openclaw-lark-multi-agent 1.4.2 → 1.4.4

package/README.md

@@ -10,7 +10,7 @@ This project is a bridge layer for OpenClaw. It does **not** implement an agent
 
 Lark/Feishu gives each bot its own app identity, but OpenClaw normally exposes one assistant identity per channel account. This bridge lets you create several Lark bots such as:
 
-- `GPT Bot` → `github-copilot/gpt-5.5`
+- `GPT Bot` → `phgeek-gw/gpt-5.6-sol`
 - `Gemini Bot` → `github-copilot/gemini-3.1-pro-preview`
 - `Claude Bot` → `github-copilot/claude-opus-4.7`
 
@@ -37,7 +37,7 @@ All of them connect to the same OpenClaw Gateway while keeping sessions, queues,
 - Feishu image download and OpenClaw multimodal attachment forwarding
 - Bridge attachment marker protocol for generated files/images/documents
 - Feishu CardKit v2 Markdown rendering, including native table elements for pipe tables
-- Live status card: in non-verbose mode each run shows a single self-updating Feishu interactive card (title + recent activity window with per-line timestamps + elapsed/model footer, refreshed once per second), which collapses to a compact one-line summary on a clean finish and retains the recent activity on failure for debugging
+- Live status card: in non-verbose mode each run shows a self-updating Feishu interactive card (title + recent activity window with per-line timestamps + elapsed footer, refreshed once per second), which collapses to tool-call count + elapsed on a clean finish; the final answer is sent separately at the bottom with a model footer
 - Bridge-level slash commands and escaped OpenClaw slash commands
 - `/discuss` mode for barrier-style multi-bot group discussion, including per-round markers and no-reply status notices
 - `/chairman` role: a single per-group chairman that answers plain messages when no bot is in Free mode, and acts as host, challenger, and summarizer inside `/discuss`
@@ -149,7 +149,7 @@ Edit `config.json`:
       "name": "GPT",
       "appId": "cli_xxx",
       "appSecret": "YOUR_LARK_APP_SECRET",
-      "model": "github-copilot/gpt-5.5"
+      "model": "phgeek-gw/gpt-5.6-sol"
     },
     {
       "name": "Gemini",
@@ -463,7 +463,7 @@ While running, the card shows:
 - a rolling window of the most recent activity lines (tool start `▸`, tool end
   `✓`, and intermediate assistant text `•`), each prefixed with the relative
   time `mm:ss` since the run started;
-- a footer with elapsed time and the bound model name.
+- a footer with elapsed time.
 
 The card is created lazily (a fast reply that finishes within the create delay
 never spawns a card, to avoid flicker) and is updated with `im.message.patch`,
@@ -479,8 +479,9 @@ When the run ends:
   header, so the steps leading up to the failure stay visible for debugging.
 
 The final answer is always delivered separately through the normal interactive-card
-delivery path, so Markdown renders correctly; the live status card is a distinct
-message and never replaces or blocks the final reply.
+delivery path, so it is created at completion time and remains below any user messages
+inserted during the run. Its footer shows only the bound model name. The live-status
+card remains a distinct earlier message and owns tool-call count + elapsed time.
 
 Live status is on by default and can be toggled per bot/chat with
 `/livestatus [on|off]`. It can be disabled globally by setting

package/README.zh-CN.md

@@ -10,7 +10,7 @@
 
 Lark/飞书里每个机器人都有自己的 App 身份，但 OpenClaw 通常在一个 channel account 下暴露一个助手身份。这个桥接层可以让你创建多个飞书机器人，例如：
 
-- `GPT Bot` → `github-copilot/gpt-5.5`
+- `GPT Bot` → `phgeek-gw/gpt-5.6-sol`
 - `Gemini Bot` → `github-copilot/gemini-3.1-pro-preview`
 - `Claude Bot` → `github-copilot/claude-opus-4.7`
 
@@ -127,7 +127,7 @@ cp config.example.json config.json
       "name": "GPT",
       "appId": "cli_xxx",
       "appSecret": "YOUR_LARK_APP_SECRET",
-      "model": "github-copilot/gpt-5.5"
+      "model": "phgeek-gw/gpt-5.6-sol"
     },
     {
       "name": "Gemini",
@@ -408,6 +408,12 @@ v1 行为边界：如果消息已经进入 OpenClaw 正在处理，暂不 abort
 
 如果 Agent 需要发送生成的文件、图片或文档，应使用 bridge attachment marker 协议，而不是直接调用飞书消息工具。桥接层会从可见回复中剥离 marker，校验文件路径位于配置的附件目录下，然后上传/发送附件，并写入本地上下文。Markdown 文档也可以通过这个路径转换成飞书云文档。
 
