstat .p {
-#log .assistant .body > :first-child { margin-top: 0; }
+  flex: 1 1 auto; min-width: 0; overflow: hidden; text-overflow: ellipsis;
-#log .body pre {
+  white-space: nowrap; font-family: var(--mono); font-size: 12px;
-  background: var(--bg2); border: 1px solid var(--line); border-radius: 6px;
-  padding: 8px 10px; overflow: auto;
 }
-#log .body code { background: var(--bg2); border-radius: 4px; padding: 0 3px; }
+.fstat .a, .fstat .d { font-variant-numeric: tabular-nums; font-size: 12px; }
-#log .body pre code { background: none; padding: 0; }
+.fstat .a { color: var(--text-success); }
-#log .body table { border-collapse: collapse; }
+.fstat .d { color: var(--text-error); }
-#log .body th, #log .body td { border: 1px solid var(--line); padding: 2px 6px; }
-#log .body blockquote { border-left: 3px solid var(--line); margin: 0; padding-left: 10px; color: var(--muted); }
-#log .body a { color: var(--accent); }
-#log .body img { max-width: min(420px, 100%); border-radius: 6px; border: 1px solid var(--line); }
 
-details.think { color: var(--muted); margin: 4px 0; }
+::-webkit-scrollbar { width: 10px; height: 10px; }
-details.think summary { cursor: pointer; }
+::-webkit-scrollbar-thumb {
-details.tool {
+  background: var(--line-strong); border-radius: 99px;
-  border: 1px solid var(--line); border-radius: 6px; margin: 6px 0; background: var(--bg2);
+  border: 3px solid transparent; background-clip: content-box;
 }
-details.tool > summary { cursor: pointer; padding: 4px 8px; color: var(--tool); }
+::-webkit-scrollbar-thumb:hover { background: var(--fg-faint); background-clip: content-box; }
-details.tool .args, details.tool pre { margin: 0; padding: 6px 10px; white-space: pre-wrap; }
-details.tool pre { border-top: 1px solid var(--line); max-height: 40vh; overflow: auto; }
-.tool .exit-bad { color: var(--err); }
-.spin::after { content: " …"; color: var(--warn); }
 
-#todo {
+/* --- frame ---------------------------------------------------------------- */
-  border-top: 1px solid var(--line); background: var(--bg2); padding: 6px 12px;
+#app {
-  max-height: 22vh; overflow: auto; white-space: pre-wrap; font-size: 13px;
+  display: grid;
+  grid-template-columns: var(--rail) minmax(0, 1fr) var(--panel);
+  grid-template-rows: minmax(0, 1fr);
+  height: 100dvh;
+  /* the rail keeps its track and collapses to 0px, so the two states have the
+   * same track count and the column width can actually be interpolated */
+  transition: grid-template-columns 300ms var(--ease);
 }
-#todo h4 { margin: 0 0 4px; color: var(--muted); font-size: 12px; font-weight: normal; }
+/* a zeroed track plus display:none used to slide #main into column one and
+ * crush it to nothing; the rail now stays in flow and is clipped instead */
+body.no-side #app { grid-template-columns: 0px minmax(0, 1fr) var(--panel); }
+body.no-panel #app { grid-template-columns: var(--rail) minmax(0, 1fr) 0px; }
+body.no-side.no-panel #app { grid-template-columns: 0px minmax(0, 1fr) 0px; }
+/* the expand control only exists while the rail is folded away, so exactly one
+ * toggle is ever on screen */
+#btn-side { display: none; }
+body.no-side #btn-side { display: inline-flex; }
 
-#composer { border-top: 1px solid var(--line); background: var(--bg2); padding: 8px 10px; }
+.icon {
-#composer .row { display: flex; gap: 8px; align-items: flex-end; }
+  width: 32px; height: 32px; border-radius: 9px; flex: 0 0 auto;
-#input {
+  display: inline-flex; align-items: center; justify-content: center;
-  flex: 1; resize: vertical; min-height: 34px; max-height: 40vh;
+  color: var(--fg-dim); font-size: 15px;
-  background: var(--bg); color: var(--fg); border: 1px solid var(--line);
