discord-bot: fix "no response", serialize turns, attribution, mentions, post-at-bottom

client.py: send() falls back to ResultMessage.result when no TextBlock streams
(the "(no response)" bug) and reconnects+retries once on a closed SDK session.

message_handler.py: per-thread turn lock so messages arriving mid-turn or from a
second user queue in order (nothing dropped); per-session requester-attribution
env (discord_id -> users.json key), pinned to the thread opener; _USER_MAP caches
only on a successful load; final answer posts as a fresh message at the BOTTOM
(no edit-in-place); a <@id> tag goes out as a fresh send so it actually pings.

main.py: allowed_mentions permits user pings, blocks @everyone/@here/roles.

DISCORD_CLAUDE.md: no thread auto-delete; tiered close-out (Q&A -> one-line rolling
log, substantive -> /save); @mention guidance; opener-pinned attribution note.

whoami-block.sh / sync.sh: bot-context attribution (Executed by ClaudeTools Bot /
Requested by <person>; git author = mapped requester, committer = bot). Strict
no-op for interactive sessions.

users.json: discord_id for Mike/Howard; added Winter Williams (bot-only, full trust).

Reviewed by Code Review Agent + Grok + Gemini (Gemini's "malformed email" finding
verified as a false positive).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

projects/discord-bot/bot/handlers/message_handler.py

@@ -2,6 +2,7 @@
 from __future__ import annotations
 
 import asyncio
+import json
 import logging
 import shutil
 from pathlib import Path
@@ -21,9 +22,51 @@ ATTACHMENT_ROOT = settings.claudetools_root / "projects" / "discord-bot" / ".att
 
 
 class MessageHandler:
+    _USER_MAP: dict[str, dict] | None = None
+
     def __init__(self, bot: discord.Client, agents: ClaudeAgentManager) -> None:
         self.bot = bot
         self.agents = agents
+        # One lock per thread serializes turns: a message that arrives while the
+        # bot is mid-turn (or a second user chiming in) waits and is processed
+        # next, in order — nothing collides on the single SDK session, nothing
+        # is dropped. Different threads still run concurrently (separate locks).
+        self._thread_locks: dict[int, asyncio.Lock] = {}
+
+    @classmethod
+    def _users(cls) -> dict[str, dict]:
+        """discord_id -> {user, full_name} map from .claude/users.json (cached)."""
+        if cls._USER_MAP is None:
+            mapping: dict[str, dict] = {}
+            try:
+                p = settings.claudetools_root / ".claude" / "users.json"
+                data = json.loads(p.read_text(encoding="utf-8"))
+                for key, u in (data.get("users") or {}).items():
+                    did = str(u.get("discord_id") or "").strip()
+                    if did:
+                        mapping[did] = {"user": key, "full_name": u.get("full_name", key)}
+                cls._USER_MAP = mapping  # cache only on a successful load
+            except Exception as e:  # noqa: BLE001
+                logger.warning("[WARNING] could not load users.json discord map: %s", e)
+                return mapping  # do NOT cache a failed/empty load — retry next call
+        return cls._USER_MAP
+
+    def _requester_env(self, author: discord.abc.User) -> dict[str, str]:
+        """Per-session attribution env: marks the bot as executor and the Discord
+        requester (mapped to a known user key when their discord_id is on file)."""
+        mapped = self._users().get(str(author.id))
+        display = getattr(author, "display_name", author.name)
+        if mapped:
+            label = f"{mapped['full_name']} (@{author.name}, via Discord)"
+            user_key = mapped["user"]
+        else:
+            label = f"@{author.name} (display: {display}, via Discord)"
+            user_key = ""
+        return {
+            "CLAUDETOOLS_ACTOR": "discord-bot",
+            "CLAUDETOOLS_REQUESTER": label,
+            "CLAUDETOOLS_REQUESTER_USER": user_key,
+        }
 
     async def handle_mention(self, message: discord.Message) -> None:
         if message.author == self.bot.user:
@@ -75,7 +118,12 @@ class MessageHandler:
         if not content:
             content = "User uploaded file(s) without a message."
 
-        await self._run_turn(thread, content)
+        # Attribution pins to the THREAD OPENER: this env is honored only when the
+        # thread's SDK session is first created and is reused for every later turn.
+        # If a second person posts in the same thread, the work is still credited
+        # to whoever opened it (a thread = one person's request — see DISCORD_CLAUDE.md).
+        req_env = self._requester_env(author)
+        await self._run_turn(thread, content, req_env)
 
     @staticmethod
     async def _download_attachments(
@@ -130,12 +178,16 @@ class MessageHandler:
             name += "..."
         return name or "ClaudeTools Conversation"
 
-    async def _run_turn(self, thread: discord.Thread, user_message: str) -> None:
+    async def _run_turn(
+        self,
+        thread: discord.Thread,
+        user_message: str,
+        env: dict[str, str] | None = None,
+    ) -> None:
         # The Claude Code CLI cold-start can take a few seconds; show feedback.
+        # (Shown immediately; queued turns sit here while an earlier turn runs.)
         status_msg = await thread.send("[INFO] Thinking...")
 
-        agent = await self.agents.get_or_create(thread.id)
-
         buffer: list[str] = []
         last_edit = 0.0
         lock = asyncio.Lock()
@@ -162,7 +214,14 @@ class MessageHandler:
             logger.info("[INFO] thread=%d tool=%s", thread.id, tool_name)
 
         try:
-            full_text = await agent.send(user_message, on_text, on_tool_use)
+            # Serialize turns within this thread: a message that lands while a
+            # turn is in flight (or a second user chiming in) waits here and runs
+            # next, in order — nothing collides on the single SDK session, nothing
+            # is dropped. Separate threads still run concurrently.
+            turn_lock = self._thread_locks.setdefault(thread.id, asyncio.Lock())
+            async with turn_lock:
+                agent = await self.agents.get_or_create(thread.id, env=env)
+                full_text = await agent.send(user_message, on_text, on_tool_use)
         except Exception as e:
             logger.exception("[ERROR] Agent turn failed in thread %d", thread.id)
             await status_msg.edit(content=f"[ERROR] {e}")
@@ -179,11 +238,17 @@ class MessageHandler:
         text: str,
     ) -> None:
         chunks = self._split(text)
+        # Deliver the finished answer as NEW message(s) at the BOTTOM of the
+        # thread, like a normal human reply — do NOT edit the in-place
+        # "Thinking..." preview into the answer. The live edit is good for showing
+        # progress while working; the final answer belongs at the bottom where the
+        # next person expects it. (A fresh send is also what makes any <@id>
+        # mention actually notify the user — edits do not ping.)
         try:
-            await status_msg.edit(content=chunks[0])
-        except discord.errors.NotFound:
-            await thread.send(chunks[0])
-        for chunk in chunks[1:]:
+            await status_msg.delete()
+        except discord.errors.HTTPException:
+            pass
+        for chunk in chunks:
             await thread.send(chunk)
 
     @staticmethod