feat(hub): session transcript 连续性 + slash commands (/new /resume /reset)

修复每次 @bot 都是失忆状态的问题。
- transcript.ts: JSONL 文件存 session 对话消息(workspace/.cph/sessions/
  <id>.jsonl),append-only;和 Claude Code 一致;ADR-0003 说的'不存全
  历史'是群聊历史,session 对话是 Hub 自己产生的,不冲突
- runner.ts: RunRequest 加 transcriptPath;run 开始时读历史拼进初始
  messages(system prompt 只在首条);run 结束时 append 本轮新消息
  (loadedCount 区分历史 vs 新增,不重复写);best-effort(写失败不丢
  run 结果)
- trigger.ts: slash commands 在 lock 检查之前(/new /resume /reset
  不创建 run 不需要锁);transcriptPath 传给 runner
  /new = 归档当前 session,下次 @bot 自动建新的
  /resume = 恢复最近归档的 session
  /reset = 同 /new
  未知 /cmd 透传给 agent 当普通 prompt
- unit: transcript.test.ts 读写回环/append 累积/损坏行恢复/路径(6)
- integration: trigger.test.ts 加 /new /resume /reset /unknown(4)
修了 slash command 被 lock 挡住的问题(提到 lock 之前)。
vitest run 45/45 通过;tsc rc=0。

hub/src/agent/runner.ts

@@ -11,6 +11,7 @@
  */
 import type { AgentProvider, ChatResponse, Message, ToolCallPart } from "./provider.js";
 import type { ToolContext, ToolRegistry } from "./tools.js";
+import { readTranscript, appendTranscript } from "./transcript.js";
 
 /** What the runner needs about the project to seed and bound a run. */
 export interface ProjectContext {
@@ -29,6 +30,9 @@ export interface RunRequest {
   readonly systemPrompt?: string;
   /** Iteration cap before the run is returned as `length`. Default 25. */
   readonly maxIterations?: number;
+  /** Path to the session transcript JSONL. If set, prior messages are loaded
+   *  from it before the run, and new messages are appended after. */
+  readonly transcriptPath?: string;
 }
 
 export type RunStatus = "completed" | "length" | "failed";
@@ -59,9 +63,18 @@ export async function runAgent(
     boundChatId: req.project.boundChatId,
     workspaceDir: req.project.workspaceDir,
   };
-
   const messages: Message[] = [];
-  if (req.systemPrompt !== undefined) {
+  // Load prior session messages from transcript (continuity across @bot calls
+  // in the same session). ADR-0003: session messages ≠ group chat history.
+  let loadedCount = 0;
+  if (req.transcriptPath !== undefined) {
+    const prior = await readTranscript(req.transcriptPath);
+    loadedCount = prior.length;
+    messages.push(...prior);
+  }
+  if (req.systemPrompt !== undefined && messages.length === 0) {
+    // System prompt only at the very start of a session; on resume it's
+    // already in the transcript.
     messages.push({ role: "system", parts: [{ type: "text", text: req.systemPrompt }] });
   }
   messages.push({ role: "user", parts: [{ type: "text", text: req.prompt }] });
@@ -79,12 +92,14 @@ export async function runAgent(
         tools: tools.specs(),
       });
     } catch (e) {
-      return {
+      const result: RunResult = {
         status: "failed",
         messages,
         usage: { inputTokens, outputTokens },
         error: e instanceof Error ? e.message : String(e),
       };
+      await appendTranscriptIfSet(req, messages, loadedCount);
+      return result;
     }
 
     messages.push(res.message);
@@ -94,9 +109,11 @@ export async function runAgent(
     }
 
     if (res.finishReason === "stop") {
+      await appendTranscriptIfSet(req, messages, loadedCount);
       return { status: "completed", messages, usage: { inputTokens, outputTokens } };
     }
     if (res.finishReason !== "tool_calls") {
+      await appendTranscriptIfSet(req, messages, loadedCount);
       return { status: "length", messages, usage: { inputTokens, outputTokens } };
     }
 
@@ -111,6 +128,7 @@ export async function runAgent(
     }
   }
 
+  await appendTranscriptIfSet(req, messages, loadedCount);
   return {
     status: "length",
     messages,
@@ -119,6 +137,21 @@ export async function runAgent(
   };
 }
 
+/// Append only the messages produced this run (skip the `loadedCount` prior
+/// ones already in the file). Errors are swallowed — a transcript write
+/// failure must not lose the run result.
+async function appendTranscriptIfSet(req: RunRequest, messages: readonly Message[], loadedCount: number): Promise<void> {
+  if (req.transcriptPath === undefined) return;
+  const newMessages = messages.slice(loadedCount);
+  if (newMessages.length === 0) return;
+  try {
+    await appendTranscript(req.transcriptPath, newMessages);
+  } catch {
+    // Swallow — transcript is best-effort persistence; the run result is
+    // returned regardless. ADR-0002 lock ensures no concurrent writer.
+  }
+}
+
 function toolCallsOfAssistant(msg: Message): readonly ToolCallPart[] {
   if (msg.role !== "assistant") return [];
   return msg.parts.filter((p): p is ToolCallPart => p.type === "tool_call");