+  transition: background var(--t-fast), color var(--t-fast), transform 90ms var(--ease);
-  border-radius: 6px; padding: 7px 9px; font: inherit;
 }
-.att {
+.icon:hover { background: var(--bg-hover); color: var(--fg); }
-  border: 1px solid var(--line); border-radius: 6px; padding: 5px 9px; cursor: pointer;
+.icon:active { transform: scale(.94); }
+.icon.tiny { width: 26px; height: 26px; font-size: 13px; }
+.round { border-radius: 50%; }
+.chip {
+  display: inline-flex; align-items: center; gap: 5px; height: 30px;
+  padding: 0 11px; border-radius: 99px; border: 1px solid transparent;
+  background: none; color: var(--fg-dim); font-size: 13px;
+  max-width: 280px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
+  transition: background var(--t-fast), color var(--t-fast), border-color var(--t-fast), transform 90ms var(--ease);
+}
+.chip:hover { background: var(--bg-hover); color: var(--fg); }
+.chip:active { transform: scale(.97); }
+.chip.model { color: var(--fg); font-weight: 600; background: var(--bg-lift); border-color: var(--line); }
+.chip.model:hover { border-color: var(--line-strong); }
+.chip.warn { color: var(--warn); }
+.chip .chev { font-size: 11px; opacity: .65; }
+.badge {
+  min-width: 18px; height: 18px; padding: 0 5px; border-radius: 99px;
+  background: var(--accent-weak); color: var(--accent);
+  font-size: 11px; font-weight: 700;
+  display: inline-flex; align-items: center; justify-content: center;
 }
-.hint { display: flex; gap: 10px; font-size: 12px; color: var(--muted); padding-top: 4px; }
-#pending { color: var(--warn); font-size: 12px; padding-bottom: 4px; }
 
+/* --- rail ----------------------------------------------------------------- */
+#side {
+  background: var(--sidebar-surface-primary); border-right: 1px solid var(--border-light);
+  min-width: 0; overflow: hidden;      /* clips the rail while its track collapses */
+}
+/* the contents keep their own width and slide out, so nothing reflows mid-flight
+ * and the exit reads as one movement instead of a squeeze */
+.side-inner {
+  width: var(--rail); height: 100%; min-width: 0;
+  display: flex; flex-direction: column; padding: 12px 10px 10px;
+  transition: transform 300ms var(--ease-pop), opacity 200ms var(--ease);
+}
+body.no-side .side-inner { transform: translateX(-18px); opacity: 0; }
+body.no-side #side { pointer-events: none; }
+.side-head { display: flex; align-items: center; gap: 2px; margin-bottom: 14px; }
+/* the wordmark is a label, not a control: no logo tile, nothing to click */
+.brand { flex: 1 1 auto; display: flex; align-items: center; min-width: 0; padding: 6px 8px; }
+.brand-name {
+  font-weight: 700; letter-spacing: .2px; font-size: 15px;
+  overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
+}
+
+.new-task {
+  display: flex; align-items: center; gap: 9px; height: 40px; padding: 0 12px;
+  margin-bottom: 18px; border-radius: 12px; font-weight: 600;
+  background: var(--bg-lift); border: 1px solid var(--line);
+  transition: border-color var(--t-fast), background var(--t-fast), transform 90ms var(--ease);
+}
+.new-task:hover { border-color: var(--line-strong); background: var(--bg-hover); }
+.new-task:active { transform: scale(.985); }
+.new-task .plus { color: var(--accent); font-size: 16px; line-height: 1; }
+
+.side-sec {
+  display: flex; align-items: center; gap: 6px; padding: 0 8px 6px;
+  color: var(--fg-faint); font-size: 11px; font-weight: 600;
+  letter-spacing: .7px; text-transform: uppercase;
+}
+.sessions { flex: 1 1 auto; overflow-y: auto; min-height: 40px; scrollbar-gutter: stable; }
+.sess-item {
+  display: flex; align-items: baseline; gap: 8px; width: 100%;
+  padding: 7px 9px; border-radius: 9px; text-align: left;
