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/api/client.ts

@@ -152,6 +152,13 @@ export const api = {
         `/api/chats/${chatId}/force_send`,
         { method: 'POST', body: JSON.stringify({ content }) }
       ),
+    // v1.8.2: extend an inference that hit the tool budget. `sentinelMessageId`
+    // is the cap-hit sentinel message the user clicked Continue on.
+    continue: (chatId: string, sentinelMessageId: string) =>
+      request<{ assistant_message_id: string }>(
+        `/api/chats/${chatId}/continue`,
+        { method: 'POST', body: JSON.stringify({ sentinel_message_id: sentinelMessageId }) }
+      ),
     fork: (chatId: string, body: { messageId: string; name?: string }) =>
       request<Chat>(`/api/chats/${chatId}/fork`, {
         method: 'POST',

apps/web/src/api/types.ts

@@ -44,6 +44,10 @@ export interface Agent {
   tools: string[];
   model: string | null;
   source: AgentSource;
+  // v1.8.2: per-agent tool-loop budget. null means resolve at runtime from
+  // the agent's toolset (30 for all read-only, 10 otherwise) or 15 for raw
+  // chat with no agent.
+  max_tool_calls: number | null;
 }
 
 export interface AgentParseError {
@@ -89,6 +93,32 @@ export interface ToolResult {
   error?: string;
 }
 
+// v1.8.2: structured reason codes that flow through error frames / metadata.
+// `error` text stays human; `reason` is the discriminator the UI matches on.
+export type ErrorReason =
+  | 'llm_provider_error'
+  | 'tool_execution_failed'
+  | 'summary_after_cap_failed';
+
+// v1.8.2: shapes stored in Message.metadata. Discriminated on `kind`.
+//   cap_hit — sentinel emitted when the tool budget is hit; carries the
+//             budget + agent name + whether Continue is still allowed.
+//   error   — attached to a failed assistant message so the bubble can show
+//             a specific reason on reload (WS error frame is one-shot).
+export type MessageMetadata =
+  | {
+      kind: 'cap_hit';
+      used: number;
+      limit: number;
+      agent_name: string | null;
+      can_continue: boolean;
+    }
+  | {
+      kind: 'error';
+      error_reason: ErrorReason;
+      error_text: string;
+    };
+
 export interface Message {
   id: string;
   session_id: string;
@@ -106,6 +136,9 @@ export interface Message {
   started_at: string | null;
   finished_at: string | null;
   created_at: string;
+  // v1.8.2: per-message metadata; see MessageMetadata. null for the vast
+  // majority of messages.
+  metadata: MessageMetadata | null;
 }
 
 export interface ModelInfo {
@@ -225,7 +258,13 @@ export type WsFrame =
       ctx_max?: number | null;
       started_at?: string | null;
       finished_at?: string | null;
+      // v1.8.2: piggybacks the persisted metadata onto the terminal frame so
+      // cap-hit sentinels (and any future stamped-on-complete metadata) flow
+      // to the client without a refetch.
+      metadata?: MessageMetadata | null;
     }
   | { type: 'messages_deleted'; message_ids: string[]; chat_id?: string }
   | { type: 'chat_renamed'; chat_id: string; name: string }
-  | { type: 'error'; message_id?: string; chat_id?: string; error: string };
+  // v1.8.2: `reason` discriminates structured failures (the UI prefers it
+  // over `error` text when present).
+  | { type: 'error'; message_id?: string; chat_id?: string; error: string; reason?: ErrorReason };