+## Live Status 与最终回复
+
+非 verbose 模式下，执行过程显示一张可更新的 live status 卡片。运行中显示最近活动和耗时；完成后收缩为“累计工具调用次数 + 总耗时”。
+
+最终回复不会覆盖旧的 live status，而是在任务完成时新发一张卡片，因此用户执行途中插入的新消息不会排在最终答案之后。最终回复卡片底部只显示本次使用的模型名；工具调用次数和耗时只保留在 live status 中。
+
 ## 数据模型
 
 SQLite 状态位于配置的数据目录。主要表：

package/config.example.json

@@ -14,7 +14,7 @@
       "name": "GPT",
       "appId": "cli_xxx2",
       "appSecret": "xxx2",
-      "model": "github-copilot/gpt-5.5"
+      "model": "phgeek-gw/gpt-5.6-sol"
     },
     {
       "name": "Gemini",

package/dist/cli.js

@@ -65,7 +65,7 @@ function sampleConfig() {
                 name: "GPT",
                 appId: "cli_xxx",
                 appSecret: "YOUR_LARK_APP_SECRET",
-                model: "github-copilot/gpt-5.5",
+                model: "phgeek-gw/gpt-5.6-sol",
             },
             {
                 name: "Gemini",

package/dist/feishu-bot.d.ts

@@ -35,6 +35,13 @@ export declare class FeishuBot {
     private sendQueue;
     /** Per-chat delayed runtime failure notifications, canceled if a real reply arrives. */
     private delayedFailureTimers;
+    /** Ephemeral model footer overrides used by final-message wrappers. Keeping
+     * replyMessage/sendMessage two-argument APIs avoids contaminating ordinary
+     * command/error/card sends with model attribution. */
+    private replyModelFooters;
+    private sendModelFooters;
+    /** Per-chat durable outbox retry timer. */
+    private deliveryRetryTimers;
     /** Last time a real assistant-visible reply was successfully handed to the delivery pipeline. */
     private lastRealDeliveryAt;
     /** Per-chat: whether we've already sent the high-context alert this cycle. */
@@ -118,6 +125,11 @@ export declare class FeishuBot {
     private cleanMentions;
     private stripLeadingCommandMentions;
     private buildMarkdownCard;
+    private deliveryOwnsVisiblePayload;
+    private completionSummary;
+    /** Best-effort terminal cleanup for status-only rows and legacy v1.4.3
+     * outbox entries that once targeted the live-status card. */
+    private patchLiveStatusDoneSummary;
     private formatUserVisibleError;
     private isBridgeControlReply;
     private isLegacyBridgeControlMessage;
@@ -126,16 +138,14 @@ export declare class FeishuBot {
      * Heuristic: does this reply look truncated / cut off mid-task? Used as the
      * SOLE auto-retry trigger — if true, we ask the session a one-line “done?” probe.
      *
-     * Signals (any one is enough):
-     *   1. Unbalanced code fence — almost certainly cut off mid code block.
-     *   2. Trailing clause-joining punctuation (comma/colon/semicolon/、) — a
-     *      sentence was left hanging.
-     *   3. A dangling connector / lead-in (“然后”, “接下来”, “let me”, “and”…).
-     *   4. Ends without ANY sentence-ending punctuation / closer (no terminal
-     *      punctuation, closing bracket/quote, code fence, or wrap-up emoji).
-     *      Per Stephen: a reply that ends with no punctuation at all is also
-     *      treated as likely unfinished. A false positive only costs one cheap,
-     *      invisible confirmation probe; the session itself is the real arbiter.
+     * Signals are intentionally HIGH PRECISION. A reply is suspicious only when:
+     *   1. Its Markdown/code structure is visibly unclosed; or
+     *   2. It ends on punctuation/words that grammatically demand continuation.
+     *
+     * Merely lacking a final punctuation mark is NOT enough. Short answers,
+     * headings, model lists, paths, hashes, commands, English labels, and normal
+     * chat prose routinely end without punctuation; treating all of them as
+     * truncated caused obvious false-positive confirmation probes.
      */
     private looksTruncated;
     /** Current context usage percent for a session (totalTokens / contextTokens),
@@ -178,6 +188,7 @@ export declare class FeishuBot {
     private deliverySourceId;
     private sendSystemDelivery;
     private enqueueAndDispatchDelivery;
+    private scheduleDeliveryRetry;
     private dispatchPendingDeliveries;
     private hasFreeModeBot;
     private mentionedBotNames;
@@ -218,6 +229,7 @@ export declare class FeishuBot {
     private replyTextMessage;
     private editTextMessage;
     private deleteMessageById;
+    private replyFinalMessage;
     private replyMessage;
     private extractBridgeAttachments;
     /**
@@ -262,6 +274,7 @@ export declare class FeishuBot {
     /**
      * Send a proactive message to a chat (not a reply).
      */
+    private sendFinalMessage;
     private sendMessage;
     /**
      * Enqueue a message send to guarantee ordering per chat.