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/server/src/routes/chats.ts

@@ -231,7 +231,7 @@ export function registerChatRoutes(
           INSERT INTO messages (
             session_id, chat_id, role, content, kind, tool_calls, tool_results,
             status, tokens_used, ctx_used, ctx_max, started_at, finished_at,
-            created_at
+            created_at, metadata
           )
           SELECT
             ${source.session_id}, ${chat!.id}, role, content, kind,
@@ -239,7 +239,8 @@ export function registerChatRoutes(
             tokens_used, ctx_used, ctx_max, started_at, finished_at,
             clock_timestamp() + (
               ROW_NUMBER() OVER (ORDER BY created_at ASC, id ASC) * INTERVAL '1 microsecond'
-            )
+            ),
+            metadata
           FROM messages
           WHERE chat_id = ${source.id}
             AND created_at <= ${target.created_at}::timestamptz
@@ -268,7 +269,7 @@ export function registerChatRoutes(
       }
       const rows = await sql<Message[]>`
         SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
-               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
         FROM messages
         WHERE chat_id = ${req.params.id}
         ORDER BY created_at ASC, id ASC

apps/server/src/routes/messages.ts

@@ -7,6 +7,13 @@ const SendBody = z.object({
   content: z.string().min(1).max(64_000),
 });
 
+// v1.8.2: Continue extends an inference loop that hit the tool budget. Caller
+// passes the sentinel message it's continuing from; server validates shape
+// and the per-chat hard ceiling before resuming.
+const ContinueBody = z.object({
+  sentinel_message_id: z.string().uuid(),
+});
+
 interface MessageHandlers {
   enqueueInference: (sessionId: string, chatId: string, assistantMessageId: string, user: string) => void;
   enqueueCompact: (sessionId: string, chatId: string, compactMessageId: string, user: string) => void;
@@ -36,7 +43,7 @@ export function registerMessageRoutes(
       }
       const rows = await sql<Message[]>`
         SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
-               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
         FROM messages
         WHERE session_id = ${req.params.id}
         ORDER BY created_at ASC, id ASC
@@ -253,6 +260,76 @@ export function registerMessageRoutes(
     }
   );
 
+  app.post<{ Params: { id: string } }>(
+    '/api/chats/:id/continue',
+    async (req, reply) => {
+      const parsed = ContinueBody.safeParse(req.body);
+      if (!parsed.success) {
+        reply.code(400);
+        return { error: 'invalid body', details: parsed.error.flatten() };
+      }
+
+      const chatRows = await sql<Chat[]>`
+        SELECT id, session_id FROM chats WHERE id = ${req.params.id} AND status = 'open'
+      `;
+      if (chatRows.length === 0) {
+        reply.code(404);
+        return { error: 'chat not found' };
+      }
+      const chat = chatRows[0]!;
+      const sessionId = chat.session_id;
+
+      // Cap-hit sentinels are only ever inserted after a turn completes, so
+      // there must not be an active inference at this moment. If there is,
+      // the client is racing the cap-hit summary that just emitted the
+      // sentinel — bail rather than enqueue a parallel run.
+      if (handlers.hasActiveInference(chat.id)) {
+        reply.code(409);
+        return { error: 'chat is currently streaming' };
+      }
+
+      const sentinel = await sql<{ metadata: { kind?: unknown; can_continue?: unknown } | null }[]>`
+        SELECT metadata
+        FROM messages
+        WHERE id = ${parsed.data.sentinel_message_id}
+          AND chat_id = ${chat.id}
+          AND role = 'system'
+      `;
+      if (sentinel.length === 0) {
+        reply.code(404);
+        return { error: 'sentinel not found' };
+      }
+      const meta = sentinel[0]!.metadata;
+      if (!meta || meta.kind !== 'cap_hit') {
+        reply.code(400);
+        return { error: 'message is not a cap-hit sentinel' };
+      }
+      // Server-side hard ceiling check. UI already disables the button when
+      // can_continue is false; defending against a stale tab or a direct
+      // API hit is the only reason this lives on the server too.
+      if (meta.can_continue !== true) {
+        reply.code(409);
+        return { error: 'hard limit reached for this chat' };
+      }
+
+      const result = await sql.begin(async (tx) => {
+        const [assistantMsg] = await tx<{ id: string }[]>`
+          INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
+          VALUES (${sessionId}, ${chat.id}, 'assistant', '', 'streaming', clock_timestamp())
+          RETURNING id
+        `;
+        await tx`UPDATE sessions SET updated_at = clock_timestamp() WHERE id = ${sessionId}`;
+        await tx`UPDATE chats SET updated_at = clock_timestamp() WHERE id = ${chat.id}`;
+        return { assistant_message_id: assistantMsg!.id };
+      });
+
+      handlers.enqueueInference(sessionId, chat.id, result.assistant_message_id, 'default');
+
+      reply.code(202);
+      return result;
+    }
+  );
+
   app.post<{ Params: { id: string } }>(
     '/api/chats/:id/force_send',
     async (req, reply) => {