+  color: var(--text-secondary); font-size: 13.5px;
+  animation: fade-in var(--t) var(--ease) both;
+  transition: background var(--t-fast), color var(--t-fast);
+}
+.sess-item:hover { background: var(--hover); color: var(--text-primary); }
+.sess-item.on { background: var(--sidebar-surface-tertiary); color: var(--text-primary); font-weight: 600; }
+.sess-item.on::before {
+  content: ""; width: 5px; height: 5px; border-radius: 50%;
+  background: var(--accent); flex: 0 0 auto; align-self: center;
+}
+.sess-item .t { flex: 1 1 auto; min-width: 0; overflow: hidden; }
+.sess-item .ts { display: block; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
+/* a title that does not fit fades at the edge and scrolls itself on hover, the
+ * way the reference sidebar handles long names (its data-marquee-text pattern) */
+.sess-item .t.mq { mask-image: linear-gradient(90deg, #000 calc(100% - 18px), transparent); }
+.sess-item:hover .t.mq { mask-image: none; }
+.sess-item:hover .t.mq .ts {
+  width: max-content; text-overflow: clip;
+  animation: marquee 2.6s var(--ease) 160ms infinite alternate;
+}
+@keyframes marquee { from { transform: none; } to { transform: translateX(calc(-1 * var(--mq, 0px))); } }
+.sess-item .n { font-size: 11px; color: var(--text-quaternary); font-weight: 400; white-space: nowrap; }
+.side-foot {
+  display: flex; align-items: center; gap: 6px; padding-top: 10px;
+  margin-top: 6px; border-top: 1px solid var(--line);
+}
+.who { display: flex; align-items: center; gap: 9px; min-width: 0; flex: 1 1 auto; }
+.avatar {
+  width: 28px; height: 28px; border-radius: 50%; flex: 0 0 auto;
+  background: linear-gradient(135deg, var(--violet), var(--accent));
+  color: #fff; font-weight: 800; font-size: 13px;
+  display: flex; align-items: center; justify-content: center;
+}
+.who-text { min-width: 0; display: flex; flex-direction: column; line-height: 1.3; }
+.who-text b { font-size: 12.5px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
+.who-text i { font-size: 11px; color: var(--fg-faint); font-style: normal; }
+
+/* --- top bar -------------------------------------------------------------- */
+#main { display: flex; flex-direction: column; min-width: 0; position: relative; }
+#topbar { display: flex; align-items: center; gap: 4px; padding: 9px 12px; border-bottom: 1px solid var(--line); }
+.seg {
+  display: flex; background: var(--bg-soft); border: 1px solid var(--line);
+  border-radius: 99px; padding: 2px; position: relative;
+}
+.seg button {
+  height: 25px; padding: 0 12px; border-radius: 99px; color: var(--fg-dim); font-size: 12.5px;
+  transition: color var(--t-fast), background var(--t);
+}
+.seg button.on { background: var(--bg-lift); color: var(--fg); font-weight: 600; }
+.only-narrow { display: none; }
+
+#scroll {
+  flex: 1 1 auto; overflow-y: auto; padding: 22px 0 10px;
+  scroll-behavior: smooth; scrollbar-gutter: stable;
+}
+#log { max-width: 760px; margin: 0 auto; padding: 0 20px; }
+#log:empty { display: none; }
+
+/* --- empty state ---------------------------------------------------------- */
+/* the first screen is one line: no logo, no suggestion wall. It goes away the
+ * moment the first message lands (see showEmpty). */
+#empty { margin: 22vh auto 0; padding: 0 20px; text-align: center; }
+#empty.gone { display: none; }
+#empty .ready {
+  margin: 0; color: var(--text-tertiary); font-size: 15px; letter-spacing: .3px;
+  animation: fade-in 320ms var(--ease) both;
+}
+
+/* --- transcript ----------------------------------------------------------- */
+.msg { display: flex; gap: 12px; padding: 13px 0 0; animation: fade-up var(--t) var(--ease) both; }
