v1.8.2: tool loop cap-hit summary + tool call UI compaction

Old hardcoded MAX_TOOL_LOOP_DEPTH=15 replaced by per-agent
max_tool_calls (1-100, AGENTS.md frontmatter) with defaults: 30 for
read-only-only agents, 10 for agents that include any non-read-only
tool, 15 for raw chat. When the loop hits cap, fire one final summary
call with tools disabled, stream the wrap-up into the in-flight
assistant message, then insert a system sentinel with
metadata.kind='cap_hit'. The sentinel renders an amber bubble with a
Continue button (latest sentinel only) that POSTs to a new
/api/chats/:id/continue route to extend. Hard ceiling: 3 cap-hits per
chat (2 continues max) — third sentinel reports can_continue=false.

Error frames carry a machine-readable reason code alongside human
error text. Failed messages persist the reason via
metadata.kind='error' so the bubble renders specifics on reload (WS
error frame is one-shot).

Tool call UI rewired: ToolCallLine renders inline (↳ name args
spinner/check/✗, expand-on-tap for args+result); ToolCallGroup
collapses 3+ consecutive same-tool runs into a compact card.
MessageList owns a three-pass pre-render (flatten + fold tool
results onto matching runs by id + group same-tool runs + number
sentinels). MessageBubble drops tool rendering and adds the
sentinel / error-reason branches. ToolCallCard deleted.

Roadmap follow-up logged: add explicit max_tool_calls: 30 to the 6
agents in /data/AGENTS.md and /opt/boocode/AGENTS.md post-ship for
discoverability (defaults handle behavior identically).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

apps/web/src/hooks/sessionEvents.ts

@@ -2,7 +2,7 @@
 // across hooks (e.g. AI rename arriving via WS in the session view needs to
 // also refresh the sidebar's session list).
 
-import type { Chat, Project, Session } from '@/api/types';
+import type { Chat, ErrorReason, Project, Session } from '@/api/types';
 import type { Attachment } from '@/lib/attachments';
 
 export interface SessionRenamedEvent {
@@ -118,11 +118,14 @@ export interface ProjectUpdatedEvent {
 // v1.8 mobile-tabs: broadcast on user channel from inference.ts so any device
 // subscribed sees a chat working/idle/error. Frontend stores per-chat; panes
 // derive their dot from pane.activeChatId.
+// v1.8.2: optional `reason` carries a machine-readable code when status is
+// 'error'. UI prefers reason for inline error rendering.
 export interface ChatStatusEvent {
   type: 'chat_status';
   chat_id: string;
   status: 'working' | 'idle' | 'error';
   at: string;
+  reason?: ErrorReason;
 }
 
 export type SessionEvent =

apps/web/src/hooks/useSessionStream.ts

@@ -29,7 +29,9 @@ function applyFrame(state: State, frame: WsFrame): State {
         kind: 'message',
         tool_calls: null,
         tool_results: null,
-        status: 'streaming',
+        // v1.8.2: cap-hit sentinels arrive role='system' and are static, so
+        // skipping the streaming dot for them keeps the UI accurate.
+        status: frame.role === 'system' ? 'complete' : 'streaming',
         last_seq: 0,
         tokens_used: null,
         ctx_used: null,
@@ -37,6 +39,7 @@ function applyFrame(state: State, frame: WsFrame): State {
         started_at: null,
         finished_at: null,
         created_at: new Date().toISOString(),
+        metadata: null,
       };
       return { ...state, messages: [...state.messages, newMsg] };
     }
@@ -96,6 +99,7 @@ function applyFrame(state: State, frame: WsFrame): State {
         started_at: null,
         finished_at: null,
         created_at: new Date().toISOString(),
+        metadata: null,
       };
       return { ...state, messages: [...state.messages, newMsg] };
     }
@@ -110,6 +114,10 @@ function applyFrame(state: State, frame: WsFrame): State {
               ...(frame.ctx_max !== undefined ? { ctx_max: frame.ctx_max } : {}),
               ...(frame.started_at !== undefined ? { started_at: frame.started_at } : {}),
               ...(frame.finished_at !== undefined ? { finished_at: frame.finished_at } : {}),
+              // v1.8.2: cap-hit sentinels (and future stamped metadata) ride
+              // in on this terminal frame so the reducer can attach it
+              // without waiting for a refetch.
+              ...(frame.metadata !== undefined ? { metadata: frame.metadata } : {}),
             }
           : m
       );
@@ -133,9 +141,22 @@ function applyFrame(state: State, frame: WsFrame): State {
       return state;
     }
     case 'error': {
+      // v1.8.2: when the frame carries a structured reason, stamp it onto the
+      // failed message's metadata so the bubble can render specifics inline
+      // (the WS error frame is one-shot; refresh-safe rendering needs the
+      // value persisted on the message).
+      const errorMeta = frame.reason
+        ? { kind: 'error' as const, error_reason: frame.reason, error_text: frame.error }
+        : null;
       const next = frame.message_id
         ? state.messages.map((m) =>
-            m.id === frame.message_id ? { ...m, status: 'failed' as const } : m
+            m.id === frame.message_id
+              ? {
+                  ...m,
+                  status: 'failed' as const,
+                  ...(errorMeta ? { metadata: errorMeta } : {}),
+                }
+              : m
           )
         : state.messages;
       return { ...state, messages: next, error: frame.error };