apps/server/src/routes/ws.ts

@@ -23,7 +23,7 @@ export function registerWebSocket(
 
       const messages = await sql<Message[]>`
         SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
-               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
         FROM messages
         WHERE session_id = ${sessionId}
         ORDER BY created_at ASC, id ASC

apps/server/src/schema.sql

@@ -158,3 +158,10 @@ END $$;
 -- the DB; they live in builtins (services/agents.ts) and a per-project AGENTS.md.
 -- agent_id is the slugified agent name. NULL means "use BooCode defaults".
 ALTER TABLE sessions ADD COLUMN IF NOT EXISTS agent_id TEXT;
+
+-- v1.8.2: per-message metadata for sentinels (cap-hit) and structured error
+-- reasons. JSONB so future kinds can extend without further schema churn.
+-- Shape for cap_hit:  { kind: 'cap_hit', used: number, limit: number,
+--                       agent_name: string|null, can_continue: boolean }
+-- Shape for errors:   { error_reason: 'llm_provider_error'|..., error_text: string }
+ALTER TABLE messages ADD COLUMN IF NOT EXISTS metadata JSONB;

apps/server/src/services/__tests__/inference.test.ts

@@ -21,6 +21,7 @@ function makeSession(overrides: Partial<Session> = {}): Session {
     status: 'open',
     created_at: new Date(0).toISOString(),
     updated_at: new Date(0).toISOString(),
+    agent_id: null,
     ...overrides,
   };
 }
@@ -62,6 +63,7 @@ function makeMessage(
     started_at: null,
     finished_at: null,
     created_at: new Date(counter * 1000).toISOString(),
+    metadata: null,
     ...overrides,
   };
 }

apps/server/src/services/agents.ts

@@ -29,6 +29,9 @@ interface ParsedFrontmatter {
   tools?: string[];
   description?: string;
   model?: string;
+  // v1.8.2: optional per-agent tool-loop budget. Absent → inference resolves
+  // from the agent's toolset at runtime.
+  max_tool_calls?: number;
 }
 
 function stripQuotes(s: string): string {
@@ -89,6 +92,21 @@ function parseFrontmatter(yaml: string): { data: ParsedFrontmatter; errors: stri
       data.description = stripQuotes(valueRaw);
     } else if (key === 'model') {
       data.model = stripQuotes(valueRaw);
+    } else if (key === 'max_tool_calls') {
+      // v1.8.2: 1..100 inclusive integer. Out-of-range values are skipped
+      // with a warning rather than throwing — agents shouldn't be unusable
+      // because of a typo on a defaulted field. Non-numeric or non-integer
+      // still hard-fails the block, matching `temperature` behavior.
+      const n = Number(valueRaw);
+      if (Number.isInteger(n) && n >= 1 && n <= 100) {
+        data.max_tool_calls = n;
+      } else if (Number.isInteger(n)) {
+        console.warn(
+          `agents: max_tool_calls ${n} out of range 1-100, ignoring (falling back to default)`,
+        );
+      } else {
+        errors.push(`max_tool_calls must be an integer 1-100 (got "${valueRaw}")`);
+      }
     }
     // Unknown keys silently ignored — forward-compat.
   }
@@ -177,6 +195,7 @@ function parseAgentSection(section: RawSection): Omit<Agent, 'source'> {
     temperature: typeof fm.temperature === 'number' ? fm.temperature : DEFAULT_TEMPERATURE,
     tools: filteredTools,
     model: typeof fm.model === 'string' && fm.model.length > 0 ? fm.model : null,
+    max_tool_calls: typeof fm.max_tool_calls === 'number' ? fm.max_tool_calls : null,
   };
 }
 