+.msg .gutter { flex: 0 0 24px; padding-top: 2px; color: var(--fg-faint); font-size: 11px; text-align: center; user-select: none; }
+.msg .body { min-width: 0; flex: 1 1 auto; }
+.msg.user { justify-content: flex-end; }
+.msg.user .gutter { display: none; }
+.msg.user .body {
+  background: var(--bg-lift); border-radius: 18px 18px 6px 18px;
+  padding: 9px 15px; max-width: 76%; white-space: pre-wrap; word-break: break-word;
+}
+.msg.error .body { color: var(--danger); }
+.body > :first-child, .live-html > :first-child { margin-top: 0; }
+.body > :last-child, .live-html > :last-child { margin-bottom: 0; }
+.body h1, .body h2, .body h3, .body h4 { line-height: 1.35; margin: 1.1em 0 .5em; }
+.body h1 { font-size: 1.45em; } .body h2 { font-size: 1.25em; } .body h3 { font-size: 1.1em; }
+.body p, .body ul, .body ol { margin: .55em 0; }
+.body ul, .body ol { padding-left: 1.4em; }
+.body li { margin: .22em 0; }
+.body a { color: var(--link); }
+.body code {
+  font-family: var(--mono); font-size: .88em; background: var(--bg-code);
+  border: 1px solid var(--line); border-radius: 6px; padding: .1em .35em;
+}
+.body pre {
+  background: var(--bg-code); border: 1px solid var(--line);
+  border-radius: 12px; padding: 12px 14px; overflow-x: auto; margin: .75em 0;
+}
+.body pre code { background: none; border: 0; padding: 0; font-size: 13px; }
+.body blockquote { margin: .75em 0; padding: .1em 0 .1em 12px; border-left: 3px solid var(--line-strong); color: var(--fg-dim); }
+.body table { border-collapse: collapse; margin: .75em 0; font-size: 13.5px; display: block; overflow-x: auto; }
+.body th, .body td { border: 1px solid var(--line); padding: 5px 9px; text-align: left; }
+.body th { background: var(--bg-soft); }
+.body img { max-width: 100%; border-radius: 10px; }
+.body hr { border: 0; border-top: 1px solid var(--line); margin: 1.2em 0; }
+/* a caret while tokens are still arriving */
+.body.live > .live-html > :last-child::after {
+  content: ""; display: inline-block; width: 7px; height: 14px;
+  margin-left: 3px; vertical-align: -2px; border-radius: 2px;
+  background: var(--accent); animation: blink 1.1s steps(2, start) infinite;
+}
+
+.attach-strip { display: flex; flex-wrap: wrap; gap: 8px; margin: 2px 0 8px; justify-content: flex-end; }
+.attach-strip img {
+  width: 108px; height: 108px; object-fit: cover; border-radius: 12px;
+  border: 1px solid var(--line); animation: rise var(--t) var(--ease) both;
+}
+
+.turn-meta { display: flex; align-items: center; gap: 10px; padding: 10px 0 2px 36px; }
+.turn-meta details > summary { cursor: pointer; list-style: none; color: var(--fg-faint); font-size: 12px; transition: color var(--t-fast); }
+.turn-meta details > summary::-webkit-details-marker { display: none; }
+.turn-meta details > summary:hover { color: var(--fg-dim); }
+.msg-actions { display: flex; gap: 2px; padding: 4px 0 0 36px; opacity: 0; transition: opacity var(--t) var(--ease); }
+.msg:hover .msg-actions, .msg-actions:focus-within { opacity: 1; }
+.msg-actions button {
+  height: 26px; padding: 0 9px; border-radius: 8px; color: var(--fg-faint); font-size: 12px;
+  transition: background var(--t-fast), color var(--t-fast);
+}
+.msg-actions button:hover { background: var(--bg-hover); color: var(--fg); }
+
+.think { margin: .1em 0 .5em; }
+.think summary { cursor: pointer; list-style: none; color: var(--fg-faint); font-size: 12.5px; transition: color var(--t-fast); }
+.think summary::-webkit-details-marker { display: none; }
+.think summary::before { content: "▸ "; }
+.think[open] summary::before { content: "▾ "; }
+.think summary:hover { color: var(--fg-dim); }
+.think > div {
+  color: var(--fg-dim); font-size: 13.5px; white-space: pre-wrap;
+  padding: 6px 0 2px 14px; border-left: 2px solid var(--line);
+  animation: fade-in var(--t) var(--ease) both;
+}
+
+/* tool calls: one line, opens on demand (like "已执行 python · <<PY>") */
+.turn-steps { padding: 6px 0 0 36px; }
+.turn-steps > summary { cursor: pointer; list-style: none; color: var(--fg-faint); font-size: 12.5px; transition: color var(--t-fast); }
+.turn-steps > summary::-webkit-details-marker { display: none; }
+.turn-steps > summary::before { content: "⌘ "; }
+.turn-steps > summary:hover { color: var(--fg-dim); }
+.steps-box { padding: 2px 0 0 12px; margin-top: 4px; border-left: 2px solid var(--line); }
+.step-line { animation: fade-up var(--t) var(--ease) both; }
+.step-line > summary {
+  display: flex; align-items: baseline; gap: 8px; cursor: pointer; list-style: none;
+  padding: 5px 0; font-size: 13px; color: var(--fg-dim);
+  transition: color var(--t-fast);
+}
+.step-line > summary::-webkit-details-marker { display: none; }
+.step-line > summary:hover { color: var(--fg); }
+.step-line .name { font-family: var(--mono); font-size: 12.5px; color: var(--fg); }
+.step-line .args { flex: 1 1 auto; min-width: 0; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; font-family: var(--mono); font-size: 12px; }
+.step-line .phase { font-size: 11.5px; color: var(--fg-faint); white-space: nowrap; display: inline-flex; align-items: center; gap: 6px; }
+.step-line.run .phase { color: var(--warn); }
+.step-line.run .phase::before {
+  content: ""; width: 6px; height: 6px; border-radius: 50%;
+  background: var(--warn); animation: pulse 1.1s var(--ease) infinite;
+}
+.step-line.bad .phase, .step-line.bad .name { color: var(--danger); }
+.step-line.done .phase::before { content: "✓"; }
+.step-body { padding: 0 0 6px; animation: fade-in var(--t) var(--ease) both; }
+.step-out, .step-args-full {
+  font-family: var(--mono); font-size: 12px; background: var(--bg-code);
+  border: 1px solid var(--line); border-radius: 10px; padding: 9px 11px;
+  margin: 4px 0 0; max-height: 300px; overflow: auto; white-space: pre-wrap; word-break: break-word;
+}
+
+#to-bottom {
+  position: absolute; right: 26px; bottom: 172px; z-index: 5;
+  width: 38px; height: 38px; display: flex; align-items: center; justify-content: center;
+  background: var(--bg-lift); border: 1px solid var(--line-strong); color: var(--fg-dim);
+  box-shadow: var(--shadow-sm); font-size: 16px;
+  animation: fade-in var(--t) var(--ease) both;
+  transition: color var(--t-fast), transform 90ms var(--ease), background var(--t-fast);
+}
+#to-bottom:hover { color: var(--fg); background: var(--bg-hover); }
+#to-bottom:active { transform: scale(.94); }
+
+/* --- composer ------------------------------------------------------------- */
+#composer { padding: 8px 20px 12px; }
+#composer > * { max-width: 760px; margin: 0 auto; }
+.pending { display: flex; flex-wrap: wrap; gap: 8px; padding: 0 0 8px; }
+.pending .chip { background: var(--bg-soft); border-color: var(--line); }
+
+.box {
+  border: 1px solid var(--border-medium); border-radius: var(--radius-lg);
+  background: var(--composer-surface-primary); padding: 11px 13px 9px;
+  transition: border-color var(--t), box-shadow var(--t), background var(--t);
+}
+.box:hover { border-color: var(--border-heavy); }
+.box:focus-within {
+  border-color: var(--accent-line);
+  box-shadow: 0 0 0 3px var(--accent-weak);
+}
+.box textarea {
+  width: 100%; border: 0; background: none; resize: none; outline: none;
+  max-height: 240px; min-height: 26px; padding: 2px 2px 8px;
+  caret-color: var(--accent);
+}
+.box textarea::placeholder { color: var(--fg-faint); }
+.box-row { display: flex; align-items: center; gap: 6px; }
+.att { border: 1px solid var(--line); font-size: 17px; line-height: 1; }