apps/server/src/services/inference.ts

@@ -1,8 +1,23 @@
 import type { FastifyBaseLogger } from 'fastify';
 import type { Sql } from '../db.js';
 import type { Config } from '../config.js';
-import type { Agent, Message, Project, Session, ToolCall, UserStreamFrame } from '../types/api.js';
-import { ALL_TOOLS, TOOLS_BY_NAME, toolJsonSchemas, type ToolJsonSchema } from './tools.js';
+import type {
+  Agent,
+  ErrorReason,
+  Message,
+  MessageMetadata,
+  Project,
+  Session,
+  ToolCall,
+  UserStreamFrame,
+} from '../types/api.js';
+import {
+  ALL_TOOLS,
+  READ_ONLY_TOOL_NAMES,
+  TOOLS_BY_NAME,
+  toolJsonSchemas,
+  type ToolJsonSchema,
+} from './tools.js';
 import { PathScopeError, resolveProjectRoot } from './path_guard.js';
 import { maybeAutoNameChat } from './auto_name.js';
 import { getAgentById } from './agents.js';
@@ -11,7 +26,39 @@ const BASE_SYSTEM_PROMPT = (projectPath: string) =>
   `You are BooCode Chat, a code investigation assistant. The user is working on a project located at ${projectPath}. Use the file-read tools (view_file, list_dir, grep, find_files) to investigate code when needed. Be concise. Cite file paths and line numbers when discussing code. Do not hallucinate file contents — read the file first. Tool results may be truncated; if so, narrow your query rather than guessing.`;
 
 const DB_FLUSH_INTERVAL_MS = 500;
-const MAX_TOOL_LOOP_DEPTH = 15;
+
+// v1.8.2: tool-call budget defaults. Resolved per-turn by resolveToolBudget.
+//   - Agent with explicit max_tool_calls: that value.
+//   - Agent with read-only-only tools:    BUDGET_READ_ONLY (30).
+//   - Agent with any non-read-only tool:  BUDGET_NON_READ_ONLY (10).
+//   - No agent (raw chat):                BUDGET_NO_AGENT (15).
+const BUDGET_READ_ONLY = 30;
+const BUDGET_NON_READ_ONLY = 10;
+const BUDGET_NO_AGENT = 15;
+
+const READ_ONLY_SET: ReadonlySet<string> = new Set(READ_ONLY_TOOL_NAMES);
+
+function resolveToolBudget(agent: Agent | null): number {
+  if (agent?.max_tool_calls != null) return agent.max_tool_calls;
+  if (!agent) return BUDGET_NO_AGENT;
+  const allReadOnly = agent.tools.every((t) => READ_ONLY_SET.has(t));
+  return allReadOnly ? BUDGET_READ_ONLY : BUDGET_NON_READ_ONLY;
+}
+
+// Synthetic system note appended to the cap-hit summary call. Verbatim from
+// the v1.8.2 spec — do not paraphrase: the model is more reliable when the
+// instruction is short, declarative, and identical across calls.
+const CAP_HIT_SUMMARY_NOTE = (limit: number) =>
+  `You've reached the tool budget (${limit} calls). Produce the best answer you can with what you have. Do not call more tools.`;
+
+function isCapHitSentinel(m: Message): boolean {
+  return (
+    m.role === 'system' &&
+    m.metadata !== null &&
+    typeof m.metadata === 'object' &&
+    (m.metadata as { kind?: unknown }).kind === 'cap_hit'
+  );
+}
 