+.cost { color: var(--fg-faint); font-size: 12px; padding: 0 4px; white-space: nowrap; }
+.cost:hover { color: var(--fg-dim); }
+.send {
+  width: 36px; height: 36px; flex: 0 0 auto; font-size: 17px; font-weight: 800;
+  background: var(--accent); color: var(--accent-fg);
+  transition: filter var(--t-fast), transform 90ms var(--ease), opacity var(--t-fast);
+}
+.send:hover { filter: brightness(1.08); }
+.send:active { transform: scale(.94); }
+.send:disabled { opacity: .38; }
+.icon.stop { border: 1px solid var(--line); font-size: 12px; }
+.hint-line { display: flex; align-items: center; gap: 10px; padding: 7px 6px 0; font-size: 12px; color: var(--fg-faint); }
+
+/* permission gate: inline, the turn really is waiting on it */
+.gate {
+  border: 1px solid color-mix(in srgb, var(--warn) 45%, transparent);
+  border-radius: var(--radius); padding: 11px 13px; margin-bottom: 10px;
+  background: color-mix(in srgb, var(--warn) 7%, var(--bg-soft));
+  animation: rise var(--t) var(--ease) both;
+}
+.gate-head { display: flex; align-items: center; gap: 8px; font-weight: 650; font-size: 14px; }
+.gate-timer { color: var(--warn); font-size: 12.5px; font-variant-numeric: tabular-nums; }
+.gate pre {
+  margin: 8px 0 0; background: var(--bg-code); border: 1px solid var(--line);
+  border-radius: 10px; padding: 9px 11px; max-height: 180px; overflow: auto;
+  font-family: var(--mono); font-size: 12.5px; white-space: pre-wrap; word-break: break-word;
+}
+.gate-keys { padding: 8px 0 2px; color: var(--fg-dim); font-size: 12.5px; }
+.gate-row { display: flex; flex-wrap: wrap; gap: 8px; margin-top: 6px; }
+.gate-row button {
+  height: 34px; padding: 0 14px; border-radius: 10px; font-weight: 600;
+  border: 1px solid var(--line-strong); background: var(--bg-lift);
+  transition: filter var(--t-fast), transform 90ms var(--ease), background var(--t-fast);
+}
+.gate-row button.ok { background: var(--accent); color: var(--accent-fg); border-color: transparent; }
+.gate-row button.danger { color: var(--danger); }
+.gate-row button:hover { filter: brightness(1.12); }
+.gate-row button:active { transform: scale(.97); }
+
+/* --- popovers: anchored, animated, and the only place settings live ------- */
+.pop {
+  position: fixed; z-index: 45; min-width: 236px; max-width: 320px;
+  background: var(--main-surface-tertiary); border: 1px solid var(--border-medium);
+  border-radius: 14px; padding: 6px; box-shadow: var(--shadow);
+  animation: pop-in 160ms var(--ease) both;
+}
+.pop-item {
+  display: flex; align-items: flex-start; gap: 10px; width: 100%;
+  padding: 9px 10px; border-radius: 10px; text-align: left;
+  transition: background var(--t-fast);
+}
+.pop-item:hover { background: var(--bg-hover); }
+.pop-item .pi { width: 18px; flex: 0 0 auto; text-align: center; color: var(--fg-dim); font-size: 14px; line-height: 1.4; }
+/* title over description: two lines, never one run-on line */
+.pop-item .pm { min-width: 0; flex: 1 1 auto; display: flex; flex-direction: column; gap: 2px; }
+.pop-item .pt { font-size: 13.5px; font-weight: 600; line-height: 1.35; }
+.pop-item .pd { font-size: 11.5px; color: var(--fg-faint); line-height: 1.4; }
+.pop-item .pk { flex: 0 0 auto; color: var(--accent); font-size: 13px; }
+.pop-item.on { background: var(--accent-weak); }
+.pop-item.on .pi, .pop-item.on .pt { color: var(--accent); }
+.pop-item.danger .pi, .pop-item.danger .pt { color: var(--danger); }
+.pop-sep { height: 1px; background: var(--line); margin: 5px 4px; }
+.pop-title { padding: 8px 10px 4px; color: var(--fg-faint); font-size: 11.5px; font-weight: 600; letter-spacing: .4px; }
+.pop-input { display: flex; gap: 6px; padding: 4px 6px 6px; }
+.pop-input input {
+  flex: 1 1 auto; min-width: 0; background: var(--bg-soft); border: 1px solid var(--line);
+  border-radius: 9px; padding: 7px 9px; outline: none; font-size: 13px;
+  caret-color: var(--accent);
+  transition: border-color var(--t-fast);
+}
+.pop-input input:focus { border-color: var(--accent-line); }
+.pop-input button {
+  height: 32px; padding: 0 12px; border-radius: 9px; font-weight: 600; font-size: 13px;
+  background: var(--accent); color: var(--accent-fg);
+  transition: filter var(--t-fast), transform 90ms var(--ease);
+}
+.pop-input button:active { transform: scale(.96); }
+.kv { display: flex; align-items: center; justify-content: space-between; gap: 10px; padding: 5px 10px; font-size: 13px; }
+.kv span { color: var(--fg-dim); }
+.kv b { font-variant-numeric: tabular-nums; font-weight: 600; }
+
+/* --- right panel ---------------------------------------------------------- */
+/* the right panel mirrors the rail: fixed-width contents, clipped by the track,
+ * so folding it in and out is one eased movement on each side */
+#panel { background: var(--main-surface-secondary); border-left: 1px solid var(--border-light); min-width: 0; overflow: hidden; }
+.panel-inner {
+  width: var(--panel); height: 100%; overflow-y: auto; padding: 12px;
+  transition: transform 300ms var(--ease-pop), opacity 200ms var(--ease);
+}
+body.no-panel .panel-inner { transform: translateX(18px); opacity: 0; }
+body.no-panel #panel { pointer-events: none; }
+.panel-head {
+  display: flex; align-items: center; gap: 6px; padding: 2px 4px 10px;
+  color: var(--fg-faint); font-size: 11px; font-weight: 600;
+  letter-spacing: .7px; text-transform: uppercase;
+}
+.card { border-top: 1px solid var(--line); padding: 12px 2px; }
+.card:first-of-type { border-top: 0; }
+.card h4 { margin: 0 0 8px; font-size: 12.5px; font-weight: 650; display: flex; align-items: center; gap: 6px; }
+.card .kv { padding: 3px 0; }
+.todo-list { margin: 0; padding: 0; list-style: none; font-size: 13.5px; }
+.todo-list li { display: flex; gap: 8px; padding: 3px 0; animation: fade-in var(--t) var(--ease) both; transition: color var(--t-fast); }
+.todo-list .boxmark { color: var(--fg-faint); }
+.todo-list li.done { color: var(--fg-faint); text-decoration: line-through; }
+.todo-list li.doing { color: var(--fg); font-weight: 600; }
+#steps-body .step-line > summary { font-size: 12.5px; }
+#steps-body .step-line .phase { font-size: 11px; }
+
+/* --- modal sheet (session list) ------------------------------------------- */
 #modal {
-  position: fixed; inset: 0; background: rgba(0, 0, 0, .55);
+  position: fixed; inset: 0; background: rgba(0, 0, 0, .5); z-index: 40;
-  display: flex; align-items: center; justify-content: center; z-index: 9;
+  display: flex; align-items: center; justify-content: center; padding: 16px;
+  animation: fade-in var(--t) var(--ease) both;
 }
 #modal-box {
-  background: var(--bg2); border: 1px solid var(--line); border-radius: 10px;
+  width: min(560px, 100%); max-height: 82vh; overflow-y: auto;
-  padding: 14px; width: min(820px, 94vw); max-height: 88vh; overflow: auto;
+  background: var(--main-surface-tertiary); border: 1px solid var(--border-medium);
+  border-radius: 18px; padding: 16px 18px; box-shadow: var(--shadow);
+  animation: pop-in 180ms var(--ease) both;
 }
-#modal-box h3 { margin: 0 0 8px; }
+#modal-box h3 { margin: 0 0 12px; font-size: 17px; }
-#modal-box pre {
+#modal-box .field { display: flex; align-items: center; gap: 8px; margin: 9px 0; flex-wrap: wrap; }
-  background: var(--bg); border: 1px solid var(--line); border-radius: 6px;
+#modal-box .field > span { width: 70px; color: var(--fg-dim); font-size: 13px; }
-  padding: 8px; max-height: 46vh; overflow: auto; white-space: pre-wrap;