 export interface InferenceFrame {
   type:
@@ -29,12 +76,22 @@ export interface InferenceFrame {
   chat_id?: string;
   tool_message_id?: string;
   tool_call_id?: string;
-  role?: 'assistant' | 'tool' | 'user';
+  // v1.8.2: 'system' added so cap-hit sentinel messages can announce themselves
+  // through the normal message_started → delta → message_complete sequence.
+  role?: 'assistant' | 'tool' | 'user' | 'system';
   content?: string;
   tool_call?: ToolCall;
   output?: unknown;
   truncated?: boolean;
   error?: string;
+  // v1.8.2: structured error reason. Set on `type: 'error'` so the UI can
+  // surface a specific message; `error` stays the human-readable text.
+  reason?: ErrorReason;
+  // v1.8.2: piggybacks on `message_complete` so static or terminally-resolved
+  // messages can carry their persisted metadata to the live stream without a
+  // refetch (sentinels carry { kind: 'cap_hit', ... }; failed messages carry
+  // { kind: 'error', ... }).
+  metadata?: MessageMetadata | null;
   tokens_used?: number | null;
   ctx_used?: number | null;
   ctx_max?: number | null;
@@ -135,6 +192,11 @@ export function buildMessagesPayload(
       out.push({ role: 'system', content: m.content });
       continue;
     }
+    // v1.8.2: cap-hit sentinels are UI-only — never send them to the LLM. The
+    // synthetic "you've reached the tool budget" note lives only inside the
+    // summary call's messages array and is never persisted, so on Continue
+    // the model resumes with a clean context.
+    if (isCapHitSentinel(m)) continue;
     if (m.role === 'assistant' && m.status === 'streaming') continue;
     if (m.role === 'assistant' && m.status === 'cancelled') continue;
     if (m.role === 'tool') {
@@ -193,7 +255,7 @@ async function loadContext(
 
   const history = await sql<Message[]>`
     SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
-           tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at
+           tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
     FROM messages
     WHERE chat_id = ${chatId}
     ORDER BY created_at ASC, id ASC
@@ -379,7 +441,10 @@ interface TurnArgs {
   sessionId: string;
   chatId: string;
   assistantMessageId: string;
-  depth: number;
+  // v1.8.2: cumulative tool calls executed this run. Compared against the
+  // resolved budget at the top of each turn. Replaces the older `depth`
+  // counter (which counted iterations, not invocations).
+  toolsUsed: number;
   signal: AbortSignal | undefined;
 }
 
@@ -480,13 +545,32 @@ async function handleAbortOrError(
   const { sessionId, chatId, assistantMessageId } = args;
   const isAbort = err instanceof Error && err.name === 'AbortError';
   const finalStatus = isAbort ? 'cancelled' : 'failed';
-  await ctx.sql`
-    UPDATE messages
-    SET status = ${finalStatus},
-        content = ${accumulated},
-        finished_at = clock_timestamp()
-    WHERE id = ${assistantMessageId}
-  `;
+  const errMsg = err instanceof Error ? err.message : String(err);
+  // v1.8.2: persist a structured error metadata blob on genuine failures so
+  // the bubble can render the reason on reload without re-deriving from the
+  // (one-shot) WS error frame. User-initiated abort skips this — there's no
+  // "reason" to surface for a stop the user already explicitly chose.
+  const errorMetadata: MessageMetadata | null = isAbort
+    ? null
+    : { kind: 'error', error_reason: 'llm_provider_error', error_text: errMsg };
+  if (errorMetadata) {
+    await ctx.sql`
+      UPDATE messages
+      SET status = ${finalStatus},
+          content = ${accumulated},
+          finished_at = clock_timestamp(),
+          metadata = ${ctx.sql.json(errorMetadata as never)}
+      WHERE id = ${assistantMessageId}
+    `;
+  } else {
+    await ctx.sql`
+      UPDATE messages
+      SET status = ${finalStatus},
+          content = ${accumulated},
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+    `;
+  }
   const [failSessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
     UPDATE sessions SET updated_at = clock_timestamp()
     WHERE id = ${sessionId}
@@ -494,9 +578,10 @@ async function handleAbortOrError(
   `;
   ctx.publishUser({ type: 'session_updated', session_id: sessionId, project_id: failSessRow!.project_id, name: failSessRow!.name, updated_at: failSessRow!.updated_at });
   // v1.8 mobile-tabs: cancellation is a user-initiated stop, treat as idle;
-  // genuine errors flip the dot red.
-  ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: isAbort ? 'idle' : 'error', at: new Date().toISOString() });
+  // genuine errors flip the dot red. v1.8.2: error path also carries a
+  // machine-readable `reason` so the UI can render specifics inline.
   if (isAbort) {
+    ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
     ctx.publish(sessionId, {
       type: 'message_complete',
       message_id: assistantMessageId,
@@ -504,12 +589,19 @@ async function handleAbortOrError(
     });
     ctx.log.info({ sessionId, chatId, assistantMessageId }, 'inference cancelled');
   } else {
-    const errMsg = err instanceof Error ? err.message : String(err);
+    ctx.publishUser({
+      type: 'chat_status',
+      chat_id: chatId,
+      status: 'error',
+      at: new Date().toISOString(),
+      reason: 'llm_provider_error',
+    });
     ctx.publish(sessionId, {
       type: 'error',
       message_id: assistantMessageId,
       chat_id: chatId,
       error: errMsg,
+      reason: 'llm_provider_error',
     });
     ctx.log.error({ err, sessionId, assistantMessageId }, 'inference failed');
   }
@@ -523,7 +615,7 @@ async function executeToolPhase(
   session: Session,
   projectRoot: string
 ): Promise<void> {
-  const { sessionId, chatId, assistantMessageId, depth, signal } = args;
+  const { sessionId, chatId, assistantMessageId, toolsUsed, signal } = args;
   const { content, toolCalls, promptTokens, completionTokens, nCtx } = result;
 
   const [updated] = await ctx.sql<
@@ -607,7 +699,10 @@ async function executeToolPhase(
     sessionId,
     chatId,
     assistantMessageId: nextAssistant!.id,
-    depth: depth + 1,
+    // v1.8.2: charge this turn's actual tool invocations against the budget.
+    // One assistant message can emit multiple tool_calls, so we add the run
+    // count, not 1. The next turn's budget check sees the cumulative total.
+    toolsUsed: toolsUsed + result.toolCalls.length,
     signal,
   });
 }
@@ -671,25 +766,7 @@ async function runAssistantTurn(
   ctx: InferenceContext,
   args: TurnArgs,
 ): Promise<void> {
-  const { sessionId, chatId, assistantMessageId, depth } = args;
-
-  if (depth > MAX_TOOL_LOOP_DEPTH) {
-    await ctx.sql`
-      UPDATE messages
-      SET status = 'failed',
-          content = ${'tool loop depth exceeded'},
-          finished_at = clock_timestamp()
-      WHERE id = ${assistantMessageId}
-    `;
-    ctx.publish(sessionId, {
-      type: 'error',
-      message_id: assistantMessageId,
-      chat_id: chatId,
-      error: 'tool loop depth exceeded',
-    });
-    ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'error', at: new Date().toISOString() });
-    return;
-  }
+  const { sessionId, chatId } = args;
 
   const loaded = await loadContext(ctx.sql, sessionId, chatId);
   if (!loaded) {
@@ -704,6 +781,17 @@ async function runAssistantTurn(
   const agent = session.agent_id
     ? await getAgentById(project.path, session.agent_id)
     : null;
+
+  // v1.8.2: cap-hit replaces the older "tool loop depth exceeded" failure.
+  // When we've already burned the budget *before* this turn even runs, we
+  // skip straight to the summary flow — the in-flight assistant message slot
+  // gets reused for the wrap-up reply instead of being marked failed.
+  const budget = resolveToolBudget(agent);
+  if (args.toolsUsed >= budget) {
+    await runCapHitSummary(ctx, args, session, project, history, agent, budget);
+    return;
+  }
+
   const messages = buildMessagesPayload(session, project, history, agent);
 
   const state: StreamPhaseState = { accumulated: '', startedAt: null };
@@ -730,7 +818,264 @@ export async function runInference(
   assistantMessageId: string,
   signal?: AbortSignal
 ): Promise<void> {
-  return runAssistantTurn(ctx, { sessionId, chatId, assistantMessageId, depth: 0, signal });
+  // v1.8.2: every fresh inference (initial send, regenerate, force_send,
+  // continue) starts with a clean budget. Tool-call accumulation across
+  // Continue invocations is what the hard ceiling guards against, not the
+  // per-call budget.
+  return runAssistantTurn(ctx, { sessionId, chatId, assistantMessageId, toolsUsed: 0, signal });
+}
+
+// v1.8.2: cap-hit summary flow. Called instead of erroring when the loop
+// hits its budget. Reuses the in-flight assistant message slot to stream a
+// short wrap-up reply with the synthetic note prepended and tools disabled,
+// then always inserts a cap_hit sentinel afterward (regardless of summary
+// outcome) so the UI can show a Continue affordance.
+async function runCapHitSummary(
+  ctx: InferenceContext,
+  args: TurnArgs,
+  session: Session,
+  project: Project,
+  history: Message[],
+  agent: Agent | null,
+  budget: number,
+): Promise<void> {
+  const { sessionId, chatId, assistantMessageId, signal } = args;
+
+  const messages = buildMessagesPayload(session, project, history, agent);
+  messages.push({ role: 'system', content: CAP_HIT_SUMMARY_NOTE(budget) });
+
+  const startedRow = await ctx.sql<{ started_at: string }[]>`
+    UPDATE messages
+    SET started_at = clock_timestamp()
+    WHERE id = ${assistantMessageId}
+    RETURNING started_at
+  `;
+  const startedAt = startedRow[0]?.started_at ?? null;
+
+  ctx.publish(sessionId, {
+    type: 'message_started',
+    message_id: assistantMessageId,
+    chat_id: chatId,
+    role: 'assistant',
+  });
+
+  let accumulated = '';
+  let pendingFlushTimer: NodeJS.Timeout | null = null;
+  let flushPromise: Promise<unknown> = Promise.resolve();
+  const flushNow = () => {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    const snapshot = accumulated;
+    flushPromise = flushPromise.then(() =>
+      ctx.sql`UPDATE messages SET content = ${snapshot} WHERE id = ${assistantMessageId}`
+    );
+  };
+  const scheduleFlush = () => {
+    if (pendingFlushTimer) return;
+    pendingFlushTimer = setTimeout(() => {
+      pendingFlushTimer = null;
+      flushNow();
+    }, DB_FLUSH_INTERVAL_MS);
+  };
+
+  let summaryOk = false;
+  let summarySoftCancelled = false;
+  let summaryError: string | null = null;
+  let result: StreamResult | null = null;
+  try {
+    result = await streamCompletion(
+      ctx,
+      session.model,
+      messages,
+      { tools: null, temperature: agent?.temperature },
+      (delta) => {
+        accumulated += delta;
+        ctx.publish(sessionId, {
+          type: 'delta',
+          message_id: assistantMessageId,
+          chat_id: chatId,
+          content: delta,
+        });
+        scheduleFlush();
+      },
+      signal,
+    );
+    summaryOk = true;
+  } catch (err) {
+    if (err instanceof Error && err.name === 'AbortError') {
+      summarySoftCancelled = true;
+    } else {
+      summaryError = err instanceof Error ? err.message : String(err);
+    }
+  } finally {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    await flushPromise;
+  }
+
+  // Finalize the summary message based on the three outcomes. The sentinel
+  // is inserted regardless so the user always has the Continue affordance —
+  // even on a partial / failed summary the chat history shows where the
+  // budget was hit.
+  if (summaryOk && result) {
+    const [updated] = await ctx.sql<
+      { tokens_used: number | null; ctx_used: number | null; ctx_max: number | null; finished_at: string | null }[]
+    >`
+      UPDATE messages
+      SET content = ${result.content},
+          status = 'complete',
+          tokens_used = ${result.completionTokens},
+          ctx_used = ${result.promptTokens},
+          ctx_max = ${result.nCtx},
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+      RETURNING tokens_used, ctx_used, ctx_max, finished_at
+    `;
+    ctx.publish(sessionId, {
+      type: 'message_complete',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+      tokens_used: updated?.tokens_used ?? null,
+      ctx_used: updated?.ctx_used ?? null,
+      ctx_max: updated?.ctx_max ?? null,
+      started_at: startedAt,
+      finished_at: updated?.finished_at ?? null,
+      model: session.model,
+    });
+  } else if (summarySoftCancelled) {
+    await ctx.sql`
+      UPDATE messages
+      SET content = ${accumulated},
+          status = 'cancelled',
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+    `;
+    ctx.publish(sessionId, {
+      type: 'message_complete',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+    });
+  } else {
+    const errMeta: MessageMetadata = {
+      kind: 'error',
+      error_reason: 'summary_after_cap_failed',
+      error_text: summaryError ?? 'summary failed',
+    };
+    await ctx.sql`
+      UPDATE messages
+      SET content = ${accumulated},
+          status = 'failed',
+          finished_at = clock_timestamp(),
+          metadata = ${ctx.sql.json(errMeta as never)}
+      WHERE id = ${assistantMessageId}
+    `;
+    ctx.publish(sessionId, {
+      type: 'error',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+      error: summaryError ?? 'summary failed',
+      reason: 'summary_after_cap_failed',
+    });
+  }
+
+  // Bump session/chat updated_at exactly once for this turn.
+  const [sessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
+    UPDATE sessions SET updated_at = clock_timestamp()
+    WHERE id = ${sessionId}
+    RETURNING project_id, name, updated_at
+  `;
+  ctx.publishUser({
+    type: 'session_updated',
+    session_id: sessionId,
+    project_id: sessRow!.project_id,
+    name: sessRow!.name,
+    updated_at: sessRow!.updated_at,
+  });
+
+  await insertCapHitSentinel(ctx, sessionId, chatId, agent, budget);
+
+  // Status frame fires last so the dot color reflects the terminal state.
+  // Success → idle, abort → idle (user-driven stop), error → error+reason.
+  if (summaryOk) {
+    ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
+  } else if (summarySoftCancelled) {
+    ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
+  } else {
+    ctx.publishUser({
+      type: 'chat_status',
+      chat_id: chatId,
+      status: 'error',
+      at: new Date().toISOString(),
+      reason: 'summary_after_cap_failed',
+    });
+  }
+
+  ctx.log.info(
+    { sessionId, chatId, assistantMessageId, budget, summaryOk, summaryCancelled: summarySoftCancelled },
+    'inference cap-hit summary finished',
+  );
+}
+
+async function insertCapHitSentinel(
+  ctx: InferenceContext,
+  sessionId: string,
+  chatId: string,
+  agent: Agent | null,
+  budget: number,
+): Promise<void> {
+  // Hard ceiling: count prior cap_hit sentinels in this chat. After two
+  // continues (sentinel count of 2), the next sentinel reports can_continue
+  // false and the UI disables the Continue button.
+  const priorRows = await ctx.sql<{ count: number }[]>`
+    SELECT COUNT(*)::int AS count
+    FROM messages
+    WHERE chat_id = ${chatId}
+      AND role = 'system'
+      AND metadata->>'kind' = 'cap_hit'
+  `;
+  const priorCount = priorRows[0]?.count ?? 0;
+  const canContinue = priorCount < 2;
+  const metadata: MessageMetadata = {
+    kind: 'cap_hit',
+    used: budget,
+    limit: budget,
+    agent_name: agent?.name ?? null,
+    can_continue: canContinue,
+  };
+  const content = `Reached tool budget (${budget}/${budget}). Continue to extend.`;
+
+  const [row] = await ctx.sql<{ id: string }[]>`
+    INSERT INTO messages (session_id, chat_id, role, content, status, created_at, metadata)
+    VALUES (${sessionId}, ${chatId}, 'system', ${content}, 'complete', clock_timestamp(), ${ctx.sql.json(metadata as never)})
+    RETURNING id
+  `;
+
+  // The sentinel content is static, but we still walk the standard frame
+  // sequence (started → delta → complete) so useSessionStream's reducer
+  // appends it via the same path it uses for streaming assistant messages.
+  // The delta carries the full text in one chunk.
+  ctx.publish(sessionId, {
+    type: 'message_started',
+    message_id: row!.id,
+    chat_id: chatId,
+    role: 'system',
+  });
+  ctx.publish(sessionId, {
+    type: 'delta',
+    message_id: row!.id,
+    chat_id: chatId,
+    content,
+  });
+  ctx.publish(sessionId, {
+    type: 'message_complete',
+    message_id: row!.id,
+    chat_id: chatId,
+    metadata,
+  });
 }
 
 const COMPACT_SYSTEM_PROMPT =

apps/server/src/services/tools.ts

@@ -308,6 +308,19 @@ export const ALL_TOOLS: ReadonlyArray<ToolDef<unknown>> = [
   gitStatus as ToolDef<unknown>,
 ];
 
+// v1.8.2: forward-compatible read-only whitelist. An agent whose `tools` is
+// fully contained in this set gets a generous default tool budget (30);
+// anything outside means the agent can mutate state and gets a tighter
+// default (10). Every tool in v1.8.2 happens to be read-only, so the
+// non-RO branch only takes effect once BooCoder lands write tools.
+export const READ_ONLY_TOOL_NAMES = [
+  'view_file',
+  'list_dir',
+  'grep',
+  'find_files',
+  'git_status',
+] as const;
+
 export const TOOLS_BY_NAME: Record<string, ToolDef<unknown>> = Object.fromEntries(
   ALL_TOOLS.map((t) => [t.name, t])
 );

apps/server/src/types/api.ts

@@ -45,6 +45,10 @@ export interface Agent {
   tools: string[];       // whitelist of tool names; empty = no tools allowed
   model: string | null;  // null means "session.model wins"
   source: AgentSource;
+  // v1.8.2: per-agent tool-loop budget. null means resolve at runtime from the
+  // agent's toolset (30 if all tools are read-only, 10 otherwise) or 15 for
+  // raw chat with no agent.
+  max_tool_calls: number | null;
 }
 
 // One entry per malformed `## Name` block. Per-block errors don't fail the
@@ -100,6 +104,31 @@ export interface ToolResult {
   error?: string;
 }
 
+// v1.8.2: structured reason codes for failed inferences. `error` carries the
+// human text; `reason` is the machine-readable discriminator the UI matches
+// on (with `error` as fallback when reason is absent or unrecognized).
+export type ErrorReason =
+  | 'llm_provider_error'
+  | 'tool_execution_failed'
+  | 'summary_after_cap_failed';
+
+// v1.8.2: shapes stored in messages.metadata. Discriminated on `kind`.
+//   cap_hit  — system sentinel emitted when tool budget is exhausted
+//   error    — attached to a failed assistant message so UI can show reason
+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;
@@ -117,6 +146,9 @@ export interface Message {
   started_at: string | null;
   finished_at: string | null;
   created_at: string;
+  // v1.8.2: per-message metadata. See MessageMetadata for the discriminated
+  // shapes currently in use.
+  metadata: MessageMetadata | null;
 }
 
 export interface ModelInfo {
@@ -257,11 +289,14 @@ export interface ProjectUpdatedFrame {
 }
 // v1.8 mobile-tabs: server can't know about client-side panes, so status
 // is keyed by chat_id. Frontend dot derives pane status from pane.activeChatId.
+// v1.8.2: optional `reason` carries a machine-readable code when status is
+// 'error'. UI prefers reason; falls back to no detail when absent.
 export interface ChatStatusFrame {
   type: 'chat_status';
   chat_id: string;
   status: 'working' | 'idle' | 'error';
   at: string;
+  reason?: ErrorReason;
 }
 export type UserStreamFrame =
   | ProjectCreatedFrame