+#modal-box .field input {
+  flex: 1 1 auto; min-width: 150px; background: var(--bg-lift);
+  border: 1px solid var(--line); border-radius: 10px; padding: 8px 10px; outline: none;
+}
+#modal-box .buttons { display: flex; flex-wrap: wrap; gap: 8px; align-items: center; margin-top: 12px; }
+#modal-box .buttons button {
+  height: 34px; padding: 0 14px; border-radius: 10px; font-weight: 600;
+  border: 1px solid var(--line-strong); background: var(--bg-lift);
+  transition: filter var(--t-fast), transform 90ms var(--ease);
+}
+#modal-box .buttons button:active { transform: scale(.97); }
+#modal-box .buttons button.ok { background: var(--accent); color: var(--accent-fg); border-color: transparent; }
+#modal-box .buttons button.danger { color: var(--danger); }
+#modal-box .sess {
+  display: flex; align-items: center; gap: 8px; padding: 8px 6px;
+  border-bottom: 1px solid var(--line); border-radius: 8px;
+  transition: background var(--t-fast);
+}
+#modal-box .sess:hover { background: var(--bg-hover); }
+#modal-box .sess .id { font-family: var(--mono); font-size: 11.5px; color: var(--fg-faint); }
+#modal-box .sess .t { flex: 1 1 auto; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; font-size: 13.5px; }
+
+/* --- narrow screens: rail and panel become drawers ------------------------ */
+#backdrop { position: fixed; inset: 0; background: rgba(0, 0, 0, .45); z-index: 30; display: none; animation: fade-in var(--t) var(--ease) both; }
+body.drawer-open #backdrop { display: block; }
+@media (max-width: 900px) {
+  #app { grid-template-columns: minmax(0, 1fr) !important; transition: none; }
+  #side, #panel {
+    position: fixed; top: 0; bottom: 0; width: min(310px, 86vw); z-index: 31;
+    display: block; transition: transform 260ms var(--ease-pop);
+  }
+  .side-inner { width: auto; transform: none !important; opacity: 1 !important; }
+  #side { overflow: visible; pointer-events: auto; }
+  #side { left: 0; transform: translateX(-102%); }
+  #panel { right: 0; transform: translateX(102%); }
+  body.side-open #side, body.panel-open #panel { transform: none; }
+  .only-narrow { display: inline-flex; }
+  #to-bottom { bottom: 150px; right: 16px; }
+  .hero h1 { font-size: 21px; }
+  .msg.user .body { max-width: 88%; }
+  .turn-meta, .msg-actions, .turn-steps { padding-left: 0; }
+}
+@media (min-width: 901px) { #backdrop { display: none !important; } }
+
+/* --- motion --------------------------------------------------------------- */
+@keyframes fade-in { from { opacity: 0; } to { opacity: 1; } }
+@keyframes fade-up { from { opacity: 0; transform: translateY(6px); } to { opacity: 1; transform: none; } }
+@keyframes rise { from { opacity: 0; transform: translateY(10px) scale(.99); } to { opacity: 1; transform: none; } }
+@keyframes pop-in { from { opacity: 0; transform: translateY(-4px) scale(.97); } to { opacity: 1; transform: none; } }
+@keyframes pulse { 0%, 100% { opacity: .3; transform: scale(.85); } 50% { opacity: 1; transform: scale(1); } }
+@keyframes blink { 0%, 100% { opacity: 1; } 50% { opacity: 0; } }
+@media (prefers-reduced-motion: reduce) {
+  *, *::before, *::after { animation-duration: 1ms !important; transition-duration: 1ms !important; }
+  #scroll { scroll-behavior: auto; }
 }
-#modal-box .buttons { display: flex; gap: 8px; flex-wrap: wrap; margin-top: 10px; }
-#modal-box .danger { border-color: var(--err); color: var(--err); }
-#modal-box .ok { border-color: var(--ok); color: var(--ok); }
-.sess { display: flex; gap: 8px; align-items: center; padding: 4px 0; border-bottom: 1px solid var(--line); }
-.sess .id { color: var(--muted); font-size: 12px; }
-.sess .t { flex: 1; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }